diff options
Diffstat (limited to 'net/ipv4')
40 files changed, 872 insertions, 841 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index a3c217b0d..7ccd693db 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -353,6 +353,7 @@ config INET_ESP select CRYPTO_CBC select CRYPTO_SHA1 select CRYPTO_DES + select CRYPTO_ECHAINIV ---help--- Support for IPsec ESP. @@ -436,6 +437,19 @@ config INET_UDP_DIAG Support for UDP socket monitoring interface used by the ss tool. If unsure, say Y. +config INET_DIAG_DESTROY + bool "INET: allow privileged process to administratively close sockets" + depends on INET_DIAG + default n + ---help--- + Provides a SOCK_DESTROY operation that allows privileged processes + (e.g., a connection manager or a network administration tool such as + ss) to close sockets opened by other processes. Closing a socket in + this way interrupts any blocking read/write/connect operations on + the socket and causes future socket calls to behave as if the socket + had been disconnected. + If unsure, say N. + menuconfig TCP_CONG_ADVANCED bool "TCP: advanced congestion control" ---help--- diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index c29809f76..62c049b64 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -56,7 +56,6 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o -obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 744e5936c..d07fc076b 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -289,10 +289,8 @@ static void __node_free_rcu(struct rcu_head *head) if (!n->tn_bits) kmem_cache_free(trie_leaf_kmem, n); - else if (n->tn_bits <= TNODE_KMALLOC_MAX) - kfree(n); else - vfree(n); + kvfree(n); } #define node_free(n) call_rcu(&tn_info(n)->rcu, __node_free_rcu) @@ -1396,9 +1394,10 @@ found: struct fib_info *fi = fa->fa_info; int nhsel, err; - if ((index >= (1ul << fa->fa_slen)) && - ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen != KEYLENGTH))) - continue; + if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) { + if (index >= (1ul << fa->fa_slen)) + continue; + } if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) continue; if (fi->fib_dead) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index bd903fe0f..976f0dcf6 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -498,7 +498,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg, sk->sk_allocation = GFP_ATOMIC; if (cfg->udp_config.family == AF_INET) { - err = udp_add_offload(&fou->udp_offloads); + err = udp_add_offload(net, &fou->udp_offloads); if (err) goto error; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 05e4cba14..b3086cf27 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -356,9 +356,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) skb_dst_set(skb, &rt->dst); skb->dev = dev; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index ab9f8a666..6029157a1 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -350,40 +350,60 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, nlmsg_flags, unlh); } -int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, - struct sk_buff *in_skb, - const struct nlmsghdr *nlh, - const struct inet_diag_req_v2 *req) +struct sock *inet_diag_find_one_icsk(struct net *net, + struct inet_hashinfo *hashinfo, + const struct inet_diag_req_v2 *req) { - struct net *net = sock_net(in_skb->sk); - struct sk_buff *rep; struct sock *sk; - int err; - err = -EINVAL; if (req->sdiag_family == AF_INET) sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); #if IS_ENABLED(CONFIG_IPV6) - else if (req->sdiag_family == AF_INET6) - sk = inet6_lookup(net, hashinfo, - (struct in6_addr *)req->id.idiag_dst, - req->id.idiag_dport, - (struct in6_addr *)req->id.idiag_src, - req->id.idiag_sport, - req->id.idiag_if); + else if (req->sdiag_family == AF_INET6) { + if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && + ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) + sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3], + req->id.idiag_dport, req->id.idiag_src[3], + req->id.idiag_sport, req->id.idiag_if); + else + sk = inet6_lookup(net, hashinfo, + (struct in6_addr *)req->id.idiag_dst, + req->id.idiag_dport, + (struct in6_addr *)req->id.idiag_src, + req->id.idiag_sport, + req->id.idiag_if); + } #endif else - goto out_nosk; + return ERR_PTR(-EINVAL); - err = -ENOENT; if (!sk) - goto out_nosk; + return ERR_PTR(-ENOENT); - err = sock_diag_check_cookie(sk, req->id.idiag_cookie); - if (err) - goto out; + if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { + sock_gen_put(sk); + return ERR_PTR(-ENOENT); + } + + return sk; +} +EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk); + +int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, + struct sk_buff *in_skb, + const struct nlmsghdr *nlh, + const struct inet_diag_req_v2 *req) +{ + struct net *net = sock_net(in_skb->sk); + struct sk_buff *rep; + struct sock *sk; + int err; + + sk = inet_diag_find_one_icsk(net, hashinfo, req); + if (IS_ERR(sk)) + return PTR_ERR(sk); rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL); if (!rep) { @@ -409,12 +429,11 @@ out: if (sk) sock_gen_put(sk); -out_nosk: return err; } EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk); -static int inet_diag_get_exact(struct sk_buff *in_skb, +static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, const struct nlmsghdr *nlh, const struct inet_diag_req_v2 *req) { @@ -424,8 +443,12 @@ static int inet_diag_get_exact(struct sk_buff *in_skb, handler = inet_diag_lock_handler(req->sdiag_protocol); if (IS_ERR(handler)) err = PTR_ERR(handler); - else + else if (cmd == SOCK_DIAG_BY_FAMILY) err = handler->dump_one(in_skb, nlh, req); + else if (cmd == SOCK_DESTROY && handler->destroy) + err = handler->destroy(in_skb, req); + else + err = -EOPNOTSUPP; inet_diag_unlock_handler(handler); return err; @@ -938,7 +961,7 @@ static int inet_diag_get_exact_compat(struct sk_buff *in_skb, req.idiag_states = rc->idiag_states; req.id = rc->id; - return inet_diag_get_exact(in_skb, nlh, &req); + return inet_diag_cmd_exact(SOCK_DIAG_BY_FAMILY, in_skb, nlh, &req); } static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) @@ -972,7 +995,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) return inet_diag_get_exact_compat(skb, nlh); } -static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) +static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct inet_diag_req_v2); struct net *net = sock_net(skb->sk); @@ -980,7 +1003,8 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) if (nlmsg_len(h) < hdrlen) return -EINVAL; - if (h->nlmsg_flags & NLM_F_DUMP) { + if (h->nlmsg_type == SOCK_DIAG_BY_FAMILY && + h->nlmsg_flags & NLM_F_DUMP) { if (nlmsg_attrlen(h, hdrlen)) { struct nlattr *attr; @@ -999,7 +1023,7 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } } - return inet_diag_get_exact(skb, h, nlmsg_data(h)); + return inet_diag_cmd_exact(h->nlmsg_type, skb, h, nlmsg_data(h)); } static @@ -1050,14 +1074,16 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk) static const struct sock_diag_handler inet_diag_handler = { .family = AF_INET, - .dump = inet_diag_handler_dump, + .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, + .destroy = inet_diag_handler_cmd, }; static const struct sock_diag_handler inet6_diag_handler = { .family = AF_INET6, - .dump = inet_diag_handler_dump, + .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, + .destroy = inet_diag_handler_cmd, }; int inet_diag_register(const struct inet_diag_handler *h) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index fe144dae7..3a88b0c73 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -285,14 +285,6 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) } EXPORT_SYMBOL(inet_frag_kill); -static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f, - struct sk_buff *skb) -{ - if (f->skb_free) - f->skb_free(skb); - kfree_skb(skb); -} - void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) { struct sk_buff *fp; @@ -309,7 +301,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) struct sk_buff *xp = fp->next; sum_truesize += fp->truesize; - frag_kfree_skb(nf, f, fp); + kfree_skb(fp); fp = xp; } sum = sum_truesize + f->qsize; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b8a0607da..187c6fcc3 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -892,7 +892,6 @@ void __init ipfrag_init(void) ip4_frags.hashfn = ip4_hashfn; ip4_frags.constructor = ip4_frag_init; ip4_frags.destructor = ip4_frag_free; - ip4_frags.skb_free = NULL; ip4_frags.qsize = sizeof(struct ipq); ip4_frags.match = ip4_frag_match; ip4_frags.frag_expire = ip_expire; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 614521437..41ba68de4 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -24,7 +24,6 @@ #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> -#include <linux/mroute.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/in6.h> @@ -562,10 +561,9 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) tunnel_id_to_key(tun_info->key.tun_id), 0); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; - err = iptunnel_xmit(skb->sk, rt, skb, fl.saddr, - key->u.ipv4.dst, IPPROTO_GRE, - key->tos, key->ttl, df, false); - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + + iptunnel_xmit(skb->sk, rt, skb, fl.saddr, key->u.ipv4.dst, IPPROTO_GRE, + key->tos, key->ttl, df, false); return; err_free_rt: @@ -1056,8 +1054,9 @@ static const struct net_device_ops gre_tap_netdev_ops = { static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); - dev->netdev_ops = &gre_tap_netdev_ops; - dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + dev->netdev_ops = &gre_tap_netdev_ops; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } @@ -1242,6 +1241,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, err = ipgre_newlink(net, dev, tb, NULL); if (err < 0) goto out; + + /* openvswitch users expect packet sizes to be unrestricted, + * so set the largest MTU we can. + */ + err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false); + if (err) + goto out; + return dev; out: free_netdev(dev); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index b1209b633..d77eb0c3b 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -316,7 +316,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; - if (sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk) { + if (sysctl_ip_early_demux && + !skb_dst(skb) && + !skb->sk && + !ip_is_fragment(iph)) { const struct net_protocol *ipprot; int protocol = iph->protocol; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 49f028563..565bf64b2 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -76,7 +76,6 @@ #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> -#include <linux/mroute.h> #include <linux/netlink.h> #include <linux/tcp.h> @@ -913,7 +912,7 @@ static int __ip_append_data(struct sock *sk, */ if (transhdrlen && length + fragheaderlen <= mtu && - rt->dst.dev->features & NETIF_F_V4_CSUM && + rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) && !(flags & MSG_MORE) && !exthdrlen) csummode = CHECKSUM_PARTIAL; @@ -1237,13 +1236,16 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, if (!skb) return -EINVAL; - cork->length += size; if ((size + skb->len > mtu) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { + if (skb->ip_summed != CHECKSUM_PARTIAL) + return -EOPNOTSUPP; + skb_shinfo(skb)->gso_size = mtu - fragheaderlen; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; } + cork->length += size; while (size > 0) { if (skb_is_gso(skb)) { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index cbb51f3fa..336e6892a 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -30,7 +30,6 @@ #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> -#include <linux/mroute.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> @@ -657,12 +656,13 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, struct rtable *rt; /* Route to the other host */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst; - int err; bool connected; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ @@ -760,7 +760,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); dst_link_failure(skb); } else tunnel->err_count = 0; @@ -795,10 +794,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, return; } - err = iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, - tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); - + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, + df, !net_eq(tunnel->net, dev_net(dev))); return; #if IS_ENABLED(CONFIG_IPV6) @@ -947,17 +944,31 @@ done: } EXPORT_SYMBOL_GPL(ip_tunnel_ioctl); -int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) +int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); + int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen; - if (new_mtu < 68 || - new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen) + if (new_mtu < 68) return -EINVAL; + + if (new_mtu > max_mtu) { + if (strict) + return -EINVAL; + + new_mtu = max_mtu; + } + dev->mtu = new_mtu; return 0; } +EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu); + +int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) +{ + return __ip_tunnel_change_mtu(dev, new_mtu, true); +} EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu); static void ip_tunnel_dev_free(struct net_device *dev) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 6cb9009c3..859d415c0 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -24,7 +24,6 @@ #include <linux/netdevice.h> #include <linux/in.h> #include <linux/if_arp.h> -#include <linux/mroute.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> @@ -48,12 +47,13 @@ #include <net/rtnetlink.h> #include <net/dst_metadata.h> -int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, - __be32 src, __be32 dst, __u8 proto, - __u8 tos, __u8 ttl, __be16 df, bool xnet) +void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, + __be32 src, __be32 dst, __u8 proto, + __u8 tos, __u8 ttl, __be16 df, bool xnet) { int pkt_len = skb->len - skb_inner_network_offset(skb); struct net *net = dev_net(rt->dst.dev); + struct net_device *dev = skb->dev; struct iphdr *iph; int err; @@ -82,7 +82,7 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, err = ip_local_out(net, sk, skb); if (unlikely(net_xmit_eval(err))) pkt_len = 0; - return pkt_len; + iptunnel_xmit_stats(dev, pkt_len); } EXPORT_SYMBOL_GPL(iptunnel_xmit); @@ -251,7 +251,7 @@ static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr, tun_info = lwt_tun_info(new_state); if (tb[LWTUNNEL_IP_ID]) - tun_info->key.tun_id = nla_get_u64(tb[LWTUNNEL_IP_ID]); + tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP_ID]); if (tb[LWTUNNEL_IP_DST]) tun_info->key.u.ipv4.dst = nla_get_be32(tb[LWTUNNEL_IP_DST]); @@ -266,7 +266,7 @@ static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr, tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); if (tb[LWTUNNEL_IP_FLAGS]) - tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP_FLAGS]); + tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP_FLAGS]); tun_info->mode = IP_TUNNEL_INFO_TX; tun_info->options_len = 0; @@ -281,12 +281,12 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb, { struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); - if (nla_put_u64(skb, LWTUNNEL_IP_ID, tun_info->key.tun_id) || + if (nla_put_be64(skb, LWTUNNEL_IP_ID, tun_info->key.tun_id) || nla_put_be32(skb, LWTUNNEL_IP_DST, tun_info->key.u.ipv4.dst) || nla_put_be32(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || - nla_put_u16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags)) + nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags)) return -ENOMEM; return 0; @@ -346,7 +346,7 @@ static int ip6_tun_build_state(struct net_device *dev, struct nlattr *attr, tun_info = lwt_tun_info(new_state); if (tb[LWTUNNEL_IP6_ID]) - tun_info->key.tun_id = nla_get_u64(tb[LWTUNNEL_IP6_ID]); + tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP6_ID]); if (tb[LWTUNNEL_IP6_DST]) tun_info->key.u.ipv6.dst = nla_get_in6_addr(tb[LWTUNNEL_IP6_DST]); @@ -361,7 +361,7 @@ static int ip6_tun_build_state(struct net_device *dev, struct nlattr *attr, tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); if (tb[LWTUNNEL_IP6_FLAGS]) - tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP6_FLAGS]); + tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]); tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6; tun_info->options_len = 0; @@ -376,12 +376,12 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb, { struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); - if (nla_put_u64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id) || + if (nla_put_be64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id) || nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) || nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.ttl) || - nla_put_u16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags)) + nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags)) return -ENOMEM; return 0; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 4d8f0b698..5cf10b777 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -30,7 +30,6 @@ #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> -#include <linux/mroute.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> @@ -200,7 +199,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) err = skb->len; - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + iptunnel_xmit_stats(dev, err); return NETDEV_TX_OK; tx_error_icmp: diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 0bc7412d9..2ed9dd2b5 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -65,15 +65,6 @@ #include <net/checksum.h> #include <asm/processor.h> -/* Define this to allow debugging output */ -#undef IPCONFIG_DEBUG - -#ifdef IPCONFIG_DEBUG -#define DBG(x) printk x -#else -#define DBG(x) do { } while(0) -#endif - #if defined(CONFIG_IP_PNP_DHCP) #define IPCONFIG_DHCP #endif @@ -152,7 +143,11 @@ static char dhcp_client_identifier[253] __initdata; /* Persistent data: */ +#ifdef IPCONFIG_DYNAMIC static int ic_proto_used; /* Protocol used, if any */ +#else +#define ic_proto_used 0 +#endif static __be32 ic_nameservers[CONF_NAMESERVERS_MAX]; /* DNS Server IP addresses */ static u8 ic_domain[64]; /* DNS (not NIS) domain name */ @@ -227,7 +222,7 @@ static int __init ic_open_devs(void) if (dev->mtu >= 364) able |= IC_BOOTP; else - pr_warn("DHCP/BOOTP: Ignoring device %s, MTU %d too small", + pr_warn("DHCP/BOOTP: Ignoring device %s, MTU %d too small\n", dev->name, dev->mtu); if (!(dev->flags & IFF_NOARP)) able |= IC_RARP; @@ -254,8 +249,8 @@ static int __init ic_open_devs(void) else d->xid = 0; ic_proto_have_if |= able; - DBG(("IP-Config: %s UP (able=%d, xid=%08x)\n", - dev->name, able, d->xid)); + pr_debug("IP-Config: %s UP (able=%d, xid=%08x)\n", + dev->name, able, d->xid); } } @@ -311,7 +306,7 @@ static void __init ic_close_devs(void) next = d->next; dev = d->dev; if (dev != ic_dev && !netdev_uses_dsa(dev)) { - DBG(("IP-Config: Downing %s\n", dev->name)); + pr_debug("IP-Config: Downing %s\n", dev->name); dev_change_flags(dev, d->flags); } kfree(d); @@ -464,7 +459,8 @@ static int __init ic_defaults(void) &ic_myaddr); return -1; } - printk("IP-Config: Guessing netmask %pI4\n", &ic_netmask); + pr_notice("IP-Config: Guessing netmask %pI4\n", + &ic_netmask); } return 0; @@ -675,9 +671,7 @@ ic_dhcp_init_options(u8 *options) u8 *e = options; int len; -#ifdef IPCONFIG_DEBUG - printk("DHCP: Sending message type %d\n", mt); -#endif + pr_debug("DHCP: Sending message type %d\n", mt); memcpy(e, ic_bootp_cookie, 4); /* RFC1048 Magic Cookie */ e += 4; @@ -847,7 +841,8 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d else if (dev->type == ARPHRD_FDDI) b->htype = ARPHRD_ETHER; else { - printk("Unknown ARP type 0x%04x for device %s\n", dev->type, dev->name); + pr_warn("Unknown ARP type 0x%04x for device %s\n", dev->type, + dev->name); b->htype = dev->type; /* can cause undefined behavior */ } @@ -904,14 +899,12 @@ static void __init ic_do_bootp_ext(u8 *ext) int i; __be16 mtu; -#ifdef IPCONFIG_DEBUG u8 *c; - printk("DHCP/BOOTP: Got extension %d:",*ext); + pr_debug("DHCP/BOOTP: Got extension %d:", *ext); for (c=ext+2; c<ext+2+ext[1]; c++) - printk(" %02x", *c); - printk("\n"); -#endif + pr_debug(" %02x", *c); + pr_debug("\n"); switch (*ext++) { case 1: /* Subnet mask */ @@ -1080,9 +1073,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str } } -#ifdef IPCONFIG_DEBUG - printk("DHCP: Got message type %d\n", mt); -#endif + pr_debug("DHCP: Got message type %d\n", mt); switch (mt) { case DHCPOFFER: @@ -1095,10 +1086,8 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str /* Let's accept that offer. */ ic_myaddr = b->your_ip; ic_servaddr = server_id; -#ifdef IPCONFIG_DEBUG - printk("DHCP: Offered address %pI4 by server %pI4\n", - &ic_myaddr, &b->iph.saddr); -#endif + pr_debug("DHCP: Offered address %pI4 by server %pI4\n", + &ic_myaddr, &b->iph.saddr); /* The DHCP indicated server address takes * precedence over the bootp header one if * they are different. @@ -1295,11 +1284,10 @@ static int __init ic_dynamic(void) return -1; } - printk("IP-Config: Got %s answer from %pI4, ", + pr_info("IP-Config: Got %s answer from %pI4, my address is %pI4\n", ((ic_got_reply & IC_RARP) ? "RARP" - : (ic_proto_enabled & IC_USE_DHCP) ? "DHCP" : "BOOTP"), - &ic_addrservaddr); - pr_cont("my address is %pI4\n", &ic_myaddr); + : (ic_proto_enabled & IC_USE_DHCP) ? "DHCP" : "BOOTP"), + &ic_addrservaddr, &ic_myaddr); return 0; } @@ -1426,7 +1414,7 @@ static int __init ip_auto_config(void) if (!ic_enable) return 0; - DBG(("IP-Config: Entered.\n")); + pr_debug("IP-Config: Entered.\n"); #ifdef IPCONFIG_DYNAMIC try_try_again: #endif @@ -1542,7 +1530,7 @@ static int __init ip_auto_config(void) pr_cont(", mtu=%d", ic_dev_mtu); for (i = 0; i < CONF_NAMESERVERS_MAX; i++) if (ic_nameservers[i] != NONE) { - pr_info(" nameserver%u=%pI4", + pr_cont(" nameserver%u=%pI4", i, &ic_nameservers[i]); break; } @@ -1585,7 +1573,7 @@ static int __init ic_proto_name(char *name) return 1; *v = 0; if (kstrtou8(client_id, 0, dhcp_client_identifier)) - DBG("DHCP: Invalid client identifier type\n"); + pr_debug("DHCP: Invalid client identifier type\n"); strncpy(dhcp_client_identifier + 1, v + 1, 251); *v = ','; } @@ -1644,7 +1632,7 @@ static int __init ip_auto_config_setup(char *addrs) if ((cp = strchr(ip, ':'))) *cp++ = '\0'; if (strlen(ip) > 0) { - DBG(("IP-Config: Parameter #%d: `%s'\n", num, ip)); + pr_debug("IP-Config: Parameter #%d: `%s'\n", num, ip); switch (num) { case 0: if ((ic_myaddr = in_aton(ip)) == ANY) @@ -1716,7 +1704,7 @@ static int __init vendor_class_identifier_setup(char *addrs) if (strlcpy(vendor_class_identifier, addrs, sizeof(vendor_class_identifier)) >= sizeof(vendor_class_identifier)) - pr_warn("DHCP: vendorclass too long, truncated to \"%s\"", + pr_warn("DHCP: vendorclass too long, truncated to \"%s\"\n", vendor_class_identifier); return 1; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index a09fb0dec..4044da61e 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -103,7 +103,6 @@ #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> -#include <linux/mroute.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c3a38353f..395e2814a 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -66,28 +66,7 @@ #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 -#endif - -struct mr_table { - struct list_head list; - possible_net_t net; - u32 id; - struct sock __rcu *mroute_sk; - struct timer_list ipmr_expire_timer; - struct list_head mfc_unres_queue; - struct list_head mfc_cache_array[MFC_LINES]; - struct vif_device vif_table[MAXVIFS]; - int maxvif; - atomic_t cache_resolve_queue_len; - 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 -}; +#include <net/nexthop.h> struct ipmr_rule { struct fib_rule common; @@ -103,11 +82,7 @@ struct ipmr_result { static DEFINE_RWLOCK(mrt_lock); -/* - * Multicast router control variables - */ - -#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL) +/* Multicast router control variables */ /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); @@ -252,8 +227,8 @@ static int __net_init ipmr_rules_init(struct net *net) INIT_LIST_HEAD(&net->ipv4.mr_tables); mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); - if (!mrt) { - err = -ENOMEM; + if (IS_ERR(mrt)) { + err = PTR_ERR(mrt); goto err1; } @@ -301,8 +276,13 @@ static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, static int __net_init ipmr_rules_init(struct net *net) { - net->ipv4.mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); - return net->ipv4.mrt ? 0 : -ENOMEM; + struct mr_table *mrt; + + mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); + if (IS_ERR(mrt)) + return PTR_ERR(mrt); + net->ipv4.mrt = mrt; + return 0; } static void __net_exit ipmr_rules_exit(struct net *net) @@ -319,13 +299,17 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) struct mr_table *mrt; unsigned int i; + /* "pimreg%u" should not exceed 16 bytes (IFNAMSIZ) */ + if (id != RT_TABLE_DEFAULT && id >= 1000000000) + return ERR_PTR(-EINVAL); + mrt = ipmr_get_table(net, id); if (mrt) return mrt; mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); if (!mrt) - return NULL; + return ERR_PTR(-ENOMEM); write_pnet(&mrt->net, net); mrt->id = id; @@ -338,9 +322,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process, (unsigned long)mrt); -#ifdef CONFIG_IP_PIMSM mrt->mroute_reg_vif_num = -1; -#endif #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables); #endif @@ -387,8 +369,24 @@ static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v) } } -static -struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) +/* Initialize ipmr pimreg/tunnel in_device */ +static bool ipmr_init_vif_indev(const struct net_device *dev) +{ + struct in_device *in_dev; + + ASSERT_RTNL(); + + in_dev = __in_dev_get_rtnl(dev); + if (!in_dev) + return false; + ipv4_devconf_setall(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); + IPV4_DEVCONF(in_dev->cnf, RP_FILTER) = 0; + + return true; +} + +static struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) { struct net_device *dev; @@ -399,7 +397,6 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) int err; struct ifreq ifr; struct ip_tunnel_parm p; - struct in_device *in_dev; memset(&p, 0, sizeof(p)); p.iph.daddr = v->vifc_rmt_addr.s_addr; @@ -424,15 +421,8 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) if (err == 0 && (dev = __dev_get_by_name(net, p.name)) != NULL) { dev->flags |= IFF_MULTICAST; - - in_dev = __in_dev_get_rtnl(dev); - if (!in_dev) + if (!ipmr_init_vif_indev(dev)) goto failure; - - ipv4_devconf_setall(in_dev); - neigh_parms_data_state_setall(in_dev->arp_parms); - IPV4_DEVCONF(in_dev->cnf, RP_FILTER) = 0; - if (dev_open(dev)) goto failure; dev_hold(dev); @@ -445,8 +435,7 @@ failure: return NULL; } -#ifdef CONFIG_IP_PIMSM - +#if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); @@ -496,7 +485,6 @@ static void reg_vif_setup(struct net_device *dev) static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) { struct net_device *dev; - struct in_device *in_dev; char name[IFNAMSIZ]; if (mrt->id == RT_TABLE_DEFAULT) @@ -516,18 +504,8 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) return NULL; } - rcu_read_lock(); - in_dev = __in_dev_get_rcu(dev); - if (!in_dev) { - rcu_read_unlock(); + if (!ipmr_init_vif_indev(dev)) goto failure; - } - - ipv4_devconf_setall(in_dev); - neigh_parms_data_state_setall(in_dev->arp_parms); - IPV4_DEVCONF(in_dev->cnf, RP_FILTER) = 0; - rcu_read_unlock(); - if (dev_open(dev)) goto failure; @@ -539,13 +517,56 @@ failure: unregister_netdevice(dev); return NULL; } + +/* called with rcu_read_lock() */ +static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, + unsigned int pimlen) +{ + struct net_device *reg_dev = NULL; + struct iphdr *encap; + + encap = (struct iphdr *)(skb_transport_header(skb) + pimlen); + /* Check that: + * a. packet is really sent to a multicast group + * b. packet is not a NULL-REGISTER + * c. packet is not truncated + */ + if (!ipv4_is_multicast(encap->daddr) || + encap->tot_len == 0 || + ntohs(encap->tot_len) + pimlen > skb->len) + return 1; + + read_lock(&mrt_lock); + if (mrt->mroute_reg_vif_num >= 0) + reg_dev = mrt->vif_table[mrt->mroute_reg_vif_num].dev; + read_unlock(&mrt_lock); + + if (!reg_dev) + return 1; + + skb->mac_header = skb->network_header; + skb_pull(skb, (u8 *)encap - skb->data); + skb_reset_network_header(skb); + skb->protocol = htons(ETH_P_IP); + skb->ip_summed = CHECKSUM_NONE; + + skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev)); + + netif_rx(skb); + + return NET_RX_SUCCESS; +} +#else +static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) +{ + return NULL; +} #endif /** * vif_delete - Delete a VIF entry * @notify: Set to 1, if the caller is a notifier_call */ - static int vif_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { @@ -567,10 +588,8 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, return -EADDRNOTAVAIL; } -#ifdef CONFIG_IP_PIMSM if (vifi == mrt->mroute_reg_vif_num) mrt->mroute_reg_vif_num = -1; -#endif if (vifi + 1 == mrt->maxvif) { int tmp; @@ -617,7 +636,6 @@ static inline void ipmr_cache_free(struct mfc_cache *c) /* Destroy an unresolved cache entry, killing queued skbs * and reporting error to netlink readers. */ - static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) { struct net *net = read_pnet(&mrt->net); @@ -645,9 +663,7 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) ipmr_cache_free(c); } - /* Timer process for the unresolved queue. */ - static void ipmr_expire_process(unsigned long arg) { struct mr_table *mrt = (struct mr_table *)arg; @@ -687,7 +703,6 @@ out: } /* Fill oifs list. It is called under write locked mrt_lock. */ - static void ipmr_update_thresholds(struct mr_table *mrt, struct mfc_cache *cache, unsigned char *ttls) { @@ -723,10 +738,10 @@ static int vif_add(struct net *net, struct mr_table *mrt, return -EADDRINUSE; switch (vifc->vifc_flags) { -#ifdef CONFIG_IP_PIMSM case VIFF_REGISTER: - /* - * Special Purpose VIF in PIM + if (!ipmr_pimsm_enabled()) + return -EINVAL; + /* Special Purpose VIF in PIM * All the packets will be sent to the daemon */ if (mrt->mroute_reg_vif_num >= 0) @@ -741,7 +756,6 @@ static int vif_add(struct net *net, struct mr_table *mrt, return err; } break; -#endif case VIFF_TUNNEL: dev = ipmr_new_tunnel(net, vifc); if (!dev) @@ -753,7 +767,6 @@ static int vif_add(struct net *net, struct mr_table *mrt, return err; } break; - case VIFF_USE_IFINDEX: case 0: if (vifc->vifc_flags == VIFF_USE_IFINDEX) { @@ -807,10 +820,8 @@ static int vif_add(struct net *net, struct mr_table *mrt, /* And finish update writing critical data */ write_lock_bh(&mrt_lock); v->dev = dev; -#ifdef CONFIG_IP_PIMSM if (v->flags & VIFF_REGISTER) mrt->mroute_reg_vif_num = vifi; -#endif if (vifi+1 > mrt->maxvif) mrt->maxvif = vifi+1; write_unlock_bh(&mrt_lock); @@ -875,9 +886,7 @@ skip: return ipmr_cache_find_any_parent(mrt, vifi); } -/* - * Allocate a multicast cache entry - */ +/* Allocate a multicast cache entry */ static struct mfc_cache *ipmr_cache_alloc(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); @@ -898,10 +907,7 @@ static struct mfc_cache *ipmr_cache_alloc_unres(void) return c; } -/* - * A cache entry has gone into a resolved state from queued - */ - +/* A cache entry has gone into a resolved state from queued */ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, struct mfc_cache *uc, struct mfc_cache *c) { @@ -909,7 +915,6 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, struct nlmsgerr *e; /* Play the pending entries through our router */ - while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); @@ -933,34 +938,29 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, } } -/* - * Bounce a cache query up to mrouted. We could use netlink for this but mrouted - * expects the following bizarre scheme. +/* Bounce a cache query up to mrouted. We could use netlink for this but mrouted + * expects the following bizarre scheme. * - * Called under mrt_lock. + * Called under mrt_lock. */ - static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert) { - struct sk_buff *skb; const int ihl = ip_hdrlen(pkt); + struct sock *mroute_sk; struct igmphdr *igmp; struct igmpmsg *msg; - struct sock *mroute_sk; + struct sk_buff *skb; int ret; -#ifdef CONFIG_IP_PIMSM if (assert == IGMPMSG_WHOLEPKT) skb = skb_realloc_headroom(pkt, sizeof(struct iphdr)); else -#endif skb = alloc_skb(128, GFP_ATOMIC); if (!skb) return -ENOBUFS; -#ifdef CONFIG_IP_PIMSM if (assert == IGMPMSG_WHOLEPKT) { /* Ugly, but we have no choice with this interface. * Duplicate old header, fix ihl, length etc. @@ -978,28 +978,23 @@ static int ipmr_cache_report(struct mr_table *mrt, ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2; ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) + sizeof(struct iphdr)); - } else -#endif - { - - /* Copy the IP header */ - - skb_set_network_header(skb, skb->len); - skb_put(skb, ihl); - skb_copy_to_linear_data(skb, pkt->data, ihl); - ip_hdr(skb)->protocol = 0; /* Flag to the kernel this is a route add */ - msg = (struct igmpmsg *)skb_network_header(skb); - msg->im_vif = vifi; - skb_dst_set(skb, dst_clone(skb_dst(pkt))); - - /* Add our header */ - - igmp = (struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); - igmp->type = - msg->im_msgtype = assert; - igmp->code = 0; - ip_hdr(skb)->tot_len = htons(skb->len); /* Fix the length */ - skb->transport_header = skb->network_header; + } else { + /* Copy the IP header */ + skb_set_network_header(skb, skb->len); + skb_put(skb, ihl); + skb_copy_to_linear_data(skb, pkt->data, ihl); + /* Flag to the kernel this is a route add */ + ip_hdr(skb)->protocol = 0; + msg = (struct igmpmsg *)skb_network_header(skb); + msg->im_vif = vifi; + skb_dst_set(skb, dst_clone(skb_dst(pkt))); + /* Add our header */ + igmp = (struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); + igmp->type = assert; + msg->im_msgtype = assert; + igmp->code = 0; + ip_hdr(skb)->tot_len = htons(skb->len); /* Fix the length */ + skb->transport_header = skb->network_header; } rcu_read_lock(); @@ -1011,7 +1006,6 @@ static int ipmr_cache_report(struct mr_table *mrt, } /* Deliver to mrouted */ - ret = sock_queue_rcv_skb(mroute_sk, skb); rcu_read_unlock(); if (ret < 0) { @@ -1022,12 +1016,9 @@ static int ipmr_cache_report(struct mr_table *mrt, return ret; } -/* - * Queue a packet for resolution. It gets locked cache entry! - */ - -static int -ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) +/* Queue a packet for resolution. It gets locked cache entry! */ +static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, + struct sk_buff *skb) { bool found = false; int err; @@ -1045,7 +1036,6 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) if (!found) { /* Create a new entry if allowable */ - if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 || (c = ipmr_cache_alloc_unres()) == NULL) { spin_unlock_bh(&mfc_unres_lock); @@ -1055,13 +1045,11 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) } /* Fill in the new cache entry */ - c->mfc_parent = -1; c->mfc_origin = iph->saddr; c->mfc_mcastgrp = iph->daddr; /* Reflect first query at mrouted. */ - err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry @@ -1083,7 +1071,6 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) } /* See if we can append the packet */ - if (c->mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; @@ -1096,9 +1083,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) return err; } -/* - * MFC cache manipulation by user space mroute daemon - */ +/* MFC cache manipulation by user space mroute daemon */ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) { @@ -1169,9 +1154,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, list_add_rcu(&c->list, &mrt->mfc_cache_array[line]); - /* - * Check to see if we resolved a queued list. If so we - * need to send on the frames and tidy up. + /* Check to see if we resolved a queued list. If so we + * need to send on the frames and tidy up. */ found = false; spin_lock_bh(&mfc_unres_lock); @@ -1196,10 +1180,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, return 0; } -/* - * Close the multicast socket, and clear the vif tables etc - */ - +/* Close the multicast socket, and clear the vif tables etc */ static void mroute_clean_tables(struct mr_table *mrt, bool all) { int i; @@ -1207,7 +1188,6 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) struct mfc_cache *c, *next; /* Shut down all active vif entries */ - for (i = 0; i < mrt->maxvif; i++) { if (!all && (mrt->vif_table[i].flags & VIFF_STATIC)) continue; @@ -1216,7 +1196,6 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) unregister_netdevice_many(&list); /* Wipe the cache */ - for (i = 0; i < MFC_LINES; i++) { list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) { if (!all && (c->mfc_flags & MFC_STATIC)) @@ -1260,44 +1239,52 @@ static void mrtsock_destruct(struct sock *sk) rtnl_unlock(); } -/* - * Socket options and virtual interface manipulation. The whole - * virtual interface system is a complete heap, but unfortunately - * that's how BSD mrouted happens to think. Maybe one day with a proper - * MOSPF/PIM router set up we can clean this up. +/* Socket options and virtual interface manipulation. The whole + * virtual interface system is a complete heap, but unfortunately + * that's how BSD mrouted happens to think. Maybe one day with a proper + * MOSPF/PIM router set up we can clean this up. */ -int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) +int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, + unsigned int optlen) { - int ret, parent = 0; - struct vifctl vif; - struct mfcctl mfc; struct net *net = sock_net(sk); + int val, ret = 0, parent = 0; struct mr_table *mrt; + struct vifctl vif; + struct mfcctl mfc; + u32 uval; + /* There's one exception to the lock - MRT_DONE which needs to unlock */ + rtnl_lock(); if (sk->sk_type != SOCK_RAW || - inet_sk(sk)->inet_num != IPPROTO_IGMP) - return -EOPNOTSUPP; + inet_sk(sk)->inet_num != IPPROTO_IGMP) { + ret = -EOPNOTSUPP; + goto out_unlock; + } mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); - if (!mrt) - return -ENOENT; - + if (!mrt) { + ret = -ENOENT; + goto out_unlock; + } if (optname != MRT_INIT) { if (sk != rcu_access_pointer(mrt->mroute_sk) && - !ns_capable(net->user_ns, CAP_NET_ADMIN)) - return -EACCES; + !ns_capable(net->user_ns, CAP_NET_ADMIN)) { + ret = -EACCES; + goto out_unlock; + } } switch (optname) { case MRT_INIT: - if (optlen != sizeof(int)) - return -EINVAL; - - rtnl_lock(); + if (optlen != sizeof(int)) { + ret = -EINVAL; + break; + } if (rtnl_dereference(mrt->mroute_sk)) { - rtnl_unlock(); - return -EADDRINUSE; + ret = -EADDRINUSE; + break; } ret = ip_ra_control(sk, 1, mrtsock_destruct); @@ -1308,129 +1295,133 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); } - rtnl_unlock(); - return ret; + break; case MRT_DONE: - if (sk != rcu_access_pointer(mrt->mroute_sk)) - return -EACCES; - return ip_ra_control(sk, 0, NULL); + if (sk != rcu_access_pointer(mrt->mroute_sk)) { + ret = -EACCES; + } else { + /* We need to unlock here because mrtsock_destruct takes + * care of rtnl itself and we can't change that due to + * the IP_ROUTER_ALERT setsockopt which runs without it. + */ + rtnl_unlock(); + ret = ip_ra_control(sk, 0, NULL); + goto out; + } + break; case MRT_ADD_VIF: case MRT_DEL_VIF: - if (optlen != sizeof(vif)) - return -EINVAL; - if (copy_from_user(&vif, optval, sizeof(vif))) - return -EFAULT; - if (vif.vifc_vifi >= MAXVIFS) - return -ENFILE; - rtnl_lock(); + if (optlen != sizeof(vif)) { + ret = -EINVAL; + break; + } + if (copy_from_user(&vif, optval, sizeof(vif))) { + ret = -EFAULT; + break; + } + if (vif.vifc_vifi >= MAXVIFS) { + ret = -ENFILE; + break; + } if (optname == MRT_ADD_VIF) { ret = vif_add(net, mrt, &vif, sk == rtnl_dereference(mrt->mroute_sk)); } else { ret = vif_delete(mrt, vif.vifc_vifi, 0, NULL); } - rtnl_unlock(); - return ret; - - /* - * Manipulate the forwarding caches. These live - * in a sort of kernel/user symbiosis. - */ + break; + /* Manipulate the forwarding caches. These live + * in a sort of kernel/user symbiosis. + */ case MRT_ADD_MFC: case MRT_DEL_MFC: parent = -1; case MRT_ADD_MFC_PROXY: case MRT_DEL_MFC_PROXY: - if (optlen != sizeof(mfc)) - return -EINVAL; - if (copy_from_user(&mfc, optval, sizeof(mfc))) - return -EFAULT; + if (optlen != sizeof(mfc)) { + ret = -EINVAL; + break; + } + if (copy_from_user(&mfc, optval, sizeof(mfc))) { + ret = -EFAULT; + break; + } if (parent == 0) parent = mfc.mfcc_parent; - rtnl_lock(); if (optname == MRT_DEL_MFC || optname == MRT_DEL_MFC_PROXY) ret = ipmr_mfc_delete(mrt, &mfc, parent); else ret = ipmr_mfc_add(net, mrt, &mfc, sk == rtnl_dereference(mrt->mroute_sk), parent); - rtnl_unlock(); - return ret; - /* - * Control PIM assert. - */ + break; + /* Control PIM assert. */ 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; - return 0; - } -#ifdef CONFIG_IP_PIMSM + if (optlen != sizeof(val)) { + ret = -EINVAL; + break; + } + if (get_user(val, (int __user *)optval)) { + ret = -EFAULT; + break; + } + mrt->mroute_do_assert = val; + break; case MRT_PIM: - { - int v; - - if (optlen != sizeof(v)) - return -EINVAL; - if (get_user(v, (int __user *)optval)) - return -EFAULT; - v = !!v; + if (!ipmr_pimsm_enabled()) { + ret = -ENOPROTOOPT; + break; + } + if (optlen != sizeof(val)) { + ret = -EINVAL; + break; + } + if (get_user(val, (int __user *)optval)) { + ret = -EFAULT; + break; + } - rtnl_lock(); - ret = 0; - if (v != mrt->mroute_do_pim) { - mrt->mroute_do_pim = v; - mrt->mroute_do_assert = v; + val = !!val; + if (val != mrt->mroute_do_pim) { + mrt->mroute_do_pim = val; + mrt->mroute_do_assert = val; } - rtnl_unlock(); - return ret; - } -#endif -#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES + break; case MRT_TABLE: - { - u32 v; - - if (optlen != sizeof(u32)) - return -EINVAL; - if (get_user(v, (u32 __user *)optval)) - return -EFAULT; - - /* "pimreg%u" should not exceed 16 bytes (IFNAMSIZ) */ - if (v != RT_TABLE_DEFAULT && v >= 1000000000) - return -EINVAL; + if (!IS_BUILTIN(CONFIG_IP_MROUTE_MULTIPLE_TABLES)) { + ret = -ENOPROTOOPT; + break; + } + if (optlen != sizeof(uval)) { + ret = -EINVAL; + break; + } + if (get_user(uval, (u32 __user *)optval)) { + ret = -EFAULT; + break; + } - rtnl_lock(); - ret = 0; if (sk == rtnl_dereference(mrt->mroute_sk)) { ret = -EBUSY; } else { - if (!ipmr_new_table(net, v)) - ret = -ENOMEM; + mrt = ipmr_new_table(net, uval); + if (IS_ERR(mrt)) + ret = PTR_ERR(mrt); else - raw_sk(sk)->ipmr_table = v; + raw_sk(sk)->ipmr_table = uval; } - rtnl_unlock(); - return ret; - } -#endif - /* - * Spurious command, or MRT_VERSION which you cannot - * set. - */ + break; + /* Spurious command, or MRT_VERSION which you cannot set. */ default: - return -ENOPROTOOPT; + ret = -ENOPROTOOPT; } +out_unlock: + rtnl_unlock(); +out: + return ret; } -/* - * Getsock opt support for the multicast routing system. - */ - +/* Getsock opt support for the multicast routing system. */ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen) { int olr; @@ -1446,39 +1437,35 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int if (!mrt) return -ENOENT; - if (optname != MRT_VERSION && -#ifdef CONFIG_IP_PIMSM - optname != MRT_PIM && -#endif - optname != MRT_ASSERT) + switch (optname) { + case MRT_VERSION: + val = 0x0305; + break; + case MRT_PIM: + if (!ipmr_pimsm_enabled()) + return -ENOPROTOOPT; + val = mrt->mroute_do_pim; + break; + case MRT_ASSERT: + val = mrt->mroute_do_assert; + break; + default: return -ENOPROTOOPT; + } if (get_user(olr, optlen)) return -EFAULT; - olr = min_t(unsigned int, olr, sizeof(int)); if (olr < 0) return -EINVAL; - if (put_user(olr, optlen)) return -EFAULT; - if (optname == MRT_VERSION) - val = 0x0305; -#ifdef CONFIG_IP_PIMSM - else if (optname == MRT_PIM) - val = mrt->mroute_do_pim; -#endif - else - val = mrt->mroute_do_assert; if (copy_to_user(optval, &val, olr)) return -EFAULT; return 0; } -/* - * The IP multicast ioctl support routines. - */ - +/* The IP multicast ioctl support routines. */ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) { struct sioc_sg_req sr; @@ -1611,7 +1598,6 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) } #endif - static int ipmr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); @@ -1633,17 +1619,14 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v return NOTIFY_DONE; } - static struct notifier_block ip_mr_notifier = { .notifier_call = ipmr_device_event, }; -/* - * Encapsulate a packet by attaching a valid IPIP header to it. - * This avoids tunnel drivers and other mess and gives us the speed so - * important for multicast video. +/* Encapsulate a packet by attaching a valid IPIP header to it. + * This avoids tunnel drivers and other mess and gives us the speed so + * important for multicast video. */ - static void ip_encap(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr) { @@ -1685,9 +1668,7 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk, return dst_output(net, sk, skb); } -/* - * Processing handlers for ipmr_forward - */ +/* Processing handlers for ipmr_forward */ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, int vifi) @@ -1702,7 +1683,6 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, if (!vif->dev) goto out_free; -#ifdef CONFIG_IP_PIMSM if (vif->flags & VIFF_REGISTER) { vif->pkt_out++; vif->bytes_out += skb->len; @@ -1711,7 +1691,6 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT); goto out_free; } -#endif if (vif->flags & VIFF_TUNNEL) { rt = ip_route_output_ports(net, &fl4, NULL, @@ -1738,7 +1717,6 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, * allow to send ICMP, so that packets will disappear * to blackhole. */ - IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); ip_rt_put(rt); goto out_free; @@ -1770,8 +1748,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, IPCB(skb)->flags |= IPSKB_FORWARDED; - /* - * RFC1584 teaches, that DVMRP/PIM router must deliver packets locally + /* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output * interfaces. It is clear, if mrouter runs a multicasting * program, it should receive packets not depending to what interface @@ -1802,7 +1779,6 @@ static int ipmr_find_vif(struct mr_table *mrt, struct net_device *dev) } /* "local" means that we should preserve one skb (for local delivery) */ - static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *cache, int local) @@ -1827,9 +1803,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, goto forward; } - /* - * Wrong interface: drop packet and (maybe) send PIM assert. - */ + /* Wrong interface: drop packet and (maybe) send PIM assert. */ if (mrt->vif_table[vif].dev != skb->dev) { if (rt_is_output_route(skb_rtable(skb))) { /* It is our own packet, looped back. @@ -1868,9 +1842,7 @@ forward: mrt->vif_table[vif].pkt_in++; mrt->vif_table[vif].bytes_in += skb->len; - /* - * Forward the frame - */ + /* Forward the frame */ if (cache->mfc_origin == htonl(INADDR_ANY) && cache->mfc_mcastgrp == htonl(INADDR_ANY)) { if (true_vifi >= 0 && @@ -1944,11 +1916,9 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) return mrt; } -/* - * Multicast packets for forwarding arrive here - * Called with rcu_read_lock(); +/* Multicast packets for forwarding arrive here + * Called with rcu_read_lock(); */ - int ip_mr_input(struct sk_buff *skb) { struct mfc_cache *cache; @@ -1999,9 +1969,7 @@ int ip_mr_input(struct sk_buff *skb) vif); } - /* - * No usable cache entry - */ + /* No usable cache entry */ if (!cache) { int vif; @@ -2042,53 +2010,8 @@ dont_forward: return 0; } -#ifdef CONFIG_IP_PIMSM -/* called with rcu_read_lock() */ -static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, - unsigned int pimlen) -{ - struct net_device *reg_dev = NULL; - struct iphdr *encap; - - encap = (struct iphdr *)(skb_transport_header(skb) + pimlen); - /* - * Check that: - * a. packet is really sent to a multicast group - * b. packet is not a NULL-REGISTER - * c. packet is not truncated - */ - if (!ipv4_is_multicast(encap->daddr) || - encap->tot_len == 0 || - ntohs(encap->tot_len) + pimlen > skb->len) - return 1; - - read_lock(&mrt_lock); - if (mrt->mroute_reg_vif_num >= 0) - reg_dev = mrt->vif_table[mrt->mroute_reg_vif_num].dev; - read_unlock(&mrt_lock); - - if (!reg_dev) - return 1; - - skb->mac_header = skb->network_header; - skb_pull(skb, (u8 *)encap - skb->data); - skb_reset_network_header(skb); - skb->protocol = htons(ETH_P_IP); - skb->ip_summed = CHECKSUM_NONE; - - skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev)); - - netif_rx(skb); - - return NET_RX_SUCCESS; -} -#endif - #ifdef CONFIG_IP_PIMSM_V1 -/* - * Handle IGMP messages of PIMv1 - */ - +/* Handle IGMP messages of PIMv1 */ int pim_rcv_v1(struct sk_buff *skb) { struct igmphdr *pim; @@ -2249,8 +2172,6 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, } read_lock(&mrt_lock); - if (!nowait && (rtm->rtm_flags & RTM_F_NOTIFY)) - cache->mfc_flags |= MFC_NOTIFY; err = __ipmr_fill_mroute(mrt, skb, cache, rtm); read_unlock(&mrt_lock); rcu_read_unlock(); @@ -2412,10 +2333,133 @@ done: return skb->len; } +static const struct nla_policy rtm_ipmr_policy[RTA_MAX + 1] = { + [RTA_SRC] = { .type = NLA_U32 }, + [RTA_DST] = { .type = NLA_U32 }, + [RTA_IIF] = { .type = NLA_U32 }, + [RTA_TABLE] = { .type = NLA_U32 }, + [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, +}; + +static bool ipmr_rtm_validate_proto(unsigned char rtm_protocol) +{ + switch (rtm_protocol) { + case RTPROT_STATIC: + case RTPROT_MROUTED: + return true; + } + return false; +} + +static int ipmr_nla_get_ttls(const struct nlattr *nla, struct mfcctl *mfcc) +{ + struct rtnexthop *rtnh = nla_data(nla); + int remaining = nla_len(nla), vifi = 0; + + while (rtnh_ok(rtnh, remaining)) { + mfcc->mfcc_ttls[vifi] = rtnh->rtnh_hops; + if (++vifi == MAXVIFS) + break; + rtnh = rtnh_next(rtnh, &remaining); + } + + return remaining > 0 ? -EINVAL : vifi; +} + +/* returns < 0 on error, 0 for ADD_MFC and 1 for ADD_MFC_PROXY */ +static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh, + struct mfcctl *mfcc, int *mrtsock, + struct mr_table **mrtret) +{ + struct net_device *dev = NULL; + u32 tblid = RT_TABLE_DEFAULT; + struct mr_table *mrt; + struct nlattr *attr; + struct rtmsg *rtm; + int ret, rem; + + ret = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipmr_policy); + if (ret < 0) + goto out; + rtm = nlmsg_data(nlh); + + ret = -EINVAL; + if (rtm->rtm_family != RTNL_FAMILY_IPMR || rtm->rtm_dst_len != 32 || + rtm->rtm_type != RTN_MULTICAST || + rtm->rtm_scope != RT_SCOPE_UNIVERSE || + !ipmr_rtm_validate_proto(rtm->rtm_protocol)) + goto out; + + memset(mfcc, 0, sizeof(*mfcc)); + mfcc->mfcc_parent = -1; + ret = 0; + nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), rem) { + switch (nla_type(attr)) { + case RTA_SRC: + mfcc->mfcc_origin.s_addr = nla_get_be32(attr); + break; + case RTA_DST: + mfcc->mfcc_mcastgrp.s_addr = nla_get_be32(attr); + break; + case RTA_IIF: + dev = __dev_get_by_index(net, nla_get_u32(attr)); + if (!dev) { + ret = -ENODEV; + goto out; + } + break; + case RTA_MULTIPATH: + if (ipmr_nla_get_ttls(attr, mfcc) < 0) { + ret = -EINVAL; + goto out; + } + break; + case RTA_PREFSRC: + ret = 1; + break; + case RTA_TABLE: + tblid = nla_get_u32(attr); + break; + } + } + mrt = ipmr_get_table(net, tblid); + if (!mrt) { + ret = -ENOENT; + goto out; + } + *mrtret = mrt; + *mrtsock = rtm->rtm_protocol == RTPROT_MROUTED ? 1 : 0; + if (dev) + mfcc->mfcc_parent = ipmr_find_vif(mrt, dev); + +out: + return ret; +} + +/* takes care of both newroute and delroute */ +static int ipmr_rtm_route(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + int ret, mrtsock, parent; + struct mr_table *tbl; + struct mfcctl mfcc; + + mrtsock = 0; + tbl = NULL; + ret = rtm_to_ipmr_mfcc(net, nlh, &mfcc, &mrtsock, &tbl); + if (ret < 0) + return ret; + + parent = ret ? mfcc.mfcc_parent : -1; + if (nlh->nlmsg_type == RTM_NEWROUTE) + return ipmr_mfc_add(net, tbl, &mfcc, mrtsock, parent); + else + return ipmr_mfc_delete(tbl, &mfcc, parent); +} + #ifdef CONFIG_PROC_FS -/* - * The /proc interfaces to multicast routing : - * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif +/* The /proc interfaces to multicast routing : + * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif */ struct ipmr_vif_iter { struct seq_net_private p; @@ -2699,10 +2743,7 @@ static const struct net_protocol pim_protocol = { }; #endif - -/* - * Setup for IP multicast routing - */ +/* Setup for IP multicast routing */ static int __net_init ipmr_net_init(struct net *net) { int err; @@ -2752,8 +2793,6 @@ int __init ip_mr_init(void) sizeof(struct mfc_cache), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); - if (!mrt_cachep) - return -ENOMEM; err = register_pernet_subsys(&ipmr_net_ops); if (err) @@ -2771,6 +2810,10 @@ int __init ip_mr_init(void) #endif rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, NULL, ipmr_rtm_dumproute, NULL); + rtnl_register(RTNL_FAMILY_IPMR, RTM_NEWROUTE, + ipmr_rtm_route, NULL, NULL); + rtnl_register(RTNL_FAMILY_IPMR, RTM_DELROUTE, + ipmr_rtm_route, NULL, NULL); return 0; #ifdef CONFIG_IP_PIMSM_V2 diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 11dccba47..b488cac9c 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -38,13 +38,13 @@ MODULE_DESCRIPTION("arptables core"); /*#define DEBUG_ARP_TABLES_USER*/ #ifdef DEBUG_ARP_TABLES -#define dprintf(format, args...) printk(format , ## args) +#define dprintf(format, args...) pr_debug(format, ## args) #else #define dprintf(format, args...) #endif #ifdef DEBUG_ARP_TABLES_USER -#define duprintf(format, args...) printk(format , ## args) +#define duprintf(format, args...) pr_debug(format, ## args) #else #define duprintf(format, args...) #endif @@ -1905,7 +1905,7 @@ static int __init arp_tables_init(void) if (ret < 0) goto err4; - printk(KERN_INFO "arp_tables: (C) 2002 David S. Miller\n"); + pr_info("arp_tables: (C) 2002 David S. Miller\n"); return 0; err4: diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 461ca926f..e3c46e8e2 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -451,7 +451,7 @@ static int __init nf_conntrack_l3proto_ipv4_init(void) ret = nf_register_sockopt(&so_getorigdst); if (ret < 0) { - printk(KERN_ERR "Unable to register netfilter socket option\n"); + pr_err("Unable to register netfilter socket option\n"); return ret; } diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index 5075b7ecd..61c7cc22e 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -132,7 +132,8 @@ static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_PARTIAL) { if (!(rt->rt_flags & RTCF_LOCAL) && - (!skb->dev || skb->dev->features & NETIF_F_V4_CSUM)) { + (!skb->dev || skb->dev->features & + (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM))) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index ddb894ac1..c9b52c361 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1048,7 +1048,7 @@ static int snmp_parse_mangle(unsigned char *msg, if (!asn1_uint_decode (&ctx, end, &vers)) return 0; if (debug > 1) - printk(KERN_DEBUG "bsalg: snmp version: %u\n", vers + 1); + pr_debug("bsalg: snmp version: %u\n", vers + 1); if (vers > 1) return 1; @@ -1064,10 +1064,10 @@ static int snmp_parse_mangle(unsigned char *msg, if (debug > 1) { unsigned int i; - printk(KERN_DEBUG "bsalg: community: "); + pr_debug("bsalg: community: "); for (i = 0; i < comm.len; i++) - printk("%c", comm.data[i]); - printk("\n"); + pr_cont("%c", comm.data[i]); + pr_cont("\n"); } kfree(comm.data); @@ -1091,9 +1091,9 @@ static int snmp_parse_mangle(unsigned char *msg, }; if (pdutype > SNMP_PDU_TRAP2) - printk(KERN_DEBUG "bsalg: bad pdu type %u\n", pdutype); + pr_debug("bsalg: bad pdu type %u\n", pdutype); else - printk(KERN_DEBUG "bsalg: pdu: %s\n", pdus[pdutype]); + pr_debug("bsalg: pdu: %s\n", pdus[pdutype]); } if (pdutype != SNMP_PDU_RESPONSE && pdutype != SNMP_PDU_TRAP1 && pdutype != SNMP_PDU_TRAP2) @@ -1119,7 +1119,7 @@ static int snmp_parse_mangle(unsigned char *msg, return 0; if (debug > 1) - printk(KERN_DEBUG "bsalg: request: id=0x%lx error_status=%u " + pr_debug("bsalg: request: id=0x%lx error_status=%u " "error_index=%u\n", req.id, req.error_status, req.error_index); } @@ -1145,13 +1145,13 @@ static int snmp_parse_mangle(unsigned char *msg, } if (debug > 1) { - printk(KERN_DEBUG "bsalg: object: "); + pr_debug("bsalg: object: "); for (i = 0; i < obj->id_len; i++) { if (i > 0) - printk("."); - printk("%lu", obj->id[i]); + pr_cont("."); + pr_cont("%lu", obj->id[i]); } - printk(": type=%u\n", obj->type); + pr_cont(": type=%u\n", obj->type); } diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index c747b2d9e..b6ea57ec5 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -14,7 +14,6 @@ #include <net/netfilter/ipv4/nf_reject.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> -#include <net/netfilter/ipv4/nf_reject.h> const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook) diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c index 9d09d4f59..cd84d4295 100644 --- a/net/ipv4/netfilter/nf_tables_arp.c +++ b/net/ipv4/netfilter/nf_tables_arp.c @@ -57,7 +57,7 @@ err: static void nf_tables_arp_exit_net(struct net *net) { - nft_unregister_afinfo(net->nft.arp); + nft_unregister_afinfo(net, net->nft.arp); kfree(net->nft.arp); } diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c index ca9dc3c46..e44ba3b12 100644 --- a/net/ipv4/netfilter/nf_tables_ipv4.c +++ b/net/ipv4/netfilter/nf_tables_ipv4.c @@ -78,7 +78,7 @@ err: static void nf_tables_ipv4_exit_net(struct net *net) { - nft_unregister_afinfo(net->nft.ipv4); + nft_unregister_afinfo(net, net->nft.ipv4); kfree(net->nft.ipv4); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index aa67e0e64..d3a27165f 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -1065,6 +1065,7 @@ static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos) } void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family) + __acquires(ping_table.lock) { struct ping_iter_state *state = seq->private; state->bucket = 0; @@ -1096,6 +1097,7 @@ void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) EXPORT_SYMBOL_GPL(ping_seq_next); void ping_seq_stop(struct seq_file *seq, void *v) + __releases(ping_table.lock) { read_unlock_bh(&ping_table.lock); } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 4cbe9f0a4..643a86c49 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -351,7 +351,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) treq->snt_synack.v64 = 0; treq->tfo_listener = false; - ireq->ir_iif = sk->sk_bound_dev_if; + ireq->ir_iif = inet_request_bound_dev_if(sk, skb); /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) @@ -371,7 +371,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark, + flowi4_init_output(&fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, inet_sk_flowi_flags(sk), opt->srr ? opt->faddr : ireq->ir_rmt_addr, diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a0bd7a551..4d367b413 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -24,7 +24,6 @@ #include <net/cipso_ipv4.h> #include <net/inet_frag.h> #include <net/ping.h> -#include <net/tcp_memcontrol.h> static int zero; static int one = 1; @@ -337,27 +336,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .procname = "tcp_keepalive_time", - .data = &sysctl_tcp_keepalive_time, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "tcp_keepalive_probes", - .data = &sysctl_tcp_keepalive_probes, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_keepalive_intvl", - .data = &sysctl_tcp_keepalive_intvl, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { .procname = "tcp_retries1", .data = &sysctl_tcp_retries1, .maxlen = sizeof(int), @@ -915,6 +893,17 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_NET_L3_MASTER_DEV + { + .procname = "tcp_l3mdev_accept", + .data = &init_net.ipv4.sysctl_tcp_l3mdev_accept, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif { .procname = "tcp_mtu_probing", .data = &init_net.ipv4.sysctl_tcp_mtu_probing, @@ -950,6 +939,27 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_keepalive_time", + .data = &init_net.ipv4.sysctl_tcp_keepalive_time, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "tcp_keepalive_probes", + .data = &init_net.ipv4.sysctl_tcp_keepalive_probes, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_keepalive_intvl", + .data = &init_net.ipv4.sysctl_tcp_keepalive_intvl, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 694e969a3..0da50fe0a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -424,7 +424,8 @@ void tcp_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); - sock_update_memcg(sk); + if (mem_cgroup_sockets_enabled) + sock_update_memcg(sk); sk_sockets_allocated_inc(sk); local_bh_enable(); } @@ -1020,7 +1021,7 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, ssize_t res; if (!(sk->sk_route_caps & NETIF_F_SG) || - !(sk->sk_route_caps & NETIF_F_ALL_CSUM)) + !sk_check_csum_caps(sk)) return sock_no_sendpage(sk->sk_socket, page, offset, size, flags); @@ -1177,7 +1178,7 @@ new_segment: /* * Check whether we can use HW checksum. */ - if (sk->sk_route_caps & NETIF_F_ALL_CSUM) + if (sk_check_csum_caps(sk)) skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, skb); @@ -3059,7 +3060,7 @@ static void __tcp_alloc_md5sig_pool(void) struct crypto_hash *hash; hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR_OR_NULL(hash)) + if (IS_ERR(hash)) return; per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash; } @@ -3194,6 +3195,52 @@ void tcp_done(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_done); +int tcp_abort(struct sock *sk, int err) +{ + if (!sk_fullsock(sk)) { + if (sk->sk_state == TCP_NEW_SYN_RECV) { + struct request_sock *req = inet_reqsk(sk); + + local_bh_disable(); + inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, + req); + local_bh_enable(); + return 0; + } + sock_gen_put(sk); + return -EOPNOTSUPP; + } + + /* Don't race with userspace socket closes such as tcp_close. */ + lock_sock(sk); + + if (sk->sk_state == TCP_LISTEN) { + tcp_set_state(sk, TCP_CLOSE); + inet_csk_listen_stop(sk); + } + + /* Don't race with BH socket closes such as inet_csk_listen_stop. */ + local_bh_disable(); + bh_lock_sock(sk); + + if (!sock_flag(sk, SOCK_DEAD)) { + sk->sk_err = err; + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + smp_wmb(); + sk->sk_error_report(sk); + if (tcp_need_reset(sk->sk_state)) + tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_done(sk); + } + + bh_unlock_sock(sk); + local_bh_enable(); + release_sock(sk); + sock_put(sk); + return 0; +} +EXPORT_SYMBOL_GPL(tcp_abort); + extern struct tcp_congestion_ops tcp_reno; static __initdata unsigned long thash_entries; diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index b31604086..4d610934f 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -10,6 +10,8 @@ */ #include <linux/module.h> +#include <linux/net.h> +#include <linux/sock_diag.h> #include <linux/inet_diag.h> #include <linux/tcp.h> @@ -46,12 +48,29 @@ static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req); } +#ifdef CONFIG_INET_DIAG_DESTROY +static int tcp_diag_destroy(struct sk_buff *in_skb, + const struct inet_diag_req_v2 *req) +{ + struct net *net = sock_net(in_skb->sk); + struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req); + + if (IS_ERR(sk)) + return PTR_ERR(sk); + + return sock_diag_destroy(sk, ECONNABORTED); +} +#endif + static const struct inet_diag_handler tcp_diag_handler = { .dump = tcp_diag_dump, .dump_one = tcp_diag_dump_one, .idiag_get_info = tcp_diag_get_info, .idiag_type = IPPROTO_TCP, .idiag_info_size = sizeof(struct tcp_info), +#ifdef CONFIG_INET_DIAG_DESTROY + .destroy = tcp_diag_destroy, +#endif }; static int __init tcp_diag_init(void) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e4600e3c9..b3a47bc08 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2167,8 +2167,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int cnt, oldcnt; - int err; + int cnt, oldcnt, lost; unsigned int mss; /* Use SACK to deduce losses of new sequences sent during recovery */ const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; @@ -2208,9 +2207,10 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) break; mss = tcp_skb_mss(skb); - err = tcp_fragment(sk, skb, (packets - oldcnt) * mss, - mss, GFP_ATOMIC); - if (err < 0) + /* If needed, chop off the prefix to mark as lost. */ + lost = (packets - oldcnt) * mss; + if (lost < skb->len && + tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0) break; cnt = packets; } @@ -2369,8 +2369,6 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) tp->snd_ssthresh = tp->prior_ssthresh; tcp_ecn_withdraw_cwr(tp); } - } else { - tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh); } tp->snd_cwnd_stamp = tcp_time_stamp; tp->undo_marker = 0; @@ -2901,7 +2899,10 @@ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) { const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ; struct rtt_meas *m = tcp_sk(sk)->rtt_min; - struct rtt_meas rttm = { .rtt = (rtt_us ? : 1), .ts = now }; + struct rtt_meas rttm = { + .rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1), + .ts = now, + }; u32 elapsed; /* Check if the new measurement updates the 1st, 2nd, or 3rd choices */ @@ -6293,7 +6294,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_openreq_init(req, &tmp_opt, skb, sk); /* Note: tcp_v6_init_req() might override ir_iif for link locals */ - inet_rsk(req)->ir_iif = sk->sk_bound_dev_if; + inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb); af_ops->init_req(req, sk, skb); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0ab7b38dd..6dded9573 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -73,7 +73,6 @@ #include <net/timewait_sock.h> #include <net/xfrm.h> #include <net/secure_seq.h> -#include <net/tcp_memcontrol.h> #include <net/busy_poll.h> #include <net/secure_seq.h> @@ -608,7 +607,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) } rep; struct ip_reply_arg arg; #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *key; + struct tcp_md5sig_key *key = NULL; const __u8 *hash_location = NULL; unsigned char newhash[16]; int genhash; @@ -648,7 +647,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); #ifdef CONFIG_TCP_MD5SIG hash_location = tcp_parse_md5sig_option(th); - if (!sk && hash_location) { + if (sk && sk_fullsock(sk)) { + key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *) + &ip_hdr(skb)->saddr, AF_INET); + } else if (hash_location) { /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. @@ -672,10 +674,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto release_sk1; - } else { - key = sk ? tcp_md5_do_lookup(sk, (union tcp_md5_addr *) - &ip_hdr(skb)->saddr, - AF_INET) : NULL; } if (key) { @@ -696,7 +694,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; - arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; + arg.flags = (sk && inet_sk_transparent(sk)) ? IP_REPLY_ARG_NOSRCCHECK : 0; + /* When socket is gone, all binding information is lost. * routing might fail in this case. No choice here, if we choose to force * input interface, we will misroute in case of asymmetric route. @@ -704,6 +703,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) if (sk) arg.bound_dev_if = sk->sk_bound_dev_if; + BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != + offsetof(struct inet_timewait_sock, tw_bound_dev_if)); + arg.tos = ip_hdr(skb)->tos; ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -1300,6 +1302,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, ireq = inet_rsk(req); sk_daddr_set(newsk, ireq->ir_rmt_addr); sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); + newsk->sk_bound_dev_if = ireq->ir_iif; newinet->inet_saddr = ireq->ir_loc_addr; inet_opt = ireq->opt; rcu_assign_pointer(newinet->inet_opt, inet_opt); @@ -1742,7 +1745,9 @@ do_time_wait: tcp_v4_timewait_ack(sk, skb); break; case TCP_TW_RST: - goto no_tcp_socket; + tcp_v4_send_reset(sk, skb); + inet_twsk_deschedule_put(inet_twsk(sk)); + goto discard_it; case TCP_TW_SUCCESS:; } goto discard_it; @@ -1849,7 +1854,9 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); - sock_release_memcg(sk); + + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + sock_release_memcg(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); @@ -2373,11 +2380,7 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_MEMCG_KMEM - .init_cgroup = tcp_init_cgroup, - .destroy_cgroup = tcp_destroy_cgroup, - .proto_cgroup = tcp_proto_cgroup, -#endif + .diag_destroy = tcp_abort, }; EXPORT_SYMBOL(tcp_prot); @@ -2415,6 +2418,10 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; + net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; + net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; + net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL; + return 0; fail: tcp_sk_exit(net); diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c deleted file mode 100644 index 2379c1b4e..000000000 --- a/net/ipv4/tcp_memcontrol.c +++ /dev/null @@ -1,233 +0,0 @@ -#include <net/tcp.h> -#include <net/tcp_memcontrol.h> -#include <net/sock.h> -#include <net/ip.h> -#include <linux/nsproxy.h> -#include <linux/memcontrol.h> -#include <linux/module.h> - -int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss) -{ - /* - * The root cgroup does not use page_counters, but rather, - * rely on the data already collected by the network - * subsystem - */ - struct mem_cgroup *parent = parent_mem_cgroup(memcg); - struct page_counter *counter_parent = NULL; - struct cg_proto *cg_proto, *parent_cg; - - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) - return 0; - - cg_proto->sysctl_mem[0] = sysctl_tcp_mem[0]; - cg_proto->sysctl_mem[1] = sysctl_tcp_mem[1]; - cg_proto->sysctl_mem[2] = sysctl_tcp_mem[2]; - cg_proto->memory_pressure = 0; - cg_proto->memcg = memcg; - - parent_cg = tcp_prot.proto_cgroup(parent); - if (parent_cg) - counter_parent = &parent_cg->memory_allocated; - - page_counter_init(&cg_proto->memory_allocated, counter_parent); - percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL); - - return 0; -} -EXPORT_SYMBOL(tcp_init_cgroup); - -void tcp_destroy_cgroup(struct mem_cgroup *memcg) -{ - struct cg_proto *cg_proto; - - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) - return; - - percpu_counter_destroy(&cg_proto->sockets_allocated); - - if (test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) - static_key_slow_dec(&memcg_socket_limit_enabled); - -} -EXPORT_SYMBOL(tcp_destroy_cgroup); - -static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) -{ - struct cg_proto *cg_proto; - int i; - int ret; - - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) - return -EINVAL; - - ret = page_counter_limit(&cg_proto->memory_allocated, nr_pages); - if (ret) - return ret; - - for (i = 0; i < 3; i++) - cg_proto->sysctl_mem[i] = min_t(long, nr_pages, - sysctl_tcp_mem[i]); - - if (nr_pages == PAGE_COUNTER_MAX) - clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); - else { - /* - * The active bit needs to be written after the static_key - * update. This is what guarantees that the socket activation - * function is the last one to run. See sock_update_memcg() for - * details, and note that we don't mark any socket as belonging - * to this memcg until that flag is up. - * - * We need to do this, because static_keys will span multiple - * sites, but we can't control their order. If we mark a socket - * as accounted, but the accounting functions are not patched in - * yet, we'll lose accounting. - * - * We never race with the readers in sock_update_memcg(), - * because when this value change, the code to process it is not - * patched in yet. - * - * The activated bit is used to guarantee that no two writers - * will do the update in the same memcg. Without that, we can't - * properly shutdown the static key. - */ - if (!test_and_set_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) - static_key_slow_inc(&memcg_socket_limit_enabled); - set_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); - } - - return 0; -} - -enum { - RES_USAGE, - RES_LIMIT, - RES_MAX_USAGE, - RES_FAILCNT, -}; - -static DEFINE_MUTEX(tcp_limit_mutex); - -static ssize_t tcp_cgroup_write(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off) -{ - struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); - unsigned long nr_pages; - int ret = 0; - - buf = strstrip(buf); - - switch (of_cft(of)->private) { - case RES_LIMIT: - /* see memcontrol.c */ - ret = page_counter_memparse(buf, "-1", &nr_pages); - if (ret) - break; - mutex_lock(&tcp_limit_mutex); - ret = tcp_update_limit(memcg, nr_pages); - mutex_unlock(&tcp_limit_mutex); - break; - default: - ret = -EINVAL; - break; - } - return ret ?: nbytes; -} - -static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft) -{ - struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct cg_proto *cg_proto = tcp_prot.proto_cgroup(memcg); - u64 val; - - switch (cft->private) { - case RES_LIMIT: - if (!cg_proto) - return PAGE_COUNTER_MAX; - val = cg_proto->memory_allocated.limit; - val *= PAGE_SIZE; - break; - case RES_USAGE: - if (!cg_proto) - val = atomic_long_read(&tcp_memory_allocated); - else - val = page_counter_read(&cg_proto->memory_allocated); - val *= PAGE_SIZE; - break; - case RES_FAILCNT: - if (!cg_proto) - return 0; - val = cg_proto->memory_allocated.failcnt; - break; - case RES_MAX_USAGE: - if (!cg_proto) - return 0; - val = cg_proto->memory_allocated.watermark; - val *= PAGE_SIZE; - break; - default: - BUG(); - } - return val; -} - -static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off) -{ - struct mem_cgroup *memcg; - struct cg_proto *cg_proto; - - memcg = mem_cgroup_from_css(of_css(of)); - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) - return nbytes; - - switch (of_cft(of)->private) { - case RES_MAX_USAGE: - page_counter_reset_watermark(&cg_proto->memory_allocated); - break; - case RES_FAILCNT: - cg_proto->memory_allocated.failcnt = 0; - break; - } - - return nbytes; -} - -static struct cftype tcp_files[] = { - { - .name = "kmem.tcp.limit_in_bytes", - .write = tcp_cgroup_write, - .read_u64 = tcp_cgroup_read, - .private = RES_LIMIT, - }, - { - .name = "kmem.tcp.usage_in_bytes", - .read_u64 = tcp_cgroup_read, - .private = RES_USAGE, - }, - { - .name = "kmem.tcp.failcnt", - .private = RES_FAILCNT, - .write = tcp_cgroup_reset, - .read_u64 = tcp_cgroup_read, - }, - { - .name = "kmem.tcp.max_usage_in_bytes", - .private = RES_MAX_USAGE, - .write = tcp_cgroup_reset, - .read_u64 = tcp_cgroup_read, - }, - { } /* terminate */ -}; - -static int __init tcp_memcontrol_init(void) -{ - WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, tcp_files)); - return 0; -} -__initcall(tcp_memcontrol_init); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c8cbc2b4b..a726d7853 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -550,7 +550,7 @@ reset: */ if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt /= 8 * USEC_PER_MSEC; + crtt /= 8 * USEC_PER_SEC / HZ; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ac6b1961f..9b02af213 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -131,7 +131,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, goto kill; if (th->syn && !before(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt)) - goto kill_with_rst; + return TCP_TW_RST; /* Dup ACK? */ if (!th->ack || @@ -145,11 +145,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, * reset. */ if (!th->fin || - TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) { -kill_with_rst: - inet_twsk_deschedule_put(tw); + TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) return TCP_TW_RST; - } /* FIN arrived, enter true time-wait state. */ tw->tw_substate = TCP_TIME_WAIT; @@ -458,7 +455,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->segs_in = 0; + newtp->segs_in = 1; newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; @@ -818,6 +815,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; + tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); if (!sock_owned_by_user(child)) { ret = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fac7cd5c7..20f2812a9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2303,7 +2303,7 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, return; if (tcp_write_xmit(sk, cur_mss, nonagle, 0, - sk_gfp_atomic(sk, GFP_ATOMIC))) + sk_gfp_mask(sk, GFP_ATOMIC))) tcp_check_probe_timer(sk); } @@ -2820,13 +2820,16 @@ begin_fwd: */ void sk_forced_mem_schedule(struct sock *sk, int size) { - int amt, status; + int amt; if (size <= sk->sk_forward_alloc) return; amt = sk_mem_pages(size); sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - sk_memory_allocated_add(sk, amt, &status); + sk_memory_allocated_add(sk, amt); + + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + mem_cgroup_charge_skmem(sk->sk_memcg, amt); } /* Send a FIN. The caller locks the socket for us. @@ -3368,8 +3371,9 @@ void tcp_send_ack(struct sock *sk) * tcp_transmit_skb() will set the ownership to this * sock. */ - buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); - if (!buff) { + buff = alloc_skb(MAX_TCP_HEADER, + sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); + if (unlikely(!buff)) { inet_csk_schedule_ack(sk); inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, @@ -3391,7 +3395,7 @@ void tcp_send_ack(struct sock *sk) /* Send it off, this clears delayed acks for us. */ skb_mstamp_get(&buff->skb_mstamp); - tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC)); + tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0); } EXPORT_SYMBOL_GPL(tcp_send_ack); @@ -3412,7 +3416,8 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) struct sk_buff *skb; /* We don't queue it, tcp_transmit_skb() sets ownership. */ - skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); + skb = alloc_skb(MAX_TCP_HEADER, + sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); if (!skb) return -1; @@ -3425,7 +3430,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); skb_mstamp_get(&skb->skb_mstamp); NET_INC_STATS(sock_net(sk), mib); - return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC); + return tcp_transmit_skb(sk, skb, 0, (__force gfp_t)0); } void tcp_send_window_probe(struct sock *sk) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 193ba1fa8..a4730a28b 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -24,9 +24,6 @@ int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES; int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES; -int sysctl_tcp_keepalive_time __read_mostly = TCP_KEEPALIVE_TIME; -int sysctl_tcp_keepalive_probes __read_mostly = TCP_KEEPALIVE_PROBES; -int sysctl_tcp_keepalive_intvl __read_mostly = TCP_KEEPALIVE_INTVL; int sysctl_tcp_retries1 __read_mostly = TCP_RETR1; int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; int sysctl_tcp_orphan_retries __read_mostly; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7f8ab46ad..95d2f1980 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -113,6 +113,7 @@ #include <trace/events/skb.h> #include <net/busy_poll.h> #include "udp_impl.h" +#include <net/sock_reuseport.h> struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); @@ -137,7 +138,8 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, unsigned long *bitmap, struct sock *sk, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2), + const struct sock *sk2, + bool match_wildcard), unsigned int log) { struct sock *sk2; @@ -152,8 +154,9 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && (!sk2->sk_reuseport || !sk->sk_reuseport || + rcu_access_pointer(sk->sk_reuseport_cb) || !uid_eq(uid, sock_i_uid(sk2))) && - saddr_comp(sk, sk2)) { + saddr_comp(sk, sk2, true)) { if (!bitmap) return 1; __set_bit(udp_sk(sk2)->udp_port_hash >> log, bitmap); @@ -170,7 +173,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, struct udp_hslot *hslot2, struct sock *sk, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2)) + const struct sock *sk2, + bool match_wildcard)) { struct sock *sk2; struct hlist_nulls_node *node; @@ -186,8 +190,9 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && (!sk2->sk_reuseport || !sk->sk_reuseport || + rcu_access_pointer(sk->sk_reuseport_cb) || !uid_eq(uid, sock_i_uid(sk2))) && - saddr_comp(sk, sk2)) { + saddr_comp(sk, sk2, true)) { res = 1; break; } @@ -196,6 +201,35 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, return res; } +static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot, + int (*saddr_same)(const struct sock *sk1, + const struct sock *sk2, + bool match_wildcard)) +{ + struct net *net = sock_net(sk); + struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); + struct sock *sk2; + + sk_nulls_for_each(sk2, node, &hslot->head) { + if (net_eq(sock_net(sk2), net) && + sk2 != sk && + sk2->sk_family == sk->sk_family && + ipv6_only_sock(sk2) == ipv6_only_sock(sk) && + (udp_sk(sk2)->udp_port_hash == udp_sk(sk)->udp_port_hash) && + (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && + (*saddr_same)(sk, sk2, false)) { + return reuseport_add_sock(sk, sk2); + } + } + + /* Initial allocation may have already happened via setsockopt */ + if (!rcu_access_pointer(sk->sk_reuseport_cb)) + return reuseport_alloc(sk); + return 0; +} + /** * udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6 * @@ -207,7 +241,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, */ int udp_lib_get_port(struct sock *sk, unsigned short snum, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2), + const struct sock *sk2, + bool match_wildcard), unsigned int hash2_nulladdr) { struct udp_hslot *hslot, *hslot2; @@ -290,6 +325,14 @@ found: udp_sk(sk)->udp_port_hash = snum; udp_sk(sk)->udp_portaddr_hash ^= snum; if (sk_unhashed(sk)) { + if (sk->sk_reuseport && + udp_reuseport_add_sock(sk, hslot, saddr_comp)) { + inet_sk(sk)->inet_num = 0; + udp_sk(sk)->udp_port_hash = 0; + udp_sk(sk)->udp_portaddr_hash ^= snum; + goto fail_unlock; + } + sk_nulls_add_node_rcu(sk, &hslot->head); hslot->count++; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -309,13 +352,22 @@ fail: } EXPORT_SYMBOL(udp_lib_get_port); -static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) +/* match_wildcard == true: 0.0.0.0 equals to any IPv4 addresses + * match_wildcard == false: addresses must be exactly the same, i.e. + * 0.0.0.0 only equals to 0.0.0.0 + */ +static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2, + bool match_wildcard) { struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); - return (!ipv6_only_sock(sk2) && - (!inet1->inet_rcv_saddr || !inet2->inet_rcv_saddr || - inet1->inet_rcv_saddr == inet2->inet_rcv_saddr)); + if (!ipv6_only_sock(sk2)) { + if (inet1->inet_rcv_saddr == inet2->inet_rcv_saddr) + return 1; + if (!inet1->inet_rcv_saddr || !inet2->inet_rcv_saddr) + return match_wildcard; + } + return 0; } static u32 udp4_portaddr_hash(const struct net *net, __be32 saddr, @@ -441,11 +493,13 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr, static struct sock *udp4_lib_lookup2(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif, - struct udp_hslot *hslot2, unsigned int slot2) + struct udp_hslot *hslot2, unsigned int slot2, + struct sk_buff *skb) { struct sock *sk, *result; struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; begin: @@ -461,6 +515,17 @@ begin: if (reuseport) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } + } matches = 1; } } else if (score == badness && reuseport) { @@ -478,6 +543,7 @@ begin: if (get_nulls_value(node) != slot2) goto begin; if (result) { +found: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, @@ -494,7 +560,7 @@ begin: */ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, - int dif, struct udp_table *udptable) + int dif, struct udp_table *udptable, struct sk_buff *skb) { struct sock *sk, *result; struct hlist_nulls_node *node; @@ -502,6 +568,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; rcu_read_lock(); @@ -514,7 +581,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, result = udp4_lib_lookup2(net, saddr, sport, daddr, hnum, dif, - hslot2, slot2); + hslot2, slot2, skb); if (!result) { hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum); slot2 = hash2 & udptable->mask; @@ -524,7 +591,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, result = udp4_lib_lookup2(net, saddr, sport, htonl(INADDR_ANY), hnum, dif, - hslot2, slot2); + hslot2, slot2, skb); } rcu_read_unlock(); return result; @@ -542,6 +609,17 @@ begin: if (reuseport) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } + } matches = 1; } } else if (score == badness && reuseport) { @@ -560,6 +638,7 @@ begin: goto begin; if (result) { +found: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, @@ -581,13 +660,14 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport, iph->daddr, dport, inet_iif(skb), - udptable); + udptable, skb); } struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif) { - return __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table); + return __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, + &udp_table, NULL); } EXPORT_SYMBOL_GPL(udp4_lib_lookup); @@ -635,7 +715,8 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) struct net *net = dev_net(skb->dev); sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, - iph->saddr, uh->source, skb->dev->ifindex, udptable); + iph->saddr, uh->source, skb->dev->ifindex, udptable, + NULL); if (!sk) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; /* No socket for error */ @@ -772,7 +853,8 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, else if (skb_is_gso(skb)) uh->check = ~udp_v4_check(len, saddr, daddr, 0); else if (skb_dst(skb) && skb_dst(skb)->dev && - (skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) { + (skb_dst(skb)->dev->features & + (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM))) { BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); @@ -1275,6 +1357,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int peeked, off = 0; int err; int is_udplite = IS_UDPLITE(sk); + bool checksum_valid = false; bool slow; if (flags & MSG_ERRQUEUE) @@ -1300,11 +1383,12 @@ try_again: */ if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { - if (udp_lib_checksum_complete(skb)) + checksum_valid = !udp_lib_checksum_complete(skb); + if (!checksum_valid) goto csum_copy_err; } - if (skb_csum_unnecessary(skb)) + if (checksum_valid || skb_csum_unnecessary(skb)) err = skb_copy_datagram_msg(skb, sizeof(struct udphdr), msg, copied); else { @@ -1400,6 +1484,8 @@ void udp_lib_unhash(struct sock *sk) hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); spin_lock_bh(&hslot->lock); + if (rcu_access_pointer(sk->sk_reuseport_cb)) + reuseport_detach_sock(sk); if (sk_nulls_del_node_init_rcu(sk)) { hslot->count--; inet_sk(sk)->inet_num = 0; @@ -1427,22 +1513,28 @@ void udp_lib_rehash(struct sock *sk, u16 newhash) hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); nhslot2 = udp_hashslot2(udptable, newhash); udp_sk(sk)->udp_portaddr_hash = newhash; - if (hslot2 != nhslot2) { + + if (hslot2 != nhslot2 || + rcu_access_pointer(sk->sk_reuseport_cb)) { hslot = udp_hashslot(udptable, sock_net(sk), udp_sk(sk)->udp_port_hash); /* we must lock primary chain too */ spin_lock_bh(&hslot->lock); - - spin_lock(&hslot2->lock); - hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); - hslot2->count--; - spin_unlock(&hslot2->lock); - - spin_lock(&nhslot2->lock); - hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, - &nhslot2->head); - nhslot2->count++; - spin_unlock(&nhslot2->lock); + if (rcu_access_pointer(sk->sk_reuseport_cb)) + reuseport_detach_sock(sk); + + if (hslot2 != nhslot2) { + spin_lock(&hslot2->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hslot2->count--; + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + &nhslot2->head); + nhslot2->count++; + spin_unlock(&nhslot2->lock); + } spin_unlock_bh(&hslot->lock); } diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 6116604bf..df1966f3b 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -44,7 +44,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, sk = __udp4_lib_lookup(net, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_dst[0], req->id.idiag_dport, - req->id.idiag_if, tbl); + req->id.idiag_if, tbl, NULL); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) sk = __udp6_lib_lookup(net, @@ -52,7 +52,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, req->id.idiag_sport, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, - req->id.idiag_if, tbl); + req->id.idiag_if, tbl, NULL); #endif else goto out_nosk; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index f9386160c..4c519c1dc 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -21,6 +21,7 @@ static struct udp_offload_priv __rcu *udp_offload_base __read_mostly; struct udp_offload_priv { struct udp_offload *offload; + possible_net_t net; struct rcu_head rcu; struct udp_offload_priv __rcu *next; }; @@ -60,8 +61,9 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, /* Try to offload checksum if possible */ offload_csum = !!(need_csum && - (skb->dev->features & - (is_ipv6 ? NETIF_F_V6_CSUM : NETIF_F_V4_CSUM))); + ((skb->dev->features & NETIF_F_HW_CSUM) || + (skb->dev->features & (is_ipv6 ? + NETIF_F_IPV6_CSUM : NETIF_F_IP_CSUM)))); /* segment inner packet. */ enc_features = skb->dev->hw_enc_features & features; @@ -241,13 +243,14 @@ out: return segs; } -int udp_add_offload(struct udp_offload *uo) +int udp_add_offload(struct net *net, struct udp_offload *uo) { struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_ATOMIC); if (!new_offload) return -ENOMEM; + write_pnet(&new_offload->net, net); new_offload->offload = uo; spin_lock(&udp_offload_lock); @@ -311,7 +314,8 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, rcu_read_lock(); uo_priv = rcu_dereference(udp_offload_base); for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) { - if (uo_priv->offload->port == uh->dest && + if (net_eq(read_pnet(&uo_priv->net), dev_net(skb->dev)) && + uo_priv->offload->port == uh->dest && uo_priv->offload->callbacks.gro_receive) goto unflush; } @@ -389,7 +393,8 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff) uo_priv = rcu_dereference(udp_offload_base); for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) { - if (uo_priv->offload->port == uh->dest && + if (net_eq(read_pnet(&uo_priv->net), dev_net(skb->dev)) && + uo_priv->offload->port == uh->dest && uo_priv->offload->callbacks.gro_complete) break; } diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index aba428626..96599d1a1 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -74,10 +74,10 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, } EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock); -int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, - __be32 src, __be32 dst, __u8 tos, __u8 ttl, - __be16 df, __be16 src_port, __be16 dst_port, - bool xnet, bool nocheck) +void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, + __be32 src, __be32 dst, __u8 tos, __u8 ttl, + __be16 df, __be16 src_port, __be16 dst_port, + bool xnet, bool nocheck) { struct udphdr *uh; @@ -89,10 +89,11 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, uh->source = src_port; uh->len = htons(skb->len); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + udp_set_csum(nocheck, skb, src, dst, skb->len); - return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, - tos, ttl, df, xnet); + iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); } EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb); |