diff options
Diffstat (limited to 'net/ipv4')
53 files changed, 1207 insertions, 742 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 55bd72997b31..b24d74616637 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -758,7 +758,9 @@ void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *new sock_rps_record_flow(newsk); WARN_ON(!((1 << newsk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_RECV | - TCPF_CLOSE_WAIT | TCPF_CLOSE))); + TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | + TCPF_CLOSING | TCPF_CLOSE_WAIT | + TCPF_CLOSE))); if (test_bit(SOCK_SUPPORT_ZC, &sock->flags)) set_bit(SOCK_SUPPORT_ZC, &newsock->flags); @@ -771,16 +773,16 @@ void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *new * Accept a pending connection. The TCP layer now gives BSD semantics. */ -int inet_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +int inet_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct sock *sk1 = sock->sk, *sk2; - int err = -EINVAL; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ - sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, flags, &err, kern); + arg->err = -EINVAL; + sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, arg); if (!sk2) - return err; + return arg->err; lock_sock(sk2); __inet_accept(sock, newsock, sk2); @@ -1072,6 +1074,7 @@ const struct proto_ops inet_stream_ops = { #endif .splice_eof = inet_splice_eof, .splice_read = tcp_splice_read, + .set_peek_off = sk_set_peek_off, .read_sock = tcp_read_sock, .read_skb = tcp_read_skb, .sendmsg_locked = tcp_sendmsg_locked, @@ -1306,8 +1309,8 @@ static int inet_sk_reselect_saddr(struct sock *sk) int inet_sk_rebuild_header(struct sock *sk) { + struct rtable *rt = dst_rtable(__sk_dst_check(sk, 0)); struct inet_sock *inet = inet_sk(sk); - struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0); __be32 daddr; struct ip_options_rcu *inet_opt; struct flowi4 *fl4; @@ -1481,7 +1484,6 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) struct sk_buff *p; unsigned int hlen; unsigned int off; - unsigned int id; int flush = 1; int proto; @@ -1507,13 +1509,10 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) goto out; NAPI_GRO_CB(skb)->proto = proto; - id = ntohl(*(__be32 *)&iph->id); - flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF)); - id >>= 16; + flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (ntohl(*(__be32 *)&iph->id) & ~IP_DF)); list_for_each_entry(p, head, list) { struct iphdr *iph2; - u16 flush_id; if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -1530,48 +1529,10 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) NAPI_GRO_CB(p)->same_flow = 0; continue; } - - /* All fields must match except length and checksum. */ - NAPI_GRO_CB(p)->flush |= - (iph->ttl ^ iph2->ttl) | - (iph->tos ^ iph2->tos) | - ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)); - - NAPI_GRO_CB(p)->flush |= flush; - - /* We need to store of the IP ID check to be included later - * when we can verify that this packet does in fact belong - * to a given flow. - */ - flush_id = (u16)(id - ntohs(iph2->id)); - - /* This bit of code makes it much easier for us to identify - * the cases where we are doing atomic vs non-atomic IP ID - * checks. Specifically an atomic check can return IP ID - * values 0 - 0xFFFF, while a non-atomic check can only - * return 0 or 0xFFFF. - */ - if (!NAPI_GRO_CB(p)->is_atomic || - !(iph->frag_off & htons(IP_DF))) { - flush_id ^= NAPI_GRO_CB(p)->count; - flush_id = flush_id ? 0xFFFF : 0; - } - - /* If the previous IP ID value was based on an atomic - * datagram we can overwrite the value and ignore it. - */ - if (NAPI_GRO_CB(skb)->is_atomic) - NAPI_GRO_CB(p)->flush_id = flush_id; - else - NAPI_GRO_CB(p)->flush_id |= flush_id; } - NAPI_GRO_CB(skb)->is_atomic = !!(iph->frag_off & htons(IP_DF)); NAPI_GRO_CB(skb)->flush |= flush; - skb_set_network_header(skb, off); - /* The above will be needed by the transport layer if there is one - * immediately following this IP hdr. - */ + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off; /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 0d0d725b46ad..11c1519b3699 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -456,7 +456,8 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) /*unsigned long now; */ struct net *net = dev_net(dev); - rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev)); + rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev), + RT_SCOPE_UNIVERSE); if (IS_ERR(rt)) return 1; if (rt->dst.dev != dev) { @@ -1002,6 +1003,55 @@ out_of_mem: * User level interface (ioctl) */ +static struct net_device *arp_req_dev_by_name(struct net *net, struct arpreq *r, + bool getarp) +{ + struct net_device *dev; + + if (getarp) + dev = dev_get_by_name_rcu(net, r->arp_dev); + else + dev = __dev_get_by_name(net, r->arp_dev); + if (!dev) + return ERR_PTR(-ENODEV); + + /* Mmmm... It is wrong... ARPHRD_NETROM == 0 */ + if (!r->arp_ha.sa_family) + r->arp_ha.sa_family = dev->type; + + if ((r->arp_flags & ATF_COM) && r->arp_ha.sa_family != dev->type) + return ERR_PTR(-EINVAL); + + return dev; +} + +static struct net_device *arp_req_dev(struct net *net, struct arpreq *r) +{ + struct net_device *dev; + struct rtable *rt; + __be32 ip; + + if (r->arp_dev[0]) + return arp_req_dev_by_name(net, r, false); + + if (r->arp_flags & ATF_PUBL) + return NULL; + + ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; + + rt = ip_route_output(net, ip, 0, 0, 0, RT_SCOPE_LINK); + if (IS_ERR(rt)) + return ERR_CAST(rt); + + dev = rt->dst.dev; + ip_rt_put(rt); + + if (!dev) + return ERR_PTR(-EINVAL); + + return dev; +} + /* * Set (create) an ARP cache entry. */ @@ -1022,11 +1072,8 @@ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) static int arp_req_set_public(struct net *net, struct arpreq *r, struct net_device *dev) { - __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; - if (mask && mask != htonl(0xFFFFFFFF)) - return -EINVAL; if (!dev && (r->arp_flags & ATF_COM)) { dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family, r->arp_ha.sa_data); @@ -1034,6 +1081,8 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, return -ENODEV; } if (mask) { + __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; + if (!pneigh_lookup(&arp_tbl, net, &ip, dev, 1)) return -ENOBUFS; return 0; @@ -1042,29 +1091,20 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, return arp_req_set_proxy(net, dev, 1); } -static int arp_req_set(struct net *net, struct arpreq *r, - struct net_device *dev) +static int arp_req_set(struct net *net, struct arpreq *r) { - __be32 ip; struct neighbour *neigh; + struct net_device *dev; + __be32 ip; int err; + dev = arp_req_dev(net, r); + if (IS_ERR(dev)) + return PTR_ERR(dev); + if (r->arp_flags & ATF_PUBL) return arp_req_set_public(net, r, dev); - ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; - if (r->arp_flags & ATF_PERM) - r->arp_flags |= ATF_COM; - if (!dev) { - struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0); - - if (IS_ERR(rt)) - return PTR_ERR(rt); - dev = rt->dst.dev; - ip_rt_put(rt); - if (!dev) - return -EINVAL; - } switch (dev->type) { #if IS_ENABLED(CONFIG_FDDI) case ARPHRD_FDDI: @@ -1086,12 +1126,18 @@ static int arp_req_set(struct net *net, struct arpreq *r, break; } + ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; + neigh = __neigh_lookup_errno(&arp_tbl, &ip, dev); err = PTR_ERR(neigh); if (!IS_ERR(neigh)) { unsigned int state = NUD_STALE; - if (r->arp_flags & ATF_PERM) + + if (r->arp_flags & ATF_PERM) { + r->arp_flags |= ATF_COM; state = NUD_PERMANENT; + } + err = neigh_update(neigh, (r->arp_flags & ATF_COM) ? r->arp_ha.sa_data : NULL, state, NEIGH_UPDATE_F_OVERRIDE | @@ -1115,27 +1161,40 @@ static unsigned int arp_state_to_flags(struct neighbour *neigh) * Get an ARP cache entry. */ -static int arp_req_get(struct arpreq *r, struct net_device *dev) +static int arp_req_get(struct net *net, struct arpreq *r) { __be32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr; struct neighbour *neigh; - int err = -ENXIO; + struct net_device *dev; + + if (!r->arp_dev[0]) + return -ENODEV; + + dev = arp_req_dev_by_name(net, r, true); + if (IS_ERR(dev)) + return PTR_ERR(dev); neigh = neigh_lookup(&arp_tbl, &ip, dev); - if (neigh) { - if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) { - read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, - min(dev->addr_len, sizeof(r->arp_ha.sa_data_min))); - r->arp_flags = arp_state_to_flags(neigh); - read_unlock_bh(&neigh->lock); - r->arp_ha.sa_family = dev->type; - strscpy(r->arp_dev, dev->name, sizeof(r->arp_dev)); - err = 0; - } + if (!neigh) + return -ENXIO; + + if (READ_ONCE(neigh->nud_state) & NUD_NOARP) { neigh_release(neigh); + return -ENXIO; } - return err; + + read_lock_bh(&neigh->lock); + memcpy(r->arp_ha.sa_data, neigh->ha, + min(dev->addr_len, sizeof(r->arp_ha.sa_data_min))); + r->arp_flags = arp_state_to_flags(neigh); + read_unlock_bh(&neigh->lock); + + neigh_release(neigh); + + r->arp_ha.sa_family = dev->type; + netdev_copy_name(dev, r->arp_dev); + + return 0; } int arp_invalidate(struct net_device *dev, __be32 ip, bool force) @@ -1166,36 +1225,31 @@ int arp_invalidate(struct net_device *dev, __be32 ip, bool force) static int arp_req_delete_public(struct net *net, struct arpreq *r, struct net_device *dev) { - __be32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr; __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; - if (mask == htonl(0xFFFFFFFF)) - return pneigh_delete(&arp_tbl, net, &ip, dev); + if (mask) { + __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; - if (mask) - return -EINVAL; + return pneigh_delete(&arp_tbl, net, &ip, dev); + } return arp_req_set_proxy(net, dev, 0); } -static int arp_req_delete(struct net *net, struct arpreq *r, - struct net_device *dev) +static int arp_req_delete(struct net *net, struct arpreq *r) { + struct net_device *dev; __be32 ip; + dev = arp_req_dev(net, r); + if (IS_ERR(dev)) + return PTR_ERR(dev); + if (r->arp_flags & ATF_PUBL) return arp_req_delete_public(net, r, dev); ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; - if (!dev) { - struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0); - if (IS_ERR(rt)) - return PTR_ERR(rt); - dev = rt->dst.dev; - ip_rt_put(rt); - if (!dev) - return -EINVAL; - } + return arp_invalidate(dev, ip, true); } @@ -1205,9 +1259,9 @@ static int arp_req_delete(struct net *net, struct arpreq *r, int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) { - int err; struct arpreq r; - struct net_device *dev = NULL; + __be32 *netmask; + int err; switch (cmd) { case SIOCDARP: @@ -1230,42 +1284,34 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!(r.arp_flags & ATF_PUBL) && (r.arp_flags & (ATF_NETMASK | ATF_DONTPUB))) return -EINVAL; + + netmask = &((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr; if (!(r.arp_flags & ATF_NETMASK)) - ((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr = - htonl(0xFFFFFFFFUL); - rtnl_lock(); - if (r.arp_dev[0]) { - err = -ENODEV; - dev = __dev_get_by_name(net, r.arp_dev); - if (!dev) - goto out; - - /* Mmmm... It is wrong... ARPHRD_NETROM==0 */ - if (!r.arp_ha.sa_family) - r.arp_ha.sa_family = dev->type; - err = -EINVAL; - if ((r.arp_flags & ATF_COM) && r.arp_ha.sa_family != dev->type) - goto out; - } else if (cmd == SIOCGARP) { - err = -ENODEV; - goto out; - } + *netmask = htonl(0xFFFFFFFFUL); + else if (*netmask && *netmask != htonl(0xFFFFFFFFUL)) + return -EINVAL; switch (cmd) { case SIOCDARP: - err = arp_req_delete(net, &r, dev); + rtnl_lock(); + err = arp_req_delete(net, &r); + rtnl_unlock(); break; case SIOCSARP: - err = arp_req_set(net, &r, dev); + rtnl_lock(); + err = arp_req_set(net, &r); + rtnl_unlock(); break; case SIOCGARP: - err = arp_req_get(&r, dev); + rcu_read_lock(); + err = arp_req_get(net, &r); + rcu_read_unlock(); + + if (!err && copy_to_user(arg, &r, sizeof(r))) + err = -EFAULT; break; } -out: - rtnl_unlock(); - if (cmd == SIOCGARP && !err && copy_to_user(arg, &r, sizeof(r))) - err = -EFAULT; + return err; } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 7f518ea5f4ac..18227757ec0c 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -107,6 +107,9 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, case offsetof(struct tcp_sock, snd_cwnd_cnt): end = offsetofend(struct tcp_sock, snd_cwnd_cnt); break; + case offsetof(struct tcp_sock, snd_cwnd_stamp): + end = offsetofend(struct tcp_sock, snd_cwnd_stamp); + break; case offsetof(struct tcp_sock, snd_ssthresh): end = offsetofend(struct tcp_sock, snd_ssthresh); break; @@ -307,7 +310,8 @@ static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk) return 0; } -static void bpf_tcp_ca_cong_control(struct sock *sk, const struct rate_sample *rs) +static void bpf_tcp_ca_cong_control(struct sock *sk, u32 ack, int flag, + const struct rate_sample *rs) { } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 8b17d83e5fde..dd6d46015058 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1815,6 +1815,7 @@ static int cipso_v4_genopt(unsigned char *buf, u32 buf_len, * @sk: the socket * @doi_def: the CIPSO DOI to use * @secattr: the specific security attributes of the socket + * @sk_locked: true if caller holds the socket lock * * Description: * Set the CIPSO option on the given socket using the DOI definition and @@ -1826,7 +1827,8 @@ static int cipso_v4_genopt(unsigned char *buf, u32 buf_len, */ int cipso_v4_sock_setattr(struct sock *sk, const struct cipso_v4_doi *doi_def, - const struct netlbl_lsm_secattr *secattr) + const struct netlbl_lsm_secattr *secattr, + bool sk_locked) { int ret_val = -EPERM; unsigned char *buf = NULL; @@ -1876,8 +1878,7 @@ int cipso_v4_sock_setattr(struct sock *sk, sk_inet = inet_sk(sk); - old = rcu_dereference_protected(sk_inet->inet_opt, - lockdep_sock_is_held(sk)); + old = rcu_dereference_protected(sk_inet->inet_opt, sk_locked); if (inet_test_bit(IS_ICSK, sk)) { sk_conn = inet_csk(sk); if (old) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 7a437f0d4190..d09f557eaa77 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -224,6 +224,7 @@ static struct in_ifaddr *inet_alloc_ifa(void) static void inet_rcu_free_ifa(struct rcu_head *head) { struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head); + if (ifa->ifa_dev) in_dev_put(ifa->ifa_dev); kfree(ifa); @@ -231,7 +232,11 @@ static void inet_rcu_free_ifa(struct rcu_head *head) static void inet_free_ifa(struct in_ifaddr *ifa) { - call_rcu(&ifa->rcu_head, inet_rcu_free_ifa); + /* Our reference to ifa->ifa_dev must be freed ASAP + * to release the reference to the netdev the same way. + * in_dev_put() -> in_dev_finish_destroy() -> netdev_put() + */ + call_rcu_hurry(&ifa->rcu_head, inet_rcu_free_ifa); } static void in_dev_free_rcu(struct rcu_head *head) @@ -1683,6 +1688,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa, struct nlmsghdr *nlh; unsigned long tstamp; u32 preferred, valid; + u32 flags; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm), args->flags); @@ -1692,7 +1698,13 @@ static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa, ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; - ifm->ifa_flags = READ_ONCE(ifa->ifa_flags); + + flags = READ_ONCE(ifa->ifa_flags); + /* Warning : ifm->ifa_flags is an __u8, it holds only 8 bits. + * The 32bit value is given in IFA_FLAGS attribute. + */ + ifm->ifa_flags = (__u8)flags; + ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; @@ -1701,7 +1713,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa, goto nla_put_failure; tstamp = READ_ONCE(ifa->ifa_tstamp); - if (!(ifm->ifa_flags & IFA_F_PERMANENT)) { + if (!(flags & IFA_F_PERMANENT)) { preferred = READ_ONCE(ifa->ifa_preferred_lft); valid = READ_ONCE(ifa->ifa_valid_lft); if (preferred != INFINITY_LIFE_TIME) { @@ -1732,7 +1744,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa, nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || (ifa->ifa_proto && nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) || - nla_put_u32(skb, IFA_FLAGS, ifm->ifa_flags) || + nla_put_u32(skb, IFA_FLAGS, flags) || (ifa->ifa_rt_priority && nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) || put_cacheinfo(skb, READ_ONCE(ifa->ifa_cstamp), tstamp, @@ -1875,10 +1887,11 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) goto done; if (fillargs.ifindex) { - err = -ENODEV; dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); - if (!dev) + if (!dev) { + err = -ENODEV; goto done; + } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto done; @@ -1890,7 +1903,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = inet_base_seq(tgt_net); - for_each_netdev_dump(net, dev, ctx->ifindex) { + for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; @@ -2515,7 +2528,7 @@ static int ipv4_doint_and_flush(struct ctl_table *ctl, int write, static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; - struct ctl_table devinet_vars[__IPV4_DEVCONF_MAX]; + struct ctl_table devinet_vars[IPV4_DEVCONF_MAX]; } devinet_sysctl = { .devinet_vars = { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", @@ -2578,7 +2591,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, if (!t) goto out; - for (i = 0; i < ARRAY_SIZE(t->devinet_vars) - 1; i++) { + for (i = 0; i < ARRAY_SIZE(t->devinet_vars); i++) { t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf; t->devinet_vars[i].extra1 = p; t->devinet_vars[i].extra2 = net; @@ -2652,7 +2665,6 @@ static struct ctl_table ctl_forward_entry[] = { .extra1 = &ipv4_devconf, .extra2 = &init_net, }, - { }, }; #endif @@ -2749,7 +2761,7 @@ err_alloc_all: static __net_exit void devinet_exit_net(struct net *net) { #ifdef CONFIG_SYSCTL - struct ctl_table *tbl; + const struct ctl_table *tbl; tbl = net->ipv4.forw_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.forw_hdr); @@ -2793,7 +2805,7 @@ void __init devinet_init(void) rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, 0); rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, 0); rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, - RTNL_FLAG_DUMP_UNLOCKED); + RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE); rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf, inet_netconf_dump_devconf, RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index d33d12421814..3968d3f98e08 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -20,6 +20,7 @@ #include <net/udp.h> #include <net/tcp.h> #include <net/espintcp.h> +#include <linux/skbuff_ref.h> #include <linux/highmem.h> @@ -114,7 +115,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - skb_page_unref(skb, sg_page(sg), false); + skb_page_unref(sg_page(sg), skb->pp_recycle); } #ifdef CONFIG_INET_ESPINTCP @@ -347,7 +348,6 @@ static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb, __be16 dport) { struct udphdr *uh; - __be32 *udpdata32; unsigned int len; len = skb->len + esp->tailen - skb_transport_offset(skb); @@ -362,12 +362,6 @@ static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb, *skb_mac_header(skb) = IPPROTO_UDP; - if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) { - udpdata32 = (__be32 *)(uh + 1); - udpdata32[0] = udpdata32[1] = 0; - return (struct ip_esp_hdr *)(udpdata32 + 2); - } - return (struct ip_esp_hdr *)(uh + 1); } @@ -423,7 +417,6 @@ static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb, switch (encap_type) { default: case UDP_ENCAP_ESPINUDP: - case UDP_ENCAP_ESPINUDP_NON_IKE: esph = esp_output_udp_encap(skb, encap_type, esp, sport, dport); break; case TCP_ENCAP_ESPINTCP: @@ -775,7 +768,6 @@ int esp_input_done2(struct sk_buff *skb, int err) source = th->source; break; case UDP_ENCAP_ESPINUDP: - case UDP_ENCAP_ESPINUDP_NON_IKE: source = uh->source; break; default: @@ -1179,9 +1171,6 @@ static int esp_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) case UDP_ENCAP_ESPINUDP: x->props.header_len += sizeof(struct udphdr); break; - case UDP_ENCAP_ESPINUDP_NON_IKE: - x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32); - break; #ifdef CONFIG_INET_ESPINTCP case TCP_ENCAP_ESPINTCP: /* only the length field, TCP encap is done by diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 48741352a88a..7ad2cafb9276 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1660,5 +1660,5 @@ void __init ip_fib_init(void) rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, 0); rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, 0); rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, - RTNL_FLAG_DUMP_UNLOCKED); + RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE); } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 5eb1b8d302bb..f669da98d11d 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -254,7 +254,7 @@ void free_fib_info(struct fib_info *fi) return; } - call_rcu(&fi->rcu, free_fib_info_rcu); + call_rcu_hurry(&fi->rcu, free_fib_info_rcu); } EXPORT_SYMBOL_GPL(free_fib_info); diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c index 06e5572f296f..54984f3170a8 100644 --- a/net/ipv4/fou_bpf.c +++ b/net/ipv4/fou_bpf.c @@ -64,7 +64,7 @@ __bpf_kfunc int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx, info->encap.type = TUNNEL_ENCAP_NONE; } - if (info->key.tun_flags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)) info->encap.flags |= TUNNEL_ENCAP_FLAG_CSUM; info->encap.sport = encap->sport; diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 3757fd93523f..6701a98d9a9f 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -73,7 +73,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; - tpi->flags = gre_flags_to_tnl_flags(greh->flags); + gre_flags_to_tnl_flags(tpi->flags, greh->flags); hdr_len = gre_calc_hlen(tpi->flags); if (!pskb_may_pull(skb, nhs + hdr_len)) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index e63a3bf99617..ab6d0d98dbc3 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -92,6 +92,9 @@ #include <net/inet_common.h> #include <net/ip_fib.h> #include <net/l3mdev.h> +#include <net/addrconf.h> +#define CREATE_TRACE_POINTS +#include <trace/events/icmp.h> /* * Build xmit assembly blocks @@ -482,6 +485,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct icmp_bxm *param) { struct net_device *route_lookup_dev; + struct dst_entry *dst, *dst2; struct rtable *rt, *rt2; struct flowi4 fl4_dec; int err; @@ -507,16 +511,17 @@ static struct rtable *icmp_route_lookup(struct net *net, /* No need to clone since we're just using its address. */ rt2 = rt; - rt = (struct rtable *) xfrm_lookup(net, &rt->dst, - flowi4_to_flowi(fl4), NULL, 0); - if (!IS_ERR(rt)) { + dst = xfrm_lookup(net, &rt->dst, + flowi4_to_flowi(fl4), NULL, 0); + rt = dst_rtable(dst); + if (!IS_ERR(dst)) { if (rt != rt2) return rt; - } else if (PTR_ERR(rt) == -EPERM) { + } else if (PTR_ERR(dst) == -EPERM) { rt = NULL; - } else + } else { return rt; - + } err = xfrm_decode_session_reverse(net, skb_in, flowi4_to_flowi(&fl4_dec), AF_INET); if (err) goto relookup_failed; @@ -550,19 +555,19 @@ static struct rtable *icmp_route_lookup(struct net *net, if (err) goto relookup_failed; - rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst, - flowi4_to_flowi(&fl4_dec), NULL, - XFRM_LOOKUP_ICMP); - if (!IS_ERR(rt2)) { + dst2 = xfrm_lookup(net, &rt2->dst, flowi4_to_flowi(&fl4_dec), NULL, + XFRM_LOOKUP_ICMP); + rt2 = dst_rtable(dst2); + if (!IS_ERR(dst2)) { dst_release(&rt->dst); memcpy(fl4, &fl4_dec, sizeof(*fl4)); rt = rt2; - } else if (PTR_ERR(rt2) == -EPERM) { + } else if (PTR_ERR(dst2) == -EPERM) { if (rt) dst_release(&rt->dst); return rt2; } else { - err = PTR_ERR(rt2); + err = PTR_ERR(dst2); goto relookup_failed; } return rt; @@ -767,6 +772,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, if (!fl4.saddr) fl4.saddr = htonl(INADDR_DUMMY); + trace_icmp_send(skb_in, type, code); + icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); @@ -1032,6 +1039,8 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) struct icmp_ext_hdr *ext_hdr, _ext_hdr; struct icmp_ext_echo_iio *iio, _iio; struct net *net = dev_net(skb->dev); + struct inet6_dev *in6_dev; + struct in_device *in_dev; struct net_device *dev; char buff[IFNAMSIZ]; u16 ident_len; @@ -1115,10 +1124,15 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) /* Fill bits in reply message */ if (dev->flags & IFF_UP) status |= ICMP_EXT_ECHOREPLY_ACTIVE; - if (__in_dev_get_rcu(dev) && __in_dev_get_rcu(dev)->ifa_list) + + in_dev = __in_dev_get_rcu(dev); + if (in_dev && rcu_access_pointer(in_dev->ifa_list)) status |= ICMP_EXT_ECHOREPLY_IPV4; - if (!list_empty(&rcu_dereference(dev->ip6_ptr)->addr_list)) + + in6_dev = __in6_dev_get(dev); + if (in6_dev && !list_empty(&in6_dev->addr_list)) status |= ICMP_EXT_ECHOREPLY_IPV6; + dev_put(dev); icmphdr->un.echo.sequence |= htons(status); return true; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 717e97a389a8..9bf09de6a2e7 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1842,7 +1842,8 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) if (!dev) { struct rtable *rt = ip_route_output(net, imr->imr_multiaddr.s_addr, - 0, 0, 0); + 0, 0, 0, + RT_SCOPE_UNIVERSE); if (!IS_ERR(rt)) { dev = rt->dst.dev; ip_rt_put(rt); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 7d8090f109ef..d81f74ce0f02 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -203,8 +203,15 @@ static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { - if (sk->sk_family == AF_INET && ipv6_only_sock(sk2)) - return false; + if (ipv6_only_sock(sk2)) { + if (sk->sk_family == AF_INET) + return false; + +#if IS_ENABLED(CONFIG_IPV6) + if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + return false; +#endif + } return inet_bind_conflict(sk, sk2, sk_uid, relax, reuseport_cb_ok, reuseport_ok); @@ -287,6 +294,7 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l struct sock_reuseport *reuseport_cb; struct inet_bind_hashbucket *head2; struct inet_bind2_bucket *tb2; + bool conflict = false; bool reuseport_cb_ok; rcu_read_lock(); @@ -299,18 +307,20 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l spin_lock(&head2->lock); - inet_bind_bucket_for_each(tb2, &head2->chain) - if (inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk)) - break; + inet_bind_bucket_for_each(tb2, &head2->chain) { + if (!inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk)) + continue; - if (tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, - reuseport_ok)) { - spin_unlock(&head2->lock); - return true; + if (!inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok)) + continue; + + conflict = true; + break; } spin_unlock(&head2->lock); - return false; + + return conflict; } /* @@ -651,7 +661,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) /* * This will accept the next outstanding connection. */ -struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) +struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; @@ -670,7 +680,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) /* Find already established connection */ if (reqsk_queue_empty(queue)) { - long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + long timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); /* If this is a non blocking socket don't sleep */ error = -EAGAIN; @@ -682,6 +692,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) goto out_err; } req = reqsk_queue_remove(queue, sk); + arg->is_empty = reqsk_queue_empty(queue); newsk = req->sk; if (sk->sk_protocol == IPPROTO_TCP && @@ -735,7 +746,7 @@ out: out_err: newsk = NULL; req = NULL; - *err = error; + arg->err = error; goto out; } EXPORT_SYMBOL(inet_csk_accept); @@ -771,6 +782,20 @@ void inet_csk_clear_xmit_timers(struct sock *sk) } EXPORT_SYMBOL(inet_csk_clear_xmit_timers); +void inet_csk_clear_xmit_timers_sync(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + /* ongoing timer handlers need to acquire socket lock. */ + sock_not_owned_by_me(sk); + + icsk->icsk_pending = icsk->icsk_ack.pending = 0; + + sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer_sync(sk, &icsk->icsk_delack_timer); + sk_stop_timer_sync(sk, &sk->sk_timer); +} + void inet_csk_delete_keepalive_timer(struct sock *sk) { sk_stop_timer(sk, &sk->sk_timer); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 7072fc0783ef..faaec92a46ac 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -24,6 +24,8 @@ #include <net/ip.h> #include <net/ipv6.h> +#include "../core/sock_destructor.h" + /* Use skb->cb to track consecutive/adjacent fragments coming at * the end of the queue. Nodes in the rb-tree queue will * contain "runs" of one or more adjacent fragments. @@ -39,6 +41,7 @@ struct ipfrag_skb_cb { }; struct sk_buff *next_frag; int frag_run_len; + int ip_defrag_offset; }; #define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) @@ -172,7 +175,7 @@ static void fqdir_free_fn(struct work_struct *work) } } -static DECLARE_WORK(fqdir_free_work, fqdir_free_fn); +static DECLARE_DELAYED_WORK(fqdir_free_work, fqdir_free_fn); static void fqdir_work_fn(struct work_struct *work) { @@ -181,7 +184,7 @@ static void fqdir_work_fn(struct work_struct *work) rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL); if (llist_add(&fqdir->free_list, &fqdir_free_list)) - queue_work(system_wq, &fqdir_free_work); + queue_delayed_work(system_wq, &fqdir_free_work, HZ); } int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net) @@ -396,12 +399,12 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, */ if (!last) fragrun_create(q, skb); /* First fragment. */ - else if (last->ip_defrag_offset + last->len < end) { + else if (FRAG_CB(last)->ip_defrag_offset + last->len < end) { /* This is the common case: skb goes to the end. */ /* Detect and discard overlaps. */ - if (offset < last->ip_defrag_offset + last->len) + if (offset < FRAG_CB(last)->ip_defrag_offset + last->len) return IPFRAG_OVERLAP; - if (offset == last->ip_defrag_offset + last->len) + if (offset == FRAG_CB(last)->ip_defrag_offset + last->len) fragrun_append_to_last(q, skb); else fragrun_create(q, skb); @@ -418,13 +421,13 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, parent = *rbn; curr = rb_to_skb(parent); - curr_run_end = curr->ip_defrag_offset + + curr_run_end = FRAG_CB(curr)->ip_defrag_offset + FRAG_CB(curr)->frag_run_len; - if (end <= curr->ip_defrag_offset) + if (end <= FRAG_CB(curr)->ip_defrag_offset) rbn = &parent->rb_left; else if (offset >= curr_run_end) rbn = &parent->rb_right; - else if (offset >= curr->ip_defrag_offset && + else if (offset >= FRAG_CB(curr)->ip_defrag_offset && end <= curr_run_end) return IPFRAG_DUP; else @@ -438,7 +441,7 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, rb_insert_color(&skb->rbnode, &q->rb_fragments); } - skb->ip_defrag_offset = offset; + FRAG_CB(skb)->ip_defrag_offset = offset; return IPFRAG_OK; } @@ -448,13 +451,28 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, struct sk_buff *parent) { struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); - struct sk_buff **nextp; + void (*destructor)(struct sk_buff *); + unsigned int orig_truesize = 0; + struct sk_buff **nextp = NULL; + struct sock *sk = skb->sk; int delta; + if (sk && is_skb_wmem(skb)) { + /* TX: skb->sk might have been passed as argument to + * dst->output and must remain valid until tx completes. + * + * Move sk to reassembled skb and fix up wmem accounting. + */ + orig_truesize = skb->truesize; + destructor = skb->destructor; + } + if (head != skb) { fp = skb_clone(skb, GFP_ATOMIC); - if (!fp) - return NULL; + if (!fp) { + head = skb; + goto out_restore_sk; + } FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; if (RB_EMPTY_NODE(&skb->rbnode)) FRAG_CB(parent)->next_frag = fp; @@ -463,6 +481,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, &q->rb_fragments); if (q->fragments_tail == skb) q->fragments_tail = fp; + + if (orig_truesize) { + /* prevent skb_morph from releasing sk */ + skb->sk = NULL; + skb->destructor = NULL; + } skb_morph(skb, head); FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; rb_replace_node(&head->rbnode, &skb->rbnode, @@ -470,13 +494,13 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, consume_skb(head); head = skb; } - WARN_ON(head->ip_defrag_offset != 0); + WARN_ON(FRAG_CB(head)->ip_defrag_offset != 0); delta = -head->truesize; /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) - return NULL; + goto out_restore_sk; delta += head->truesize; if (delta) @@ -492,7 +516,7 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, clone = alloc_skb(0, GFP_ATOMIC); if (!clone) - return NULL; + goto out_restore_sk; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); for (i = 0; i < skb_shinfo(head)->nr_frags; i++) @@ -509,6 +533,21 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, nextp = &skb_shinfo(head)->frag_list; } +out_restore_sk: + if (orig_truesize) { + int ts_delta = head->truesize - orig_truesize; + + /* if this reassembled skb is fragmented later, + * fraglist skbs will get skb->sk assigned from head->sk, + * and each frag skb will be released via sock_wfree. + * + * Update sk_wmem_alloc. + */ + head->sk = sk; + head->destructor = destructor; + refcount_add(ts_delta, &sk->sk_wmem_alloc); + } + return nextp; } EXPORT_SYMBOL(inet_frag_reasm_prepare); @@ -516,6 +555,8 @@ EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, void *reasm_data, bool try_coalesce) { + struct sock *sk = is_skb_wmem(head) ? head->sk : NULL; + const unsigned int head_truesize = head->truesize; struct sk_buff **nextp = reasm_data; struct rb_node *rbn; struct sk_buff *fp; @@ -579,6 +620,9 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, head->prev = NULL; head->tstamp = q->stamp; head->mono_delivery_time = q->mono_delivery_time; + + if (sk) + refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc); } EXPORT_SYMBOL(inet_frag_reasm_finish); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index cf88eca5f1b4..48d0d494185b 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -565,7 +565,8 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, if (likely(inet_match(net, sk2, acookie, ports, dif, sdif))) { if (sk2->sk_state == TCP_TIME_WAIT) { tw = inet_twsk(sk2); - if (twsk_unique(sk, sk2, twp)) + if (sk->sk_protocol == IPPROTO_TCP && + tcp_twsk_unique(sk, sk2, twp)) break; } goto not_unique; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index e8de45d34d56..e28075f0006e 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -264,14 +264,18 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) EXPORT_SYMBOL_GPL(__inet_twsk_schedule); /* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */ -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) +void inet_twsk_purge(struct inet_hashinfo *hashinfo) { + struct inet_ehash_bucket *head = &hashinfo->ehash[0]; + unsigned int ehash_mask = hashinfo->ehash_mask; struct hlist_nulls_node *node; unsigned int slot; struct sock *sk; - for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { - struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; + for (slot = 0; slot <= ehash_mask; slot++, head++) { + if (hlist_nulls_empty(&head->chain)) + continue; + restart_rcu: cond_resched(); rcu_read_lock(); @@ -283,15 +287,13 @@ restart: TCPF_NEW_SYN_RECV)) continue; - if (sk->sk_family != family || - refcount_read(&sock_net(sk)->ns.count)) + if (refcount_read(&sock_net(sk)->ns.count)) continue; if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) continue; - if (unlikely(sk->sk_family != family || - refcount_read(&sock_net(sk)->ns.count))) { + if (refcount_read(&sock_net(sk)->ns.count)) { sock_gen_put(sk); goto restart; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index a4941f53b523..08e2c92e25ab 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -384,6 +384,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) } skb_dst_drop(skb); + skb_orphan(skb); return -EINPROGRESS; insert_error: @@ -487,7 +488,6 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) struct ipq *qp; __IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS); - skb_orphan(skb); /* Lookup (or create) queue header */ qp = ip_find(net, ip_hdr(skb), user, vif); @@ -580,7 +580,6 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = &dist_min, }, - { } }; /* secret interval has been deprecated */ @@ -593,7 +592,6 @@ static struct ctl_table ip4_frags_ctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { } }; static int __net_init ip4_frags_ns_ctl_register(struct net *net) @@ -632,7 +630,7 @@ err_alloc: static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; table = net->ipv4.frags_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.frags_hdr); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7b16c211b904..ba205473522e 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -265,6 +265,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; + IP_TUNNEL_DECLARE_FLAGS(flags); struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; @@ -272,18 +273,25 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int ver; int len; + ip_tunnel_flags_copy(flags, tpi->flags); + itn = net_generic(net, erspan_net_id); iph = ip_hdr(skb); if (is_erspan_type1(gre_hdr_len)) { ver = 0; - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, - tpi->flags | TUNNEL_NO_KEY, + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); } else { + if (unlikely(!pskb_may_pull(skb, + gre_hdr_len + sizeof(*ershdr)))) + return PACKET_REJECT; + ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, - tpi->flags | TUNNEL_KEY, + iph = ip_hdr(skb); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, tpi->key); } @@ -307,10 +315,9 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; - __be16 flags; - tpi->flags |= TUNNEL_KEY; - flags = tpi->flags; + __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); + ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, @@ -333,7 +340,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, ERSPAN_V2_MDSIZE); info = &tun_dst->u.tun_info; - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + info->key.tun_flags); info->options_len = sizeof(*md); } @@ -376,10 +384,13 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, tnl_params = &tunnel->parms.iph; if (tunnel->collect_md || tnl_params->daddr == 0) { - __be16 flags; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __be64 tun_id; - flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY); + __set_bit(IP_TUNNEL_CSUM_BIT, flags); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + ip_tunnel_flags_and(flags, tpi->flags, flags); + tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) @@ -459,12 +470,15 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - __be16 flags = tunnel->parms.o_flags; + IP_TUNNEL_DECLARE_FLAGS(flags); + + ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -478,10 +492,10 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tunnel_hlen; - __be16 flags; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || @@ -495,14 +509,19 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, goto err_free_skb; /* Push Tunnel header. */ - if (gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto err_free_skb; - flags = tun_info->key.tun_flags & - (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); + __set_bit(IP_TUNNEL_CSUM_BIT, flags); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + ip_tunnel_flags_and(flags, tun_info->key.tun_flags, flags); + gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -516,6 +535,7 @@ err_free_skb: static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; @@ -531,7 +551,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; key = &tun_info->key; - if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) goto err_free_skb; if (tun_info->options_len < sizeof(*md)) goto err_free_skb; @@ -584,8 +604,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; } - gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + gre_build_header(skb, 8, flags, proto, 0, + htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -659,7 +680,8 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, tnl_params = &tunnel->parms.iph; } - if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto free_skb; __gre_xmit(skb, dev, tnl_params, skb->protocol); @@ -701,7 +723,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, /* Push ERSPAN header */ if (tunnel->erspan_ver == 0) { proto = htons(ETH_P_ERSPAN); - tunnel->parms.o_flags &= ~TUNNEL_SEQ; + __clear_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags); } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, @@ -716,7 +738,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, goto free_skb; } - tunnel->parms.o_flags &= ~TUNNEL_KEY; + __clear_bit(IP_TUNNEL_KEY_BIT, tunnel->parms.o_flags); __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; @@ -739,7 +761,8 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } - if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) @@ -757,7 +780,6 @@ free_skb: static void ipgre_link_update(struct net_device *dev, bool set_mtu) { struct ip_tunnel *tunnel = netdev_priv(dev); - __be16 flags; int len; len = tunnel->tun_hlen; @@ -771,12 +793,11 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) dev->needed_headroom += len; if (set_mtu) - dev->mtu = max_t(int, dev->mtu - len, 68); + WRITE_ONCE(dev->mtu, max_t(int, dev->mtu - len, 68)); - flags = tunnel->parms.o_flags; - - if (flags & TUNNEL_SEQ || - (flags & TUNNEL_CSUM && tunnel->encap.type != TUNNEL_ENCAP_NONE)) { + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags) || + (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && + tunnel->encap.type != TUNNEL_ENCAP_NONE)) { dev->features &= ~NETIF_F_GSO_SOFTWARE; dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; } else { @@ -785,20 +806,29 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) } } -static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, +static int ipgre_tunnel_ctl(struct net_device *dev, + struct ip_tunnel_parm_kern *p, int cmd) { + __be16 i_flags, o_flags; int err; + if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || + !ip_tunnel_flags_is_be16_compat(p->o_flags)) + return -EOVERFLOW; + + i_flags = ip_tunnel_flags_to_be16(p->i_flags); + o_flags = ip_tunnel_flags_to_be16(p->o_flags); + if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_GRE || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)) || - ((p->i_flags | p->o_flags) & (GRE_VERSION | GRE_ROUTING))) + ((i_flags | o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } - p->i_flags = gre_flags_to_tnl_flags(p->i_flags); - p->o_flags = gre_flags_to_tnl_flags(p->o_flags); + gre_flags_to_tnl_flags(p->i_flags, i_flags); + gre_flags_to_tnl_flags(p->o_flags, o_flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) @@ -807,15 +837,18 @@ static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); - t->parms.i_flags = p->i_flags; - t->parms.o_flags = p->o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } - p->i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); - p->o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); + i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); + ip_tunnel_flags_from_be16(p->i_flags, i_flags); + o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); + ip_tunnel_flags_from_be16(p->o_flags, o_flags); + return 0; } @@ -955,7 +988,6 @@ static void ipgre_tunnel_setup(struct net_device *dev) static void __gre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; - __be16 flags; tunnel = netdev_priv(dev); tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); @@ -967,14 +999,13 @@ static void __gre_tunnel_init(struct net_device *dev) dev->features |= GRE_FEATURES | NETIF_F_LLTX; dev->hw_features |= GRE_FEATURES; - flags = tunnel->parms.o_flags; - /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ - if (flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags)) return; - if (flags & TUNNEL_CSUM && tunnel->encap.type != TUNNEL_ENCAP_NONE) + if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && + tunnel->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; @@ -1131,7 +1162,7 @@ static int erspan_validate(struct nlattr *tb[], struct nlattr *data[], static int ipgre_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); @@ -1147,10 +1178,12 @@ static int ipgre_netlink_parms(struct net_device *dev, parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) - parms->i_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_IFLAGS])); + gre_flags_to_tnl_flags(parms->i_flags, + nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) - parms->o_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_OFLAGS])); + gre_flags_to_tnl_flags(parms->o_flags, + nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); @@ -1198,7 +1231,7 @@ static int ipgre_netlink_parms(struct net_device *dev, static int erspan_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); @@ -1357,7 +1390,7 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip_tunnel_parm p; + struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; @@ -1375,7 +1408,7 @@ static int erspan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip_tunnel_parm p; + struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; @@ -1394,8 +1427,8 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; - struct ip_tunnel_parm p; int err; err = ipgre_newlink_encap_setup(dev, data); @@ -1410,8 +1443,8 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], if (err < 0) return err; - t->parms.i_flags = p.i_flags; - t->parms.o_flags = p.o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); ipgre_link_update(dev, !tb[IFLA_MTU]); @@ -1423,8 +1456,8 @@ static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; - struct ip_tunnel_parm p; int err; err = ipgre_newlink_encap_setup(dev, data); @@ -1439,8 +1472,8 @@ static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], if (err < 0) return err; - t->parms.i_flags = p.i_flags; - t->parms.o_flags = p.o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); return 0; } @@ -1496,8 +1529,10 @@ static size_t ipgre_get_size(const struct net_device *dev) static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm *p = &t->parms; - __be16 o_flags = p->o_flags; + struct ip_tunnel_parm_kern *p = &t->parms; + IP_TUNNEL_DECLARE_FLAGS(o_flags); + + ip_tunnel_flags_copy(o_flags, p->o_flags); if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, @@ -1545,7 +1580,7 @@ static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) if (t->erspan_ver <= 2) { if (t->erspan_ver != 0 && !t->collect_md) - t->parms.o_flags |= TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags); if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) goto nla_put_failure; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 5e9c8156656a..d6fbcbd2358a 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -616,7 +616,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, dst = skb_dst(skb); if (curr_dst != dst) { hint = ip_extract_route_hint(net, skb, - ((struct rtable *)dst)->rt_type); + dst_rtable(dst)->rt_type); /* dispatch old sublist */ if (!list_empty(&sublist)) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 1fe794967211..9500031a1f55 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -198,7 +198,7 @@ EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - struct rtable *rt = (struct rtable *)dst; + struct rtable *rt = dst_rtable(dst); struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; @@ -475,7 +475,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, goto packet_routed; /* Make sure we can route this packet. */ - rt = (struct rtable *)__sk_dst_check(sk, 0); + rt = dst_rtable(__sk_dst_check(sk, 0)); if (!rt) { __be32 daddr; @@ -971,7 +971,7 @@ static int __ip_append_data(struct sock *sk, bool zc = false; unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; - struct rtable *rt = (struct rtable *)cork->dst; + struct rtable *rt = dst_rtable(cork->dst); bool paged, hold_tskey, extra_uref = false; unsigned int wmem_alloc_delta = 0; u32 tskey = 0; @@ -1390,7 +1390,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options *opt = NULL; - struct rtable *rt = (struct rtable *)cork->dst; + struct rtable *rt = dst_rtable(cork->dst); struct iphdr *iph; u8 pmtudisc, ttl; __be16 df = 0; @@ -1473,7 +1473,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * by icmp_hdr(skb)->type. */ if (sk->sk_type == SOCK_RAW && - !inet_test_bit(HDRINCL, sk)) + !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH)) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 1b8d8ff9a237..bccef2fcf620 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -56,17 +56,13 @@ static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) IP_TNL_HASH_BITS); } -static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, - __be16 flags, __be32 key) +static bool ip_tunnel_key_match(const struct ip_tunnel_parm_kern *p, + const unsigned long *flags, __be32 key) { - if (p->i_flags & TUNNEL_KEY) { - if (flags & TUNNEL_KEY) - return key == p->i_key; - else - /* key expected, none present */ - return false; - } else - return !(flags & TUNNEL_KEY); + if (!test_bit(IP_TUNNEL_KEY_BIT, flags)) + return !test_bit(IP_TUNNEL_KEY_BIT, p->i_flags); + + return test_bit(IP_TUNNEL_KEY_BIT, p->i_flags) && p->i_key == key; } /* Fallback tunnel: no source, no destination, no key, no options @@ -81,7 +77,7 @@ static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, Given src, dst and key, find appropriate for input tunnel. */ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, - int link, __be16 flags, + int link, const unsigned long *flags, __be32 remote, __be32 local, __be32 key) { @@ -143,7 +139,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, } hlist_for_each_entry_rcu(t, head, hash_node) { - if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) || + if ((!test_bit(IP_TUNNEL_NO_KEY_BIT, flags) && + t->parms.i_key != key) || t->parms.iph.saddr != 0 || t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) @@ -171,7 +168,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, EXPORT_SYMBOL_GPL(ip_tunnel_lookup); static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { unsigned int h; __be32 remote; @@ -182,7 +179,8 @@ static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, else remote = 0; - if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI)) + if (!test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags) && + test_bit(IP_TUNNEL_VTI_BIT, parms->i_flags)) i_key = 0; h = ip_tunnel_hash(i_key, remote); @@ -206,17 +204,19 @@ static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t) } static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, int type) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; + IP_TUNNEL_DECLARE_FLAGS(flags); __be32 key = parms->i_key; - __be16 flags = parms->i_flags; int link = parms->link; struct ip_tunnel *t = NULL; struct hlist_head *head = ip_bucket(itn, parms); + ip_tunnel_flags_copy(flags, parms->i_flags); + hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && @@ -230,7 +230,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, static struct net_device *__ip_tunnel_create(struct net *net, const struct rtnl_link_ops *ops, - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { int err; struct ip_tunnel *tunnel; @@ -326,7 +326,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) static struct ip_tunnel *ip_tunnel_create(struct net *net, struct ip_tunnel_net *itn, - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { struct ip_tunnel *nt; struct net_device *dev; @@ -386,15 +386,15 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, } #endif - if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) || - ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) { + if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != + test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } - if (tunnel->parms.i_flags&TUNNEL_SEQ) { - if (!(tpi->flags&TUNNEL_SEQ) || + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { + if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); DEV_STATS_INC(tunnel->dev, rx_errors); @@ -543,7 +543,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, struct rt6_info *rt6; __be32 daddr; - rt6 = skb_valid_dst(skb) ? (struct rt6_info *)skb_dst(skb) : + rt6 = skb_valid_dst(skb) ? dst_rt6_info(skb_dst(skb)) : NULL; daddr = md ? dst : tunnel->parms.iph.daddr; @@ -638,7 +638,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } - if (key->tun_flags & TUNNEL_DONT_FRAGMENT) + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags)) df = htons(IP_DF); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen, key->u.ipv4.dst, true)) { @@ -871,7 +871,7 @@ EXPORT_SYMBOL_GPL(ip_tunnel_xmit); static void ip_tunnel_update(struct ip_tunnel_net *itn, struct ip_tunnel *t, struct net_device *dev, - struct ip_tunnel_parm *p, + struct ip_tunnel_parm_kern *p, bool set_mtu, __u32 fwmark) { @@ -897,13 +897,14 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, t->fwmark = fwmark; mtu = ip_tunnel_bind_dev(dev); if (set_mtu) - dev->mtu = mtu; + WRITE_ONCE(dev->mtu, mtu); } dst_cache_reset(&t->dst_cache); netdev_state_change(dev); } -int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, + int cmd) { int err = 0; struct ip_tunnel *t = netdev_priv(dev); @@ -927,10 +928,10 @@ int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) goto done; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); - if (!(p->i_flags & VTI_ISVTI)) { - if (!(p->i_flags & TUNNEL_KEY)) + if (!test_bit(IP_TUNNEL_VTI_BIT, p->i_flags)) { + if (!test_bit(IP_TUNNEL_KEY_BIT, p->i_flags)) p->i_key = 0; - if (!(p->o_flags & TUNNEL_KEY)) + if (!test_bit(IP_TUNNEL_KEY_BIT, p->o_flags)) p->o_key = 0; } @@ -1005,16 +1006,58 @@ done: } EXPORT_SYMBOL_GPL(ip_tunnel_ctl); +bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp, + const void __user *data) +{ + struct ip_tunnel_parm p; + + if (copy_from_user(&p, data, sizeof(p))) + return false; + + strscpy(kp->name, p.name); + kp->link = p.link; + ip_tunnel_flags_from_be16(kp->i_flags, p.i_flags); + ip_tunnel_flags_from_be16(kp->o_flags, p.o_flags); + kp->i_key = p.i_key; + kp->o_key = p.o_key; + memcpy(&kp->iph, &p.iph, min(sizeof(kp->iph), sizeof(p.iph))); + + return true; +} +EXPORT_SYMBOL_GPL(ip_tunnel_parm_from_user); + +bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp) +{ + struct ip_tunnel_parm p; + + if (!ip_tunnel_flags_is_be16_compat(kp->i_flags) || + !ip_tunnel_flags_is_be16_compat(kp->o_flags)) + return false; + + memset(&p, 0, sizeof(p)); + + strscpy(p.name, kp->name); + p.link = kp->link; + p.i_flags = ip_tunnel_flags_to_be16(kp->i_flags); + p.o_flags = ip_tunnel_flags_to_be16(kp->o_flags); + p.i_key = kp->i_key; + p.o_key = kp->o_key; + memcpy(&p.iph, &kp->iph, min(sizeof(p.iph), sizeof(kp->iph))); + + return !copy_to_user(data, &p, sizeof(p)); +} +EXPORT_SYMBOL_GPL(ip_tunnel_parm_to_user); + int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { - struct ip_tunnel_parm p; + struct ip_tunnel_parm_kern p; int err; - if (copy_from_user(&p, data, sizeof(p))) + if (!ip_tunnel_parm_from_user(&p, data)) return -EFAULT; err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, cmd); - if (!err && copy_to_user(data, &p, sizeof(p))) + if (!err && !ip_tunnel_parm_to_user(data, &p)) return -EFAULT; return err; } @@ -1039,7 +1082,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) new_mtu = max_mtu; } - dev->mtu = new_mtu; + WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu); @@ -1077,7 +1120,7 @@ struct net *ip_tunnel_get_link_net(const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - return tunnel->net; + return READ_ONCE(tunnel->net); } EXPORT_SYMBOL(ip_tunnel_get_link_net); @@ -1093,7 +1136,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname) { struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id); - struct ip_tunnel_parm parms; + struct ip_tunnel_parm_kern parms; unsigned int i; itn->rtnl_link_ops = ops; @@ -1171,7 +1214,7 @@ void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark) + struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *nt; struct net *net = dev_net(dev); @@ -1225,7 +1268,7 @@ err_register_netdevice: EXPORT_SYMBOL_GPL(ip_tunnel_newlink); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark) + struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *t; struct ip_tunnel *tunnel = netdev_priv(dev); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 80ccd6661aa3..a3676155be78 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -125,6 +125,7 @@ EXPORT_SYMBOL_GPL(__iptunnel_pull_header); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags) { + IP_TUNNEL_DECLARE_FLAGS(tun_flags) = { }; struct metadata_dst *res; struct ip_tunnel_info *dst, *src; @@ -144,10 +145,10 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, sizeof(struct in6_addr)); else dst->key.u.ipv4.dst = src->key.u.ipv4.src; - dst->key.tun_flags = src->key.tun_flags; + ip_tunnel_flags_copy(dst->key.tun_flags, src->key.tun_flags); dst->mode = src->mode | IP_TUNNEL_INFO_TX; ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src), - src->options_len, 0); + src->options_len, tun_flags); return res; } @@ -497,7 +498,7 @@ static int ip_tun_parse_opts_geneve(struct nlattr *attr, opt->opt_class = nla_get_be16(attr); attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE]; opt->type = nla_get_u8(attr); - info->key.tun_flags |= TUNNEL_GENEVE_OPT; + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags); } return sizeof(struct geneve_opt) + data_len; @@ -525,7 +526,7 @@ static int ip_tun_parse_opts_vxlan(struct nlattr *attr, attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP]; md->gbp = nla_get_u32(attr); md->gbp &= VXLAN_GBP_MASK; - info->key.tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags); } return sizeof(struct vxlan_metadata); @@ -574,7 +575,7 @@ static int ip_tun_parse_opts_erspan(struct nlattr *attr, set_hwid(&md->u.md2, nla_get_u8(attr)); } - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); } return sizeof(struct erspan_metadata); @@ -585,7 +586,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, { int err, rem, opt_len, opts_len = 0; struct nlattr *nla; - __be16 type = 0; + u32 type = 0; if (!attr) return 0; @@ -598,7 +599,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) { switch (nla_type(nla)) { case LWTUNNEL_IP_OPTS_GENEVE: - if (type && type != TUNNEL_GENEVE_OPT) + if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) return -EINVAL; opt_len = ip_tun_parse_opts_geneve(nla, info, opts_len, extack); @@ -607,7 +608,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, opts_len += opt_len; if (opts_len > IP_TUNNEL_OPTS_MAX) return -EINVAL; - type = TUNNEL_GENEVE_OPT; + type = IP_TUNNEL_GENEVE_OPT_BIT; break; case LWTUNNEL_IP_OPTS_VXLAN: if (type) @@ -617,7 +618,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_VXLAN_OPT; + type = IP_TUNNEL_VXLAN_OPT_BIT; break; case LWTUNNEL_IP_OPTS_ERSPAN: if (type) @@ -627,7 +628,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_ERSPAN_OPT; + type = IP_TUNNEL_ERSPAN_OPT_BIT; break; default: return -EINVAL; @@ -705,10 +706,16 @@ static int ip_tun_build_state(struct net *net, struct nlattr *attr, if (tb[LWTUNNEL_IP_TOS]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); - if (tb[LWTUNNEL_IP_FLAGS]) - tun_info->key.tun_flags |= - (nla_get_be16(tb[LWTUNNEL_IP_FLAGS]) & - ~TUNNEL_OPTIONS_PRESENT); + if (tb[LWTUNNEL_IP_FLAGS]) { + IP_TUNNEL_DECLARE_FLAGS(flags); + + ip_tunnel_flags_from_be16(flags, + nla_get_be16(tb[LWTUNNEL_IP_FLAGS])); + ip_tunnel_clear_options_present(flags); + + ip_tunnel_flags_or(tun_info->key.tun_flags, + tun_info->key.tun_flags, flags); + } tun_info->mode = IP_TUNNEL_INFO_TX; tun_info->options_len = opt_len; @@ -812,18 +819,18 @@ static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type, struct nlattr *nest; int err = 0; - if (!(tun_info->key.tun_flags & TUNNEL_OPTIONS_PRESENT)) + if (!ip_tunnel_is_options_present(tun_info->key.tun_flags)) return 0; nest = nla_nest_start_noflag(skb, type); if (!nest) return -ENOMEM; - if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT) + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_geneve(skb, tun_info); - else if (tun_info->key.tun_flags & TUNNEL_VXLAN_OPT) + else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_vxlan(skb, tun_info); - else if (tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT) + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_erspan(skb, tun_info); if (err) { @@ -846,7 +853,8 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb, nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || - nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags) || + nla_put_be16(skb, LWTUNNEL_IP_FLAGS, + ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) || ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info)) return -ENOMEM; @@ -857,11 +865,11 @@ static int ip_tun_opts_nlsize(struct ip_tunnel_info *info) { int opt_len; - if (!(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT)) + if (!ip_tunnel_is_options_present(info->key.tun_flags)) return 0; opt_len = nla_total_size(0); /* LWTUNNEL_IP_OPTS */ - if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) { struct geneve_opt *opt; int offset = 0; @@ -874,10 +882,10 @@ static int ip_tun_opts_nlsize(struct ip_tunnel_info *info) /* OPT_GENEVE_DATA */ offset += sizeof(*opt) + opt->length * 4; } - } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + } else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_VXLAN */ + nla_total_size(4); /* OPT_VXLAN_GBP */ - } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) { + } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) { struct erspan_metadata *md = ip_tunnel_info_opts(info); opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_ERSPAN */ @@ -984,10 +992,17 @@ static int ip6_tun_build_state(struct net *net, struct nlattr *attr, if (tb[LWTUNNEL_IP6_TC]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); - if (tb[LWTUNNEL_IP6_FLAGS]) - tun_info->key.tun_flags |= - (nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]) & - ~TUNNEL_OPTIONS_PRESENT); + if (tb[LWTUNNEL_IP6_FLAGS]) { + IP_TUNNEL_DECLARE_FLAGS(flags); + __be16 data; + + data = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]); + ip_tunnel_flags_from_be16(flags, data); + ip_tunnel_clear_options_present(flags); + + ip_tunnel_flags_or(tun_info->key.tun_flags, + tun_info->key.tun_flags, flags); + } tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6; tun_info->options_len = opt_len; @@ -1008,7 +1023,8 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb, nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) || - nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags) || + nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, + ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) || ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info)) return -ENOMEM; @@ -1116,7 +1132,7 @@ bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], EXPORT_SYMBOL_GPL(ip_tunnel_netlink_encap_parms); void ip_tunnel_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { if (data[IFLA_IPTUN_LINK]) parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); @@ -1139,8 +1155,12 @@ void ip_tunnel_netlink_parms(struct nlattr *data[], if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); - if (data[IFLA_IPTUN_FLAGS]) - parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + if (data[IFLA_IPTUN_FLAGS]) { + __be16 flags; + + flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + ip_tunnel_flags_from_be16(parms->i_flags, flags); + } if (data[IFLA_IPTUN_PROTO]) parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index ee587adb169f..14536da9f5dc 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -51,8 +51,11 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, const struct iphdr *iph = ip_hdr(skb); struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) @@ -167,7 +170,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct ip_tunnel_parm *parms = &tunnel->parms; + struct ip_tunnel_parm_kern *parms = &tunnel->parms; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ int pkt_len = skb->len; @@ -322,8 +325,11 @@ static int vti4_err(struct sk_buff *skb, u32 info) const struct iphdr *iph = (const struct iphdr *)skb->data; int protocol = iph->protocol; struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->daddr, iph->saddr, 0); if (!tunnel) return -1; @@ -373,8 +379,9 @@ static int vti4_err(struct sk_buff *skb, u32 info) } static int -vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; int err = 0; if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { @@ -383,20 +390,26 @@ vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) return -EINVAL; } - if (!(p->i_flags & GRE_KEY)) + if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || + !ip_tunnel_flags_is_be16_compat(p->o_flags)) + return -EOVERFLOW; + + if (!(ip_tunnel_flags_to_be16(p->i_flags) & GRE_KEY)) p->i_key = 0; - if (!(p->o_flags & GRE_KEY)) + if (!(ip_tunnel_flags_to_be16(p->o_flags) & GRE_KEY)) p->o_key = 0; - p->i_flags = VTI_ISVTI; + __set_bit(IP_TUNNEL_VTI_BIT, flags); + ip_tunnel_flags_copy(p->i_flags, flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { - p->i_flags |= GRE_KEY; - p->o_flags |= GRE_KEY; + ip_tunnel_flags_from_be16(flags, GRE_KEY); + ip_tunnel_flags_or(p->i_flags, p->i_flags, flags); + ip_tunnel_flags_or(p->o_flags, p->o_flags, flags); } return 0; } @@ -531,7 +544,7 @@ static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], } static void vti_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); @@ -541,7 +554,7 @@ static void vti_netlink_parms(struct nlattr *data[], if (!data) return; - parms->i_flags = VTI_ISVTI; + __set_bit(IP_TUNNEL_VTI_BIT, parms->i_flags); if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); @@ -566,7 +579,7 @@ static int vti_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip_tunnel_parm parms; + struct ip_tunnel_parm_kern parms; __u32 fwmark = 0; vti_netlink_parms(data, &parms, &fwmark); @@ -578,8 +591,8 @@ static int vti_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; - struct ip_tunnel_parm p; vti_netlink_parms(data, &p, &fwmark); return ip_tunnel_changelink(dev, tb, &p, fwmark); @@ -606,7 +619,7 @@ static size_t vti_get_size(const struct net_device *dev) static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm *p = &t->parms; + struct ip_tunnel_parm_kern *p = &t->parms; if (nla_put_u32(skb, IFLA_VTI_LINK, p->link) || nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key) || diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index f2696eaadbe6..923a2ef68c2f 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -130,13 +130,16 @@ static int ipip_err(struct sk_buff *skb, u32 info) 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; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; int err = 0; - t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, - iph->daddr, iph->saddr, 0); + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + + t = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->daddr, + iph->saddr, 0); if (!t) { err = -ENOENT; goto out; @@ -213,13 +216,16 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst = NULL; struct ip_tunnel *tunnel; const struct iphdr *iph; + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + iph = ip_hdr(skb); - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, - iph->saddr, iph->daddr, 0); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, + iph->daddr, 0); if (tunnel) { const struct tnl_ptk_info *tpi; @@ -238,7 +244,9 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (tunnel->collect_md) { - tun_dst = ip_tun_rx_dst(skb, 0, 0, 0); + ip_tunnel_flags_zero(flags); + + tun_dst = ip_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) return 0; ip_tunnel_md_udp_encap(skb, &tun_dst->u.tun_info); @@ -330,7 +338,7 @@ static bool ipip_tunnel_ioctl_verify_protocol(u8 ipproto) } static int -ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || @@ -340,7 +348,8 @@ ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) } p->i_key = p->o_key = 0; - p->i_flags = p->o_flags = 0; + ip_tunnel_flags_zero(p->i_flags); + ip_tunnel_flags_zero(p->o_flags); return ip_tunnel_ctl(dev, p, cmd); } @@ -405,8 +414,8 @@ static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], } static void ipip_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms, bool *collect_md, - __u32 *fwmark) + struct ip_tunnel_parm_kern *parms, + bool *collect_md, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); @@ -432,8 +441,8 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev, struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; + struct ip_tunnel_parm_kern p; __u32 fwmark = 0; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { @@ -452,8 +461,8 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; + struct ip_tunnel_parm_kern p; bool collect_md; __u32 fwmark = t->fwmark; @@ -510,7 +519,7 @@ static size_t ipip_get_size(const struct net_device *dev) static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct ip_tunnel_parm *parm = &tunnel->parms; + struct ip_tunnel_parm_kern *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index fd5c01c8489f..6c750bd13dd8 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -441,7 +441,7 @@ static bool ipmr_init_vif_indev(const struct net_device *dev) static struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) { struct net_device *tunnel_dev, *new_dev; - struct ip_tunnel_parm p = { }; + struct ip_tunnel_parm_kern p = { }; int err; tunnel_dev = __dev_get_by_name(net, "tunl0"); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 8f6e950163a7..1b991b889506 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -329,6 +329,7 @@ config NFT_COMPAT_ARP config IP_NF_ARPFILTER tristate "arptables-legacy packet filtering support" select IP_NF_ARPTABLES + select NETFILTER_FAMILY_ARP depends on NETFILTER_XTABLES help ARP packet filtering defines a table `filter', which has a series of diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 2407066b0fec..14365b20f1c5 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -956,6 +956,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -964,6 +966,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1254,6 +1258,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1262,6 +1268,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 7da1df4997d0..fe89a056eb06 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1108,6 +1108,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1116,6 +1118,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1492,6 +1496,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1500,6 +1506,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index b9062f4552ac..3ab908b74795 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -44,7 +44,7 @@ static int iptable_filter_table_init(struct net *net) return -ENOMEM; /* Entry 1 is the FORWARD hook */ ((struct ipt_standard *)repl->entries)[1].target.verdict = - forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; + forward ? -NF_ACCEPT - 1 : NF_DROP - 1; err = ipt_register_table(net, &packet_filter, repl, filter_ops); kfree(repl); diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index 69e331799604..73e66a088e25 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -58,6 +58,8 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) laddr = 0; indev = __in_dev_get_rcu(skb->dev); + if (!indev) + return daddr; in_dev_for_each_ifa_rcu(ifa, indev) { if (ifa->ifa_flags & IFA_F_SECONDARY) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 74928a9d1aa4..535856b0f0ed 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -768,8 +768,10 @@ static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used) struct net *net = nh->net; int err; - if (nexthop_notifiers_is_empty(net)) + if (nexthop_notifiers_is_empty(net)) { + *hw_stats_used = false; return 0; + } err = nh_notifier_grp_hw_stats_init(&info, nh); if (err) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 914bc9c35cc7..6c4664c681ca 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -33,6 +33,7 @@ #include <net/protocol.h> #include <net/tcp.h> #include <net/mptcp.h> +#include <net/proto_memory.h> #include <net/udp.h> #include <net/udplite.h> #include <linux/bottom_half.h> diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index dcb11f22cbf2..4cb43401e0e0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -612,6 +612,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = 0; + fl4.fl4_icmp_code = 0; + if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c8f76f56dc16..b3073d1c8f8f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -106,9 +106,6 @@ #include "fib_lookup.h" -#define RT_FL_TOS(oldflp4) \ - ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) - #define RT_GC_TIMEOUT (300*HZ) #define DEFAULT_MIN_PMTU (512 + 20 + 20) @@ -132,7 +129,8 @@ struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst); -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, @@ -498,15 +496,6 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) } EXPORT_SYMBOL(__ip_select_ident); -static void ip_rt_fix_tos(struct flowi4 *fl4) -{ - __u8 tos = RT_FL_TOS(fl4); - - fl4->flowi4_tos = tos & IPTOS_RT_MASK; - if (tos & RTO_ONLINK) - fl4->flowi4_scope = RT_SCOPE_LINK; -} - static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct sock *sk, const struct iphdr *iph, int oif, __u8 tos, u8 prot, u32 mark, @@ -831,28 +820,21 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf u32 mark = skb->mark; __u8 tos = iph->tos; - rt = (struct rtable *) dst; + rt = dst_rtable(dst); __build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0); __ip_do_redirect(rt, skb, &fl4, true); } -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst) { - struct rtable *rt = (struct rtable *)dst; - struct dst_entry *ret = dst; + struct rtable *rt = dst_rtable(dst); - if (rt) { - if (dst->obsolete > 0) { - ip_rt_put(rt); - ret = NULL; - } else if ((rt->rt_flags & RTCF_REDIRECTED) || - rt->dst.expires) { - ip_rt_put(rt); - ret = NULL; - } - } - return ret; + if ((dst->obsolete > 0) || + (rt->rt_flags & RTCF_REDIRECTED) || + rt->dst.expires) + sk_dst_reset(sk); } /* @@ -926,13 +908,11 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->n_redirects; -#ifdef CONFIG_IP_ROUTE_VERBOSE - if (log_martians && + if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians && peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); -#endif } out_put_peer: inet_putpeer(peer); @@ -1058,7 +1038,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { - struct rtable *rt = (struct rtable *) dst; + struct rtable *rt = dst_rtable(dst); struct flowi4 fl4; ip_rt_build_flow_key(&fl4, sk, skb); @@ -1129,7 +1109,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); - rt = (struct rtable *)odst; + rt = dst_rtable(odst); if (odst->obsolete && !odst->ops->check(odst, 0)) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) @@ -1138,7 +1118,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) new = true; } - __ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu); + __ip_rt_update_pmtu(dst_rtable(xfrm_dst_path(&rt->dst)), &fl4, mtu); if (!dst_check(&rt->dst, 0)) { if (new) @@ -1195,7 +1175,7 @@ EXPORT_SYMBOL_GPL(ipv4_sk_redirect); INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { - struct rtable *rt = (struct rtable *) dst; + struct rtable *rt = dst_rtable(dst); /* All IPV4 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down @@ -1530,10 +1510,8 @@ void rt_del_uncached_list(struct rtable *rt) static void ipv4_dst_destroy(struct dst_entry *dst) { - struct rtable *rt = (struct rtable *)dst; - ip_dst_metrics_put(dst); - rt_del_uncached_list(rt); + rt_del_uncached_list(dst_rtable(dst)); } void rt_flush_dev(struct net_device *dev) @@ -2168,6 +2146,9 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, int err = -EINVAL; u32 tag = 0; + if (!in_dev) + return -EINVAL; + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; @@ -2638,7 +2619,7 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, struct rtable *rth; fl4->flowi4_iif = LOOPBACK_IFINDEX; - ip_rt_fix_tos(fl4); + fl4->flowi4_tos &= IPTOS_RT_MASK; rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); @@ -2831,7 +2812,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) { - struct rtable *ort = (struct rtable *) dst_orig; + struct rtable *ort = dst_rtable(dst_orig); struct rtable *rt; rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, DST_OBSOLETE_DEAD, 0); @@ -2876,9 +2857,9 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, if (flp4->flowi4_proto) { flp4->flowi4_oif = rt->dst.dev->ifindex; - rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst, - flowi4_to_flowi(flp4), - sk, 0); + rt = dst_rtable(xfrm_lookup_route(net, &rt->dst, + flowi4_to_flowi(flp4), + sk, 0)); } return rt; @@ -3509,7 +3490,6 @@ static struct ctl_table ipv4_route_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; static const char ipv4_route_flush_procname[] = "flush"; @@ -3543,7 +3523,6 @@ static struct ctl_table ipv4_route_netns_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { }, }; static __net_init int sysctl_route_net_init(struct net *net) @@ -3561,16 +3540,14 @@ static __net_init int sysctl_route_net_init(struct net *net) /* Don't export non-whitelisted sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) { - if (tbl[0].procname != ipv4_route_flush_procname) { - tbl[0].procname = NULL; + if (tbl[0].procname != ipv4_route_flush_procname) table_size = 0; - } } /* Update the variables to point into the current struct net * except for the first element flush */ - for (i = 1; i < ARRAY_SIZE(ipv4_route_netns_table) - 1; i++) + for (i = 1; i < table_size; i++) tbl[i].data += (void *)net - (void *)&init_net; } tbl[0].extra1 = net; @@ -3590,7 +3567,7 @@ err_dup: static __net_exit void sysctl_route_net_exit(struct net *net) { - struct ctl_table *tbl; + const struct ctl_table *tbl; tbl = net->ipv4.route_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.route_hdr); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 500f665f98cb..b61d36810fe3 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -462,7 +462,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) } /* Try to redo what tcp_v4_send_synack did. */ - req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); + req->rsk_window_clamp = READ_ONCE(tp->window_clamp) ? : + dst_metric(&rt->dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ full_space = tcp_full_space(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 7e4f16a7dcc1..162a0a3b6ba5 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -575,7 +575,6 @@ static struct ctl_table ipv4_table[] = { .extra1 = &sysctl_fib_sync_mem_min, .extra2 = &sysctl_fib_sync_mem_max, }, - { } }; static struct ctl_table ipv4_net_table[] = { @@ -1502,11 +1501,11 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ONE, }, - { } }; static __net_init int ipv4_sysctl_init_net(struct net *net) { + size_t table_size = ARRAY_SIZE(ipv4_net_table); struct ctl_table *table; table = ipv4_net_table; @@ -1517,7 +1516,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) if (!table) goto err_alloc; - for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) { + for (i = 0; i < table_size; i++) { if (table[i].data) { /* Update the variables to point into * the current struct net @@ -1533,7 +1532,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) } net->ipv4.ipv4_hdr = register_net_sysctl_sz(net, "net/ipv4", table, - ARRAY_SIZE(ipv4_net_table)); + table_size); if (!net->ipv4.ipv4_hdr) goto err_reg; @@ -1554,7 +1553,7 @@ err_alloc: static __net_exit void ipv4_sysctl_exit_net(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; kfree(net->ipv4.sysctl_local_reserved_ports); table = net->ipv4.ipv4_hdr->ctl_table_arg; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d20b62d52171..e6790ea74877 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -272,13 +272,16 @@ #include <net/inet_common.h> #include <net/tcp.h> #include <net/mptcp.h> +#include <net/proto_memory.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/sock.h> +#include <net/rstreason.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/busy_poll.h> +#include <net/hotdata.h> #include <net/rps.h> /* Track pending CMSGs. */ @@ -290,6 +293,9 @@ enum { DEFINE_PER_CPU(unsigned int, tcp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); +DEFINE_PER_CPU(u32, tcp_tw_isn); +EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn); + long sysctl_tcp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_tcp_mem); @@ -1159,6 +1165,9 @@ new_segment: process_backlog++; +#ifdef CONFIG_SKB_DECRYPTED + skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); +#endif tcp_skb_entail(sk, skb); copy = size_goal; @@ -1184,7 +1193,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i >= READ_ONCE(sysctl_max_skb_frags)) { + if (i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1416,8 +1425,6 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) struct sk_buff *skb; int copied = 0, err = 0; - /* XXX -- need to support SO_PEEK_OFF */ - skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) @@ -1721,7 +1728,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) space = tcp_space_from_win(sk, val); if (space > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, space); - tcp_sk(sk)->window_clamp = val; + WRITE_ONCE(tcp_sk(sk)->window_clamp, val); } return 0; } @@ -2328,6 +2335,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int target; /* Read at least this many bytes */ long timeo; struct sk_buff *skb, *last; + u32 peek_offset = 0; u32 urg_hole = 0; err = -ENOTCONN; @@ -2361,7 +2369,8 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, seq = &tp->copied_seq; if (flags & MSG_PEEK) { - peek_seq = tp->copied_seq; + peek_offset = max(sk_peek_offset(sk, flags), 0); + peek_seq = tp->copied_seq + peek_offset; seq = &peek_seq; } @@ -2464,11 +2473,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, } if ((flags & MSG_PEEK) && - (peek_seq - copied - urg_hole != tp->copied_seq)) { + (peek_seq - peek_offset - copied - urg_hole != tp->copied_seq)) { net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n", current->comm, task_pid_nr(current)); - peek_seq = tp->copied_seq; + peek_seq = tp->copied_seq + peek_offset; } continue; @@ -2509,7 +2518,10 @@ found_ok_skb: WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; - + if (flags & MSG_PEEK) + sk_peek_offset_fwd(sk, used); + else + sk_peek_offset_bwd(sk, used); tcp_rcv_space_adjust(sk); skip_copy: @@ -2637,6 +2649,10 @@ void tcp_set_state(struct sock *sk, int state) if (oldstate != TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); break; + case TCP_CLOSE_WAIT: + if (oldstate == TCP_SYN_RECV) + TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); + break; case TCP_CLOSE: if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED) @@ -2648,7 +2664,7 @@ void tcp_set_state(struct sock *sk, int state) inet_put_port(sk); fallthrough; default: - if (oldstate == TCP_ESTABLISHED) + if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); } @@ -2710,7 +2726,7 @@ void tcp_shutdown(struct sock *sk, int how) /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | - TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) { + TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); @@ -2744,7 +2760,15 @@ static bool tcp_too_many_orphans(int shift) READ_ONCE(sysctl_tcp_max_orphans); } -bool tcp_check_oom(struct sock *sk, int shift) +static bool tcp_out_of_memory(const struct sock *sk) +{ + if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && + sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) + return true; + return false; +} + +bool tcp_check_oom(const struct sock *sk, int shift) { bool too_many_orphans, out_of_socket_memory; @@ -2805,7 +2829,8 @@ void __tcp_close(struct sock *sk, long timeout) /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, sk->sk_allocation); + tcp_send_active_reset(sk, sk->sk_allocation, + SK_RST_REASON_NOT_SPECIFIED); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -2819,7 +2844,7 @@ void __tcp_close(struct sock *sk, long timeout) * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 - * TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible) + * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), @@ -2879,7 +2904,8 @@ adjudge_to_death: struct tcp_sock *tp = tcp_sk(sk); if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_NOT_SPECIFIED); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); } else { @@ -2897,7 +2923,8 @@ adjudge_to_death: if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_NOT_SPECIFIED); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); } else if (!check_net(sock_net(sk))) { @@ -2931,6 +2958,8 @@ void tcp_close(struct sock *sk, long timeout) lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); + if (!sk->sk_net_refcnt) + inet_csk_clear_xmit_timers_sync(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); @@ -2999,7 +3028,7 @@ int tcp_disconnect(struct sock *sk, int flags) /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ - tcp_send_active_reset(sk, gfp_any()); + tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_NOT_SPECIFIED); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) WRITE_ONCE(sk->sk_err, ECONNRESET); @@ -3008,6 +3037,7 @@ int tcp_disconnect(struct sock *sk, int flags) __skb_queue_purge(&sk->sk_receive_queue); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); WRITE_ONCE(tp->urg_data, 0); + sk_set_peek_off(sk, -1); tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); @@ -3377,7 +3407,7 @@ int tcp_set_window_clamp(struct sock *sk, int val) if (!val) { if (sk->sk_state != TCP_CLOSE) return -EINVAL; - tp->window_clamp = 0; + WRITE_ONCE(tp->window_clamp, 0); } else { u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? @@ -3386,7 +3416,7 @@ int tcp_set_window_clamp(struct sock *sk, int val) if (new_window_clamp == old_window_clamp) return 0; - tp->window_clamp = new_window_clamp; + WRITE_ONCE(tp->window_clamp, new_window_clamp); if (new_window_clamp < old_window_clamp) { /* need to apply the reserved mem provisioning only * when shrinking the window clamp @@ -4055,7 +4085,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: - val = tp->window_clamp; + val = READ_ONCE(tp->window_clamp); break; case TCP_INFO: { struct tcp_info info; @@ -4340,6 +4370,9 @@ zerocopy_rcv_out: return err; } + case TCP_IS_MPTCP: + val = 0; + break; default: return -ENOPROTOOPT; } @@ -4555,7 +4588,8 @@ int tcp_abort(struct sock *sk, int err) smp_wmb(); sk_error_report(sk); if (tcp_need_reset(sk->sk_state)) - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_NOT_SPECIFIED); tcp_done(sk); } @@ -4646,16 +4680,16 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns); - CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_clock_cache); - CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 105); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 89); /* TXRX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_clock_cache); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una); @@ -4668,7 +4702,11 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 76); + + /* 32bit arches with 8byte alignment on u64 fields might need padding + * before tcp_clock_cache. + */ + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 92 + 4); /* RX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received); diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 3afeeb68e8a7..37c42b63ff99 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -933,6 +933,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, struct tcp_ao_key *key; __be32 sisn, disn; u8 *traffic_key; + int state; u32 sne = 0; info = rcu_dereference(tcp_sk(sk)->ao_info); @@ -948,8 +949,9 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, disn = 0; } + state = READ_ONCE(sk->sk_state); /* Fast-path */ - if (likely((1 << sk->sk_state) & TCP_AO_ESTABLISHED)) { + if (likely((1 << state) & TCP_AO_ESTABLISHED)) { enum skb_drop_reason err; struct tcp_ao_key *current_key; @@ -988,6 +990,9 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, return SKB_NOT_DROPPED_YET; } + if (unlikely(state == TCP_CLOSE)) + return SKB_DROP_REASON_TCP_CLOSE; + /* Lookup key based on peer address and keyid. * current_key and rnext_key must not be used on tcp listen * sockets as otherwise: @@ -1001,7 +1006,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, if (th->syn && !th->ack) goto verify_hash; - if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV)) { + if ((1 << state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV)) { /* Make the initial syn the likely case here */ if (unlikely(req)) { sne = tcp_ao_compute_sne(0, tcp_rsk(req)->rcv_isn, @@ -1018,14 +1023,14 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, /* no way to figure out initial sisn/disn - drop */ return SKB_DROP_REASON_TCP_FLAGS; } - } else if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { + } else if ((1 << state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { disn = info->lisn; if (th->syn || th->rst) sisn = th->seq; else sisn = info->risn; } else { - WARN_ONCE(1, "TCP-AO: Unexpected sk_state %d", sk->sk_state); + WARN_ONCE(1, "TCP-AO: Unexpected sk_state %d", state); return SKB_DROP_REASON_TCP_AOFAILURE; } verify_hash: @@ -1068,6 +1073,7 @@ void tcp_ao_connect_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_ao_info *ao_info; + struct hlist_node *next; union tcp_ao_addr *addr; struct tcp_ao_key *key; int family, l3index; @@ -1090,7 +1096,7 @@ void tcp_ao_connect_init(struct sock *sk) l3index = l3mdev_master_ifindex_by_index(sock_net(sk), sk->sk_bound_dev_if); - hlist_for_each_entry_rcu(key, &ao_info->head, node) { + hlist_for_each_entry_safe(key, next, &ao_info->head, node) { if (!tcp_ao_key_cmp(key, l3index, addr, key->prefixlen, family, -1, -1)) continue; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 05dc2d05bc7c..760941e55153 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1024,7 +1024,7 @@ static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) bbr_update_gains(sk); } -__bpf_kfunc static void bbr_main(struct sock *sk, const struct rate_sample *rs) +__bpf_kfunc static void bbr_main(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); u32 bw; @@ -1156,8 +1156,6 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { }; BTF_KFUNCS_START(tcp_bbr_check_kfunc_ids) -#ifdef CONFIG_X86 -#ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, bbr_init) BTF_ID_FLAGS(func, bbr_main) BTF_ID_FLAGS(func, bbr_sndbuf_expand) @@ -1166,8 +1164,6 @@ BTF_ID_FLAGS(func, bbr_cwnd_event) BTF_ID_FLAGS(func, bbr_ssthresh) BTF_ID_FLAGS(func, bbr_min_tso_segs) BTF_ID_FLAGS(func, bbr_set_state) -#endif -#endif BTF_KFUNCS_END(tcp_bbr_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = { diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 44869ea089e3..5dbed91c6178 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -486,16 +486,12 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { }; BTF_KFUNCS_START(tcp_cubic_check_kfunc_ids) -#ifdef CONFIG_X86 -#ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, cubictcp_init) BTF_ID_FLAGS(func, cubictcp_recalc_ssthresh) BTF_ID_FLAGS(func, cubictcp_cong_avoid) BTF_ID_FLAGS(func, cubictcp_state) BTF_ID_FLAGS(func, cubictcp_cwnd_event) BTF_ID_FLAGS(func, cubictcp_acked) -#endif -#endif BTF_KFUNCS_END(tcp_cubic_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_cubic_kfunc_set = { diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index e33fbe4933e4..8a45a4aea933 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -58,7 +58,18 @@ struct dctcp { }; static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */ -module_param(dctcp_shift_g, uint, 0644); + +static int dctcp_shift_g_set(const char *val, const struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, 0, 10); +} + +static const struct kernel_param_ops dctcp_shift_g_ops = { + .set = dctcp_shift_g_set, + .get = param_get_uint, +}; + +module_param_cb(dctcp_shift_g, &dctcp_shift_g_ops, &dctcp_shift_g, 0644); MODULE_PARM_DESC(dctcp_shift_g, "parameter g for updating dctcp_alpha"); static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA; @@ -261,16 +272,12 @@ static struct tcp_congestion_ops dctcp_reno __read_mostly = { }; BTF_KFUNCS_START(tcp_dctcp_check_kfunc_ids) -#ifdef CONFIG_X86 -#ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, dctcp_init) BTF_ID_FLAGS(func, dctcp_update_alpha) BTF_ID_FLAGS(func, dctcp_cwnd_event) BTF_ID_FLAGS(func, dctcp_ssthresh) BTF_ID_FLAGS(func, dctcp_cwnd_undo) BTF_ID_FLAGS(func, dctcp_state) -#endif -#endif BTF_KFUNCS_END(tcp_dctcp_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_dctcp_kfunc_set = { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5d874817a78d..9c04a9c8be9d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -72,6 +72,7 @@ #include <linux/prefetch.h> #include <net/dst.h> #include <net/tcp.h> +#include <net/proto_memory.h> #include <net/inet_common.h> #include <linux/ipsec.h> #include <asm/unaligned.h> @@ -563,19 +564,20 @@ static void tcp_init_buffer_space(struct sock *sk) maxwin = tcp_full_space(sk); if (tp->window_clamp >= maxwin) { - tp->window_clamp = maxwin; + WRITE_ONCE(tp->window_clamp, maxwin); if (tcp_app_win && maxwin > 4 * tp->advmss) - tp->window_clamp = max(maxwin - - (maxwin >> tcp_app_win), - 4 * tp->advmss); + WRITE_ONCE(tp->window_clamp, + max(maxwin - (maxwin >> tcp_app_win), + 4 * tp->advmss)); } /* Force reservation of one segment. */ if (tcp_app_win && tp->window_clamp > 2 * tp->advmss && tp->window_clamp + tp->advmss > maxwin) - tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss); + WRITE_ONCE(tp->window_clamp, + max(2 * tp->advmss, maxwin - tp->advmss)); tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); tp->snd_cwnd_stamp = tcp_jiffies32; @@ -773,7 +775,8 @@ void tcp_rcv_space_adjust(struct sock *sk) WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make the window clamp follow along. */ - tp->window_clamp = tcp_win_from_space(sk, rcvbuf); + WRITE_ONCE(tp->window_clamp, + tcp_win_from_space(sk, rcvbuf)); } } tp->rcvq_space.space = copied; @@ -911,7 +914,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->rtt_seq = tp->snd_nxt; tp->mdev_max_us = tcp_rto_min_us(sk); - tcp_bpf_rtt(sk); + tcp_bpf_rtt(sk, mrtt_us, srtt); } } else { /* no previous measure. */ @@ -921,7 +924,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->mdev_max_us = tp->rttvar_us; tp->rtt_seq = tp->snd_nxt; - tcp_bpf_rtt(sk); + tcp_bpf_rtt(sk, mrtt_us, srtt); } tp->srtt_us = max(1U, srtt); } @@ -3539,7 +3542,7 @@ static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked, const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->cong_control) { - icsk->icsk_ca_ops->cong_control(sk, rs); + icsk->icsk_ca_ops->cong_control(sk, ack, flag, rs); return; } @@ -4803,10 +4806,8 @@ static bool tcp_try_coalesce(struct sock *sk, if (!mptcp_skb_can_collapse(to, from)) return false; -#ifdef CONFIG_TLS_DEVICE - if (from->decrypted != to->decrypted) + if (skb_cmp_decrypted(from, to)) return false; -#endif if (!skb_try_coalesce(to, from, fragstolen, &delta)) return false; @@ -5174,6 +5175,16 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) */ if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) { if (tcp_receive_window(tp) == 0) { + /* Some stacks are known to send bare FIN packets + * in a loop even if we send RWIN 0 in our ACK. + * Accepting this FIN does not hurt memory pressure + * because the FIN flag will simply be merged to the + * receive queue tail skb in most cases. + */ + if (!skb->len && + (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) + goto queue_and_out; + reason = SKB_DROP_REASON_TCP_ZEROWINDOW; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP); goto out_of_window; @@ -5188,7 +5199,7 @@ queue_and_out: inet_csk_schedule_ack(sk); sk->sk_data_ready(sk); - if (skb_queue_len(&sk->sk_receive_queue)) { + if (skb_queue_len(&sk->sk_receive_queue) && skb->len) { reason = SKB_DROP_REASON_PROTO_MEM; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); goto drop; @@ -5375,9 +5386,7 @@ restart: break; memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); -#ifdef CONFIG_TLS_DEVICE - nskb->decrypted = skb->decrypted; -#endif + skb_copy_decrypted(nskb, skb); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start; if (list) __skb_queue_before(list, skb, nskb); @@ -5407,10 +5416,8 @@ restart: !mptcp_skb_can_collapse(nskb, skb) || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) goto end; -#ifdef CONFIG_TLS_DEVICE - if (skb->decrypted != nskb->decrypted) + if (skb_cmp_decrypted(skb, nskb)) goto end; -#endif } } } @@ -6426,7 +6433,8 @@ consume: if (!tp->rx_opt.wscale_ok) { tp->rx_opt.snd_wscale = tp->rx_opt.rcv_wscale = 0; - tp->window_clamp = min(tp->window_clamp, 65535U); + WRITE_ONCE(tp->window_clamp, + min(tp->window_clamp, 65535U)); } if (tp->rx_opt.saw_tstamp) { @@ -6761,6 +6769,8 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); + if (sk->sk_shutdown & SEND_SHUTDOWN) + tcp_shutdown(sk, SEND_SHUTDOWN); break; case TCP_FIN_WAIT1: { @@ -6999,7 +7009,7 @@ EXPORT_SYMBOL(inet_reqsk_alloc); /* * Return true if a syncookie should be sent */ -static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) +static bool tcp_syn_flood_action(struct sock *sk, const char *proto) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; @@ -7100,7 +7110,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct sock *sk, struct sk_buff *skb) { struct tcp_fastopen_cookie foc = { .len = -1 }; - __u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn; struct tcp_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); @@ -7110,21 +7119,28 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct dst_entry *dst; struct flowi fl; u8 syncookies; + u32 isn; #ifdef CONFIG_TCP_AO const struct tcp_ao_hdr *aoh; #endif - syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); + isn = __this_cpu_read(tcp_tw_isn); + if (isn) { + /* TW buckets are converted to open requests without + * limitations, they conserve resources and peer is + * evidently real one. + */ + __this_cpu_write(tcp_tw_isn, 0); + } else { + syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); - /* TW buckets are converted to open requests without - * limitations, they conserve resources and peer is - * evidently real one. - */ - if ((syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) { - want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name); - if (!want_cookie) - goto drop; + if (syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) { + want_cookie = tcp_syn_flood_action(sk, + rsk_ops->slab_name); + if (!want_cookie) + goto drop; + } } if (sk_acceptq_is_full(sk)) { @@ -7163,7 +7179,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, /* Note: tcp_v6_init_req() might override ir_iif for link locals */ inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb); - dst = af_ops->route_req(sk, skb, &fl, req); + dst = af_ops->route_req(sk, skb, &fl, req, isn); if (!dst) goto drop_and_free; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a22ee5838751..b710958393e6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -70,6 +70,7 @@ #include <net/xfrm.h> #include <net/secure_seq.h> #include <net/busy_poll.h> +#include <net/rstreason.h> #include <linux/inet.h> #include <linux/ipv6.h> @@ -154,6 +155,12 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) if (tcptw->tw_ts_recent_stamp && (!twp || (reuse && time_after32(ktime_get_seconds(), tcptw->tw_ts_recent_stamp)))) { + /* inet_twsk_hashdance() sets sk_refcnt after putting twsk + * and releasing the bucket lock. + */ + if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt))) + return 0; + /* In case of repair and re-using TIME-WAIT sockets we still * want to be sure that it is safe as above but honor the * sequence numbers and time stamps set as part of the repair @@ -174,7 +181,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) tp->rx_opt.ts_recent = tcptw->tw_ts_recent; tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; } - sock_hold(sktw); + return 1; } @@ -723,7 +730,8 @@ out: * Exception: precedence violation. We do not implement it in any case. */ -static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) +static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, + enum sk_rst_reason reason) { const struct tcphdr *th = tcp_hdr(skb); struct { @@ -866,11 +874,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) * routing might fail in this case. No choice here, if we choose to force * input interface, we will misroute in case of asymmetric route. */ - if (sk) { + if (sk) arg.bound_dev_if = sk->sk_bound_dev_if; - if (sk_fullsock(sk)) - trace_tcp_send_reset(sk, skb); - } + + trace_tcp_send_reset(sk, skb, reason); BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != offsetof(struct inet_timewait_sock, tw_bound_dev_if)); @@ -1137,14 +1144,9 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, #endif } - /* RFC 7323 2.3 - * The window field (SEG.WND) of every outgoing segment, with the - * exception of <SYN> segments, MUST be right-shifted by - * Rcv.Wind.Shift bits: - */ tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, - req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, + tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), 0, &key, @@ -1667,7 +1669,8 @@ static void tcp_v4_init_req(struct request_sock *req, static struct dst_entry *tcp_v4_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct request_sock *req) + struct request_sock *req, + u32 tw_isn) { tcp_v4_init_req(req, sk, skb); @@ -1934,7 +1937,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; reset: - tcp_v4_send_reset(rsk, skb); + tcp_v4_send_reset(rsk, skb, sk_rst_convert_drop_reason(reason)); discard: kfree_skb_reason(skb, reason); /* Be careful here. If this function gets more complicated and @@ -1995,7 +1998,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { - u32 limit, tail_gso_size, tail_gso_segs; + u32 tail_gso_size, tail_gso_segs; struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; @@ -2004,6 +2007,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, bool fragstolen; u32 gso_segs; u32 gso_size; + u64 limit; int delta; /* In case all data was pulled from skb frags (in __pskb_pull_tail()), @@ -2045,10 +2049,8 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) || ((TCP_SKB_CB(tail)->tcp_flags ^ TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) || -#ifdef CONFIG_TLS_DEVICE - tail->decrypted != skb->decrypted || -#endif !mptcp_skb_can_collapse(tail, skb) || + skb_cmp_decrypted(tail, skb) || thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; @@ -2101,7 +2103,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, __skb_push(skb, hdrlen); no_coalesce: - limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1); + /* sk->sk_backlog.len is reset only at the end of __release_sock(). + * Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach + * sk_rcvbuf in normal conditions. + */ + limit = ((u64)READ_ONCE(sk->sk_rcvbuf)) << 1; + + limit += ((u32)READ_ONCE(sk->sk_sndbuf)) >> 1; /* Only socket owner can try to collapse/prune rx queues * to reduce memory overhead, so add a little headroom here. @@ -2109,6 +2117,8 @@ no_coalesce: */ limit += 64 * 1024; + limit = min_t(u64, limit, UINT_MAX); + if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); *reason = SKB_DROP_REASON_SOCKET_BACKLOG; @@ -2148,7 +2158,6 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, skb->len - th->doff * 4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); - TCP_SKB_CB(skb)->tcp_tw_isn = 0; TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = @@ -2170,6 +2179,7 @@ int tcp_v4_rcv(struct sk_buff *skb) bool refcounted; struct sock *sk; int ret; + u32 isn; drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (skb->pkt_type != PACKET_HOST) @@ -2207,7 +2217,6 @@ lookup: if (!sk) goto no_tcp_socket; -process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; @@ -2279,7 +2288,10 @@ process: } else { drop_reason = tcp_child_process(sk, nsk, skb); if (drop_reason) { - tcp_v4_send_reset(nsk, skb); + enum sk_rst_reason rst_reason; + + rst_reason = sk_rst_convert_drop_reason(drop_reason); + tcp_v4_send_reset(nsk, skb, rst_reason); goto discard_and_relse; } sock_put(sk); @@ -2287,6 +2299,7 @@ process: } } +process: if (static_branch_unlikely(&ip4_min_ttl)) { /* min_ttl can be changed concurrently from do_ip_setsockopt() */ if (unlikely(iph->ttl < READ_ONCE(inet_sk(sk)->min_ttl))) { @@ -2357,7 +2370,7 @@ csum_error: bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); } else { - tcp_v4_send_reset(NULL, skb); + tcp_v4_send_reset(NULL, skb, sk_rst_convert_drop_reason(drop_reason)); } discard_it: @@ -2385,7 +2398,7 @@ do_time_wait: inet_twsk_put(inet_twsk(sk)); goto csum_error; } - switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { + switch (tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn)) { case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, @@ -2399,6 +2412,7 @@ do_time_wait: sk = sk2; tcp_v4_restore_cb(skb); refcounted = false; + __this_cpu_write(tcp_tw_isn, isn); goto process; } } @@ -2408,7 +2422,7 @@ do_time_wait: tcp_v4_timewait_ack(sk, skb); break; case TCP_TW_RST: - tcp_v4_send_reset(sk, skb); + tcp_v4_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; case TCP_TW_SUCCESS:; @@ -2418,7 +2432,6 @@ do_time_wait: static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp_timewait_sock), - .twsk_unique = tcp_twsk_unique, .twsk_destructor= tcp_twsk_destructor, }; @@ -3501,7 +3514,7 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; - tcp_twsk_purge(net_exit_list, AF_INET); + tcp_twsk_purge(net_exit_list); list_for_each_entry(net, net_exit_list, exit_list) { inet_pernet_hashinfo_free(net->ipv4.tcp_death_row.hashinfo); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c2a925538542..e93df98de3f4 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -766,6 +766,7 @@ static int tcp_metrics_nl_dump(struct sk_buff *skb, unsigned int max_rows = 1U << tcp_metrics_hash_log; unsigned int row, s_row = cb->args[0]; int s_col = cb->args[1], col = s_col; + int res = 0; for (row = s_row; row < max_rows; row++, s_col = 0) { struct tcp_metrics_block *tm; @@ -778,7 +779,8 @@ static int tcp_metrics_nl_dump(struct sk_buff *skb, continue; if (col < s_col) continue; - if (tcp_metrics_dump_info(skb, cb, tm) < 0) { + res = tcp_metrics_dump_info(skb, cb, tm); + if (res < 0) { rcu_read_unlock(); goto done; } @@ -789,7 +791,7 @@ static int tcp_metrics_nl_dump(struct sk_buff *skb, done: cb->args[0] = row; cb->args[1] = col; - return skb->len; + return res; } static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, @@ -986,6 +988,7 @@ static struct genl_family tcp_metrics_nl_family __ro_after_init = { .maxattr = TCP_METRICS_ATTR_MAX, .policy = tcp_metrics_nl_policy, .netnsok = true, + .parallel_ops = true, .module = THIS_MODULE, .small_ops = tcp_metrics_nl_ops, .n_small_ops = ARRAY_SIZE(tcp_metrics_nl_ops), diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f0761f060a83..538c06f95918 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -22,6 +22,7 @@ #include <net/tcp.h> #include <net/xfrm.h> #include <net/busy_poll.h> +#include <net/rstreason.h> static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) { @@ -95,7 +96,7 @@ static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq) */ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, - const struct tcphdr *th) + const struct tcphdr *th, u32 *tw_isn) { struct tcp_options_received tmp_opt; struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); @@ -228,7 +229,7 @@ kill: u32 isn = tcptw->tw_snd_nxt + 65535 + 2; if (isn == 0) isn++; - TCP_SKB_CB(skb)->tcp_tw_isn = isn; + *tw_isn = isn; return TCP_TW_SYN; } @@ -388,7 +389,7 @@ void tcp_twsk_destructor(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); -void tcp_twsk_purge(struct list_head *net_exit_list, int family) +void tcp_twsk_purge(struct list_head *net_exit_list) { bool purged_once = false; struct net *net; @@ -396,14 +397,13 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family) list_for_each_entry(net, net_exit_list, exit_list) { if (net->ipv4.tcp_death_row.hashinfo->pernet) { /* Even if tw_refcount == 1, we must clean up kernel reqsk */ - inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family); + inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo); } else if (!purged_once) { - inet_twsk_purge(&tcp_hashinfo, family); + inet_twsk_purge(&tcp_hashinfo); purged_once = true; } } } -EXPORT_SYMBOL_GPL(tcp_twsk_purge); /* Warning : This function is called without sk_listener being locked. * Be sure to read socket fields once, as their value could change under us. @@ -783,8 +783,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* RFC793: "first check sequence number". */ - if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rsk_rcv_wnd)) { + if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + tcp_rsk(req)->rcv_nxt, + tcp_rsk(req)->rcv_nxt + + tcp_synack_window(req))) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST) && !tcp_oow_rate_limited(sock_net(sk), skb, @@ -879,7 +882,7 @@ embryonic_reset: * avoid becoming vulnerable to outside attack aiming at * resetting legit local connections. */ - req->rsk_ops->send_reset(sk, skb); + req->rsk_ops->send_reset(sk, skb, SK_RST_REASON_INVALID_SYN); } else if (fastopen) { /* received a valid RST pkt */ reqsk_fastopen_remove(sk, req, true); tcp_reset(sk, skb); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index ebe4722bb020..4b791e74529e 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -28,6 +28,70 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq, } } +static void __tcpv4_gso_segment_csum(struct sk_buff *seg, + __be32 *oldip, __be32 newip, + __be16 *oldport, __be16 newport) +{ + struct tcphdr *th; + struct iphdr *iph; + + if (*oldip == newip && *oldport == newport) + return; + + th = tcp_hdr(seg); + iph = ip_hdr(seg); + + inet_proto_csum_replace4(&th->check, seg, *oldip, newip, true); + inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false); + *oldport = newport; + + csum_replace4(&iph->check, *oldip, newip); + *oldip = newip; +} + +static struct sk_buff *__tcpv4_gso_segment_list_csum(struct sk_buff *segs) +{ + const struct tcphdr *th; + const struct iphdr *iph; + struct sk_buff *seg; + struct tcphdr *th2; + struct iphdr *iph2; + + seg = segs; + th = tcp_hdr(seg); + iph = ip_hdr(seg); + th2 = tcp_hdr(seg->next); + iph2 = ip_hdr(seg->next); + + if (!(*(const u32 *)&th->source ^ *(const u32 *)&th2->source) && + iph->daddr == iph2->daddr && iph->saddr == iph2->saddr) + return segs; + + while ((seg = seg->next)) { + th2 = tcp_hdr(seg); + iph2 = ip_hdr(seg); + + __tcpv4_gso_segment_csum(seg, + &iph2->saddr, iph->saddr, + &th2->source, th->source); + __tcpv4_gso_segment_csum(seg, + &iph2->daddr, iph->daddr, + &th2->dest, th->dest); + } + + return segs; +} + +static struct sk_buff *__tcp4_gso_segment_list(struct sk_buff *skb, + netdev_features_t features) +{ + skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); + if (IS_ERR(skb)) + return skb; + + return __tcpv4_gso_segment_list_csum(skb); +} + static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, netdev_features_t features) { @@ -37,6 +101,9 @@ static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct tcphdr))) return ERR_PTR(-EINVAL); + if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) + return __tcp4_gso_segment_list(skb, features); + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { const struct iphdr *iph = ip_hdr(skb); struct tcphdr *th = tcp_hdr(skb); @@ -178,63 +245,76 @@ out: return segs; } -struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb) +struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th) { - struct sk_buff *pp = NULL; + struct tcphdr *th2; struct sk_buff *p; + + list_for_each_entry(p, head, list) { + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + th2 = tcp_hdr(p); + if (*(u32 *)&th->source ^ *(u32 *)&th2->source) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + return p; + } + + return NULL; +} + +struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb) +{ + unsigned int thlen, hlen, off; struct tcphdr *th; - struct tcphdr *th2; - unsigned int len; - unsigned int thlen; - __be32 flags; - unsigned int mss = 1; - unsigned int hlen; - unsigned int off; - int flush = 1; - int i; off = skb_gro_offset(skb); hlen = off + sizeof(*th); th = skb_gro_header(skb, hlen, off); if (unlikely(!th)) - goto out; + return NULL; thlen = th->doff * 4; if (thlen < sizeof(*th)) - goto out; + return NULL; hlen = off + thlen; if (!skb_gro_may_pull(skb, hlen)) { th = skb_gro_header_slow(skb, hlen, off); if (unlikely(!th)) - goto out; + return NULL; } skb_gro_pull(skb, thlen); - len = skb_gro_len(skb); - flags = tcp_flag_word(th); - - list_for_each_entry(p, head, list) { - if (!NAPI_GRO_CB(p)->same_flow) - continue; + return th; +} - th2 = tcp_hdr(p); +struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct tcphdr *th) +{ + unsigned int thlen = th->doff * 4; + struct sk_buff *pp = NULL; + struct sk_buff *p; + struct tcphdr *th2; + unsigned int len; + __be32 flags; + unsigned int mss = 1; + int flush = 1; + int i; - if (*(u32 *)&th->source ^ *(u32 *)&th2->source) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } + len = skb_gro_len(skb); + flags = tcp_flag_word(th); - goto found; - } - p = NULL; - goto out_check_final; + p = tcp_gro_lookup(head, th); + if (!p) + goto out_check_final; -found: - /* Include the IP ID check below from the inner most IP hdr */ - flush = NAPI_GRO_CB(p)->flush; - flush |= (__force int)(flags & TCP_FLAG_CWR); + th2 = tcp_hdr(p); + flush = (__force int)(flags & TCP_FLAG_CWR); flush |= (__force int)((flags ^ tcp_flag_word(th2)) & ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH)); flush |= (__force int)(th->ack_seq ^ th2->ack_seq); @@ -242,16 +322,7 @@ found: flush |= *(u32 *)((u8 *)th + i) ^ *(u32 *)((u8 *)th2 + i); - /* When we receive our second frame we can made a decision on if we - * continue this flow as an atomic flow with a fixed ID or if we use - * an incrementing ID. - */ - if (NAPI_GRO_CB(p)->flush_id != 1 || - NAPI_GRO_CB(p)->count != 1 || - !NAPI_GRO_CB(p)->is_atomic) - flush |= NAPI_GRO_CB(p)->flush_id; - else - NAPI_GRO_CB(p)->is_atomic = false; + flush |= gro_receive_network_flush(th, th2, p); mss = skb_shinfo(p)->gso_size; @@ -265,9 +336,19 @@ found: flush |= (len - 1) >= mss; flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq); -#ifdef CONFIG_TLS_DEVICE - flush |= p->decrypted ^ skb->decrypted; -#endif + flush |= skb_cmp_decrypted(p, skb); + + if (unlikely(NAPI_GRO_CB(p)->is_flist)) { + flush |= (__force int)(flags ^ tcp_flag_word(th2)); + flush |= skb->ip_summed != p->ip_summed; + flush |= skb->csum_level != p->csum_level; + flush |= NAPI_GRO_CB(p)->count >= 64; + + if (flush || skb_gro_receive_list(p, skb)) + mss = 1; + + goto out_check_final; + } if (flush || skb_gro_receive(p, skb)) { mss = 1; @@ -290,7 +371,6 @@ out_check_final: if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) pp = p; -out: NAPI_GRO_CB(skb)->flush |= (flush != 0); return pp; @@ -316,30 +396,80 @@ void tcp_gro_complete(struct sk_buff *skb) } EXPORT_SYMBOL(tcp_gro_complete); +static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, + struct tcphdr *th) +{ + const struct iphdr *iph; + struct sk_buff *p; + struct sock *sk; + struct net *net; + int iif, sdif; + + if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST))) + return; + + p = tcp_gro_lookup(head, th); + if (p) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + inet_get_iif_sdif(skb, &iif, &sdif); + iph = skb_gro_network_header(skb); + net = dev_net(skb->dev); + sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, + iph->saddr, th->source, + iph->daddr, ntohs(th->dest), + iif, sdif); + NAPI_GRO_CB(skb)->is_flist = !sk; + if (sk) + sock_put(sk); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) { + struct tcphdr *th; + /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && skb_gro_checksum_validate(skb, IPPROTO_TCP, - inet_gro_compute_pseudo)) { - NAPI_GRO_CB(skb)->flush = 1; - return NULL; - } + inet_gro_compute_pseudo)) + goto flush; + + th = tcp_gro_pull_header(skb); + if (!th) + goto flush; - return tcp_gro_receive(head, skb); + tcp4_check_fraglist_gro(head, skb, th); + + return tcp_gro_receive(head, skb, th); + +flush: + NAPI_GRO_CB(skb)->flush = 1; + return NULL; } INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) { - const struct iphdr *iph = ip_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct tcphdr *th = tcp_hdr(skb); + if (unlikely(NAPI_GRO_CB(skb)->is_flist)) { + skb_shinfo(skb)->gso_type |= SKB_GSO_FRAGLIST | SKB_GSO_TCPV4; + skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + + __skb_incr_checksum_unnecessary(skb); + + return 0; + } + th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4 | - (NAPI_GRO_CB(skb)->is_atomic * SKB_GSO_TCP_FIXEDID); + (NAPI_GRO_CB(skb)->ip_fixedid * SKB_GSO_TCP_FIXEDID); tcp_gro_complete(skb); return 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e3167ad96567..95618d0e78e4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -39,11 +39,13 @@ #include <net/tcp.h> #include <net/mptcp.h> +#include <net/proto_memory.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/module.h> #include <linux/static_key.h> +#include <linux/skbuff_ref.h> #include <trace/events/tcp.h> @@ -203,16 +205,17 @@ static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) * This MUST be enforced by all callers. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, - __u32 *rcv_wnd, __u32 *window_clamp, + __u32 *rcv_wnd, __u32 *__window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd) { unsigned int space = (__space < 0 ? 0 : __space); + u32 window_clamp = READ_ONCE(*__window_clamp); /* If no clamp set the clamp to the max possible scaled window */ - if (*window_clamp == 0) - (*window_clamp) = (U16_MAX << TCP_MAX_WSCALE); - space = min(*window_clamp, space); + if (window_clamp == 0) + window_clamp = (U16_MAX << TCP_MAX_WSCALE); + space = min(window_clamp, space); /* Quantize space offering to a multiple of mss if possible. */ if (space > mss) @@ -229,7 +232,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else - (*rcv_wnd) = min_t(u32, space, U16_MAX); + (*rcv_wnd) = space; if (init_rcv_wnd) *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); @@ -239,12 +242,13 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, /* Set window scaling on max possible window */ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); space = max_t(u32, space, READ_ONCE(sysctl_rmem_max)); - space = min_t(u32, space, *window_clamp); + space = min_t(u32, space, window_clamp); *rcv_wscale = clamp_t(int, ilog2(space) - 15, 0, TCP_MAX_WSCALE); } /* Set the clamp no higher than max representable value */ - (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp); + WRITE_ONCE(*__window_clamp, + min_t(__u32, U16_MAX << (*rcv_wscale), window_clamp)); } EXPORT_SYMBOL(tcp_select_initial_window); @@ -1499,18 +1503,22 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) } /* Initialize TSO segments for a packet. */ -static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) +static int tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) { + int tso_segs; + if (skb->len <= mss_now) { /* Avoid the costly divide in the normal * non-TSO case. */ - tcp_skb_pcount_set(skb, 1); TCP_SKB_CB(skb)->tcp_gso_size = 0; - } else { - tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now)); - TCP_SKB_CB(skb)->tcp_gso_size = mss_now; + tcp_skb_pcount_set(skb, 1); + return 1; } + TCP_SKB_CB(skb)->tcp_gso_size = mss_now; + tso_segs = DIV_ROUND_UP(skb->len, mss_now); + tcp_skb_pcount_set(skb, tso_segs); + return tso_segs; } /* Pcount in the middle of the write queue got changed, we need to do various @@ -2070,16 +2078,10 @@ static unsigned int tcp_mss_split_point(const struct sock *sk, /* Can at least one segment of SKB be sent right now, according to the * congestion window rules? If so, return how many segments are allowed. */ -static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp, - const struct sk_buff *skb) +static u32 tcp_cwnd_test(const struct tcp_sock *tp) { u32 in_flight, cwnd, halfcwnd; - /* Don't be strict about the congestion window for the final FIN. */ - if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) && - tcp_skb_pcount(skb) == 1) - return 1; - in_flight = tcp_packets_in_flight(tp); cwnd = tcp_snd_cwnd(tp); if (in_flight >= cwnd) @@ -2100,10 +2102,9 @@ static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now) { int tso_segs = tcp_skb_pcount(skb); - if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) { - tcp_set_skb_tso_segs(skb, mss_now); - tso_segs = tcp_skb_pcount(skb); - } + if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) + return tcp_set_skb_tso_segs(skb, mss_now); + return tso_segs; } @@ -2403,6 +2404,21 @@ commit: return 0; } +/* tcp_mtu_probe() and tcp_grow_skb() can both eat an skb (src) if + * all its payload was moved to another one (dst). + * Make sure to transfer tcp_flags, eor, and tstamp. + */ +static void tcp_eat_one_skb(struct sock *sk, + struct sk_buff *dst, + struct sk_buff *src) +{ + TCP_SKB_CB(dst)->tcp_flags |= TCP_SKB_CB(src)->tcp_flags; + TCP_SKB_CB(dst)->eor = TCP_SKB_CB(src)->eor; + tcp_skb_collapse_tstamp(dst, src); + tcp_unlink_write_queue(src, sk); + tcp_wmem_free_skb(sk, src); +} + /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing @@ -2508,16 +2524,7 @@ static int tcp_mtu_probe(struct sock *sk) copy = min_t(int, skb->len, probe_size - len); if (skb->len <= copy) { - /* We've eaten all the data from this skb. - * Throw it away. */ - TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; - /* If this is the last SKB we copy and eor is set - * we need to propagate it to the new skb. - */ - TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; - tcp_skb_collapse_tstamp(nskb, skb); - tcp_unlink_write_queue(skb, sk); - tcp_wmem_free_skb(sk, skb); + tcp_eat_one_skb(sk, nskb, skb); } else { TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags & ~(TCPHDR_FIN|TCPHDR_PSH); @@ -2683,6 +2690,35 @@ void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) tcp_chrono_set(tp, TCP_CHRONO_BUSY); } +/* First skb in the write queue is smaller than ideal packet size. + * Check if we can move payload from the second skb in the queue. + */ +static void tcp_grow_skb(struct sock *sk, struct sk_buff *skb, int amount) +{ + struct sk_buff *next_skb = skb->next; + unsigned int nlen; + + if (tcp_skb_is_last(sk, skb)) + return; + + if (!tcp_skb_can_collapse(skb, next_skb)) + return; + + nlen = min_t(u32, amount, next_skb->len); + if (!nlen || !skb_shift(skb, next_skb, nlen)) + return; + + TCP_SKB_CB(skb)->end_seq += nlen; + TCP_SKB_CB(next_skb)->seq += nlen; + + if (!next_skb->len) { + /* In case FIN is set, we need to update end_seq */ + TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; + + tcp_eat_one_skb(sk, skb, next_skb); + } +} + /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. @@ -2703,10 +2739,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; unsigned int tso_segs, sent_pkts; - int cwnd_quota; + u32 cwnd_quota, max_segs; int result; bool is_cwnd_limited = false, is_rwnd_limited = false; - u32 max_segs; sent_pkts = 0; @@ -2724,6 +2759,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, max_segs = tcp_tso_segs(sk, mss_now); while ((skb = tcp_send_head(sk))) { unsigned int limit; + int missing_bytes; if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp_ns" is used as a start point for the retransmit timer */ @@ -2737,10 +2773,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_pacing_check(sk)) break; - tso_segs = tcp_init_tso_segs(skb, mss_now); - BUG_ON(!tso_segs); - - cwnd_quota = tcp_cwnd_test(tp, skb); + cwnd_quota = tcp_cwnd_test(tp); if (!cwnd_quota) { if (push_one == 2) /* Force out a loss probe pkt. */ @@ -2748,6 +2781,12 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, else break; } + cwnd_quota = min(cwnd_quota, max_segs); + missing_bytes = cwnd_quota * mss_now - skb->len; + if (missing_bytes > 0) + tcp_grow_skb(sk, skb, missing_bytes); + + tso_segs = tcp_set_skb_tso_segs(skb, mss_now); if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) { is_rwnd_limited = true; @@ -2769,9 +2808,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, - min_t(unsigned int, - cwnd_quota, - max_segs), + cwnd_quota, nonagle); if (skb->len > limit && @@ -3387,11 +3424,6 @@ start: err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } - /* To avoid taking spuriously low RTT samples based on a timestamp - * for a transmit that never happened, always mark EVER_RETRANS - */ - TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; - if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB, TCP_SKB_CB(skb)->seq, segs, err); @@ -3401,6 +3433,12 @@ start: } else if (err != -EBUSY) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); } + + /* To avoid taking spuriously low RTT samples based on a timestamp + * for a transmit that never happened, always mark EVER_RETRANS + */ + TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + return err; } @@ -3563,7 +3601,9 @@ void tcp_send_fin(struct sock *sk) return; } } else { - skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + skb = alloc_skb_fclone(MAX_TCP_HEADER, + sk_gfp_mask(sk, GFP_ATOMIC | + __GFP_NOWARN)); if (unlikely(!skb)) return; @@ -3583,7 +3623,8 @@ void tcp_send_fin(struct sock *sk) * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ -void tcp_send_active_reset(struct sock *sk, gfp_t priority) +void tcp_send_active_reset(struct sock *sk, gfp_t priority, + enum sk_rst_reason reason) { struct sk_buff *skb; @@ -3608,7 +3649,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) /* skb of trace_tcp_send_reset() keeps the skb that caused RST, * skb here is different to the troublesome skb, so use NULL */ - trace_tcp_send_reset(sk, NULL); + trace_tcp_send_reset(sk, NULL, SK_RST_REASON_NOT_SPECIFIED); } /* Send a crossed SYN-ACK during socket establishment. @@ -3855,7 +3896,7 @@ static void tcp_connect_init(struct sock *sk) tcp_ca_dst_init(sk, dst); if (!tp->window_clamp) - tp->window_clamp = dst_metric(dst, RTAX_WINDOW); + WRITE_ONCE(tp->window_clamp, dst_metric(dst, RTAX_WINDOW)); tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); tcp_initialize_rcv_mss(sk); @@ -3863,7 +3904,7 @@ static void tcp_connect_init(struct sock *sk) /* limit the window selection if the user enforce a smaller rx buffer */ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) - tp->window_clamp = tcp_full_space(sk); + WRITE_ONCE(tp->window_clamp, tcp_full_space(sk)); rcv_wnd = tcp_rwnd_init_bpf(sk); if (rcv_wnd == 0) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index d1ad20ce1c8c..83fe7f62f7f1 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,10 +22,11 @@ #include <linux/module.h> #include <linux/gfp.h> #include <net/tcp.h> +#include <net/rstreason.h> static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); u32 elapsed, user_timeout; s32 remaining; @@ -47,7 +48,7 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); u32 remaining, user_timeout; s32 elapsed; @@ -127,7 +128,8 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) (!tp->snd_wnd && !tp->packets_out)) do_reset = true; if (do_reset) - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_NOT_SPECIFIED); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; @@ -768,7 +770,7 @@ static void tcp_keepalive_timer (struct timer_list *t) goto out; } } - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_NOT_SPECIFIED); goto death; } @@ -795,7 +797,8 @@ static void tcp_keepalive_timer (struct timer_list *t) icsk->icsk_probes_out > 0) || (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_NOT_SPECIFIED); tcp_write_err(sk); goto out; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 661d0e0d273f..189c9113fe9a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -427,15 +427,21 @@ static struct sock *udp4_lib_lookup2(struct net *net, { struct sock *sk, *result; int score, badness; + bool need_rescore; result = NULL; badness = 0; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { - score = compute_score(sk, net, saddr, sport, - daddr, hnum, dif, sdif); + need_rescore = false; +rescore: + score = compute_score(need_rescore ? result : sk, net, saddr, + sport, daddr, hnum, dif, sdif); if (score > badness) { badness = score; + if (need_rescore) + continue; + if (sk->sk_state == TCP_ESTABLISHED) { result = sk; continue; @@ -456,9 +462,14 @@ static struct sock *udp4_lib_lookup2(struct net *net, if (IS_ERR(result)) continue; - badness = compute_score(result, net, saddr, sport, - daddr, hnum, dif, sdif); - + /* compute_score is too long of a function to be + * inlined, and calling it again here yields + * measureable overhead for some + * workloads. Work around it by jumping + * backwards to rescore 'result'. + */ + need_rescore = true; + goto rescore; } } return result; @@ -532,7 +543,8 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { - const struct iphdr *iph = ip_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct net *net = dev_net(skb->dev); int iif, sdif; @@ -582,6 +594,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk, } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); +EXPORT_SYMBOL(udp_encap_needed_key); + +#if IS_ENABLED(CONFIG_IPV6) +DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +EXPORT_SYMBOL(udpv6_encap_needed_key); +#endif + void udp_encap_enable(void) { static_branch_inc(&udp_encap_needed_key); @@ -1116,16 +1135,17 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); - if (err > 0) + if (err > 0) { err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); + connected = 0; + } if (unlikely(err < 0)) { kfree(ipc.opt); return err; } if (ipc.opt) free = 1; - connected = 0; } if (!ipc.opt) { struct ip_options_rcu *inet_opt; @@ -1198,7 +1218,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } if (connected) - rt = (struct rtable *)sk_dst_check(sk, 0); + rt = dst_rtable(sk_dst_check(sk, 0)); if (!rt) { struct net *net = sock_net(sk); @@ -1492,13 +1512,15 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) struct sk_buff_head *list = &sk->sk_receive_queue; int rmem, err = -ENOMEM; spinlock_t *busy = NULL; - int size; + bool becomes_readable; + int size, rcvbuf; - /* try to avoid the costly atomic add/sub pair when the receive - * queue is full; always allow at least a packet + /* Immediately drop when the receive queue is full. + * Always allow at least one packet. */ rmem = atomic_read(&sk->sk_rmem_alloc); - if (rmem > sk->sk_rcvbuf) + rcvbuf = READ_ONCE(sk->sk_rcvbuf); + if (rmem > rcvbuf) goto drop; /* Under mem pressure, it might be helpful to help udp_recvmsg() @@ -1507,7 +1529,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * - Less cache line misses at copyout() time * - Less work at consume_skb() (less alien page frag freeing) */ - if (rmem > (sk->sk_rcvbuf >> 1)) { + if (rmem > (rcvbuf >> 1)) { skb_condense(skb); busy = busylock_acquire(sk); @@ -1515,12 +1537,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) size = skb->truesize; udp_set_dev_scratch(skb); - /* we drop only if the receive buf is full and the receive - * queue contains some other skb - */ - rmem = atomic_add_return(size, &sk->sk_rmem_alloc); - if (rmem > (size + (unsigned int)sk->sk_rcvbuf)) - goto uncharge_drop; + atomic_add(size, &sk->sk_rmem_alloc); spin_lock(&list->lock); err = udp_rmem_schedule(sk, size); @@ -1536,12 +1553,19 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) */ sock_skb_set_dropcount(sk, skb); + becomes_readable = skb_queue_empty(list); __skb_queue_tail(list, skb); spin_unlock(&list->lock); - if (!sock_flag(sk, SOCK_DEAD)) - INDIRECT_CALL_1(sk->sk_data_ready, sock_def_readable, sk); - + if (!sock_flag(sk, SOCK_DEAD)) { + if (becomes_readable || + sk->sk_data_ready != sock_def_readable || + READ_ONCE(sk->sk_peek_off) >= 0) + INDIRECT_CALL_1(sk->sk_data_ready, + sock_def_readable, sk); + else + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); + } busylock_release(busy); return 0; @@ -2049,8 +2073,8 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) drop_reason = SKB_DROP_REASON_PROTO_MEM; } UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + trace_udp_fail_queue_rcv_skb(rc, sk, skb); kfree_skb_reason(skb, drop_reason); - trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } @@ -2688,8 +2712,6 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_XFRM case UDP_ENCAP_ESPINUDP: set_xfrm_gro_udp_encap_rcv(val, sk->sk_family, sk); - fallthrough; - case UDP_ENCAP_ESPINUDP_NON_IKE: #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) WRITE_ONCE(up->encap_rcv, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index b9880743765c..59448a2dbf2c 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -433,32 +433,6 @@ out: return segs; } -static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) -{ - if (unlikely(p->len + skb->len >= 65536)) - return -E2BIG; - - if (NAPI_GRO_CB(p)->last == p) - skb_shinfo(p)->frag_list = skb; - else - NAPI_GRO_CB(p)->last->next = skb; - - skb_pull(skb, skb_gro_offset(skb)); - - NAPI_GRO_CB(p)->last = skb; - NAPI_GRO_CB(p)->count++; - p->data_len += skb->len; - - /* sk owenrship - if any - completely transferred to the aggregated packet */ - skb->destructor = NULL; - p->truesize += skb->truesize; - p->len += skb->len; - - NAPI_GRO_CB(skb)->same_flow = 1; - - return 0; -} - #define UDP_GRO_CNT_MAX 64 static struct sk_buff *udp_gro_receive_segment(struct list_head *head, @@ -470,6 +444,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *p; unsigned int ulen; int ret = 0; + int flush; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { @@ -503,13 +478,15 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, return p; } + flush = gro_receive_network_flush(uh, uh2, p); + /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot * leading to excessive truesize values. * On len mismatch merge the first packet shorter than gso_size, * otherwise complete the GRO packet. */ - if (ulen > ntohs(uh2->len)) { + if (ulen > ntohs(uh2->len) || flush) { pp = p; } else { if (NAPI_GRO_CB(skb)->is_flist) { @@ -551,11 +528,19 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; - /* we can do L4 aggregation only if the packet can't land in a tunnel - * otherwise we could corrupt the inner stream + /* We can do L4 aggregation only if the packet can't land in a tunnel + * otherwise we could corrupt the inner stream. Detecting such packets + * cannot be foolproof and the aggregation might still happen in some + * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { + /* If the packet was locally encapsulated in a UDP tunnel that + * wasn't detected above, do not GRO. + */ + if (skb->encapsulation) + goto out; + if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1; @@ -709,7 +694,8 @@ EXPORT_SYMBOL(udp_gro_complete); INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) { - const struct iphdr *iph = ip_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ @@ -719,13 +705,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 860aff5f8599..e4e0fa869fa4 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -183,7 +183,8 @@ void udp_tunnel_sock_release(struct socket *sock) EXPORT_SYMBOL_GPL(udp_tunnel_sock_release); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, - __be16 flags, __be64 tunnel_id, int md_size) + const unsigned long *flags, + __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; @@ -199,7 +200,7 @@ struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, info->key.tp_src = udp_hdr(skb)->source; info->key.tp_dst = udp_hdr(skb)->dest; if (udp_hdr(skb)->check) - info->key.tun_flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); return tun_dst; } EXPORT_SYMBOL_GPL(udp_tun_rx_dst); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index dae35101d189..a620618cc568 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -63,7 +63,11 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) ip_send_check(iph); if (xo && (xo->flags & XFRM_GRO)) { - skb_mac_header_rebuild(skb); + /* The full l2 header needs to be preserved so that re-injecting the packet at l2 + * works correctly in the presence of vlan tags. + */ + skb_mac_header_rebuild_full(skb, xo->orig_mac_len); + skb_reset_network_header(skb); skb_reset_transport_header(skb); return 0; } @@ -113,19 +117,6 @@ static int __xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb, bool pull /* Must be an IKE packet.. pass it through */ return 1; break; - case UDP_ENCAP_ESPINUDP_NON_IKE: - /* Check if this is a keepalive packet. If so, eat it. */ - if (len == 1 && udpdata[0] == 0xff) { - return -EINVAL; - } else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) && - udpdata32[0] == 0 && udpdata32[1] == 0) { - - /* ESP Packet with Non-IKE marker */ - len = sizeof(struct udphdr) + 2 * sizeof(u32); - } else - /* Must be an IKE packet.. pass it through */ - return 1; - break; } /* At this point we are sure that this is an ESPinUDP packet, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index c33bca2c3841..0294fef577fa 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -69,7 +69,7 @@ static int xfrm4_get_saddr(struct net *net, int oif, static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { - struct rtable *rt = (struct rtable *)xdst->route; + struct rtable *rt = dst_rtable(xdst->route); const struct flowi4 *fl4 = &fl->u.ip4; xdst->u.rt.rt_iif = fl4->flowi4_iif; @@ -152,7 +152,6 @@ static struct ctl_table xfrm4_policy_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; static __net_init int xfrm4_net_sysctl_init(struct net *net) @@ -186,7 +185,7 @@ err_alloc: static __net_exit void xfrm4_net_sysctl_exit(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; if (!net->ipv4.xfrm4_hdr) return; |