diff options
Diffstat (limited to 'net/ipv6')
30 files changed, 1397 insertions, 735 deletions
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index b6d3f79151e..2068ac4fbda 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -7,9 +7,11 @@ obj-$(CONFIG_IPV6) += ipv6.o ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ addrlabel.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ - raw.o protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ + raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o +ipv6-offload := ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o + ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o @@ -39,5 +41,6 @@ obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o obj-$(CONFIG_IPV6_GRE) += ip6_gre.o obj-y += addrconf_core.o exthdrs_core.o +obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6_offload) obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index fab23db8ee7..fc0e13ad633 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2413,7 +2413,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) struct in6_ifreq ireq; int err; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) @@ -2432,7 +2432,7 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg) struct in6_ifreq ireq; int err; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) @@ -4037,6 +4037,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; + array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify; } static inline size_t inet6_ifla6_size(void) @@ -4705,6 +4706,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec }, { + .procname = "ndisc_notify", + .data = &ipv6_devconf.ndisc_notify, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { /* sentinel */ } }, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index a974247a9ae..b043c60429b 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -160,7 +160,8 @@ 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; sock->ops = answer->ops; @@ -282,7 +283,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return -EINVAL; snum = ntohs(addr->sin6_port); - if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) + if (snum && snum < PROT_SOCK && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; lock_sock(sk); @@ -699,249 +700,9 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ipv6_opt_accepted); -static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) -{ - const struct inet6_protocol *ops = NULL; - - for (;;) { - struct ipv6_opt_hdr *opth; - int len; - - if (proto != NEXTHDR_HOP) { - ops = rcu_dereference(inet6_protos[proto]); - - if (unlikely(!ops)) - break; - - if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) - break; - } - - if (unlikely(!pskb_may_pull(skb, 8))) - break; - - opth = (void *)skb->data; - len = ipv6_optlen(opth); - - if (unlikely(!pskb_may_pull(skb, len))) - break; - - proto = opth->nexthdr; - __skb_pull(skb, len); - } - - return proto; -} - -static int ipv6_gso_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - const struct inet6_protocol *ops; - int err = -EINVAL; - - if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) - goto out; - - ipv6h = ipv6_hdr(skb); - __skb_pull(skb, sizeof(*ipv6h)); - err = -EPROTONOSUPPORT; - - rcu_read_lock(); - ops = rcu_dereference(inet6_protos[ - ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); - - if (likely(ops && ops->gso_send_check)) { - skb_reset_transport_header(skb); - err = ops->gso_send_check(skb); - } - rcu_read_unlock(); - -out: - return err; -} - -static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, - netdev_features_t features) -{ - struct sk_buff *segs = ERR_PTR(-EINVAL); - struct ipv6hdr *ipv6h; - const struct inet6_protocol *ops; - int proto; - struct frag_hdr *fptr; - unsigned int unfrag_ip6hlen; - u8 *prevhdr; - int offset = 0; - - if (!(features & NETIF_F_V6_CSUM)) - features &= ~NETIF_F_SG; - - if (unlikely(skb_shinfo(skb)->gso_type & - ~(SKB_GSO_UDP | - SKB_GSO_DODGY | - SKB_GSO_TCP_ECN | - SKB_GSO_TCPV6 | - 0))) - goto out; - - if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) - goto out; - - ipv6h = ipv6_hdr(skb); - __skb_pull(skb, sizeof(*ipv6h)); - segs = ERR_PTR(-EPROTONOSUPPORT); - - proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); - rcu_read_lock(); - ops = rcu_dereference(inet6_protos[proto]); - if (likely(ops && ops->gso_segment)) { - skb_reset_transport_header(skb); - segs = ops->gso_segment(skb, features); - } - rcu_read_unlock(); - - if (IS_ERR(segs)) - goto out; - - for (skb = segs; skb; skb = skb->next) { - ipv6h = ipv6_hdr(skb); - ipv6h->payload_len = htons(skb->len - skb->mac_len - - sizeof(*ipv6h)); - if (proto == IPPROTO_UDP) { - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - fptr = (struct frag_hdr *)(skb_network_header(skb) + - unfrag_ip6hlen); - fptr->frag_off = htons(offset); - if (skb->next != NULL) - fptr->frag_off |= htons(IP6_MF); - offset += (ntohs(ipv6h->payload_len) - - sizeof(struct frag_hdr)); - } - } - -out: - return segs; -} - -static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) -{ - const struct inet6_protocol *ops; - struct sk_buff **pp = NULL; - struct sk_buff *p; - struct ipv6hdr *iph; - unsigned int nlen; - unsigned int hlen; - unsigned int off; - int flush = 1; - int proto; - __wsum csum; - - off = skb_gro_offset(skb); - hlen = off + sizeof(*iph); - iph = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) { - iph = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!iph)) - goto out; - } - - skb_gro_pull(skb, sizeof(*iph)); - skb_set_transport_header(skb, skb_gro_offset(skb)); - - flush += ntohs(iph->payload_len) != skb_gro_len(skb); - - rcu_read_lock(); - proto = iph->nexthdr; - ops = rcu_dereference(inet6_protos[proto]); - if (!ops || !ops->gro_receive) { - __pskb_pull(skb, skb_gro_offset(skb)); - proto = ipv6_gso_pull_exthdrs(skb, proto); - skb_gro_pull(skb, -skb_transport_offset(skb)); - skb_reset_transport_header(skb); - __skb_push(skb, skb_gro_offset(skb)); - - ops = rcu_dereference(inet6_protos[proto]); - if (!ops || !ops->gro_receive) - goto out_unlock; - - iph = ipv6_hdr(skb); - } - - NAPI_GRO_CB(skb)->proto = proto; - - flush--; - nlen = skb_network_header_len(skb); - - for (p = *head; p; p = p->next) { - const struct ipv6hdr *iph2; - __be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */ - - if (!NAPI_GRO_CB(p)->same_flow) - continue; - - iph2 = ipv6_hdr(p); - first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ; - - /* All fields must match except length and Traffic Class. */ - if (nlen != skb_network_header_len(p) || - (first_word & htonl(0xF00FFFFF)) || - memcmp(&iph->nexthdr, &iph2->nexthdr, - nlen - offsetof(struct ipv6hdr, nexthdr))) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } - /* flush if Traffic Class fields are different */ - NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); - NAPI_GRO_CB(p)->flush |= flush; - } - - NAPI_GRO_CB(skb)->flush |= flush; - - csum = skb->csum; - skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); - - pp = ops->gro_receive(head, skb); - - skb->csum = csum; - -out_unlock: - rcu_read_unlock(); - -out: - NAPI_GRO_CB(skb)->flush |= flush; - - return pp; -} - -static int ipv6_gro_complete(struct sk_buff *skb) -{ - const struct inet6_protocol *ops; - struct ipv6hdr *iph = ipv6_hdr(skb); - int err = -ENOSYS; - - iph->payload_len = htons(skb->len - skb_network_offset(skb) - - sizeof(*iph)); - - rcu_read_lock(); - ops = rcu_dereference(inet6_protos[NAPI_GRO_CB(skb)->proto]); - if (WARN_ON(!ops || !ops->gro_complete)) - goto out_unlock; - - err = ops->gro_complete(skb); - -out_unlock: - rcu_read_unlock(); - - return err; -} - static struct packet_type ipv6_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IPV6), .func = ipv6_rcv, - .gso_send_check = ipv6_gso_send_check, - .gso_segment = ipv6_gso_segment, - .gro_receive = ipv6_gro_receive, - .gro_complete = ipv6_gro_complete, }; static int __init ipv6_packet_init(void) diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 4963c769a13..2f4f584d796 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -64,7 +64,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) int ishost = !net->ipv6.devconf_all->forwarding; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (ipv6_addr_is_multicast(addr)) return -EINVAL; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 93cbad2c0aa..8edf2601065 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -701,7 +701,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } @@ -721,7 +721,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } @@ -746,7 +746,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk, err = -EINVAL; goto exit_f; } - if (!capable(CAP_NET_RAW)) { + if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index f005acc58b2..473f628f9f2 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -49,50 +49,6 @@ #include <asm/uaccess.h> -int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) -{ - const unsigned char *nh = skb_network_header(skb); - int packet_len = skb->tail - skb->network_header; - struct ipv6_opt_hdr *hdr; - int len; - - if (offset + 2 > packet_len) - goto bad; - hdr = (struct ipv6_opt_hdr *)(nh + offset); - len = ((hdr->hdrlen + 1) << 3); - - if (offset + len > packet_len) - goto bad; - - offset += 2; - len -= 2; - - while (len > 0) { - int opttype = nh[offset]; - int optlen; - - if (opttype == type) - return offset; - - switch (opttype) { - case IPV6_TLV_PAD1: - optlen = 1; - break; - default: - optlen = nh[offset + 1] + 2; - if (optlen > len) - goto bad; - break; - } - offset += optlen; - len -= optlen; - } - /* not_found */ - bad: - return -1; -} -EXPORT_SYMBOL_GPL(ipv6_find_tlv); - /* * Parsing tlv encoded headers. * @@ -528,12 +484,12 @@ unknown_rh: static const struct inet6_protocol rthdr_protocol = { .handler = ipv6_rthdr_rcv, - .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR, + .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol destopt_protocol = { .handler = ipv6_destopt_rcv, - .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR, + .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol nodata_protocol = { @@ -559,10 +515,10 @@ int __init ipv6_exthdrs_init(void) out: return ret; -out_rthdr: - inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); out_destopt: inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS); +out_rthdr: + inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); goto out; }; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index f73d59a1413..e7d756e19d1 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -111,3 +111,47 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, return start; } EXPORT_SYMBOL(ipv6_skip_exthdr); + +int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) +{ + const unsigned char *nh = skb_network_header(skb); + int packet_len = skb->tail - skb->network_header; + struct ipv6_opt_hdr *hdr; + int len; + + if (offset + 2 > packet_len) + goto bad; + hdr = (struct ipv6_opt_hdr *)(nh + offset); + len = ((hdr->hdrlen + 1) << 3); + + if (offset + len > packet_len) + goto bad; + + offset += 2; + len -= 2; + + while (len > 0) { + int opttype = nh[offset]; + int optlen; + + if (opttype == type) + return offset; + + switch (opttype) { + case IPV6_TLV_PAD1: + optlen = 1; + break; + default: + optlen = nh[offset + 1] + 2; + if (optlen > len) + goto bad; + break; + } + offset += optlen; + len -= optlen; + } + /* not_found */ + bad: + return -1; +} +EXPORT_SYMBOL_GPL(ipv6_find_tlv); diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c new file mode 100644 index 00000000000..cf77f3abfd0 --- /dev/null +++ b/net/ipv6/exthdrs_offload.c @@ -0,0 +1,41 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * IPV6 Extension Header GSO/GRO support + */ +#include <net/protocol.h> +#include "ip6_offload.h" + +static const struct net_offload rthdr_offload = { + .flags = INET6_PROTO_GSO_EXTHDR, +}; + +static const struct net_offload dstopt_offload = { + .flags = INET6_PROTO_GSO_EXTHDR, +}; + +int __init ipv6_exthdrs_offload_init(void) +{ + int ret; + + ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING); + if (!ret) + goto out; + + ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS); + if (!ret) + goto out_rt; + +out: + return ret; + +out_rt: + inet_del_offload(&rthdr_offload, IPPROTO_ROUTING); + goto out; +} diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 90bbefb5794..29124b7a04c 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -519,7 +519,8 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) } read_unlock_bh(&ip6_sk_fl_lock); - if (freq.flr_share == IPV6_FL_S_NONE && capable(CAP_NET_ADMIN)) { + if (freq.flr_share == IPV6_FL_S_NONE && + ns_capable(net->user_ns, CAP_NET_ADMIN)) { fl = fl_lookup(net, freq.flr_label); if (fl) { err = fl6_renew(fl, freq.flr_linger, freq.flr_expires); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index bbe2e7b538b..867466c96aa 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -109,21 +109,6 @@ static u32 HASH_ADDR(const struct in6_addr *addr) #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 *ip6gre_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) @@ -181,7 +166,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, ARPHRD_ETHER : ARPHRD_IP6GRE; 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 (!ipv6_addr_equal(local, &t->parms.laddr) || !ipv6_addr_equal(remote, &t->parms.raddr) || key != t->parms.i_key || @@ -206,7 +191,7 @@ static struct ip6_tnl *ip6gre_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 (!ipv6_addr_equal(remote, &t->parms.raddr) || key != t->parms.i_key || !(t->dev->flags & IFF_UP)) @@ -230,7 +215,7 @@ static struct ip6_tnl *ip6gre_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 ((!ipv6_addr_equal(local, &t->parms.laddr) && (!ipv6_addr_equal(local, &t->parms.raddr) || !ipv6_addr_is_multicast(local))) || @@ -256,7 +241,7 @@ static struct ip6_tnl *ip6gre_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; @@ -1161,7 +1146,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -1209,7 +1194,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, 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) { @@ -1633,9 +1618,9 @@ static size_t ip6gre_get_size(const struct net_device *dev) /* IFLA_GRE_OKEY */ nla_total_size(4) + /* IFLA_GRE_LOCAL */ - nla_total_size(4) + + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_REMOTE */ - nla_total_size(4) + + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_TOS */ @@ -1659,8 +1644,8 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || - nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->raddr) || - nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->laddr) || + nla_put(skb, IFLA_GRE_LOCAL, sizeof(struct in6_addr), &p->laddr) || + nla_put(skb, IFLA_GRE_REMOTE, sizeof(struct in6_addr), &p->raddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) || /*nla_put_u8(skb, IFLA_GRE_TOS, t->priority) ||*/ nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c new file mode 100644 index 00000000000..f26f0da7f09 --- /dev/null +++ b/net/ipv6/ip6_offload.c @@ -0,0 +1,282 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/socket.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/printk.h> + +#include <net/protocol.h> +#include <net/ipv6.h> + +#include "ip6_offload.h" + +static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) +{ + const struct net_offload *ops = NULL; + + for (;;) { + struct ipv6_opt_hdr *opth; + int len; + + if (proto != NEXTHDR_HOP) { + ops = rcu_dereference(inet6_offloads[proto]); + + if (unlikely(!ops)) + break; + + if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) + break; + } + + if (unlikely(!pskb_may_pull(skb, 8))) + break; + + opth = (void *)skb->data; + len = ipv6_optlen(opth); + + if (unlikely(!pskb_may_pull(skb, len))) + break; + + proto = opth->nexthdr; + __skb_pull(skb, len); + } + + return proto; +} + +static int ipv6_gso_send_check(struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h; + const struct net_offload *ops; + int err = -EINVAL; + + if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) + goto out; + + ipv6h = ipv6_hdr(skb); + __skb_pull(skb, sizeof(*ipv6h)); + err = -EPROTONOSUPPORT; + + rcu_read_lock(); + ops = rcu_dereference(inet6_offloads[ + ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); + + if (likely(ops && ops->callbacks.gso_send_check)) { + skb_reset_transport_header(skb); + err = ops->callbacks.gso_send_check(skb); + } + rcu_read_unlock(); + +out: + return err; +} + +static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + struct ipv6hdr *ipv6h; + const struct net_offload *ops; + int proto; + struct frag_hdr *fptr; + unsigned int unfrag_ip6hlen; + u8 *prevhdr; + int offset = 0; + + if (!(features & NETIF_F_V6_CSUM)) + features &= ~NETIF_F_SG; + + if (unlikely(skb_shinfo(skb)->gso_type & + ~(SKB_GSO_UDP | + SKB_GSO_DODGY | + SKB_GSO_TCP_ECN | + SKB_GSO_TCPV6 | + 0))) + goto out; + + if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) + goto out; + + ipv6h = ipv6_hdr(skb); + __skb_pull(skb, sizeof(*ipv6h)); + segs = ERR_PTR(-EPROTONOSUPPORT); + + proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); + rcu_read_lock(); + ops = rcu_dereference(inet6_offloads[proto]); + if (likely(ops && ops->callbacks.gso_segment)) { + skb_reset_transport_header(skb); + segs = ops->callbacks.gso_segment(skb, features); + } + rcu_read_unlock(); + + if (IS_ERR(segs)) + goto out; + + for (skb = segs; skb; skb = skb->next) { + ipv6h = ipv6_hdr(skb); + ipv6h->payload_len = htons(skb->len - skb->mac_len - + sizeof(*ipv6h)); + if (proto == IPPROTO_UDP) { + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + fptr = (struct frag_hdr *)(skb_network_header(skb) + + unfrag_ip6hlen); + fptr->frag_off = htons(offset); + if (skb->next != NULL) + fptr->frag_off |= htons(IP6_MF); + offset += (ntohs(ipv6h->payload_len) - + sizeof(struct frag_hdr)); + } + } + +out: + return segs; +} + +static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + const struct net_offload *ops; + struct sk_buff **pp = NULL; + struct sk_buff *p; + struct ipv6hdr *iph; + unsigned int nlen; + unsigned int hlen; + unsigned int off; + int flush = 1; + int proto; + __wsum csum; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*iph); + iph = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + iph = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!iph)) + goto out; + } + + skb_gro_pull(skb, sizeof(*iph)); + skb_set_transport_header(skb, skb_gro_offset(skb)); + + flush += ntohs(iph->payload_len) != skb_gro_len(skb); + + rcu_read_lock(); + proto = iph->nexthdr; + ops = rcu_dereference(inet6_offloads[proto]); + if (!ops || !ops->callbacks.gro_receive) { + __pskb_pull(skb, skb_gro_offset(skb)); + proto = ipv6_gso_pull_exthdrs(skb, proto); + skb_gro_pull(skb, -skb_transport_offset(skb)); + skb_reset_transport_header(skb); + __skb_push(skb, skb_gro_offset(skb)); + + ops = rcu_dereference(inet6_offloads[proto]); + if (!ops || !ops->callbacks.gro_receive) + goto out_unlock; + + iph = ipv6_hdr(skb); + } + + NAPI_GRO_CB(skb)->proto = proto; + + flush--; + nlen = skb_network_header_len(skb); + + for (p = *head; p; p = p->next) { + const struct ipv6hdr *iph2; + __be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */ + + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + iph2 = ipv6_hdr(p); + first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ; + + /* All fields must match except length and Traffic Class. */ + if (nlen != skb_network_header_len(p) || + (first_word & htonl(0xF00FFFFF)) || + memcmp(&iph->nexthdr, &iph2->nexthdr, + nlen - offsetof(struct ipv6hdr, nexthdr))) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + /* flush if Traffic Class fields are different */ + NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); + NAPI_GRO_CB(p)->flush |= flush; + } + + NAPI_GRO_CB(skb)->flush |= flush; + + csum = skb->csum; + skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); + + pp = ops->callbacks.gro_receive(head, skb); + + skb->csum = csum; + +out_unlock: + rcu_read_unlock(); + +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +static int ipv6_gro_complete(struct sk_buff *skb) +{ + const struct net_offload *ops; + struct ipv6hdr *iph = ipv6_hdr(skb); + int err = -ENOSYS; + + iph->payload_len = htons(skb->len - skb_network_offset(skb) - + sizeof(*iph)); + + rcu_read_lock(); + ops = rcu_dereference(inet6_offloads[NAPI_GRO_CB(skb)->proto]); + if (WARN_ON(!ops || !ops->callbacks.gro_complete)) + goto out_unlock; + + err = ops->callbacks.gro_complete(skb); + +out_unlock: + rcu_read_unlock(); + + return err; +} + +static struct packet_offload ipv6_packet_offload __read_mostly = { + .type = cpu_to_be16(ETH_P_IPV6), + .callbacks = { + .gso_send_check = ipv6_gso_send_check, + .gso_segment = ipv6_gso_segment, + .gro_receive = ipv6_gro_receive, + .gro_complete = ipv6_gro_complete, + }, +}; + +static int __init ipv6_offload_init(void) +{ + + if (tcpv6_offload_init() < 0) + pr_crit("%s: Cannot add TCP protocol offload\n", __func__); + if (udp_offload_init() < 0) + pr_crit("%s: Cannot add UDP protocol offload\n", __func__); + if (ipv6_exthdrs_offload_init() < 0) + pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); + + dev_add_offload(&ipv6_packet_offload); + return 0; +} + +fs_initcall(ipv6_offload_init); diff --git a/net/ipv6/ip6_offload.h b/net/ipv6/ip6_offload.h new file mode 100644 index 00000000000..2e155c651b3 --- /dev/null +++ b/net/ipv6/ip6_offload.h @@ -0,0 +1,18 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef __ip6_offload_h +#define __ip6_offload_h + +int ipv6_exthdrs_offload_init(void); +int udp_offload_init(void); +int tcpv6_offload_init(void); + +#endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3deaa4e2e8e..5552d13ae92 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -544,71 +544,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } -int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) -{ - u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = - (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); - unsigned int packet_len = skb->tail - skb->network_header; - int found_rhdr = 0; - *nexthdr = &ipv6_hdr(skb)->nexthdr; - - while (offset + 1 <= packet_len) { - - switch (**nexthdr) { - - case NEXTHDR_HOP: - break; - case NEXTHDR_ROUTING: - found_rhdr = 1; - break; - case NEXTHDR_DEST: -#if IS_ENABLED(CONFIG_IPV6_MIP6) - if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) - break; -#endif - if (found_rhdr) - return offset; - break; - default : - return offset; - } - - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; - exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + - offset); - } - - return offset; -} - -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) -{ - static atomic_t ipv6_fragmentation_id; - int old, new; - - if (rt && !(rt->dst.flags & DST_NOPEER)) { - struct inet_peer *peer; - struct net *net; - - net = dev_net(rt->dst.dev); - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); - if (peer) { - fhdr->identification = htonl(inet_getid(peer, 0)); - inet_putpeer(peer); - return; - } - } - do { - old = atomic_read(&ipv6_fragmentation_id); - new = old + 1; - if (!new) - new = 1; - } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); - fhdr->identification = htonl(new); -} - int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 09482f72306..fb828e9fe8e 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -83,6 +83,7 @@ static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); +static struct rtnl_link_ops ip6_link_ops __read_mostly; static int ip6_tnl_net_id __read_mostly; struct ip6_tnl_net { @@ -94,14 +95,6 @@ struct ip6_tnl_net { struct ip6_tnl __rcu **tnls[2]; }; -/* often modified stats are per cpu, other are shared (netdev->stats) */ -struct pcpu_tstats { - unsigned long rx_packets; - unsigned long rx_bytes; - unsigned long tx_packets; - unsigned long tx_bytes; -} __attribute__((aligned(4*sizeof(unsigned long)))); - static struct net_device_stats *ip6_get_stats(struct net_device *dev) { struct pcpu_tstats sum = { 0 }; @@ -258,6 +251,33 @@ static void ip6_dev_free(struct net_device *dev) free_netdev(dev); } +static int ip6_tnl_create2(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err; + + t = netdev_priv(dev); + err = ip6_tnl_dev_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 = &ip6_link_ops; + + dev_hold(dev); + ip6_tnl_link(ip6n, t); + return 0; + +out: + return err; +} + /** * ip6_tnl_create - create a new tunnel * @p: tunnel parameters @@ -276,7 +296,6 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) struct ip6_tnl *t; char name[IFNAMSIZ]; int err; - struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (p->name[0]) strlcpy(name, p->name, IFNAMSIZ); @@ -291,17 +310,10 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) t = netdev_priv(dev); t->parms = *p; - err = ip6_tnl_dev_init(dev); + err = ip6_tnl_create2(dev); if (err < 0) goto failed_free; - if ((err = register_netdevice(dev)) < 0) - goto failed_free; - - strcpy(t->parms.name, dev->name); - - dev_hold(dev); - ip6_tnl_link(ip6n, t); return t; failed_free: @@ -1236,6 +1248,20 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) return 0; } +static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) +{ + struct net *net = dev_net(t->dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + int err; + + ip6_tnl_unlink(ip6n, t); + synchronize_net(); + err = ip6_tnl_change(t, p); + ip6_tnl_link(ip6n, t); + netdev_state_change(t->dev); + return err; +} + static void ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u) { @@ -1324,7 +1350,7 @@ ip6_tnl_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)) break; err = -EFAULT; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) @@ -1344,11 +1370,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } else t = netdev_priv(dev); - ip6_tnl_unlink(ip6n, t); - synchronize_net(); - err = ip6_tnl_change(t, &p1); - ip6_tnl_link(ip6n, t); - netdev_state_change(dev); + err = ip6_tnl_update(t, &p1); } if (t) { err = 0; @@ -1361,7 +1383,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; case SIOCDELTUNNEL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (dev == ip6n->fb_tnl_dev) { @@ -1504,6 +1526,164 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) return 0; } +static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + u8 proto; + + if (!data) + return 0; + + proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); + if (proto != IPPROTO_IPV6 && + proto != IPPROTO_IPIP && + proto != 0) + return -EINVAL; + + return 0; +} + +static void ip6_tnl_netlink_parms(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_IPTUN_LINK]) + parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); + + if (data[IFLA_IPTUN_LOCAL]) + nla_memcpy(&parms->laddr, data[IFLA_IPTUN_LOCAL], + sizeof(struct in6_addr)); + + if (data[IFLA_IPTUN_REMOTE]) + nla_memcpy(&parms->raddr, data[IFLA_IPTUN_REMOTE], + sizeof(struct in6_addr)); + + if (data[IFLA_IPTUN_TTL]) + parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]); + + if (data[IFLA_IPTUN_ENCAP_LIMIT]) + parms->encap_limit = nla_get_u8(data[IFLA_IPTUN_ENCAP_LIMIT]); + + if (data[IFLA_IPTUN_FLOWINFO]) + parms->flowinfo = nla_get_be32(data[IFLA_IPTUN_FLOWINFO]); + + if (data[IFLA_IPTUN_FLAGS]) + parms->flags = nla_get_u32(data[IFLA_IPTUN_FLAGS]); + + if (data[IFLA_IPTUN_PROTO]) + parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); +} + +static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net *net = dev_net(dev); + struct ip6_tnl *nt; + + nt = netdev_priv(dev); + ip6_tnl_netlink_parms(data, &nt->parms); + + if (ip6_tnl_locate(net, &nt->parms, 0)) + return -EEXIST; + + return ip6_tnl_create2(dev); +} + +static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[]) +{ + struct ip6_tnl *t; + struct __ip6_tnl_parm p; + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + + if (dev == ip6n->fb_tnl_dev) + return -EINVAL; + + ip6_tnl_netlink_parms(data, &p); + + t = ip6_tnl_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + return ip6_tnl_update(t, &p); +} + +static size_t ip6_tnl_get_size(const struct net_device *dev) +{ + return + /* IFLA_IPTUN_LINK */ + nla_total_size(4) + + /* IFLA_IPTUN_LOCAL */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_REMOTE */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_TTL */ + nla_total_size(1) + + /* IFLA_IPTUN_ENCAP_LIMIT */ + nla_total_size(1) + + /* IFLA_IPTUN_FLOWINFO */ + nla_total_size(4) + + /* IFLA_IPTUN_FLAGS */ + nla_total_size(4) + + /* IFLA_IPTUN_PROTO */ + nla_total_size(1) + + 0; +} + +static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip6_tnl *tunnel = netdev_priv(dev); + struct __ip6_tnl_parm *parm = &tunnel->parms; + + if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || + nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr), + &parm->raddr) || + nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), + &parm->laddr) || + nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || + nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || + nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || + nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) || + nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = { + [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, + [IFLA_IPTUN_LOCAL] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_REMOTE] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, + [IFLA_IPTUN_ENCAP_LIMIT] = { .type = NLA_U8 }, + [IFLA_IPTUN_FLOWINFO] = { .type = NLA_U32 }, + [IFLA_IPTUN_FLAGS] = { .type = NLA_U32 }, + [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, +}; + +static struct rtnl_link_ops ip6_link_ops __read_mostly = { + .kind = "ip6tnl", + .maxtype = IFLA_IPTUN_MAX, + .policy = ip6_tnl_policy, + .priv_size = sizeof(struct ip6_tnl), + .setup = ip6_tnl_dev_setup, + .validate = ip6_tnl_validate, + .newlink = ip6_tnl_newlink, + .changelink = ip6_tnl_changelink, + .get_size = ip6_tnl_get_size, + .fill_info = ip6_tnl_fill_info, +}; + static struct xfrm6_tunnel ip4ip6_handler __read_mostly = { .handler = ip4ip6_rcv, .err_handler = ip4ip6_err, @@ -1612,9 +1792,14 @@ static int __init ip6_tunnel_init(void) pr_err("%s: can't register ip6ip6\n", __func__); goto out_ip6ip6; } + err = rtnl_link_register(&ip6_link_ops); + if (err < 0) + goto rtnl_link_failed; return 0; +rtnl_link_failed: + xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6); out_ip6ip6: xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET); out_ip4ip6: @@ -1629,6 +1814,7 @@ out_pernet: static void __exit ip6_tunnel_cleanup(void) { + rtnl_link_unregister(&ip6_link_ops); if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET)) pr_info("%s: can't deregister ip4ip6\n", __func__); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index f7c7c631972..d7330f8ea6d 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1583,7 +1583,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return -ENOENT; if (optname != MRT6_INIT) { - if (sk != mrt->mroute6_sk && !capable(CAP_NET_ADMIN)) + if (sk != mrt->mroute6_sk && !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EACCES; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a7bee6a9133..ee94d31c9d4 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -343,7 +343,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, break; case IPV6_TRANSPARENT: - if (valbool && !capable(CAP_NET_ADMIN) && !capable(CAP_NET_RAW)) { + if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) && + !ns_capable(net->user_ns, CAP_NET_RAW)) { retv = -EPERM; break; } @@ -381,7 +382,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, /* hop-by-hop / destination options are privileged option */ retv = -EPERM; - if (optname != IPV6_RTHDR && !capable(CAP_NET_RAW)) + if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) break; opt = ipv6_renew_options(sk, np->opt, optname, @@ -754,7 +755,7 @@ done: case IPV6_IPSEC_POLICY: case IPV6_XFRM_POLICY: retv = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; retv = xfrm_user_policy(sk, optname, optval, optlen); break; @@ -827,6 +828,7 @@ pref_skip_coa: if (val < 0 || val > 255) goto e_inval; np->min_hopcount = val; + retv = 0; break; case IPV6_DONTFRAG: np->dontfrag = valbool; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index a2e50dc46dc..f41853bca42 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -535,7 +535,6 @@ static void ndisc_send_unsol_na(struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; - struct in6_addr mcaddr; idev = in6_dev_get(dev); if (!idev) @@ -543,8 +542,7 @@ static void ndisc_send_unsol_na(struct net_device *dev) read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { - addrconf_addr_solict_mult(&ifa->addr, &mcaddr); - ndisc_send_na(dev, NULL, &mcaddr, &ifa->addr, + ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); @@ -1574,11 +1572,18 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = ptr; struct net *net = dev_net(dev); + struct inet6_dev *idev; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); fib6_run_gc(~0UL, net); + idev = in6_dev_get(dev); + if (!idev) + break; + if (idev->cnf.ndisc_notify) + ndisc_send_unsol_na(dev); + in6_dev_put(idev); break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 10ce76a2cb9..74cadd0719a 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1854,7 +1854,7 @@ compat_do_ip6t_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) { @@ -1969,7 +1969,7 @@ compat_do_ip6t_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) { @@ -1991,7 +1991,7 @@ do_ip6t_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) { @@ -2016,7 +2016,7 @@ do_ip6t_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/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index e418bd6350a..fa84cf8ec6b 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -186,7 +186,8 @@ nf_nat_ipv6_out(unsigned int hooknum, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3) || - (ct->tuplehash[dir].tuple.src.u.all != + (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && + ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) if (nf_xfrm_me_harder(skb, AF_INET6) < 0) ret = NF_DROP; @@ -222,6 +223,7 @@ nf_nat_ipv6_local_fn(unsigned int hooknum, } #ifdef CONFIG_XFRM else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) if (nf_xfrm_me_harder(skb, AF_INET6)) @@ -275,9 +277,7 @@ static int __net_init ip6table_nat_net_init(struct net *net) return -ENOMEM; net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl); kfree(repl); - if (IS_ERR(net->ipv6.ip6table_nat)) - return PTR_ERR(net->ipv6.ip6table_nat); - return 0; + return PTR_RET(net->ipv6.ip6table_nat); } static void __net_exit ip6table_nat_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index ccb5cbe9354..00ee17c3e89 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -21,6 +21,7 @@ #include <linux/netfilter_bridge.h> #include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> @@ -295,6 +296,55 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { }, }; +static int +ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ipv6_pinfo *inet6 = inet6_sk(sk); + const struct nf_conntrack_tuple_hash *h; + struct sockaddr_in6 sin6; + struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 }; + struct nf_conn *ct; + + tuple.src.u3.in6 = inet6->rcv_saddr; + tuple.src.u.tcp.port = inet->inet_sport; + tuple.dst.u3.in6 = inet6->daddr; + tuple.dst.u.tcp.port = inet->inet_dport; + tuple.dst.protonum = sk->sk_protocol; + + if (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_SCTP) + return -ENOPROTOOPT; + + if (*len < 0 || (unsigned int) *len < sizeof(sin6)) + return -EINVAL; + + h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple); + if (!h) { + pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n", + &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port), + &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port)); + return -ENOENT; + } + + ct = nf_ct_tuplehash_to_ctrack(h); + + sin6.sin6_family = AF_INET6; + sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port; + sin6.sin6_flowinfo = inet6->flow_label & IPV6_FLOWINFO_MASK; + memcpy(&sin6.sin6_addr, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6, + sizeof(sin6.sin6_addr)); + + nf_ct_put(ct); + + if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL) + sin6.sin6_scope_id = sk->sk_bound_dev_if; + else + sin6.sin6_scope_id = 0; + + return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0; +} + #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> @@ -359,6 +409,14 @@ MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>"); +static struct nf_sockopt_ops so_getorigdst6 = { + .pf = NFPROTO_IPV6, + .get_optmin = IP6T_SO_ORIGINAL_DST, + .get_optmax = IP6T_SO_ORIGINAL_DST + 1, + .get = ipv6_getorigdst, + .owner = THIS_MODULE, +}; + static int ipv6_net_init(struct net *net) { int ret = 0; @@ -425,6 +483,12 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) need_conntrack(); nf_defrag_ipv6_enable(); + ret = nf_register_sockopt(&so_getorigdst6); + if (ret < 0) { + pr_err("Unable to register netfilter socket option\n"); + return ret; + } + ret = register_pernet_subsys(&ipv6_net_ops); if (ret < 0) goto cleanup_pernet; @@ -440,6 +504,7 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) cleanup_ipv6: unregister_pernet_subsys(&ipv6_net_ops); cleanup_pernet: + nf_unregister_sockopt(&so_getorigdst6); return ret; } @@ -448,6 +513,7 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void) synchronize_net(); nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); unregister_pernet_subsys(&ipv6_net_ops); + nf_unregister_sockopt(&so_getorigdst6); } module_init(nf_conntrack_l3proto_ipv6_init); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 18bd9bbbd1c..22c8ea95118 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -85,7 +85,7 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = { { } }; -static int __net_init nf_ct_frag6_sysctl_register(struct net *net) +static int nf_ct_frag6_sysctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -127,7 +127,7 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) } #else -static int __net_init nf_ct_frag6_sysctl_register(struct net *net) +static int nf_ct_frag6_sysctl_register(struct net *net) { return 0; } diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c new file mode 100644 index 00000000000..c2e73e647e4 --- /dev/null +++ b/net/ipv6/output_core.c @@ -0,0 +1,76 @@ +/* + * IPv6 library code, needed by static components when full IPv6 support is + * not configured or static. These functions are needed by GSO/GRO implementation. + */ +#include <linux/export.h> +#include <net/ipv6.h> +#include <net/ip6_fib.h> + +void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +{ + static atomic_t ipv6_fragmentation_id; + int old, new; + +#if IS_ENABLED(CONFIG_IPV6) + if (rt && !(rt->dst.flags & DST_NOPEER)) { + struct inet_peer *peer; + struct net *net; + + net = dev_net(rt->dst.dev); + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + if (peer) { + fhdr->identification = htonl(inet_getid(peer, 0)); + inet_putpeer(peer); + return; + } + } +#endif + do { + old = atomic_read(&ipv6_fragmentation_id); + new = old + 1; + if (!new) + new = 1; + } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); + fhdr->identification = htonl(new); +} +EXPORT_SYMBOL(ipv6_select_ident); + +int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) +{ + u16 offset = sizeof(struct ipv6hdr); + struct ipv6_opt_hdr *exthdr = + (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); + unsigned int packet_len = skb->tail - skb->network_header; + int found_rhdr = 0; + *nexthdr = &ipv6_hdr(skb)->nexthdr; + + while (offset + 1 <= packet_len) { + + switch (**nexthdr) { + + case NEXTHDR_HOP: + break; + case NEXTHDR_ROUTING: + found_rhdr = 1; + break; + case NEXTHDR_DEST: +#if IS_ENABLED(CONFIG_IPV6_MIP6) + if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) + break; +#endif + if (found_rhdr) + return offset; + break; + default : + return offset; + } + + offset += ipv6_optlen(exthdr); + *nexthdr = &exthdr->nexthdr; + exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + + offset); + } + + return offset; +} +EXPORT_SYMBOL(ip6_find_1stfragopt); diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c index 053082dfc93..22d1bd4670d 100644 --- a/net/ipv6/protocol.c +++ b/net/ipv6/protocol.c @@ -25,7 +25,9 @@ #include <linux/spinlock.h> #include <net/protocol.h> +#if IS_ENABLED(CONFIG_IPV6) const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS] __read_mostly; +EXPORT_SYMBOL(inet6_protos); int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol) { @@ -50,3 +52,26 @@ int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol return ret; } EXPORT_SYMBOL(inet6_del_protocol); +#endif + +const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS] __read_mostly; + +int inet6_add_offload(const struct net_offload *prot, unsigned char protocol) +{ + return !cmpxchg((const struct net_offload **)&inet6_offloads[protocol], + NULL, prot) ? 0 : -1; +} +EXPORT_SYMBOL(inet6_add_offload); + +int inet6_del_offload(const struct net_offload *prot, unsigned char protocol) +{ + int ret; + + ret = (cmpxchg((const struct net_offload **)&inet6_offloads[protocol], + prot, NULL) == prot) ? 0 : -1; + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(inet6_del_offload); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index da8a4e301b1..e5253ec9e0f 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -616,6 +616,10 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) table[0].data = &net->ipv6.frags.high_thresh; table[1].data = &net->ipv6.frags.low_thresh; table[2].data = &net->ipv6.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/ipv6", table); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c1cfcb7e563..8f124f57511 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -220,7 +220,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { }; static const u32 ip6_template_metrics[RTAX_MAX] = { - [RTAX_HOPLIMIT - 1] = 255, + [RTAX_HOPLIMIT - 1] = 0, }; static const struct rt6_info ip6_null_entry_template = { @@ -321,13 +321,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) } } -static atomic_t __rt6_peer_genid = ATOMIC_INIT(0); - -static u32 rt6_peer_genid(void) -{ - return atomic_read(&__rt6_peer_genid); -} - void rt6_bind_peer(struct rt6_info *rt, int create) { struct inet_peer_base *base; @@ -341,8 +334,6 @@ void rt6_bind_peer(struct rt6_info *rt, int create) if (peer) { if (!rt6_set_peer(rt, peer)) inet_putpeer(peer); - else - rt->rt6i_peer_genid = rt6_peer_genid(); } } @@ -1099,14 +1090,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev))) return NULL; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { - if (rt->rt6i_peer_genid != rt6_peer_genid()) { - if (!rt6_has_peer(rt)) - rt6_bind_peer(rt, 0); - rt->rt6i_peer_genid = rt6_peer_genid(); - } + if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) return dst; - } + return NULL; } @@ -1301,7 +1287,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); spin_lock_bh(&icmp6_dst_lock); rt->dst.next = icmp6_dst_gc_list; @@ -1385,12 +1371,6 @@ out: return entries > rt_max_size; } -/* Clean host part of a prefix. Not necessary in radix tree, - but results in cleaner routing tables. - - Remove it only when all the things will work! - */ - int ip6_dst_hoplimit(struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); @@ -2056,7 +2036,7 @@ int ipv6_route_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; err = copy_from_user(&rtmsg, arg, sizeof(struct in6_rtmsg)); @@ -3009,6 +2989,10 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; } return table; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3ed54ffd8d5..80cb3829831 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -68,6 +68,7 @@ static int ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); static void ipip6_dev_free(struct net_device *dev); +static struct rtnl_link_ops sit_link_ops __read_mostly; static int sit_net_id __read_mostly; struct sit_net { @@ -80,22 +81,6 @@ struct sit_net { struct net_device *fb_tunnel_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_stats64 *ipip6_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) { @@ -141,20 +126,20 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); - for_each_ip_tunnel_rcu(sitn->tunnels_r_l[h0 ^ h1]) { + for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for_each_ip_tunnel_rcu(sitn->tunnels_r[h0]) { + for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for_each_ip_tunnel_rcu(sitn->tunnels_l[h1]) { + for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) @@ -231,6 +216,37 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) #endif } +static int ipip6_tunnel_create(struct net_device *dev) +{ + struct ip_tunnel *t = netdev_priv(dev); + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + int err; + + err = ipip6_tunnel_init(dev); + if (err < 0) + goto out; + ipip6_tunnel_clone_6rd(dev, sitn); + + if ((__force u16)t->parms.i_flags & SIT_ISATAP) + dev->priv_flags |= IFF_ISATAP; + + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(t->parms.name, dev->name); + dev->rtnl_link_ops = &sit_link_ops; + + dev_hold(dev); + + ipip6_tunnel_link(sitn, t); + return 0; + +out: + return err; +} + static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { @@ -271,21 +287,9 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, nt = netdev_priv(dev); nt->parms = *parms; - if (ipip6_tunnel_init(dev) < 0) + if (ipip6_tunnel_create(dev) < 0) goto failed_free; - ipip6_tunnel_clone_6rd(dev, sitn); - if (parms->i_flags & SIT_ISATAP) - dev->priv_flags |= IFF_ISATAP; - - if (register_netdevice(dev) < 0) - goto failed_free; - - strcpy(nt->parms.name, dev->name); - - dev_hold(dev); - - ipip6_tunnel_link(sitn, nt); return nt; failed_free: @@ -683,7 +687,6 @@ static netdev_tx_t ipip6_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; const struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; @@ -864,9 +867,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if ((iph->ttl = tiph->ttl) == 0) iph->ttl = iph6->hop_limit; - 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: @@ -914,6 +915,59 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) dev->iflink = tunnel->parms.link; } +static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) +{ + struct net *net = dev_net(t->dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + + ipip6_tunnel_unlink(sitn, 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); + ipip6_tunnel_link(sitn, t); + t->parms.iph.ttl = p->iph.ttl; + t->parms.iph.tos = p->iph.tos; + if (t->parms.link != p->link) { + t->parms.link = p->link; + ipip6_tunnel_bind_dev(t->dev); + } + netdev_state_change(t->dev); +} + +#ifdef CONFIG_IPV6_SIT_6RD +static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, + struct ip_tunnel_6rd *ip6rd) +{ + struct in6_addr prefix; + __be32 relay_prefix; + + if (ip6rd->relay_prefixlen > 32 || + ip6rd->prefixlen + (32 - ip6rd->relay_prefixlen) > 64) + return -EINVAL; + + ipv6_addr_prefix(&prefix, &ip6rd->prefix, ip6rd->prefixlen); + if (!ipv6_addr_equal(&prefix, &ip6rd->prefix)) + return -EINVAL; + if (ip6rd->relay_prefixlen) + relay_prefix = ip6rd->relay_prefix & + htonl(0xffffffffUL << + (32 - ip6rd->relay_prefixlen)); + else + relay_prefix = 0; + if (relay_prefix != ip6rd->relay_prefix) + return -EINVAL; + + t->ip6rd.prefix = prefix; + t->ip6rd.relay_prefix = relay_prefix; + t->ip6rd.prefixlen = ip6rd->prefixlen; + t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; + netdev_state_change(t->dev); + return 0; +} +#endif + static int ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -966,7 +1020,7 @@ ipip6_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; @@ -995,28 +1049,13 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) break; } t = netdev_priv(dev); - ipip6_tunnel_unlink(sitn, 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); - ipip6_tunnel_link(sitn, t); - netdev_state_change(dev); } + + ipip6_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; - if (t->parms.link != p.link) { - t->parms.link = p.link; - ipip6_tunnel_bind_dev(dev); - netdev_state_change(dev); - } - } if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p))) err = -EFAULT; } else @@ -1025,7 +1064,7 @@ ipip6_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 == sitn->fb_tunnel_dev) { @@ -1058,7 +1097,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCDELPRL: case SIOCCHGPRL: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EINVAL; if (dev == sitn->fb_tunnel_dev) @@ -1087,7 +1126,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCCHG6RD: case SIOCDEL6RD: err = -EPERM; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; @@ -1098,31 +1137,9 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) t = netdev_priv(dev); if (cmd != SIOCDEL6RD) { - struct in6_addr prefix; - __be32 relay_prefix; - - err = -EINVAL; - if (ip6rd.relay_prefixlen > 32 || - ip6rd.prefixlen + (32 - ip6rd.relay_prefixlen) > 64) - goto done; - - ipv6_addr_prefix(&prefix, &ip6rd.prefix, - ip6rd.prefixlen); - if (!ipv6_addr_equal(&prefix, &ip6rd.prefix)) + err = ipip6_tunnel_update_6rd(t, &ip6rd); + if (err < 0) goto done; - if (ip6rd.relay_prefixlen) - relay_prefix = ip6rd.relay_prefix & - htonl(0xffffffffUL << - (32 - ip6rd.relay_prefixlen)); - else - relay_prefix = 0; - if (relay_prefix != ip6rd.relay_prefix) - goto done; - - t->ip6rd.prefix = prefix; - t->ip6rd.relay_prefix = relay_prefix; - t->ip6rd.prefixlen = ip6rd.prefixlen; - t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen; } else ipip6_tunnel_clone_6rd(dev, sitn); @@ -1216,6 +1233,239 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) return 0; } +static void ipip6_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms) +{ + memset(parms, 0, sizeof(*parms)); + + parms->iph.version = 4; + parms->iph.protocol = IPPROTO_IPV6; + parms->iph.ihl = 5; + parms->iph.ttl = 64; + + 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); + + if (data[IFLA_IPTUN_FLAGS]) + parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); +} + +#ifdef CONFIG_IPV6_SIT_6RD +/* This function returns true when 6RD attributes are present in the nl msg */ +static bool ipip6_netlink_6rd_parms(struct nlattr *data[], + struct ip_tunnel_6rd *ip6rd) +{ + bool ret = false; + memset(ip6rd, 0, sizeof(*ip6rd)); + + if (!data) + return ret; + + if (data[IFLA_IPTUN_6RD_PREFIX]) { + ret = true; + nla_memcpy(&ip6rd->prefix, data[IFLA_IPTUN_6RD_PREFIX], + sizeof(struct in6_addr)); + } + + if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) { + ret = true; + ip6rd->relay_prefix = + nla_get_be32(data[IFLA_IPTUN_6RD_RELAY_PREFIX]); + } + + if (data[IFLA_IPTUN_6RD_PREFIXLEN]) { + ret = true; + ip6rd->prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_PREFIXLEN]); + } + + if (data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]) { + ret = true; + ip6rd->relay_prefixlen = + nla_get_u16(data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]); + } + + return ret; +} +#endif + +static int ipip6_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; +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif + int err; + + nt = netdev_priv(dev); + ipip6_netlink_parms(data, &nt->parms); + + if (ipip6_tunnel_locate(net, &nt->parms, 0)) + return -EEXIST; + + err = ipip6_tunnel_create(dev); + if (err < 0) + return err; + +#ifdef CONFIG_IPV6_SIT_6RD + if (ipip6_netlink_6rd_parms(data, &ip6rd)) + err = ipip6_tunnel_update_6rd(nt, &ip6rd); +#endif + + return err; +} + +static int ipip6_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 sit_net *sitn = net_generic(net, sit_net_id); +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif + + if (dev == sitn->fb_tunnel_dev) + return -EINVAL; + + ipip6_netlink_parms(data, &p); + + if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || + (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) + return -EINVAL; + + t = ipip6_tunnel_locate(net, &p, 0); + + if (t) { + if (t->dev != dev) + return -EEXIST; + } else + t = netdev_priv(dev); + + ipip6_tunnel_update(t, &p); + +#ifdef CONFIG_IPV6_SIT_6RD + if (ipip6_netlink_6rd_parms(data, &ip6rd)) + return ipip6_tunnel_update_6rd(t, &ip6rd); +#endif + + return 0; +} + +static size_t ipip6_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) + + /* IFLA_IPTUN_FLAGS */ + nla_total_size(2) + +#ifdef CONFIG_IPV6_SIT_6RD + /* IFLA_IPTUN_6RD_PREFIX */ + nla_total_size(sizeof(struct in6_addr)) + + /* IFLA_IPTUN_6RD_RELAY_PREFIX */ + nla_total_size(4) + + /* IFLA_IPTUN_6RD_PREFIXLEN */ + nla_total_size(2) + + /* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */ + nla_total_size(2) + +#endif + 0; +} + +static int ipip6_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))) || + nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags)) + goto nla_put_failure; + +#ifdef CONFIG_IPV6_SIT_6RD + if (nla_put(skb, IFLA_IPTUN_6RD_PREFIX, sizeof(struct in6_addr), + &tunnel->ip6rd.prefix) || + nla_put_be32(skb, IFLA_IPTUN_6RD_RELAY_PREFIX, + tunnel->ip6rd.relay_prefix) || + nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN, + tunnel->ip6rd.prefixlen) || + nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN, + tunnel->ip6rd.relay_prefixlen)) + goto nla_put_failure; +#endif + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy ipip6_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 }, + [IFLA_IPTUN_FLAGS] = { .type = NLA_U16 }, +#ifdef CONFIG_IPV6_SIT_6RD + [IFLA_IPTUN_6RD_PREFIX] = { .len = sizeof(struct in6_addr) }, + [IFLA_IPTUN_6RD_RELAY_PREFIX] = { .type = NLA_U32 }, + [IFLA_IPTUN_6RD_PREFIXLEN] = { .type = NLA_U16 }, + [IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 }, +#endif +}; + +static struct rtnl_link_ops sit_link_ops __read_mostly = { + .kind = "sit", + .maxtype = IFLA_IPTUN_MAX, + .policy = ipip6_policy, + .priv_size = sizeof(struct ip_tunnel), + .setup = ipip6_tunnel_setup, + .newlink = ipip6_newlink, + .changelink = ipip6_changelink, + .get_size = ipip6_get_size, + .fill_info = ipip6_fill_info, +}; + static struct xfrm_tunnel sit_handler __read_mostly = { .handler = ipip6_rcv, .err_handler = ipip6_err, @@ -1302,6 +1552,7 @@ static struct pernet_operations sit_net_ops = { static void __exit sit_cleanup(void) { + rtnl_link_unregister(&sit_link_ops); xfrm4_tunnel_deregister(&sit_handler, AF_INET6); unregister_pernet_device(&sit_net_ops); @@ -1319,10 +1570,21 @@ static int __init sit_init(void) return err; err = xfrm4_tunnel_register(&sit_handler, AF_INET6); if (err < 0) { - unregister_pernet_device(&sit_net_ops); pr_info("%s: can't add protocol\n", __func__); + goto xfrm_tunnel_failed; } + err = rtnl_link_register(&sit_link_ops); + if (err < 0) + goto rtnl_link_failed; + +out: return err; + +rtnl_link_failed: + xfrm4_tunnel_deregister(&sit_handler, AF_INET6); +xfrm_tunnel_failed: + unregister_pernet_device(&sit_net_ops); + goto out; } module_init(sit_init); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c73d0ebde9c..6c0f2526f3f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -77,9 +77,6 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req); static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); -static void __tcp_v6_send_check(struct sk_buff *skb, - const struct in6_addr *saddr, - const struct in6_addr *daddr); static const struct inet_connection_sock_af_ops ipv6_mapped; static const struct inet_connection_sock_af_ops ipv6_specific; @@ -119,14 +116,6 @@ static void tcp_v6_hash(struct sock *sk) } } -static __inline__ __sum16 tcp_v6_check(int len, - const struct in6_addr *saddr, - const struct in6_addr *daddr, - __wsum base) -{ - return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base); -} - static __u32 tcp_v6_init_sequence(const struct sk_buff *skb) { return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, @@ -722,94 +711,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { }; #endif -static void __tcp_v6_send_check(struct sk_buff *skb, - const struct in6_addr *saddr, const struct in6_addr *daddr) -{ - struct tcphdr *th = tcp_hdr(skb); - - if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); - } else { - th->check = tcp_v6_check(skb->len, saddr, daddr, - csum_partial(th, th->doff << 2, - skb->csum)); - } -} - -static void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) -{ - struct ipv6_pinfo *np = inet6_sk(sk); - - __tcp_v6_send_check(skb, &np->saddr, &np->daddr); -} - -static int tcp_v6_gso_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - struct tcphdr *th; - - if (!pskb_may_pull(skb, sizeof(*th))) - return -EINVAL; - - ipv6h = ipv6_hdr(skb); - th = tcp_hdr(skb); - - th->check = 0; - skb->ip_summed = CHECKSUM_PARTIAL; - __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); - return 0; -} - -static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, - struct sk_buff *skb) -{ - const struct ipv6hdr *iph = skb_gro_network_header(skb); - __wsum wsum; - __sum16 sum; - - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, - skb->csum)) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - } -flush: - NAPI_GRO_CB(skb)->flush = 1; - return NULL; - - case CHECKSUM_NONE: - wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb_gro_len(skb), - IPPROTO_TCP, 0)); - sum = csum_fold(skb_checksum(skb, - skb_gro_offset(skb), - skb_gro_len(skb), - wsum)); - if (sum) - goto flush; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - break; - } - - return tcp_gro_receive(head, skb); -} - -static int tcp6_gro_complete(struct sk_buff *skb) -{ - const struct ipv6hdr *iph = ipv6_hdr(skb); - struct tcphdr *th = tcp_hdr(skb); - - th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb), - &iph->saddr, &iph->daddr, 0); - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; - - return tcp_gro_complete(skb); -} - static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, struct tcp_md5sig_key *key, int rst, u8 tclass) { @@ -2066,10 +1967,6 @@ static const struct inet6_protocol tcpv6_protocol = { .early_demux = tcp_v6_early_demux, .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, - .gso_send_check = tcp_v6_gso_send_check, - .gso_segment = tcp_tso_segment, - .gro_receive = tcp6_gro_receive, - .gro_complete = tcp6_gro_complete, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; @@ -2124,10 +2021,10 @@ int __init tcpv6_init(void) out: return ret; -out_tcpv6_protocol: - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); +out_tcpv6_protocol: + inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); goto out; } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c new file mode 100644 index 00000000000..2ec6bf6a0aa --- /dev/null +++ b/net/ipv6/tcpv6_offload.c @@ -0,0 +1,95 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * TCPv6 GSO/GRO support + */ +#include <linux/skbuff.h> +#include <net/protocol.h> +#include <net/tcp.h> +#include <net/ip6_checksum.h> +#include "ip6_offload.h" + +static int tcp_v6_gso_send_check(struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h; + struct tcphdr *th; + + if (!pskb_may_pull(skb, sizeof(*th))) + return -EINVAL; + + ipv6h = ipv6_hdr(skb); + th = tcp_hdr(skb); + + th->check = 0; + skb->ip_summed = CHECKSUM_PARTIAL; + __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); + return 0; +} + +static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + __wsum wsum; + __sum16 sum; + + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr, + skb->csum)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } +flush: + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + + case CHECKSUM_NONE: + wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, + skb_gro_len(skb), + IPPROTO_TCP, 0)); + sum = csum_fold(skb_checksum(skb, + skb_gro_offset(skb), + skb_gro_len(skb), + wsum)); + if (sum) + goto flush; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } + + return tcp_gro_receive(head, skb); +} + +static int tcp6_gro_complete(struct sk_buff *skb) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct tcphdr *th = tcp_hdr(skb); + + th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb), + &iph->saddr, &iph->daddr, 0); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + + return tcp_gro_complete(skb); +} + +static const struct net_offload tcpv6_offload = { + .callbacks = { + .gso_send_check = tcp_v6_gso_send_check, + .gso_segment = tcp_tso_segment, + .gro_receive = tcp6_gro_receive, + .gro_complete = tcp6_gro_complete, + }, +}; + +int __init tcpv6_offload_init(void) +{ + return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP); +} diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index fc9997260a6..dfaa29b8b29 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1343,103 +1343,9 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, } #endif -static int udp6_ufo_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - struct udphdr *uh; - - if (!pskb_may_pull(skb, sizeof(*uh))) - return -EINVAL; - - ipv6h = ipv6_hdr(skb); - uh = udp_hdr(skb); - - uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, - IPPROTO_UDP, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct udphdr, check); - skb->ip_summed = CHECKSUM_PARTIAL; - return 0; -} - -static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, - netdev_features_t features) -{ - struct sk_buff *segs = ERR_PTR(-EINVAL); - unsigned int mss; - unsigned int unfrag_ip6hlen, unfrag_len; - struct frag_hdr *fptr; - u8 *mac_start, *prevhdr; - u8 nexthdr; - u8 frag_hdr_sz = sizeof(struct frag_hdr); - int offset; - __wsum csum; - - mss = skb_shinfo(skb)->gso_size; - if (unlikely(skb->len <= mss)) - goto out; - - if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { - /* Packet is from an untrusted source, reset gso_segs. */ - int type = skb_shinfo(skb)->gso_type; - - if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || - !(type & (SKB_GSO_UDP)))) - goto out; - - skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); - - segs = NULL; - goto out; - } - - /* Do software UFO. Complete and fill in the UDP checksum as HW cannot - * do checksum of UDP packets sent as multiple IP fragments. - */ - offset = skb_checksum_start_offset(skb); - csum = skb_checksum(skb, offset, skb->len - offset, 0); - offset += skb->csum_offset; - *(__sum16 *)(skb->data + offset) = csum_fold(csum); - skb->ip_summed = CHECKSUM_NONE; - - /* Check if there is enough headroom to insert fragment header. */ - if ((skb_mac_header(skb) < skb->head + frag_hdr_sz) && - pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) - goto out; - - /* Find the unfragmentable header and shift it left by frag_hdr_sz - * bytes to insert fragment header. - */ - unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - nexthdr = *prevhdr; - *prevhdr = NEXTHDR_FRAGMENT; - unfrag_len = skb_network_header(skb) - skb_mac_header(skb) + - unfrag_ip6hlen; - mac_start = skb_mac_header(skb); - memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len); - - skb->mac_header -= frag_hdr_sz; - skb->network_header -= frag_hdr_sz; - - fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); - fptr->nexthdr = nexthdr; - fptr->reserved = 0; - ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); - - /* Fragment the skb. ipv6 header and the remaining fields of the - * fragment header are updated in ipv6_gso_segment() - */ - segs = skb_segment(skb, features); - -out: - return segs; -} - static const struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, - .gso_send_check = udp6_ufo_send_check, - .gso_segment = udp6_ufo_fragment, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c new file mode 100644 index 00000000000..0c8934a317c --- /dev/null +++ b/net/ipv6/udp_offload.c @@ -0,0 +1,120 @@ +/* + * IPV6 GSO/GRO offload support + * Linux INET6 implementation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * UDPv6 GSO support + */ +#include <linux/skbuff.h> +#include <net/protocol.h> +#include <net/ipv6.h> +#include <net/udp.h> +#include <net/ip6_checksum.h> +#include "ip6_offload.h" + +static int udp6_ufo_send_check(struct sk_buff *skb) +{ + const struct ipv6hdr *ipv6h; + struct udphdr *uh; + + if (!pskb_may_pull(skb, sizeof(*uh))) + return -EINVAL; + + ipv6h = ipv6_hdr(skb); + uh = udp_hdr(skb); + + uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, + IPPROTO_UDP, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + skb->ip_summed = CHECKSUM_PARTIAL; + return 0; +} + +static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int mss; + unsigned int unfrag_ip6hlen, unfrag_len; + struct frag_hdr *fptr; + u8 *mac_start, *prevhdr; + u8 nexthdr; + u8 frag_hdr_sz = sizeof(struct frag_hdr); + int offset; + __wsum csum; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) + goto out; + + if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + int type = skb_shinfo(skb)->gso_type; + + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + !(type & (SKB_GSO_UDP)))) + goto out; + + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); + + segs = NULL; + goto out; + } + + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot + * do checksum of UDP packets sent as multiple IP fragments. + */ + offset = skb_checksum_start_offset(skb); + csum = skb_checksum(skb, offset, skb->len - offset, 0); + offset += skb->csum_offset; + *(__sum16 *)(skb->data + offset) = csum_fold(csum); + skb->ip_summed = CHECKSUM_NONE; + + /* Check if there is enough headroom to insert fragment header. */ + if ((skb_mac_header(skb) < skb->head + frag_hdr_sz) && + pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) + goto out; + + /* Find the unfragmentable header and shift it left by frag_hdr_sz + * bytes to insert fragment header. + */ + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + nexthdr = *prevhdr; + *prevhdr = NEXTHDR_FRAGMENT; + unfrag_len = skb_network_header(skb) - skb_mac_header(skb) + + unfrag_ip6hlen; + mac_start = skb_mac_header(skb); + memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len); + + skb->mac_header -= frag_hdr_sz; + skb->network_header -= frag_hdr_sz; + + fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); + fptr->nexthdr = nexthdr; + fptr->reserved = 0; + ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); + + /* Fragment the skb. ipv6 header and the remaining fields of the + * fragment header are updated in ipv6_gso_segment() + */ + segs = skb_segment(skb, features); + +out: + return segs; +} +static const struct net_offload udpv6_offload = { + .callbacks = { + .gso_send_check = udp6_ufo_send_check, + .gso_segment = udp6_ufo_fragment, + }, +}; + +int __init udp_offload_init(void) +{ + return inet6_add_offload(&udpv6_offload, IPPROTO_UDP); +} |