diff options
Diffstat (limited to 'net/ipv4')
32 files changed, 816 insertions, 258 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 766c59658563..24b384b7903e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -346,7 +346,8 @@ lookup_protocol: } err = -EPERM; - if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) + if (sock->type == SOCK_RAW && !kern && + !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; err = -EAFNOSUPPORT; @@ -473,6 +474,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; int err; @@ -496,7 +498,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); + chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); /* Not specified by any standard per-se, however it breaks too * many applications when removed. It is unfortunate since @@ -516,7 +518,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) snum = ntohs(addr->sin_port); err = -EACCES; - if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) + if (snum && snum < PROT_SOCK && + !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) goto out; /* We keep a pair of addresses. rcv_saddr is the one @@ -1251,7 +1254,7 @@ EXPORT_SYMBOL(inet_sk_rebuild_header); static int inet_gso_send_check(struct sk_buff *skb) { - const struct net_protocol *ops; + const struct net_offload *ops; const struct iphdr *iph; int proto; int ihl; @@ -1275,9 +1278,9 @@ static int inet_gso_send_check(struct sk_buff *skb) err = -EPROTONOSUPPORT; rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (likely(ops && ops->gso_send_check)) - err = ops->gso_send_check(skb); + ops = rcu_dereference(inet_offloads[proto]); + if (likely(ops && ops->callbacks.gso_send_check)) + err = ops->callbacks.gso_send_check(skb); rcu_read_unlock(); out: @@ -1288,7 +1291,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); - const struct net_protocol *ops; + const struct net_offload *ops; struct iphdr *iph; int proto; int ihl; @@ -1325,9 +1328,9 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (likely(ops && ops->gso_segment)) - segs = ops->gso_segment(skb, features); + ops = rcu_dereference(inet_offloads[proto]); + if (likely(ops && ops->callbacks.gso_segment)) + segs = ops->callbacks.gso_segment(skb, features); rcu_read_unlock(); if (!segs || IS_ERR(segs)) @@ -1356,7 +1359,7 @@ out: static struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) { - const struct net_protocol *ops; + const struct net_offload *ops; struct sk_buff **pp = NULL; struct sk_buff *p; const struct iphdr *iph; @@ -1378,8 +1381,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, proto = iph->protocol; rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (!ops || !ops->gro_receive) + ops = rcu_dereference(inet_offloads[proto]); + if (!ops || !ops->callbacks.gro_receive) goto out_unlock; if (*(u8 *)iph != 0x45) @@ -1420,7 +1423,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); - pp = ops->gro_receive(head, skb); + pp = ops->callbacks.gro_receive(head, skb); out_unlock: rcu_read_unlock(); @@ -1435,7 +1438,7 @@ static int inet_gro_complete(struct sk_buff *skb) { __be16 newlen = htons(skb->len - skb_network_offset(skb)); struct iphdr *iph = ip_hdr(skb); - const struct net_protocol *ops; + const struct net_offload *ops; int proto = iph->protocol; int err = -ENOSYS; @@ -1443,11 +1446,11 @@ static int inet_gro_complete(struct sk_buff *skb) iph->tot_len = newlen; rcu_read_lock(); - ops = rcu_dereference(inet_protos[proto]); - if (WARN_ON(!ops || !ops->gro_complete)) + ops = rcu_dereference(inet_offloads[proto]); + if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out_unlock; - err = ops->gro_complete(skb); + err = ops->callbacks.gro_complete(skb); out_unlock: rcu_read_unlock(); @@ -1558,23 +1561,33 @@ static const struct net_protocol tcp_protocol = { .early_demux = tcp_v4_early_demux, .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, - .gso_send_check = tcp_v4_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp4_gro_receive, - .gro_complete = tcp4_gro_complete, .no_policy = 1, .netns_ok = 1, }; +static const struct net_offload tcp_offload = { + .callbacks = { + .gso_send_check = tcp_v4_gso_send_check, + .gso_segment = tcp_tso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, + }, +}; + static const struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, - .gso_send_check = udp4_ufo_send_check, - .gso_segment = udp4_ufo_fragment, .no_policy = 1, .netns_ok = 1, }; +static const struct net_offload udp_offload = { + .callbacks = { + .gso_send_check = udp4_ufo_send_check, + .gso_segment = udp4_ufo_fragment, + }, +}; + static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = ping_err, @@ -1659,13 +1672,35 @@ static int ipv4_proc_init(void); * IP protocol layer initialiser */ +static struct packet_offload ip_packet_offload __read_mostly = { + .type = cpu_to_be16(ETH_P_IP), + .callbacks = { + .gso_send_check = inet_gso_send_check, + .gso_segment = inet_gso_segment, + .gro_receive = inet_gro_receive, + .gro_complete = inet_gro_complete, + }, +}; + +static int __init ipv4_offload_init(void) +{ + /* + * Add offloads + */ + if (inet_add_offload(&udp_offload, IPPROTO_UDP) < 0) + pr_crit("%s: Cannot add UDP protocol offload\n", __func__); + if (inet_add_offload(&tcp_offload, IPPROTO_TCP) < 0) + pr_crit("%s: Cannot add TCP protocol offlaod\n", __func__); + + dev_add_offload(&ip_packet_offload); + return 0; +} + +fs_initcall(ipv4_offload_init); + static struct packet_type ip_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .func = ip_rcv, - .gso_send_check = inet_gso_send_check, - .gso_segment = inet_gso_segment, - .gro_receive = inet_gro_receive, - .gro_complete = inet_gro_complete, }; static int __init inet_init(void) diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 47800459e4cb..ce6fbdfd40b8 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1161,7 +1161,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) switch (cmd) { case SIOCDARP: case SIOCSARP: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; case SIOCGARP: err = copy_from_user(&r, arg, sizeof(struct arpreq)); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 2a6abc163ed2..cc06a47f1216 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -55,6 +55,7 @@ #include <linux/sysctl.h> #endif #include <linux/kmod.h> +#include <linux/netconf.h> #include <net/arp.h> #include <net/ip.h> @@ -723,7 +724,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSIFFLAGS: ret = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; break; case SIOCSIFADDR: /* Set interface address (and family) */ @@ -731,7 +732,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSIFDSTADDR: /* Set the destination address */ case SIOCSIFNETMASK: /* Set the netmask for the interface */ ret = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; ret = -EINVAL; if (sin->sin_family != AF_INET) @@ -1442,6 +1443,155 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) return 0; } +static int inet_netconf_msgsize_devconf(int type) +{ + int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + + nla_total_size(4); /* NETCONFA_IFINDEX */ + + /* type -1 is used for ALL */ + if (type == -1 || type == NETCONFA_FORWARDING) + size += nla_total_size(4); + if (type == -1 || type == NETCONFA_RP_FILTER) + size += nla_total_size(4); + if (type == -1 || type == NETCONFA_MC_FORWARDING) + size += nla_total_size(4); + + return size; +} + +static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, + struct ipv4_devconf *devconf, u32 portid, + u32 seq, int event, unsigned int flags, + int type) +{ + struct nlmsghdr *nlh; + struct netconfmsg *ncm; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), + flags); + if (nlh == NULL) + return -EMSGSIZE; + + ncm = nlmsg_data(nlh); + ncm->ncm_family = AF_INET; + + if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) + goto nla_put_failure; + + /* type -1 is used for ALL */ + if ((type == -1 || type == NETCONFA_FORWARDING) && + nla_put_s32(skb, NETCONFA_FORWARDING, + IPV4_DEVCONF(*devconf, FORWARDING)) < 0) + goto nla_put_failure; + if ((type == -1 || type == NETCONFA_RP_FILTER) && + nla_put_s32(skb, NETCONFA_RP_FILTER, + IPV4_DEVCONF(*devconf, RP_FILTER)) < 0) + goto nla_put_failure; + if ((type == -1 || type == NETCONFA_MC_FORWARDING) && + nla_put_s32(skb, NETCONFA_MC_FORWARDING, + IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +void inet_netconf_notify_devconf(struct net *net, int type, int ifindex, + struct ipv4_devconf *devconf) +{ + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, + RTM_NEWNETCONF, 0, type); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_ATOMIC); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); +} + +static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { + [NETCONFA_IFINDEX] = { .len = sizeof(int) }, + [NETCONFA_FORWARDING] = { .len = sizeof(int) }, + [NETCONFA_RP_FILTER] = { .len = sizeof(int) }, +}; + +static int inet_netconf_get_devconf(struct sk_buff *in_skb, + struct nlmsghdr *nlh, + void *arg) +{ + struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[NETCONFA_MAX+1]; + struct netconfmsg *ncm; + struct sk_buff *skb; + struct ipv4_devconf *devconf; + struct in_device *in_dev; + struct net_device *dev; + int ifindex; + int err; + + err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, + devconf_ipv4_policy); + if (err < 0) + goto errout; + + err = EINVAL; + if (!tb[NETCONFA_IFINDEX]) + goto errout; + + ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); + switch (ifindex) { + case NETCONFA_IFINDEX_ALL: + devconf = net->ipv4.devconf_all; + break; + case NETCONFA_IFINDEX_DEFAULT: + devconf = net->ipv4.devconf_dflt; + break; + default: + dev = __dev_get_by_index(net, ifindex); + if (dev == NULL) + goto errout; + in_dev = __in_dev_get_rtnl(dev); + if (in_dev == NULL) + goto errout; + devconf = &in_dev->cnf; + break; + } + + err = -ENOBUFS; + skb = nlmsg_new(inet_netconf_msgsize_devconf(-1), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet_netconf_fill_devconf(skb, ifindex, devconf, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, RTM_NEWNETCONF, 0, + -1); + if (err < 0) { + /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); +errout: + return err; +} + #ifdef CONFIG_SYSCTL static void devinet_copy_dflt_conf(struct net *net, int i) @@ -1467,6 +1617,12 @@ static void inet_forward_change(struct net *net) IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on; IPV4_DEVCONF_DFLT(net, FORWARDING) = on; + inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv4.devconf_all); + inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_DEFAULT, + net->ipv4.devconf_dflt); for_each_netdev(net, dev) { struct in_device *in_dev; @@ -1474,8 +1630,11 @@ static void inet_forward_change(struct net *net) dev_disable_lro(dev); rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); - if (in_dev) + if (in_dev) { IN_DEV_CONF_SET(in_dev, FORWARDING, on); + inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + dev->ifindex, &in_dev->cnf); + } rcu_read_unlock(); } } @@ -1501,6 +1660,23 @@ static int devinet_conf_proc(ctl_table *ctl, int write, i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net); + if (i == IPV4_DEVCONF_RP_FILTER - 1 && + new_value != old_value) { + int ifindex; + + if (cnf == net->ipv4.devconf_dflt) + ifindex = NETCONFA_IFINDEX_DEFAULT; + else if (cnf == net->ipv4.devconf_all) + ifindex = NETCONFA_IFINDEX_ALL; + else { + struct in_device *idev = + container_of(cnf, struct in_device, + cnf); + ifindex = idev->dev->ifindex; + } + inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER, + ifindex, cnf); + } } return ret; @@ -1527,15 +1703,23 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, } if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) { inet_forward_change(net); - } else if (*valp) { + } else { struct ipv4_devconf *cnf = ctl->extra1; struct in_device *idev = container_of(cnf, struct in_device, cnf); - dev_disable_lro(idev->dev); + if (*valp) + dev_disable_lro(idev->dev); + inet_netconf_notify_devconf(net, + NETCONFA_FORWARDING, + idev->dev->ifindex, + cnf); } rtnl_unlock(); rt_cache_flush(net); - } + } else + inet_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_DEFAULT, + net->ipv4.devconf_dflt); } return ret; @@ -1809,5 +1993,7 @@ void __init devinet_init(void) rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL); rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL); rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL); + rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf, + NULL, NULL); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 825c608826de..5cd75e2dab2c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -488,7 +488,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) switch (cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&rt, arg, sizeof(rt))) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 71b125cd5db1..4797a800faf8 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -803,7 +803,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) unsigned int bytes; if (!new_size) - new_size = 1; + new_size = 16; bytes = new_size * sizeof(struct hlist_head *); new_info_hash = fib_info_hash_alloc(bytes); new_laddrhash = fib_info_hash_alloc(bytes); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d34ce2972c8f..2026542d6836 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -521,21 +521,31 @@ static inline void syn_ack_recalc(struct request_sock *req, const int thresh, int *expire, int *resend) { if (!rskq_defer_accept) { - *expire = req->retrans >= thresh; + *expire = req->num_timeout >= thresh; *resend = 1; return; } - *expire = req->retrans >= thresh && - (!inet_rsk(req)->acked || req->retrans >= max_retries); + *expire = req->num_timeout >= thresh && + (!inet_rsk(req)->acked || req->num_timeout >= max_retries); /* * Do not resend while waiting for data after ACK, * start to resend on end of deferring period to give * last chance for data or ACK to create established socket. */ *resend = !inet_rsk(req)->acked || - req->retrans >= rskq_defer_accept - 1; + req->num_timeout >= rskq_defer_accept - 1; } +int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req) +{ + int err = req->rsk_ops->rtx_syn_ack(parent, req, NULL); + + if (!err) + req->num_retrans++; + return err; +} +EXPORT_SYMBOL(inet_rtx_syn_ack); + void inet_csk_reqsk_queue_prune(struct sock *parent, const unsigned long interval, const unsigned long timeout, @@ -599,13 +609,14 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, req->rsk_ops->syn_ack_timeout(parent, req); if (!expire && (!resend || - !req->rsk_ops->rtx_syn_ack(parent, req, NULL) || + !inet_rtx_syn_ack(parent, req) || inet_rsk(req)->acked)) { unsigned long timeo; - if (req->retrans++ == 0) + if (req->num_timeout++ == 0) lopt->qlen_young--; - timeo = min((timeout << req->retrans), max_rto); + timeo = min(timeout << req->num_timeout, + max_rto); req->expires = now + timeo; reqp = &req->dl_next; continue; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e23e16dc501d..7afa2c3c788f 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -109,6 +109,9 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->id.idiag_src[0] = inet->inet_rcv_saddr; r->id.idiag_dst[0] = inet->inet_daddr; + if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown)) + goto errout; + /* IPv6 dual-stack sockets use inet->tos for IPv4 connections, * hence this needs to be included regardless of socket family. */ @@ -716,7 +719,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->idiag_family = sk->sk_family; r->idiag_state = TCP_SYN_RECV; r->idiag_timer = 1; - r->idiag_retrans = req->retrans; + r->idiag_retrans = req->num_retrans; r->id.idiag_if = sk->sk_bound_dev_if; sock_diag_save_cookie(req, r->id.idiag_cookie); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 7880af970208..fa3ae8148710 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -237,12 +237,14 @@ struct sock *__inet_lookup_established(struct net *net, rcu_read_lock(); begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { - if (INET_MATCH(sk, net, hash, acookie, - saddr, daddr, ports, dif)) { + if (sk->sk_hash != hash) + continue; + if (likely(INET_MATCH(sk, net, acookie, + saddr, daddr, ports, dif))) { if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) goto begintw; - if (unlikely(!INET_MATCH(sk, net, hash, acookie, - saddr, daddr, ports, dif))) { + if (unlikely(!INET_MATCH(sk, net, acookie, + saddr, daddr, ports, dif))) { sock_put(sk); goto begin; } @@ -260,14 +262,18 @@ begin: begintw: /* Must check for a TIME_WAIT'er before going to listener hash. */ sk_nulls_for_each_rcu(sk, node, &head->twchain) { - if (INET_TW_MATCH(sk, net, hash, acookie, - saddr, daddr, ports, dif)) { + if (sk->sk_hash != hash) + continue; + if (likely(INET_TW_MATCH(sk, net, acookie, + saddr, daddr, ports, + dif))) { if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) { sk = NULL; goto out; } - if (unlikely(!INET_TW_MATCH(sk, net, hash, acookie, - saddr, daddr, ports, dif))) { + if (unlikely(!INET_TW_MATCH(sk, net, acookie, + saddr, daddr, ports, + dif))) { sock_put(sk); goto begintw; } @@ -314,10 +320,12 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, /* Check TIME-WAIT sockets first. */ sk_nulls_for_each(sk2, node, &head->twchain) { - tw = inet_twsk(sk2); + if (sk2->sk_hash != hash) + continue; - if (INET_TW_MATCH(sk2, net, hash, acookie, - saddr, daddr, ports, dif)) { + if (likely(INET_TW_MATCH(sk2, net, acookie, + saddr, daddr, ports, dif))) { + tw = inet_twsk(sk2); if (twsk_unique(sk, sk2, twp)) goto unique; else @@ -328,8 +336,10 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, /* And established part... */ sk_nulls_for_each(sk2, node, &head->chain) { - if (INET_MATCH(sk2, net, hash, acookie, - saddr, daddr, ports, dif)) + if (sk2->sk_hash != hash) + continue; + if (likely(INET_MATCH(sk2, net, acookie, + saddr, daddr, ports, dif))) goto not_unique; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 8d5cc75dac88..eb9d63a570cd 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -801,6 +801,10 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) table[0].data = &net->ipv4.frags.high_thresh; table[1].data = &net->ipv4.frags.low_thresh; table[2].data = &net->ipv4.frags.timeout; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; } hdr = register_net_sysctl(net, "net/ipv4", table); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7240f8e2dd45..a85ae2f7a21c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -164,21 +164,6 @@ struct ipgre_net { #define tunnels_r tunnels[2] #define tunnels_l tunnels[1] #define tunnels_wc tunnels[0] -/* - * Locking : hash tables are protected by RCU and RTNL - */ - -#define for_each_ip_tunnel_rcu(start) \ - for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) - -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) @@ -250,7 +235,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, ARPHRD_ETHER : ARPHRD_IPGRE; int score, cand_score = 4; - for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) { if (local != t->parms.iph.saddr || remote != t->parms.iph.daddr || !(t->dev->flags & IFF_UP)) @@ -277,7 +262,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) { if (remote != t->parms.iph.daddr || !(t->dev->flags & IFF_UP)) continue; @@ -303,7 +288,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) { if ((local != t->parms.iph.saddr && (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) || @@ -331,7 +316,7 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, } } - for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) { + for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) { if (t->parms.i_key != key || !(t->dev->flags & IFF_UP)) continue; @@ -753,7 +738,6 @@ drop: static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct pcpu_tstats *tstats; const struct iphdr *old_iph = ip_hdr(skb); const struct iphdr *tiph; struct flowi4 fl4; @@ -977,9 +961,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } } - nf_reset(skb); - tstats = this_cpu_ptr(dev->tstats); - __IPTUNNEL_XMIT(tstats, &dev->stats); + iptunnel_xmit(skb, dev); return NETDEV_TX_OK; #if IS_ENABLED(CONFIG_IPV6) @@ -1082,7 +1064,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -1157,7 +1139,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == ign->fb_tunnel_dev) { diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 1dc01f9793d5..f6289bf6f332 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -409,7 +409,7 @@ int ip_options_compile(struct net *net, optptr[2] += 8; break; default: - if (!skb && !capable(CAP_NET_RAW)) { + if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) { pp_ptr = optptr + 3; goto error; } @@ -445,7 +445,7 @@ int ip_options_compile(struct net *net, opt->router_alert = optptr - iph; break; case IPOPT_CIPSO: - if ((!skb && !capable(CAP_NET_RAW)) || opt->cipso) { + if ((!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) || opt->cipso) { pp_ptr = optptr; goto error; } @@ -458,7 +458,7 @@ int ip_options_compile(struct net *net, case IPOPT_SEC: case IPOPT_SID: default: - if (!skb && !capable(CAP_NET_RAW)) { + if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) { pp_ptr = optptr; goto error; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6537a408a4fb..3e98ed2bff55 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -595,6 +595,10 @@ slow_path_clean: } slow_path: + /* for offloaded checksums cleanup checksum before fragmentation */ + if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb)) + goto fail; + left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 14bbfcf717ac..3c9d20880283 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -989,13 +989,14 @@ mc_msf_out: case IP_IPSEC_POLICY: case IP_XFRM_POLICY: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) break; err = xfrm_user_policy(sk, optname, optval, optlen); break; case IP_TRANSPARENT: - if (!!val && !capable(CAP_NET_RAW) && !capable(CAP_NET_ADMIN)) { + if (!!val && !ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && + !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { err = -EPERM; break; } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 858fddf6482a..c3a4233c0ac2 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -66,20 +66,6 @@ static void vti_tunnel_setup(struct net_device *dev); static void vti_dev_free(struct net_device *dev); static int vti_tunnel_bind_dev(struct net_device *dev); -/* Locking : hash tables are protected by RCU and RTNL */ - -#define for_each_ip_tunnel_rcu(start) \ - for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) - -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; - #define VTI_XMIT(stats1, stats2) do { \ int err; \ int pkt_len = skb->len; \ @@ -142,19 +128,19 @@ static struct ip_tunnel *vti_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct vti_net *ipn = net_generic(net, vti_net_id); - for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1]) if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - for_each_ip_tunnel_rcu(ipn->tunnels_r[h0]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0]) if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - for_each_ip_tunnel_rcu(ipn->tunnels_l[h1]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1]) if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) return t; - for_each_ip_tunnel_rcu(ipn->tunnels_wc[0]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_wc[0]) if (t && (t->dev->flags&IFF_UP)) return t; return NULL; @@ -502,7 +488,7 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -567,7 +553,7 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == ipn->fb_tunnel_dev) { diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 798358b10717..d763701cff1b 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1500,8 +1500,10 @@ static int __init ip_auto_config(void) * Clue in the operator. */ pr_info("IP-Config: Complete:\n"); - pr_info(" device=%s, addr=%pI4, mask=%pI4, gw=%pI4\n", - ic_dev->name, &ic_myaddr, &ic_netmask, &ic_gateway); + + pr_info(" device=%s, hwaddr=%*phC, ipaddr=%pI4, mask=%pI4, gw=%pI4\n", + ic_dev->name, ic_dev->addr_len, ic_dev->dev_addr, + &ic_myaddr, &ic_netmask, &ic_gateway); pr_info(" host=%s, domain=%s, nis-domain=%s\n", utsname()->nodename, ic_domain, utsname()->domainname); pr_info(" bootserver=%pI4, rootserver=%pI4, rootpath=%s", diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index e15b45297c09..191fc24a745a 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -138,22 +138,7 @@ struct ipip_net { static int ipip_tunnel_init(struct net_device *dev); static void ipip_tunnel_setup(struct net_device *dev); static void ipip_dev_free(struct net_device *dev); - -/* - * Locking : hash tables are protected by RCU and RTNL - */ - -#define for_each_ip_tunnel_rcu(start) \ - for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) - -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; +static struct rtnl_link_ops ipip_link_ops __read_mostly; static struct rtnl_link_stats64 *ipip_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) @@ -197,16 +182,16 @@ static struct ip_tunnel *ipip_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct ipip_net *ipn = net_generic(net, ipip_net_id); - for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1]) if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - for_each_ip_tunnel_rcu(ipn->tunnels_r[h0]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0]) if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - for_each_ip_tunnel_rcu(ipn->tunnels_l[h1]) + for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1]) if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) return t; @@ -264,6 +249,32 @@ static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t) rcu_assign_pointer(*tp, t); } +static int ipip_tunnel_create(struct net_device *dev) +{ + struct ip_tunnel *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct ipip_net *ipn = net_generic(net, ipip_net_id); + int err; + + err = ipip_tunnel_init(dev); + if (err < 0) + goto out; + + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &ipip_link_ops; + + dev_hold(dev); + ipip_tunnel_link(ipn, t); + return 0; + +out: + return err; +} + static struct ip_tunnel *ipip_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { @@ -298,16 +309,9 @@ static struct ip_tunnel *ipip_tunnel_locate(struct net *net, nt = netdev_priv(dev); nt->parms = *parms; - if (ipip_tunnel_init(dev) < 0) + if (ipip_tunnel_create(dev) < 0) goto failed_free; - if (register_netdevice(dev) < 0) - goto failed_free; - - strcpy(nt->parms.name, dev->name); - - dev_hold(dev); - ipip_tunnel_link(ipn, nt); return nt; failed_free: @@ -463,7 +467,6 @@ drop: static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct pcpu_tstats *tstats; const struct iphdr *tiph = &tunnel->parms.iph; u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; @@ -479,6 +482,10 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (skb->protocol != htons(ETH_P_IP)) goto tx_error; + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb)) + goto tx_error; + if (tos & 1) tos = old_iph->tos; @@ -586,9 +593,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if ((iph->ttl = tiph->ttl) == 0) iph->ttl = old_iph->ttl; - nf_reset(skb); - tstats = this_cpu_ptr(dev->tstats); - __IPTUNNEL_XMIT(tstats, &dev->stats); + iptunnel_xmit(skb, dev); return NETDEV_TX_OK; tx_error_icmp: @@ -635,6 +640,28 @@ static void ipip_tunnel_bind_dev(struct net_device *dev) dev->iflink = tunnel->parms.link; } +static void ipip_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) +{ + struct net *net = dev_net(t->dev); + struct ipip_net *ipn = net_generic(net, ipip_net_id); + + ipip_tunnel_unlink(ipn, t); + synchronize_net(); + t->parms.iph.saddr = p->iph.saddr; + t->parms.iph.daddr = p->iph.daddr; + memcpy(t->dev->dev_addr, &p->iph.saddr, 4); + memcpy(t->dev->broadcast, &p->iph.daddr, 4); + ipip_tunnel_link(ipn, t); + t->parms.iph.ttl = p->iph.ttl; + t->parms.iph.tos = p->iph.tos; + t->parms.iph.frag_off = p->iph.frag_off; + if (t->parms.link != p->link) { + t->parms.link = p->link; + ipip_tunnel_bind_dev(t->dev); + } + netdev_state_change(t->dev); +} + static int ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -664,7 +691,7 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -693,29 +720,13 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) break; } t = netdev_priv(dev); - ipip_tunnel_unlink(ipn, t); - synchronize_net(); - t->parms.iph.saddr = p.iph.saddr; - t->parms.iph.daddr = p.iph.daddr; - memcpy(dev->dev_addr, &p.iph.saddr, 4); - memcpy(dev->broadcast, &p.iph.daddr, 4); - ipip_tunnel_link(ipn, t); - netdev_state_change(dev); } + + ipip_tunnel_update(t, &p); } if (t) { err = 0; - if (cmd == SIOCCHGTUNNEL) { - t->parms.iph.ttl = p.iph.ttl; - t->parms.iph.tos = p.iph.tos; - t->parms.iph.frag_off = p.iph.frag_off; - if (t->parms.link != p.link) { - t->parms.link = p.link; - ipip_tunnel_bind_dev(dev); - netdev_state_change(dev); - } - } if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p))) err = -EFAULT; } else @@ -724,7 +735,7 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == ipn->fb_tunnel_dev) { @@ -773,6 +784,11 @@ static void ipip_dev_free(struct net_device *dev) free_netdev(dev); } +#define IPIP_FEATURES (NETIF_F_SG | \ + NETIF_F_FRAGLIST | \ + NETIF_F_HIGHDMA | \ + NETIF_F_HW_CSUM) + static void ipip_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip_netdev_ops; @@ -787,6 +803,9 @@ static void ipip_tunnel_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; dev->features |= NETIF_F_LLTX; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + + dev->features |= IPIP_FEATURES; + dev->hw_features |= IPIP_FEATURES; } static int ipip_tunnel_init(struct net_device *dev) @@ -829,6 +848,142 @@ static int __net_init ipip_fb_tunnel_init(struct net_device *dev) return 0; } +static void ipip_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + parms->iph.version = 4; + parms->iph.protocol = IPPROTO_IPIP; + parms->iph.ihl = 5; + + if (!data) + return; + + if (data[IFLA_IPTUN_LINK]) + parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); + + if (data[IFLA_IPTUN_LOCAL]) + parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]); + + if (data[IFLA_IPTUN_REMOTE]) + parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]); + + if (data[IFLA_IPTUN_TTL]) { + parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]); + if (parms->iph.ttl) + parms->iph.frag_off = htons(IP_DF); + } + + if (data[IFLA_IPTUN_TOS]) + parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]); + + if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) + parms->iph.frag_off = htons(IP_DF); +} + +static int ipip_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net *net = dev_net(dev); + struct ip_tunnel *nt; + + nt = netdev_priv(dev); + ipip_netlink_parms(data, &nt->parms); + + if (ipip_tunnel_locate(net, &nt->parms, 0)) + return -EEXIST; + + return ipip_tunnel_create(dev); +} + +static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip_tunnel *t; + struct ip_tunnel_parm p; + struct net *net = dev_net(dev); + struct ipip_net *ipn = net_generic(net, ipip_net_id); + + if (dev == ipn->fb_tunnel_dev) + return -EINVAL; + + ipip_netlink_parms(data, &p); + + if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || + (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) + return -EINVAL; + + t = ipip_tunnel_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + ipip_tunnel_update(t, &p); + return 0; +} + +static size_t ipip_get_size(const struct net_device *dev) +{ + return + /* IFLA_IPTUN_LINK */ + nla_total_size(4) + + /* IFLA_IPTUN_LOCAL */ + nla_total_size(4) + + /* IFLA_IPTUN_REMOTE */ + nla_total_size(4) + + /* IFLA_IPTUN_TTL */ + nla_total_size(1) + + /* IFLA_IPTUN_TOS */ + nla_total_size(1) + + /* IFLA_IPTUN_PMTUDISC */ + nla_total_size(1) + + 0; +} + +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; + + if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || + nla_put_be32(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || + nla_put_be32(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || + nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || + nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || + nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, + !!(parm->iph.frag_off & htons(IP_DF)))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = { + [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, + [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, + [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, + [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, + [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, + [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, +}; + +static struct rtnl_link_ops ipip_link_ops __read_mostly = { + .kind = "ipip", + .maxtype = IFLA_IPTUN_MAX, + .policy = ipip_policy, + .priv_size = sizeof(struct ip_tunnel), + .setup = ipip_tunnel_setup, + .newlink = ipip_newlink, + .changelink = ipip_changelink, + .get_size = ipip_get_size, + .fill_info = ipip_fill_info, +}; + static struct xfrm_tunnel ipip_handler __read_mostly = { .handler = ipip_rcv, .err_handler = ipip_err, @@ -925,14 +1080,26 @@ static int __init ipip_init(void) return err; err = xfrm4_tunnel_register(&ipip_handler, AF_INET); if (err < 0) { - unregister_pernet_device(&ipip_net_ops); pr_info("%s: can't register tunnel\n", __func__); + goto xfrm_tunnel_failed; } + err = rtnl_link_register(&ipip_link_ops); + if (err < 0) + goto rtnl_link_failed; + +out: return err; + +rtnl_link_failed: + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); +xfrm_tunnel_failed: + unregister_pernet_device(&ipip_net_ops); + goto out; } static void __exit ipip_fini(void) { + rtnl_link_unregister(&ipip_link_ops); if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET)) pr_info("%s: can't deregister tunnel\n", __func__); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3eab2b2ffd34..a9454cbd953c 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -65,6 +65,7 @@ #include <net/checksum.h> #include <net/netlink.h> #include <net/fib_rules.h> +#include <linux/netconf.h> #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) #define CONFIG_IP_PIMSM 1 @@ -83,8 +84,8 @@ struct mr_table { struct vif_device vif_table[MAXVIFS]; int maxvif; atomic_t cache_resolve_queue_len; - int mroute_do_assert; - int mroute_do_pim; + bool mroute_do_assert; + bool mroute_do_pim; #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) int mroute_reg_vif_num; #endif @@ -133,6 +134,8 @@ static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); +static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, + int cmd); static void mroute_clean_tables(struct mr_table *mrt); static void ipmr_expire_process(unsigned long arg); @@ -582,6 +585,9 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, in_dev = __in_dev_get_rtnl(dev); if (in_dev) { IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--; + inet_netconf_notify_devconf(dev_net(dev), + NETCONFA_MC_FORWARDING, + dev->ifindex, &in_dev->cnf); ip_rt_multicast_event(in_dev); } @@ -665,6 +671,7 @@ static void ipmr_expire_process(unsigned long arg) } list_del(&c->list); + mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_destroy_unres(mrt, c); } @@ -772,6 +779,8 @@ static int vif_add(struct net *net, struct mr_table *mrt, return -EADDRNOTAVAIL; } IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++; + inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, dev->ifindex, + &in_dev->cnf); ip_rt_multicast_event(in_dev); /* Fill in the VIF structures */ @@ -1020,6 +1029,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->list, &mrt->mfc_unres_queue); + mroute_netlink_event(mrt, c, RTM_NEWROUTE); if (atomic_read(&mrt->cache_resolve_queue_len) == 1) mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires); @@ -1054,7 +1064,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) if (c->mfc_origin == mfc->mfcc_origin.s_addr && c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { list_del_rcu(&c->list); - + mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_cache_free(c); return 0; } @@ -1089,6 +1099,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); + mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1131,6 +1142,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, ipmr_cache_resolve(net, mrt, uc, c); ipmr_cache_free(uc); } + mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1159,6 +1171,7 @@ static void mroute_clean_tables(struct mr_table *mrt) if (c->mfc_flags & MFC_STATIC) continue; list_del_rcu(&c->list); + mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_cache_free(c); } } @@ -1167,6 +1180,7 @@ static void mroute_clean_tables(struct mr_table *mrt) spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { list_del(&c->list); + mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_destroy_unres(mrt, c); } spin_unlock_bh(&mfc_unres_lock); @@ -1185,6 +1199,9 @@ static void mrtsock_destruct(struct sock *sk) ipmr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; + inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv4.devconf_all); RCU_INIT_POINTER(mrt->mroute_sk, NULL); mroute_clean_tables(mrt); } @@ -1207,23 +1224,24 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi struct net *net = sock_net(sk); struct mr_table *mrt; + if (sk->sk_type != SOCK_RAW || + inet_sk(sk)->inet_num != IPPROTO_IGMP) + return -EOPNOTSUPP; + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (mrt == NULL) return -ENOENT; if (optname != MRT_INIT) { if (sk != rcu_access_pointer(mrt->mroute_sk) && - !capable(CAP_NET_ADMIN)) + !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EACCES; } switch (optname) { case MRT_INIT: - if (sk->sk_type != SOCK_RAW || - inet_sk(sk)->inet_num != IPPROTO_IGMP) - return -EOPNOTSUPP; if (optlen != sizeof(int)) - return -ENOPROTOOPT; + return -EINVAL; rtnl_lock(); if (rtnl_dereference(mrt->mroute_sk)) { @@ -1235,6 +1253,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi if (ret == 0) { rcu_assign_pointer(mrt->mroute_sk, sk); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; + inet_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv4.devconf_all); } rtnl_unlock(); return ret; @@ -1284,9 +1305,11 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi case MRT_ASSERT: { int v; + if (optlen != sizeof(v)) + return -EINVAL; if (get_user(v, (int __user *)optval)) return -EFAULT; - mrt->mroute_do_assert = (v) ? 1 : 0; + mrt->mroute_do_assert = v; return 0; } #ifdef CONFIG_IP_PIMSM @@ -1294,9 +1317,11 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi { int v; + if (optlen != sizeof(v)) + return -EINVAL; if (get_user(v, (int __user *)optval)) return -EFAULT; - v = (v) ? 1 : 0; + v = !!v; rtnl_lock(); ret = 0; @@ -1329,7 +1354,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi } else { if (!ipmr_new_table(net, v)) ret = -ENOMEM; - raw_sk(sk)->ipmr_table = v; + else + raw_sk(sk)->ipmr_table = v; } rtnl_unlock(); return ret; @@ -1355,6 +1381,10 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int struct net *net = sock_net(sk); struct mr_table *mrt; + if (sk->sk_type != SOCK_RAW || + inet_sk(sk)->inet_num != IPPROTO_IGMP) + return -EOPNOTSUPP; + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (mrt == NULL) return -ENOENT; @@ -2024,6 +2054,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, int ct; struct rtnexthop *nhp; struct nlattr *mp_attr; + struct rta_mfc_stats mfcs; /* If cache is unresolved, don't try to parse IIF and OIF */ if (c->mfc_parent >= MAXVIFS) @@ -2052,6 +2083,12 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, nla_nest_end(skb, mp_attr); + mfcs.mfcs_packets = c->mfc_un.res.pkt; + mfcs.mfcs_bytes = c->mfc_un.res.bytes; + mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; + if (nla_put(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs) < 0) + return -EMSGSIZE; + rtm->rtm_type = RTN_MULTICAST; return 1; } @@ -2121,12 +2158,13 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, } static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc_cache *c) + u32 portid, u32 seq, struct mfc_cache *c, int cmd) { struct nlmsghdr *nlh; struct rtmsg *rtm; + int err; - nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); if (nlh == NULL) return -EMSGSIZE; @@ -2140,13 +2178,18 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; - rtm->rtm_protocol = RTPROT_UNSPEC; + if (c->mfc_flags & MFC_STATIC) + rtm->rtm_protocol = RTPROT_STATIC; + else + rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; if (nla_put_be32(skb, RTA_SRC, c->mfc_origin) || nla_put_be32(skb, RTA_DST, c->mfc_mcastgrp)) goto nla_put_failure; - if (__ipmr_fill_mroute(mrt, skb, c, rtm) < 0) + err = __ipmr_fill_mroute(mrt, skb, c, rtm); + /* do not break the dump if cache is unresolved */ + if (err < 0 && err != -ENOENT) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -2156,6 +2199,52 @@ nla_put_failure: return -EMSGSIZE; } +static size_t mroute_msgsize(bool unresolved, int maxvif) +{ + size_t len = + NLMSG_ALIGN(sizeof(struct rtmsg)) + + nla_total_size(4) /* RTA_TABLE */ + + nla_total_size(4) /* RTA_SRC */ + + nla_total_size(4) /* RTA_DST */ + ; + + if (!unresolved) + len = len + + nla_total_size(4) /* RTA_IIF */ + + nla_total_size(0) /* RTA_MULTIPATH */ + + maxvif * NLA_ALIGN(sizeof(struct rtnexthop)) + /* RTA_MFC_STATS */ + + nla_total_size(sizeof(struct rta_mfc_stats)) + ; + + return len; +} + +static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, + int cmd) +{ + struct net *net = read_pnet(&mrt->net); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(mroute_msgsize(mfc->mfc_parent >= MAXVIFS, mrt->maxvif), + GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + if (err < 0) + goto errout; + + rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE, NULL, GFP_ATOMIC); + return; + +errout: + kfree_skb(skb); + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); +} + static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -2182,13 +2271,29 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ipmr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc) < 0) + mfc, RTM_NEWROUTE) < 0) goto done; next_entry: e++; } e = s_e = 0; } + spin_lock_bh(&mfc_unres_lock); + list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { + if (e < s_e) + goto next_entry2; + if (ipmr_fill_mroute(mrt, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + mfc, RTM_NEWROUTE) < 0) { + spin_unlock_bh(&mfc_unres_lock); + goto done; + } +next_entry2: + e++; + } + spin_unlock_bh(&mfc_unres_lock); + e = s_e = 0; s_h = 0; next_table: t++; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 97e61eadf580..3ea4127404d6 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1533,7 +1533,7 @@ static int compat_do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1677,7 +1677,7 @@ static int compat_do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1698,7 +1698,7 @@ static int do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1722,7 +1722,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 170b1fdd6b72..17c5e06da662 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1846,7 +1846,7 @@ compat_do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1961,7 +1961,7 @@ compat_do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -1983,7 +1983,7 @@ do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { @@ -2008,7 +2008,7 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index fe5daea5214d..75e33a7048f8 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -661,6 +661,7 @@ static ssize_t clusterip_proc_write(struct file *file, const char __user *input, #define PROC_WRITELEN 10 char buffer[PROC_WRITELEN+1]; unsigned long nodenum; + int rc; if (size > PROC_WRITELEN) return -EIO; @@ -669,11 +670,15 @@ static ssize_t clusterip_proc_write(struct file *file, const char __user *input, buffer[size] = 0; if (*buffer == '+') { - nodenum = simple_strtoul(buffer+1, NULL, 10); + rc = kstrtoul(buffer+1, 10, &nodenum); + if (rc) + return rc; if (clusterip_add_node(c, nodenum)) return -ENOMEM; } else if (*buffer == '-') { - nodenum = simple_strtoul(buffer+1, NULL,10); + rc = kstrtoul(buffer+1, 10, &nodenum); + if (rc) + return rc; if (clusterip_del_node(c, nodenum)) return -ENOENT; } else diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index a82047282dbb..da2c8a368f68 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -134,6 +134,10 @@ nf_nat_ipv4_fn(unsigned int hooknum, /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); + if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) { + nf_ct_kill_acct(ct, ctinfo, skb); + return NF_DROP; + } } return nf_nat_packet(ct, ctinfo, hooknum, skb); @@ -276,9 +280,7 @@ static int __net_init iptable_nat_net_init(struct net *net) return -ENOMEM; net->ipv4.nat_table = ipt_register_table(net, &nf_nat_ipv4_table, repl); kfree(repl); - if (IS_ERR(net->ipv4.nat_table)) - return PTR_ERR(net->ipv4.nat_table); - return 0; + return PTR_RET(net->ipv4.nat_table); } static void __net_exit iptable_nat_net_exit(struct net *net) diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index 8918eff1426d..0f9d09f54bd9 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -29,6 +29,7 @@ #include <net/protocol.h> const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly; +const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly; /* * Add a protocol handler to the hash tables @@ -41,6 +42,13 @@ int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) } EXPORT_SYMBOL(inet_add_protocol); +int inet_add_offload(const struct net_offload *prot, unsigned char protocol) +{ + return !cmpxchg((const struct net_offload **)&inet_offloads[protocol], + NULL, prot) ? 0 : -1; +} +EXPORT_SYMBOL(inet_add_offload); + /* * Remove a protocol from the hash tables. */ @@ -57,3 +65,16 @@ int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol) return ret; } EXPORT_SYMBOL(inet_del_protocol); + +int inet_del_offload(const struct net_offload *prot, unsigned char protocol) +{ + int ret; + + ret = (cmpxchg((const struct net_offload **)&inet_offloads[protocol], + prot, NULL) == prot) ? 0 : -1; + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(inet_del_offload); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index df251424d816..844a9ef60dbd 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2232,8 +2232,27 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, error = rt->dst.error; if (rt_is_input_route(rt)) { - if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) - goto nla_put_failure; +#ifdef CONFIG_IP_MROUTE + if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && + IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { + int err = ipmr_get_route(net, skb, + fl4->saddr, fl4->daddr, + r, nowait); + if (err <= 0) { + if (!nowait) { + if (err == 0) + return 0; + goto nla_put_failure; + } else { + if (err == -EMSGSIZE) + goto nla_put_failure; + error = err; + } + } + } else +#endif + if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) + goto nla_put_failure; } if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) @@ -2496,6 +2515,10 @@ static __net_init int sysctl_route_net_init(struct net *net) tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL); if (tbl == NULL) goto err_dup; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + tbl[0].procname = NULL; } tbl[0].extra1 = net; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index ba48e799b031..b236ef04914f 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -340,7 +340,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, } req->expires = 0UL; - req->retrans = 0; + req->num_retrans = 0; /* * We need to lookup the route here to get at the correct diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 63d4eccc674d..d84400b65049 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -883,6 +883,9 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) table[6].data = &net->ipv4.sysctl_ping_group_range; + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; } /* diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e457c7ab2e28..1ca253635f7a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -536,13 +536,14 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) { struct tcp_sock *tp = tcp_sk(sk); int answ; + bool slow; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; - lock_sock(sk); + slow = lock_sock_fast(sk); if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else if (sock_flag(sk, SOCK_URGINLINE) || @@ -557,7 +558,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) answ--; } else answ = tp->urg_seq - tp->copied_seq; - release_sock(sk); + unlock_sock_fast(sk, slow); break; case SIOCATMARK: answ = tp->urg_data && tp->urg_seq == tp->copied_seq; @@ -1490,15 +1491,19 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, copied += used; offset += used; } - /* - * If recv_actor drops the lock (e.g. TCP splice + /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it * while aggregating skbs from the socket queue. */ - skb = tcp_recv_skb(sk, seq-1, &offset); - if (!skb || (offset+1 != skb->len)) + skb = tcp_recv_skb(sk, seq - 1, &offset); + if (!skb) break; + /* TCP coalescing might have appended data to the skb. + * Try to splice more frags + */ + if (offset + 1 != skb->len) + continue; } if (tcp_hdr(skb)->fin) { sk_eat_skb(sk, skb, false); @@ -2300,7 +2305,7 @@ void tcp_sock_destruct(struct sock *sk) static inline bool tcp_can_repair_sock(const struct sock *sk) { - return capable(CAP_NET_ADMIN) && + return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED)); } @@ -3586,8 +3591,7 @@ void __init tcp_init(void) alloc_large_system_hash("TCP established", sizeof(struct inet_ehash_bucket), thash_entries, - (totalram_pages >= 128 * 1024) ? - 13 : 15, + 17, /* one slot per 128 KB of memory */ 0, NULL, &tcp_hashinfo.ehash_mask, @@ -3603,8 +3607,7 @@ void __init tcp_init(void) alloc_large_system_hash("TCP bind", sizeof(struct inet_bind_hashbucket), tcp_hashinfo.ehash_mask + 1, - (totalram_pages >= 128 * 1024) ? - 13 : 15, + 17, /* one slot per 128 KB of memory */ 0, &tcp_hashinfo.bhash_size, NULL, diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 1432cdb0644c..291f2ed7cc31 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -1,7 +1,7 @@ /* * Plugable TCP congestion control support and newReno * congestion control. - * Based on ideas from I/O scheduler suport and Web100. + * Based on ideas from I/O scheduler support and Web100. * * Copyright (C) 2005 Stephen Hemminger <shemminger@osdl.org> */ @@ -259,7 +259,8 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) if (!ca) err = -ENOENT; - else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || capable(CAP_NET_ADMIN))) + else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || + ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) err = -EPERM; else if (!try_module_get(ca->owner)) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 181fc8234a52..a13692560e63 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3552,6 +3552,24 @@ static bool tcp_process_frto(struct sock *sk, int flag) return false; } +/* RFC 5961 7 [ACK Throttling] */ +static void tcp_send_challenge_ack(struct sock *sk) +{ + /* unprotected vars, we dont care of overwrites */ + static u32 challenge_timestamp; + static unsigned int challenge_count; + u32 now = jiffies / HZ; + + if (now != challenge_timestamp) { + challenge_timestamp = now; + challenge_count = 0; + } + if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); + tcp_send_ack(sk); + } +} + /* This routine deals with incoming acks, but not outgoing ones. */ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { @@ -3571,8 +3589,14 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* If the ack is older than previous acks * then we can probably ignore it. */ - if (before(ack, prior_snd_una)) + if (before(ack, prior_snd_una)) { + /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ + if (before(ack, prior_snd_una - tp->max_window)) { + tcp_send_challenge_ack(sk); + return -1; + } goto old_ack; + } /* If the ack includes data we haven't sent yet, discard * this segment (RFC793 Section 3.9). @@ -5244,23 +5268,6 @@ out: } #endif /* CONFIG_NET_DMA */ -static void tcp_send_challenge_ack(struct sock *sk) -{ - /* unprotected vars, we dont care of overwrites */ - static u32 challenge_timestamp; - static unsigned int challenge_count; - u32 now = jiffies / HZ; - - if (now != challenge_timestamp) { - challenge_timestamp = now; - challenge_count = 0; - } - if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); - tcp_send_ack(sk); - } -} - /* Does PAWS and seqno based validation of an incoming segment, flags will * play significant role here. */ @@ -5992,7 +5999,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, */ if (req) { tcp_synack_rtt_meas(sk, req); - tp->total_retrans = req->retrans; + tp->total_retrans = req->num_retrans; reqsk_fastopen_remove(sk, req, false); } else { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0c4a64355603..1ed230716d51 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -138,14 +138,6 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) } EXPORT_SYMBOL_GPL(tcp_twsk_unique); -static int tcp_repair_connect(struct sock *sk) -{ - tcp_connect_init(sk); - tcp_finish_connect(sk, NULL); - - return 0; -} - /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { @@ -250,10 +242,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_id = tp->write_seq ^ jiffies; - if (likely(!tp->repair)) - err = tcp_connect(sk); - else - err = tcp_repair_connect(sk); + err = tcp_connect(sk); rt = NULL; if (err) @@ -877,10 +866,13 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, } static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req, - struct request_values *rvp) + struct request_values *rvp) { - TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v4_send_synack(sk, NULL, req, rvp, 0, false); + int res = tcp_v4_send_synack(sk, NULL, req, rvp, 0, false); + + if (!res) + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + return res; } /* @@ -1070,7 +1062,7 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family) } EXPORT_SYMBOL(tcp_md5_do_del); -void tcp_clear_md5_list(struct sock *sk) +static void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; @@ -1386,7 +1378,8 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk, struct sock *child; int err; - req->retrans = 0; + req->num_retrans = 0; + req->num_timeout = 0; req->sk = NULL; child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); @@ -1741,7 +1734,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_initialize_rcv_mss(newsk); tcp_synack_rtt_meas(newsk, req); - newtp->total_retrans = req->retrans; + newtp->total_retrans = req->num_retrans; #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ @@ -1919,7 +1912,6 @@ EXPORT_SYMBOL(tcp_v4_do_rcv); void tcp_v4_early_demux(struct sk_buff *skb) { - struct net *net = dev_net(skb->dev); const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; @@ -1927,16 +1919,16 @@ void tcp_v4_early_demux(struct sk_buff *skb) if (skb->pkt_type != PACKET_HOST) return; - if (!pskb_may_pull(skb, ip_hdrlen(skb) + sizeof(struct tcphdr))) + if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) return; iph = ip_hdr(skb); - th = (struct tcphdr *) ((char *)iph + ip_hdrlen(skb)); + th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) return; - sk = __inet_lookup_established(net, &tcp_hashinfo, + sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, ntohs(th->dest), skb->skb_iif); @@ -2640,7 +2632,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_delta_to_clock_t(delta), - req->retrans, + req->num_timeout, from_kuid_munged(seq_user_ns(f), uid), 0, /* non standard timer */ 0, /* open_requests have no inode */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a7302d974f32..f35f2dfb6401 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -553,7 +553,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * it can be estimated (approximately) * from another data. */ - tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->retrans); + tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout); paws_reject = tcp_paws_reject(&tmp_opt, th->rst); } } @@ -582,7 +582,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * Note that even if there is new data in the SYN packet * they will be thrown away too. */ - req->rsk_ops->rtx_syn_ack(sk, req, NULL); + inet_rtx_syn_ack(sk, req); return NULL; } @@ -696,7 +696,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* Got ACK for our SYNACK, so update baseline for SYNACK RTT sample. */ if (tmp_opt.saw_tstamp && tmp_opt.rcv_tsecr) tcp_rsk(req)->snt_synack = tmp_opt.rcv_tsecr; - else if (req->retrans) /* don't take RTT sample if retrans && ~TS */ + else if (req->num_retrans) /* don't take RTT sample if retrans && ~TS */ tcp_rsk(req)->snt_synack = 0; /* For Fast Open no more processing is needed (sk is the @@ -706,7 +706,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, return sk; /* While TCP_DEFER_ACCEPT is active, drop bare ACK. */ - if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && + if (req->num_timeout < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { inet_rsk(req)->acked = 1; NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDEFERACCEPTDROP); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 948ac275b9b5..5d451593ef16 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2992,6 +2992,11 @@ int tcp_connect(struct sock *sk) tcp_connect_init(sk); + if (unlikely(tp->repair)) { + tcp_finish_connect(sk, NULL); + return 0; + } + buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation); if (unlikely(buff == NULL)) return -ENOBUFS; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index d47c1b4421a3..b78aac30c498 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -318,7 +318,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk) req = tcp_sk(sk)->fastopen_rsk; req->rsk_ops->syn_ack_timeout(sk, req); - if (req->retrans >= max_retries) { + if (req->num_timeout >= max_retries) { tcp_write_err(sk); return; } @@ -327,10 +327,10 @@ static void tcp_fastopen_synack_timer(struct sock *sk) * regular retransmit because if the child socket has been accepted * it's not good to give up too easily. */ - req->rsk_ops->rtx_syn_ack(sk, req, NULL); - req->retrans++; + inet_rtx_syn_ack(sk, req); + req->num_timeout++; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - TCP_TIMEOUT_INIT << req->retrans, TCP_RTO_MAX); + TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); } /* |