diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/arp.c | 55 | ||||
-rw-r--r-- | net/ipv4/devinet.c | 1 | ||||
-rw-r--r-- | net/ipv4/fib_frontend.c | 4 | ||||
-rw-r--r-- | net/ipv4/fib_semantics.c | 76 | ||||
-rw-r--r-- | net/ipv4/icmp.c | 2 | ||||
-rw-r--r-- | net/ipv4/igmp.c | 87 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 2 | ||||
-rw-r--r-- | net/ipv4/ip_fragment.c | 39 | ||||
-rw-r--r-- | net/ipv4/ip_gre.c | 4 | ||||
-rw-r--r-- | net/ipv4/ip_sockglue.c | 14 | ||||
-rw-r--r-- | net/ipv4/ipcomp.c | 9 | ||||
-rw-r--r-- | net/ipv4/ipip.c | 7 | ||||
-rw-r--r-- | net/ipv4/proc.c | 4 | ||||
-rw-r--r-- | net/ipv4/route.c | 7 | ||||
-rw-r--r-- | net/ipv4/syncookies.c | 3 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 30 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 25 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 22 | ||||
-rw-r--r-- | net/ipv4/tcp_timer.c | 6 | ||||
-rw-r--r-- | net/ipv4/udp.c | 4 | ||||
-rw-r--r-- | net/ipv4/udplite.c | 4 |
21 files changed, 279 insertions, 126 deletions
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index c95cd93..1940b4d 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -70,6 +70,7 @@ * bonding can change the skb before * sending (e.g. insert 8021q tag). * Harald Welte : convert to make use of jenkins hash + * Jesper D. Brouer: Proxy ARP PVLAN RFC 3069 support. */ #include <linux/module.h> @@ -524,12 +525,15 @@ int arp_bind_neighbour(struct dst_entry *dst) /* * Check if we can use proxy ARP for this path */ - -static inline int arp_fwd_proxy(struct in_device *in_dev, struct rtable *rt) +static inline int arp_fwd_proxy(struct in_device *in_dev, + struct net_device *dev, struct rtable *rt) { struct in_device *out_dev; int imi, omi = -1; + if (rt->u.dst.dev == dev) + return 0; + if (!IN_DEV_PROXY_ARP(in_dev)) return 0; @@ -548,6 +552,43 @@ static inline int arp_fwd_proxy(struct in_device *in_dev, struct rtable *rt) } /* + * Check for RFC3069 proxy arp private VLAN (allow to send back to same dev) + * + * RFC3069 supports proxy arp replies back to the same interface. This + * is done to support (ethernet) switch features, like RFC 3069, where + * the individual ports are not allowed to communicate with each + * other, BUT they are allowed to talk to the upstream router. As + * described in RFC 3069, it is possible to allow these hosts to + * communicate through the upstream router, by proxy_arp'ing. + * + * RFC 3069: "VLAN Aggregation for Efficient IP Address Allocation" + * + * This technology is known by different names: + * In RFC 3069 it is called VLAN Aggregation. + * Cisco and Allied Telesyn call it Private VLAN. + * Hewlett-Packard call it Source-Port filtering or port-isolation. + * Ericsson call it MAC-Forced Forwarding (RFC Draft). + * + */ +static inline int arp_fwd_pvlan(struct in_device *in_dev, + struct net_device *dev, struct rtable *rt, + __be32 sip, __be32 tip) +{ + /* Private VLAN is only concerned about the same ethernet segment */ + if (rt->u.dst.dev != dev) + return 0; + + /* Don't reply on self probes (often done by windowz boxes)*/ + if (sip == tip) + return 0; + + if (IN_DEV_PROXY_ARP_PVLAN(in_dev)) + return 1; + else + return 0; +} + +/* * Interface to link layer: send routine and receive handler. */ @@ -833,8 +874,11 @@ static int arp_process(struct sk_buff *skb) } goto out; } else if (IN_DEV_FORWARD(in_dev)) { - if (addr_type == RTN_UNICAST && rt->u.dst.dev != dev && - (arp_fwd_proxy(in_dev, rt) || pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) { + if (addr_type == RTN_UNICAST && + (arp_fwd_proxy(in_dev, dev, rt) || + arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || + pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) + { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); @@ -863,7 +907,8 @@ static int arp_process(struct sk_buff *skb) devices (strip is candidate) */ if (n == NULL && - arp->ar_op == htons(ARPOP_REPLY) && + (arp->ar_op == htons(ARPOP_REPLY) || + (arp->ar_op == htons(ARPOP_REQUEST) && tip == sip)) && inet_addr_type(net, sip) == RTN_UNICAST) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 040c4f0..cd71a39 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1408,6 +1408,7 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"), DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"), DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"), + DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"), diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 82dbf71..9b3e28e 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -883,7 +883,7 @@ static void nl_fib_input(struct sk_buff *skb) netlink_unicast(net->ipv4.fibnl, skb, pid, MSG_DONTWAIT); } -static int nl_fib_lookup_init(struct net *net) +static int __net_init nl_fib_lookup_init(struct net *net) { struct sock *sk; sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, 0, @@ -1004,7 +1004,7 @@ fail: return err; } -static void __net_exit ip_fib_net_exit(struct net *net) +static void ip_fib_net_exit(struct net *net) { unsigned int i; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index ed19aa6..96b2101 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -62,8 +62,8 @@ static DEFINE_SPINLOCK(fib_multipath_lock); #define for_nexthops(fi) { int nhsel; const struct fib_nh * nh; \ for (nhsel=0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++) -#define change_nexthops(fi) { int nhsel; struct fib_nh * nh; \ -for (nhsel=0, nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++) +#define change_nexthops(fi) { int nhsel; struct fib_nh *nexthop_nh; \ +for (nhsel=0, nexthop_nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nexthop_nh++, nhsel++) #else /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -72,7 +72,7 @@ for (nhsel=0, nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, #define for_nexthops(fi) { int nhsel = 0; const struct fib_nh * nh = (fi)->fib_nh; \ for (nhsel=0; nhsel < 1; nhsel++) -#define change_nexthops(fi) { int nhsel = 0; struct fib_nh * nh = (struct fib_nh *)((fi)->fib_nh); \ +#define change_nexthops(fi) { int nhsel = 0; struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \ for (nhsel=0; nhsel < 1; nhsel++) #endif /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -145,9 +145,9 @@ void free_fib_info(struct fib_info *fi) return; } change_nexthops(fi) { - if (nh->nh_dev) - dev_put(nh->nh_dev); - nh->nh_dev = NULL; + if (nexthop_nh->nh_dev) + dev_put(nexthop_nh->nh_dev); + nexthop_nh->nh_dev = NULL; } endfor_nexthops(fi); fib_info_cnt--; release_net(fi->fib_net); @@ -162,9 +162,9 @@ void fib_release_info(struct fib_info *fi) if (fi->fib_prefsrc) hlist_del(&fi->fib_lhash); change_nexthops(fi) { - if (!nh->nh_dev) + if (!nexthop_nh->nh_dev) continue; - hlist_del(&nh->nh_hash); + hlist_del(&nexthop_nh->nh_hash); } endfor_nexthops(fi) fi->fib_dead = 1; fib_info_put(fi); @@ -395,19 +395,20 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, if (!rtnh_ok(rtnh, remaining)) return -EINVAL; - nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; - nh->nh_oif = rtnh->rtnh_ifindex; - nh->nh_weight = rtnh->rtnh_hops + 1; + nexthop_nh->nh_flags = + (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; + nexthop_nh->nh_oif = rtnh->rtnh_ifindex; + nexthop_nh->nh_weight = rtnh->rtnh_hops + 1; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); - nh->nh_gw = nla ? nla_get_be32(nla) : 0; + nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0; #ifdef CONFIG_NET_CLS_ROUTE nla = nla_find(attrs, attrlen, RTA_FLOW); - nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; + nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; #endif } @@ -738,7 +739,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_nhs = nhs; change_nexthops(fi) { - nh->nh_parent = fi; + nexthop_nh->nh_parent = fi; } endfor_nexthops(fi) if (cfg->fc_mx) { @@ -808,7 +809,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto failure; } else { change_nexthops(fi) { - if ((err = fib_check_nh(cfg, fi, nh)) != 0) + if ((err = fib_check_nh(cfg, fi, nexthop_nh)) != 0) goto failure; } endfor_nexthops(fi) } @@ -843,11 +844,11 @@ link_it: struct hlist_head *head; unsigned int hash; - if (!nh->nh_dev) + if (!nexthop_nh->nh_dev) continue; - hash = fib_devindex_hashfn(nh->nh_dev->ifindex); + hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex); head = &fib_info_devhash[hash]; - hlist_add_head(&nh->nh_hash, head); + hlist_add_head(&nexthop_nh->nh_hash, head); } endfor_nexthops(fi) spin_unlock_bh(&fib_info_lock); return fi; @@ -1080,21 +1081,21 @@ int fib_sync_down_dev(struct net_device *dev, int force) prev_fi = fi; dead = 0; change_nexthops(fi) { - if (nh->nh_flags&RTNH_F_DEAD) + if (nexthop_nh->nh_flags&RTNH_F_DEAD) dead++; - else if (nh->nh_dev == dev && - nh->nh_scope != scope) { - nh->nh_flags |= RTNH_F_DEAD; + else if (nexthop_nh->nh_dev == dev && + nexthop_nh->nh_scope != scope) { + nexthop_nh->nh_flags |= RTNH_F_DEAD; #ifdef CONFIG_IP_ROUTE_MULTIPATH spin_lock_bh(&fib_multipath_lock); - fi->fib_power -= nh->nh_power; - nh->nh_power = 0; + fi->fib_power -= nexthop_nh->nh_power; + nexthop_nh->nh_power = 0; spin_unlock_bh(&fib_multipath_lock); #endif dead++; } #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (force > 1 && nh->nh_dev == dev) { + if (force > 1 && nexthop_nh->nh_dev == dev) { dead = fi->fib_nhs; break; } @@ -1144,18 +1145,20 @@ int fib_sync_up(struct net_device *dev) prev_fi = fi; alive = 0; change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD)) { + if (!(nexthop_nh->nh_flags&RTNH_F_DEAD)) { alive++; continue; } - if (nh->nh_dev == NULL || !(nh->nh_dev->flags&IFF_UP)) + if (nexthop_nh->nh_dev == NULL || + !(nexthop_nh->nh_dev->flags&IFF_UP)) continue; - if (nh->nh_dev != dev || !__in_dev_get_rtnl(dev)) + if (nexthop_nh->nh_dev != dev || + !__in_dev_get_rtnl(dev)) continue; alive++; spin_lock_bh(&fib_multipath_lock); - nh->nh_power = 0; - nh->nh_flags &= ~RTNH_F_DEAD; + nexthop_nh->nh_power = 0; + nexthop_nh->nh_flags &= ~RTNH_F_DEAD; spin_unlock_bh(&fib_multipath_lock); } endfor_nexthops(fi) @@ -1182,9 +1185,9 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res) if (fi->fib_power <= 0) { int power = 0; change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD)) { - power += nh->nh_weight; - nh->nh_power = nh->nh_weight; + if (!(nexthop_nh->nh_flags&RTNH_F_DEAD)) { + power += nexthop_nh->nh_weight; + nexthop_nh->nh_power = nexthop_nh->nh_weight; } } endfor_nexthops(fi); fi->fib_power = power; @@ -1204,9 +1207,10 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res) w = jiffies % fi->fib_power; change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD) && nh->nh_power) { - if ((w -= nh->nh_power) <= 0) { - nh->nh_power--; + if (!(nexthop_nh->nh_flags&RTNH_F_DEAD) && + nexthop_nh->nh_power) { + if ((w -= nexthop_nh->nh_power) <= 0) { + nexthop_nh->nh_power--; fi->fib_power--; res->nh_sel = nhsel; spin_unlock_bh(&fib_multipath_lock); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index fe11f60..4b4c2bc 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -114,7 +114,7 @@ struct icmp_bxm { /* An array of errno for error messages from dest unreach. */ /* RFC 1122: 3.2.2.1 States that NET_UNREACH, HOST_UNREACH and SR_FAILED MUST be considered 'transient errs'. */ -struct icmp_err icmp_err_convert[] = { +const struct icmp_err icmp_err_convert[] = { { .errno = ENETUNREACH, /* ICMP_NET_UNREACH */ .fatal = 0, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 76c0840..d2836399 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1799,7 +1799,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) iml->next = inet->mc_list; iml->sflist = NULL; iml->sfmode = MCAST_EXCLUDE; - inet->mc_list = iml; + rcu_assign_pointer(inet->mc_list, iml); ip_mc_inc_group(in_dev, addr); err = 0; done: @@ -1807,24 +1807,46 @@ done: return err; } +static void ip_sf_socklist_reclaim(struct rcu_head *rp) +{ + struct ip_sf_socklist *psf; + + psf = container_of(rp, struct ip_sf_socklist, rcu); + /* sk_omem_alloc should have been decreased by the caller*/ + kfree(psf); +} + static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { + struct ip_sf_socklist *psf = iml->sflist; int err; - if (iml->sflist == NULL) { + if (psf == NULL) { /* any-source empty exclude case */ return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, 0, NULL, 0); } err = ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, - iml->sfmode, iml->sflist->sl_count, - iml->sflist->sl_addr, 0); - sock_kfree_s(sk, iml->sflist, IP_SFLSIZE(iml->sflist->sl_max)); - iml->sflist = NULL; + iml->sfmode, psf->sl_count, psf->sl_addr, 0); + rcu_assign_pointer(iml->sflist, NULL); + /* decrease mem now to avoid the memleak warning */ + atomic_sub(IP_SFLSIZE(psf->sl_max), &sk->sk_omem_alloc); + call_rcu(&psf->rcu, ip_sf_socklist_reclaim); return err; } + +static void ip_mc_socklist_reclaim(struct rcu_head *rp) +{ + struct ip_mc_socklist *iml; + + iml = container_of(rp, struct ip_mc_socklist, rcu); + /* sk_omem_alloc should have been decreased by the caller*/ + kfree(iml); +} + + /* * Ask a socket to leave a group. */ @@ -1854,12 +1876,14 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) (void) ip_mc_leave_src(sk, iml, in_dev); - *imlp = iml->next; + rcu_assign_pointer(*imlp, iml->next); if (in_dev) ip_mc_dec_group(in_dev, group); rtnl_unlock(); - sock_kfree_s(sk, iml, sizeof(*iml)); + /* decrease mem now to avoid the memleak warning */ + atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); + call_rcu(&iml->rcu, ip_mc_socklist_reclaim); return 0; } if (!in_dev) @@ -1974,9 +1998,12 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct if (psl) { for (i=0; i<psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; - sock_kfree_s(sk, psl, IP_SFLSIZE(psl->sl_max)); + /* decrease mem now to avoid the memleak warning */ + atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); + call_rcu(&psl->rcu, ip_sf_socklist_reclaim); } - pmc->sflist = psl = newpsl; + rcu_assign_pointer(pmc->sflist, newpsl); + psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i=0; i<psl->sl_count; i++) { @@ -2072,11 +2099,13 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); - sock_kfree_s(sk, psl, IP_SFLSIZE(psl->sl_max)); + /* decrease mem now to avoid the memleak warning */ + atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); + call_rcu(&psl->rcu, ip_sf_socklist_reclaim); } else (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); - pmc->sflist = newpsl; + rcu_assign_pointer(pmc->sflist, newpsl); pmc->sfmode = msf->imsf_fmode; err = 0; done: @@ -2209,30 +2238,40 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) struct ip_mc_socklist *pmc; struct ip_sf_socklist *psl; int i; + int ret; + ret = 1; if (!ipv4_is_multicast(loc_addr)) - return 1; + goto out; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for (pmc=rcu_dereference(inet->mc_list); pmc; pmc=rcu_dereference(pmc->next)) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && pmc->multi.imr_ifindex == dif) break; } + ret = inet->mc_all; if (!pmc) - return inet->mc_all; + goto unlock; psl = pmc->sflist; + ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) - return pmc->sfmode == MCAST_EXCLUDE; + goto unlock; for (i=0; i<psl->sl_count; i++) { if (psl->sl_addr[i] == rmt_addr) break; } + ret = 0; if (pmc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) - return 0; + goto unlock; if (pmc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) - return 0; - return 1; + goto unlock; + ret = 1; +unlock: + rcu_read_unlock(); +out: + return ret; } /* @@ -2251,7 +2290,7 @@ void ip_mc_drop_socket(struct sock *sk) rtnl_lock(); while ((iml = inet->mc_list) != NULL) { struct in_device *in_dev; - inet->mc_list = iml->next; + rcu_assign_pointer(inet->mc_list, iml->next); in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); @@ -2259,7 +2298,9 @@ void ip_mc_drop_socket(struct sock *sk) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); in_dev_put(in_dev); } - sock_kfree_s(sk, iml, sizeof(*iml)); + /* decrease mem now to avoid the memleak warning */ + atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); + call_rcu(&iml->rcu, ip_mc_socklist_reclaim); } rtnl_unlock(); } @@ -2603,7 +2644,7 @@ static const struct file_operations igmp_mcf_seq_fops = { .release = seq_release_net, }; -static int igmp_net_init(struct net *net) +static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; @@ -2621,7 +2662,7 @@ out_igmp: return -ENOMEM; } -static void igmp_net_exit(struct net *net) +static void __net_exit igmp_net_exit(struct net *net) { proc_net_remove(net, "mcfilter"); proc_net_remove(net, "igmp"); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index ee16475..8da6429 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -529,6 +529,8 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, syn_ack_recalc(req, thresh, max_retries, queue->rskq_defer_accept, &expire, &resend); + if (req->rsk_ops->syn_ack_timeout) + req->rsk_ops->syn_ack_timeout(parent, req); if (!expire && (!resend || !req->rsk_ops->rtx_syn_ack(parent, req, NULL) || diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 86964b3..b59430b 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -32,6 +32,8 @@ #include <linux/netdevice.h> #include <linux/jhash.h> #include <linux/random.h> +#include <net/route.h> +#include <net/dst.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> @@ -205,11 +207,34 @@ static void ip_expire(unsigned long arg) if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) { struct sk_buff *head = qp->q.fragments; - /* Send an ICMP "Fragment Reassembly Timeout" message. */ rcu_read_lock(); head->dev = dev_get_by_index_rcu(net, qp->iif); - if (head->dev) - icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); + if (!head->dev) + goto out_rcu_unlock; + + /* + * Only search router table for the head fragment, + * when defraging timeout at PRE_ROUTING HOOK. + */ + if (qp->user == IP_DEFRAG_CONNTRACK_IN && !skb_dst(head)) { + const struct iphdr *iph = ip_hdr(head); + int err = ip_route_input(head, iph->daddr, iph->saddr, + iph->tos, head->dev); + if (unlikely(err)) + goto out_rcu_unlock; + + /* + * Only an end host needs to send an ICMP + * "Fragment Reassembly Timeout" message, per RFC792. + */ + if (skb_rtable(head)->rt_type != RTN_LOCAL) + goto out_rcu_unlock; + + } + + /* Send an ICMP "Fragment Reassembly Timeout" message. */ + icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); +out_rcu_unlock: rcu_read_unlock(); } out: @@ -646,7 +671,7 @@ static struct ctl_table ip4_frags_ctl_table[] = { { } }; -static int ip4_frags_ns_ctl_register(struct net *net) +static int __net_init ip4_frags_ns_ctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -676,7 +701,7 @@ err_alloc: return -ENOMEM; } -static void ip4_frags_ns_ctl_unregister(struct net *net) +static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net) { struct ctl_table *table; @@ -704,7 +729,7 @@ static inline void ip4_frags_ctl_register(void) } #endif -static int ipv4_frags_init_net(struct net *net) +static int __net_init ipv4_frags_init_net(struct net *net) { /* * Fragment cache limits. We will commit 256K at one time. Should we @@ -726,7 +751,7 @@ static int ipv4_frags_init_net(struct net *net) return ip4_frags_ns_ctl_register(net); } -static void ipv4_frags_exit_net(struct net *net) +static void __net_exit ipv4_frags_exit_net(struct net *net) { ip4_frags_ns_ctl_unregister(net); inet_frags_exit_net(&net->ipv4.frags, &ip4_frags); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f36ce15..7631b20 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1307,7 +1307,7 @@ static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head) } } -static int ipgre_init_net(struct net *net) +static int __net_init ipgre_init_net(struct net *net) { struct ipgre_net *ign = net_generic(net, ipgre_net_id); int err; @@ -1334,7 +1334,7 @@ err_alloc_dev: return err; } -static void ipgre_exit_net(struct net *net) +static void __net_exit ipgre_exit_net(struct net *net) { struct ipgre_net *ign; LIST_HEAD(list); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index cafad9b..644dc43 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -451,7 +451,8 @@ static int do_ip_setsockopt(struct sock *sk, int level, (1<<IP_TTL) | (1<<IP_HDRINCL) | (1<<IP_MTU_DISCOVER) | (1<<IP_RECVERR) | (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) | - (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT))) || + (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT) | + (1<<IP_MINTTL))) || optname == IP_MULTICAST_TTL || optname == IP_MULTICAST_ALL || optname == IP_MULTICAST_LOOP || @@ -936,6 +937,14 @@ mc_msf_out: inet->transparent = !!val; break; + case IP_MINTTL: + if (optlen < 1) + goto e_inval; + if (val < 0 || val > 255) + goto e_inval; + inet->min_ttl = val; + break; + default: err = -ENOPROTOOPT; break; @@ -1198,6 +1207,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_TRANSPARENT: val = inet->transparent; break; + case IP_MINTTL: + val = inet->min_ttl; + break; default: release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 38fbf04..b55a0c3 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -25,6 +25,7 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) { + struct net *net = dev_net(skb->dev); __be32 spi; struct iphdr *iph = (struct iphdr *)skb->data; struct ip_comp_hdr *ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); @@ -35,7 +36,7 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) return; spi = htonl(ntohs(ipch->cpi)); - x = xfrm_state_lookup(&init_net, (xfrm_address_t *)&iph->daddr, + x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET); if (!x) return; @@ -47,9 +48,10 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) /* We always hold one tunnel user reference to indicate a tunnel */ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) { + struct net *net = xs_net(x); struct xfrm_state *t; - t = xfrm_state_alloc(&init_net); + t = xfrm_state_alloc(net); if (t == NULL) goto out; @@ -82,10 +84,11 @@ error: */ static int ipcomp_tunnel_attach(struct xfrm_state *x) { + struct net *net = xs_net(x); int err = 0; struct xfrm_state *t; - t = xfrm_state_lookup(&init_net, (xfrm_address_t *)&x->id.daddr.a4, + t = xfrm_state_lookup(net, (xfrm_address_t *)&x->id.daddr.a4, x->props.saddr.a4, IPPROTO_IPIP, AF_INET); if (!t) { t = ipcomp_tunnel_create(x); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index eda04fe..95db732 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -130,7 +130,6 @@ struct ipip_net { struct net_device *fb_tunnel_dev; }; -static void ipip_fb_tunnel_init(struct net_device *dev); static void ipip_tunnel_init(struct net_device *dev); static void ipip_tunnel_setup(struct net_device *dev); @@ -730,7 +729,7 @@ static void ipip_tunnel_init(struct net_device *dev) ipip_tunnel_bind_dev(dev); } -static void ipip_fb_tunnel_init(struct net_device *dev) +static void __net_init ipip_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -773,7 +772,7 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head) } } -static int ipip_init_net(struct net *net) +static int __net_init ipip_init_net(struct net *net) { struct ipip_net *ipn = net_generic(net, ipip_net_id); int err; @@ -806,7 +805,7 @@ err_alloc_dev: return err; } -static void ipip_exit_net(struct net *net) +static void __net_exit ipip_exit_net(struct net *net) { struct ipip_net *ipn = net_generic(net, ipip_net_id); LIST_HEAD(list); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index f25542c..1b09a6d 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -127,8 +127,8 @@ static const struct snmp_mib snmp4_ipextstats_list[] = { SNMP_MIB_SENTINEL }; -static struct { - char *name; +static const struct { + const char *name; int index; } icmpmibmap[] = { { "DestUnreachs", ICMP_DEST_UNREACH }, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d62b05d..b16dfad 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1990,8 +1990,13 @@ static int __mkroute_input(struct sk_buff *skb, if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is * invalid for proxy arp. DNAT routes are always valid. + * + * Proxy arp feature have been extended to allow, ARP + * replies back to the same interface, to support + * Private VLAN switch technologies. See arp.c. */ - if (out_dev == in_dev) { + if (out_dev == in_dev && + IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) { err = -EINVAL; goto cleanup; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 66fd80e..5c24db4 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -358,7 +358,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, tcp_select_initial_window(tcp_full_space(sk), req->mss, &req->rcv_wnd, &req->window_clamp, - ireq->wscale_ok, &rcv_wscale); + ireq->wscale_ok, &rcv_wscale, + dst_metric(&rt->u.dst, RTAX_INITRWND)); ireq->rcv_wscale = rcv_wscale; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b0a26bb..d5d69ea 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -536,8 +536,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb) tp->nonagle &= ~TCP_NAGLE_PUSH; } -static inline void tcp_mark_urg(struct tcp_sock *tp, int flags, - struct sk_buff *skb) +static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) { if (flags & MSG_OOB) tp->snd_up = tp->write_seq; @@ -546,13 +545,13 @@ static inline void tcp_mark_urg(struct tcp_sock *tp, int flags, static inline void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle) { - struct tcp_sock *tp = tcp_sk(sk); - if (tcp_send_head(sk)) { - struct sk_buff *skb = tcp_write_queue_tail(sk); + struct tcp_sock *tp = tcp_sk(sk); + if (!(flags & MSG_MORE) || forced_push(tp)) - tcp_mark_push(tp, skb); - tcp_mark_urg(tp, flags, skb); + tcp_mark_push(tp, tcp_write_queue_tail(sk)); + + tcp_mark_urg(tp, flags); __tcp_push_pending_frames(sk, mss_now, (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle); } @@ -877,12 +876,12 @@ ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset, #define TCP_PAGE(sk) (sk->sk_sndmsg_page) #define TCP_OFF(sk) (sk->sk_sndmsg_off) -static inline int select_size(struct sock *sk) +static inline int select_size(struct sock *sk, int sg) { struct tcp_sock *tp = tcp_sk(sk); int tmp = tp->mss_cache; - if (sk->sk_route_caps & NETIF_F_SG) { + if (sg) { if (sk_can_gso(sk)) tmp = 0; else { @@ -906,7 +905,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, struct sk_buff *skb; int iovlen, flags; int mss_now, size_goal; - int err, copied; + int sg, err, copied; long timeo; lock_sock(sk); @@ -934,6 +933,8 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto out_err; + sg = sk->sk_route_caps & NETIF_F_SG; + while (--iovlen >= 0) { int seglen = iov->iov_len; unsigned char __user *from = iov->iov_base; @@ -959,8 +960,9 @@ new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; - skb = sk_stream_alloc_skb(sk, select_size(sk), - sk->sk_allocation); + skb = sk_stream_alloc_skb(sk, + select_size(sk, sg), + sk->sk_allocation); if (!skb) goto wait_for_memory; @@ -997,9 +999,7 @@ new_segment: /* We can extend the last page * fragment. */ merge = 1; - } else if (i == MAX_SKB_FRAGS || - (!i && - !(sk->sk_route_caps & NETIF_F_SG))) { + } else if (i == MAX_SKB_FRAGS || !sg) { /* Need to add new fragment and cannot * do this because interface is non-SG, * or because all the page slots are diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 65b8ebf..c3588b4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -742,9 +742,9 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, * This still operates on a request_sock only, not on a big * socket. */ -static int __tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, - struct request_sock *req, - struct request_values *rvp) +static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, + struct request_sock *req, + struct request_values *rvp) { const struct inet_request_sock *ireq = inet_rsk(req); int err = -1; @@ -775,10 +775,11 @@ static int __tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, return err; } -static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req, +static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { - return __tcp_v4_send_synack(sk, NULL, req, rvp); + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + return tcp_v4_send_synack(sk, NULL, req, rvp); } /* @@ -1192,10 +1193,11 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb) struct request_sock_ops tcp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct tcp_request_sock), - .rtx_syn_ack = tcp_v4_send_synack, + .rtx_syn_ack = tcp_v4_rtx_synack, .send_ack = tcp_v4_reqsk_send_ack, .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, + .syn_ack_timeout = tcp_syn_ack_timeout, }; #ifdef CONFIG_TCP_MD5SIG @@ -1373,8 +1375,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) } tcp_rsk(req)->snt_isn = isn; - if (__tcp_v4_send_synack(sk, dst, req, - (struct request_values *)&tmp_ext) || + if (tcp_v4_send_synack(sk, dst, req, + (struct request_values *)&tmp_ext) || want_cookie) goto drop_and_free; @@ -1649,6 +1651,9 @@ int tcp_v4_rcv(struct sk_buff *skb) if (!sk) goto no_tcp_socket; + if (iph->ttl < inet_sk(sk)->min_ttl) + goto discard_and_relse; + process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; @@ -2425,12 +2430,12 @@ static struct tcp_seq_afinfo tcp4_seq_afinfo = { }, }; -static int tcp4_proc_init_net(struct net *net) +static int __net_init tcp4_proc_init_net(struct net *net) { return tcp_proc_register(net, &tcp4_seq_afinfo); } -static void tcp4_proc_exit_net(struct net *net) +static void __net_exit tcp4_proc_exit_net(struct net *net) { tcp_proc_unregister(net, &tcp4_seq_afinfo); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 383ce23..4a1605d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -183,7 +183,8 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) */ void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, - int wscale_ok, __u8 *rcv_wscale) + int wscale_ok, __u8 *rcv_wscale, + __u32 init_rcv_wnd) { unsigned int space = (__space < 0 ? 0 : __space); @@ -232,7 +233,13 @@ void tcp_select_initial_window(int __space, __u32 mss, init_cwnd = 2; else if (mss > 1460) init_cwnd = 3; - if (*rcv_wnd > init_cwnd * mss) + /* when initializing use the value from init_rcv_wnd + * rather than the default from above + */ + if (init_rcv_wnd && + (*rcv_wnd > init_rcv_wnd * mss)) + *rcv_wnd = init_rcv_wnd * mss; + else if (*rcv_wnd > init_cwnd * mss) *rcv_wnd = init_cwnd * mss; } @@ -1794,11 +1801,6 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle) { - struct sk_buff *skb = tcp_send_head(sk); - - if (!skb) - return; - /* If we are closed, the bytes will have to remain here. * In time closedown will finish, we empty the write queue and * all will be happy. @@ -2422,7 +2424,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, &req->rcv_wnd, &req->window_clamp, ireq->wscale_ok, - &rcv_wscale); + &rcv_wscale, + dst_metric(dst, RTAX_INITRWND)); ireq->rcv_wscale = rcv_wscale; } @@ -2549,7 +2552,8 @@ static void tcp_connect_init(struct sock *sk) &tp->rcv_wnd, &tp->window_clamp, sysctl_tcp_window_scaling, - &rcv_wscale); + &rcv_wscale, + dst_metric(dst, RTAX_INITRWND)); tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 8816a20..de7d1bf 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -474,6 +474,12 @@ static void tcp_synack_timer(struct sock *sk) TCP_TIMEOUT_INIT, TCP_RTO_MAX); } +void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req) +{ + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); +} +EXPORT_SYMBOL(tcp_syn_ack_timeout); + void tcp_set_keepalive(struct sock *sk, int val) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f0126fd..4f7d212 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2027,12 +2027,12 @@ static struct udp_seq_afinfo udp4_seq_afinfo = { }, }; -static int udp4_proc_init_net(struct net *net) +static int __net_init udp4_proc_init_net(struct net *net) { return udp_proc_register(net, &udp4_seq_afinfo); } -static void udp4_proc_exit_net(struct net *net) +static void __net_exit udp4_proc_exit_net(struct net *net) { udp_proc_unregister(net, &udp4_seq_afinfo); } diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 66f7951..6610bf7 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -81,12 +81,12 @@ static struct udp_seq_afinfo udplite4_seq_afinfo = { }, }; -static int udplite4_proc_init_net(struct net *net) +static int __net_init udplite4_proc_init_net(struct net *net) { return udp_proc_register(net, &udplite4_seq_afinfo); } -static void udplite4_proc_exit_net(struct net *net) +static void __net_exit udplite4_proc_exit_net(struct net *net) { udp_proc_unregister(net, &udplite4_seq_afinfo); } |