diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/arp.c | 7 | ||||
-rw-r--r-- | net/ipv4/devinet.c | 2 | ||||
-rw-r--r-- | net/ipv4/fib_frontend.c | 9 | ||||
-rw-r--r-- | net/ipv4/igmp.c | 48 | ||||
-rw-r--r-- | net/ipv4/inet_timewait_sock.c | 1 | ||||
-rw-r--r-- | net/ipv4/ip_sockglue.c | 27 | ||||
-rw-r--r-- | net/ipv4/ip_tunnel.c | 15 | ||||
-rw-r--r-- | net/ipv4/ipconfig.c | 4 | ||||
-rw-r--r-- | net/ipv4/netfilter/arp_tables.c | 4 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_CLUSTERIP.c | 16 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 6 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_nat_h323.c | 57 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_nat_snmp_basic.c | 19 | ||||
-rw-r--r-- | net/ipv4/raw.c | 15 | ||||
-rw-r--r-- | net/ipv4/route.c | 8 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 17 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 23 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_timer.c | 15 | ||||
-rw-r--r-- | net/ipv4/tcp_vegas.c | 2 | ||||
-rw-r--r-- | net/ipv4/udp.c | 5 |
21 files changed, 188 insertions, 114 deletions
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 740483aa1a62..5133f2a6aaf1 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -221,11 +221,16 @@ static bool arp_key_eq(const struct neighbour *neigh, const void *pkey) static int arp_constructor(struct neighbour *neigh) { - __be32 addr = *(__be32 *)neigh->primary_key; + __be32 addr; struct net_device *dev = neigh->dev; struct in_device *in_dev; struct neigh_parms *parms; + u32 inaddr_any = INADDR_ANY; + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len); + + addr = *(__be32 *)neigh->primary_key; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a57056d87a43..1d2fba4aeeb2 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1359,7 +1359,7 @@ skip: static bool inetdev_valid_mtu(unsigned int mtu) { - return mtu >= 68; + return mtu >= IPV4_MIN_MTU; } static void inetdev_send_gratuitous_arp(struct net_device *dev, diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index a8db70b7fe45..5095491e6141 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1181,7 +1181,7 @@ fail: static void ip_fib_net_exit(struct net *net) { - unsigned int i; + int i; rtnl_lock(); #ifdef CONFIG_IP_MULTIPLE_TABLES @@ -1189,7 +1189,12 @@ static void ip_fib_net_exit(struct net *net) RCU_INIT_POINTER(net->ipv4.fib_main, NULL); RCU_INIT_POINTER(net->ipv4.fib_default, NULL); #endif - for (i = 0; i < FIB_TABLE_HASHSZ; i++) { + /* Destroy the tables in reverse order to guarantee that the + * local table, ID 255, is destroyed before the main table, ID + * 254. This is necessary as the local table may contain + * references to data contained in the main table. + */ + for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) { struct hlist_head *head = &net->ipv4.fib_table_hash[i]; struct hlist_node *tmp; struct fib_table *tb; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index e2d3d62297ec..c17485bcb18a 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -89,6 +89,7 @@ #include <linux/rtnetlink.h> #include <linux/times.h> #include <linux/pkt_sched.h> +#include <linux/byteorder/generic.h> #include <net/net_namespace.h> #include <net/arp.h> @@ -319,6 +320,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) return scount; } +/* source address selection per RFC 3376 section 4.2.13 */ +static __be32 igmpv3_get_srcaddr(struct net_device *dev, + const struct flowi4 *fl4) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + + if (!in_dev) + return htonl(INADDR_ANY); + + for_ifa(in_dev) { + if (fl4->saddr == ifa->ifa_local) + return fl4->saddr; + } endfor_ifa(in_dev); + + return htonl(INADDR_ANY); +} + static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; @@ -366,7 +384,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; - pip->saddr = fl4.saddr; + + rcu_read_lock(); + pip->saddr = igmpv3_get_srcaddr(dev, &fl4); + rcu_read_unlock(); + pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); @@ -402,16 +424,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, - int type, struct igmpv3_grec **ppgr) + int type, struct igmpv3_grec **ppgr, unsigned int mtu) { struct net_device *dev = pmc->interface->dev; struct igmpv3_report *pih; struct igmpv3_grec *pgr; - if (!skb) - skb = igmpv3_newpack(dev, dev->mtu); - if (!skb) - return NULL; + if (!skb) { + skb = igmpv3_newpack(dev, mtu); + if (!skb) + return NULL; + } pgr = (struct igmpv3_grec *)skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; @@ -433,10 +456,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; + unsigned int mtu; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; + mtu = READ_ONCE(dev->mtu); + if (mtu < IPV4_MIN_MTU) + return skb; + isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; truncate = type == IGMPV3_MODE_IS_EXCLUDE || @@ -457,7 +485,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) igmpv3_sendpack(skb); - skb = igmpv3_newpack(dev, dev->mtu); + skb = igmpv3_newpack(dev, mtu); } } first = 1; @@ -484,12 +512,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, pgr->grec_nsrcs = htons(scount); if (skb) igmpv3_sendpack(skb); - skb = igmpv3_newpack(dev, dev->mtu); + skb = igmpv3_newpack(dev, mtu); first = 1; scount = 0; } if (first) { - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) @@ -523,7 +551,7 @@ empty_source: igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } - skb = add_grhead(skb, pmc, type, &pgr); + skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index bb96c1c4edd6..35ea352a9cef 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -212,6 +212,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, tw->tw_dport = inet->inet_dport; tw->tw_family = sk->sk_family; tw->tw_reuse = sk->sk_reuse; + tw->tw_reuseport = sk->sk_reuseport; tw->tw_hash = sk->sk_hash; tw->tw_ipv6only = 0; tw->tw_transparent = inet->transparent; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b6c7bdea4853..d4bdeed4e0a4 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -239,7 +239,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) return -EINVAL; - ipc->oif = src_info->ipi6_ifindex; + if (src_info->ipi6_ifindex) + ipc->oif = src_info->ipi6_ifindex; ipc->addr = src_info->ipi6_addr.s6_addr32[3]; continue; } @@ -262,7 +263,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo))) return -EINVAL; info = (struct in_pktinfo *)CMSG_DATA(cmsg); - ipc->oif = info->ipi_ifindex; + if (info->ipi_ifindex) + ipc->oif = info->ipi_ifindex; ipc->addr = info->ipi_spec_dst.s_addr; break; } @@ -1203,11 +1205,8 @@ int ip_setsockopt(struct sock *sk, int level, if (err == -ENOPROTOOPT && optname != IP_HDRINCL && optname != IP_IPSEC_POLICY && optname != IP_XFRM_POLICY && - !ip_mroute_opt(optname)) { - lock_sock(sk); + !ip_mroute_opt(optname)) err = nf_setsockopt(sk, PF_INET, optname, optval, optlen); - release_sock(sk); - } #endif return err; } @@ -1232,12 +1231,9 @@ int compat_ip_setsockopt(struct sock *sk, int level, int optname, if (err == -ENOPROTOOPT && optname != IP_HDRINCL && optname != IP_IPSEC_POLICY && optname != IP_XFRM_POLICY && - !ip_mroute_opt(optname)) { - lock_sock(sk); - err = compat_nf_setsockopt(sk, PF_INET, optname, - optval, optlen); - release_sock(sk); - } + !ip_mroute_opt(optname)) + err = compat_nf_setsockopt(sk, PF_INET, optname, optval, + optlen); #endif return err; } @@ -1497,10 +1493,7 @@ int ip_getsockopt(struct sock *sk, int level, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); - err = nf_getsockopt(sk, PF_INET, optname, optval, - &len); - release_sock(sk); + err = nf_getsockopt(sk, PF_INET, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); return err; @@ -1532,9 +1525,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); err = compat_nf_getsockopt(sk, PF_INET, optname, optval, &len); - release_sock(sk); if (err >= 0) err = put_user(len, optlen); return err; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 35080a708b59..2385ec7083c6 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -301,13 +301,14 @@ static struct net_device *__ip_tunnel_create(struct net *net, struct net_device *dev; char name[IFNAMSIZ]; - if (parms->name[0]) + err = -E2BIG; + if (parms->name[0]) { + if (!dev_valid_name(parms->name)) + goto failed; strlcpy(name, parms->name, IFNAMSIZ); - else { - if (strlen(ops->kind) > (IFNAMSIZ - 3)) { - err = -E2BIG; + } else { + if (strlen(ops->kind) > (IFNAMSIZ - 3)) goto failed; - } strlcpy(name, ops->kind, IFNAMSIZ); strncat(name, "%d", 2); } @@ -393,8 +394,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev) dev->needed_headroom = t_hlen + hlen; mtu -= (dev->hard_header_len + t_hlen); - if (mtu < 68) - mtu = 68; + if (mtu < IPV4_MIN_MTU) + mtu = IPV4_MIN_MTU; return mtu; } diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 8e7328c6a390..6389616ccc3f 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -148,7 +148,11 @@ static char vendor_class_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 */ diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index ebf5821caefb..7510a851d316 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1330,8 +1330,8 @@ static int translate_compat_table(struct xt_table_info **pinfo, newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - newinfo->hook_entry[i] = info->hook_entry[i]; - newinfo->underflow[i] = info->underflow[i]; + newinfo->hook_entry[i] = compatr->hook_entry[i]; + newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries[raw_smp_processor_id()]; pos = entry1; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 771ab3d01ad3..d098013855f0 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -365,7 +365,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) struct ipt_clusterip_tgt_info *cipinfo = par->targinfo; const struct ipt_entry *e = par->entryinfo; struct clusterip_config *config; - int ret; + int ret, i; if (cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP && cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT && @@ -379,8 +379,18 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) pr_info("Please specify destination IP\n"); return -EINVAL; } - - /* FIXME: further sanity checks */ + if (cipinfo->num_local_nodes > ARRAY_SIZE(cipinfo->local_nodes)) { + pr_info("bad num_local_nodes %u\n", cipinfo->num_local_nodes); + return -EINVAL; + } + for (i = 0; i < cipinfo->num_local_nodes; i++) { + if (cipinfo->local_nodes[i] - 1 >= + sizeof(config->local_nodes) * 8) { + pr_info("bad local_nodes[%d] %u\n", + i, cipinfo->local_nodes[i]); + return -EINVAL; + } + } config = clusterip_config_find_get(par->net, e->ip.dst.s_addr, 1); if (!config) { diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 30ad9554b5e9..406d69f033ac 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -261,15 +261,19 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) struct nf_conntrack_tuple tuple; memset(&tuple, 0, sizeof(tuple)); + + lock_sock(sk); tuple.src.u3.ip = inet->inet_rcv_saddr; tuple.src.u.tcp.port = inet->inet_sport; tuple.dst.u3.ip = inet->inet_daddr; tuple.dst.u.tcp.port = inet->inet_dport; tuple.src.l3num = PF_INET; tuple.dst.protonum = sk->sk_protocol; + release_sock(sk); /* We only do TCP and SCTP at the moment: is there a better way? */ - if (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_SCTP) { + if (tuple.dst.protonum != IPPROTO_TCP && + tuple.dst.protonum != IPPROTO_SCTP) { pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n"); return -ENOPROTOOPT; } diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 574f7ebba0b6..ac8342dcb55e 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -252,16 +252,16 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, if (set_h245_addr(skb, protoff, data, dataoff, taddr, &ct->tuplehash[!dir].tuple.dst.u3, htons((port & htons(1)) ? nated_port + 1 : - nated_port)) == 0) { - /* Save ports */ - info->rtp_port[i][dir] = rtp_port; - info->rtp_port[i][!dir] = htons(nated_port); - } else { + nated_port))) { nf_ct_unexpect_related(rtp_exp); nf_ct_unexpect_related(rtcp_exp); return -1; } + /* Save ports */ + info->rtp_port[i][dir] = rtp_port; + info->rtp_port[i][!dir] = htons(nated_port); + /* Success */ pr_debug("nf_nat_h323: expect RTP %pI4:%hu->%pI4:%hu\n", &rtp_exp->tuple.src.u3.ip, @@ -370,15 +370,15 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, /* Modify signal */ if (set_h225_addr(skb, protoff, data, dataoff, taddr, &ct->tuplehash[!dir].tuple.dst.u3, - htons(nated_port)) == 0) { - /* Save ports */ - info->sig_port[dir] = port; - info->sig_port[!dir] = htons(nated_port); - } else { + htons(nated_port))) { nf_ct_unexpect_related(exp); return -1; } + /* Save ports */ + info->sig_port[dir] = port; + info->sig_port[!dir] = htons(nated_port); + pr_debug("nf_nat_q931: expect H.245 %pI4:%hu->%pI4:%hu\n", &exp->tuple.src.u3.ip, ntohs(exp->tuple.src.u.tcp.port), @@ -462,24 +462,27 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, /* Modify signal */ if (set_h225_addr(skb, protoff, data, 0, &taddr[idx], &ct->tuplehash[!dir].tuple.dst.u3, - htons(nated_port)) == 0) { - /* Save ports */ - info->sig_port[dir] = port; - info->sig_port[!dir] = htons(nated_port); - - /* Fix for Gnomemeeting */ - if (idx > 0 && - get_h225_addr(ct, *data, &taddr[0], &addr, &port) && - (ntohl(addr.ip) & 0xff000000) == 0x7f000000) { - set_h225_addr(skb, protoff, data, 0, &taddr[0], - &ct->tuplehash[!dir].tuple.dst.u3, - info->sig_port[!dir]); - } - } else { + htons(nated_port))) { nf_ct_unexpect_related(exp); return -1; } + /* Save ports */ + info->sig_port[dir] = port; + info->sig_port[!dir] = htons(nated_port); + + /* Fix for Gnomemeeting */ + if (idx > 0 && + get_h225_addr(ct, *data, &taddr[0], &addr, &port) && + (ntohl(addr.ip) & 0xff000000) == 0x7f000000) { + if (set_h225_addr(skb, protoff, data, 0, &taddr[0], + &ct->tuplehash[!dir].tuple.dst.u3, + info->sig_port[!dir])) { + nf_ct_unexpect_related(exp); + return -1; + } + } + /* Success */ pr_debug("nf_nat_ras: expect Q.931 %pI4:%hu->%pI4:%hu\n", &exp->tuple.src.u3.ip, @@ -550,9 +553,9 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, } /* Modify signal */ - if (!set_h225_addr(skb, protoff, data, dataoff, taddr, - &ct->tuplehash[!dir].tuple.dst.u3, - htons(nated_port)) == 0) { + if (set_h225_addr(skb, protoff, data, dataoff, taddr, + &ct->tuplehash[!dir].tuple.dst.u3, + htons(nated_port))) { nf_ct_unexpect_related(exp); return -1; } diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index cc626e1b06d3..64a8bbc06f23 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1260,16 +1260,6 @@ static const struct nf_conntrack_expect_policy snmp_exp_policy = { .timeout = 180, }; -static struct nf_conntrack_helper snmp_helper __read_mostly = { - .me = THIS_MODULE, - .help = help, - .expect_policy = &snmp_exp_policy, - .name = "snmp", - .tuple.src.l3num = AF_INET, - .tuple.src.u.udp.port = cpu_to_be16(SNMP_PORT), - .tuple.dst.protonum = IPPROTO_UDP, -}; - static struct nf_conntrack_helper snmp_trap_helper __read_mostly = { .me = THIS_MODULE, .help = help, @@ -1288,17 +1278,10 @@ static struct nf_conntrack_helper snmp_trap_helper __read_mostly = { static int __init nf_nat_snmp_basic_init(void) { - int ret = 0; - BUG_ON(nf_nat_snmp_hook != NULL); RCU_INIT_POINTER(nf_nat_snmp_hook, help); - ret = nf_conntrack_helper_register(&snmp_trap_helper); - if (ret < 0) { - nf_conntrack_helper_unregister(&snmp_helper); - return ret; - } - return ret; + return nf_conntrack_helper_register(&snmp_trap_helper); } static void __exit nf_nat_snmp_basic_fini(void) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 9a2294d01b9d..acf09ab17a62 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -496,11 +496,16 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int err; struct ip_options_data opt_copy; struct raw_frag_vec rfv; + int hdrincl; err = -EMSGSIZE; if (len > 0xFFFF) goto out; + /* hdrincl should be READ_ONCE(inet->hdrincl) + * but READ_ONCE() doesn't work with bit fields + */ + hdrincl = inet->hdrincl; /* * Check the flags. */ @@ -575,7 +580,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* Linux does not mangle headers on raw sockets, * so that IP options + IP_HDRINCL is non-sense. */ - if (inet->hdrincl) + if (hdrincl) goto done; if (ipc.opt->opt.srr) { if (!daddr) @@ -597,12 +602,12 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, - inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk) | - (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), + (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0); - if (!inet->hdrincl) { + if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; @@ -627,7 +632,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto do_confirm; back_from_confirm: - if (inet->hdrincl) + if (hdrincl) err = raw_send_hdrinc(sk, &fl4, msg, len, &rt, msg->msg_flags); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6a9a495aff23..7a6400345cb9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -122,10 +122,13 @@ static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; -static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; +static u32 ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; + +static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; + /* * Interface to generic destination cache. */ @@ -2689,7 +2692,8 @@ static struct ctl_table ipv4_route_table[] = { .data = &ip_rt_min_pmtu, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &ip_min_valid_pmtu, }, { .procname = "min_adv_mss", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a1de8300cfce..07d65ae018ee 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2137,6 +2137,9 @@ adjudge_to_death: tcp_send_active_reset(sk, GFP_ATOMIC); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); + } else if (!check_net(sock_net(sk))) { + /* Not possible to send reset; just close */ + tcp_set_state(sk, TCP_CLOSE); } } @@ -2232,6 +2235,12 @@ int tcp_disconnect(struct sock *sk, int flags) WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; + } + sk->sk_error_report(sk); return err; } @@ -2407,7 +2416,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_REPAIR_QUEUE: if (!tp->repair) err = -EPERM; - else if (val < TCP_QUEUES_NR) + else if ((unsigned int)val < TCP_QUEUES_NR) tp->repair_queue = val; else err = -EINVAL; @@ -2539,8 +2548,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: - /* Read the IP->Key mappings from userspace */ - err = tp->af_specific->md5_parse(sk, optval, optlen); + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + err = tp->af_specific->md5_parse(sk, optval, optlen); + else + err = -EINVAL; break; #endif case TCP_USER_TIMEOUT: diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4763c431f7d8..d61371cefaf0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3819,11 +3819,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) int length = (th->doff << 2) - sizeof(*th); const u8 *ptr = (const u8 *)(th + 1); - /* If the TCP option is too short, we can short cut */ - if (length < TCPOLEN_MD5SIG) - return NULL; - - while (length > 0) { + /* If not enough data remaining, we can short cut */ + while (length >= TCPOLEN_MD5SIG) { int opcode = *ptr++; int opsize; @@ -5417,10 +5414,6 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) else tp->pred_flags = 0; - if (!sock_flag(sk, SOCK_DEAD)) { - sk->sk_state_change(sk); - sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); - } } static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, @@ -5484,6 +5477,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_cookie foc = { .len = -1 }; int saved_clamp = tp->rx_opt.mss_clamp; + bool fastopen_fail; tcp_parse_options(skb, &tp->rx_opt, 0, &foc); if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) @@ -5586,10 +5580,15 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_finish_connect(sk, skb); - if ((tp->syn_fastopen || tp->syn_data) && - tcp_rcv_fastopen_synack(sk, skb, &foc)) - return -1; + fastopen_fail = (tp->syn_fastopen || tp->syn_data) && + tcp_rcv_fastopen_synack(sk, skb, &foc); + if (!sock_flag(sk, SOCK_DEAD)) { + sk->sk_state_change(sk); + sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); + } + if (fastopen_fail) + return -1; if (sk->sk_write_pending || icsk->icsk_accept_queue.rskq_defer_accept || icsk->icsk_ack.pingpong) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2923f7f7932a..38e9dc5b735d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -814,7 +814,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, tcp_time_stamp, req->ts_recent, 0, - tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, + tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index f8c6b2343301..4a3f230ef91b 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -46,11 +46,19 @@ static void tcp_write_err(struct sock *sk) * to prevent DoS attacks. It is called when a retransmission timeout * or zero probe timeout occurs on orphaned socket. * + * Also close if our net namespace is exiting; in that case there is no + * hope of ever communicating again since all netns interfaces are already + * down (or about to be down), and we need to release our dst references, + * which have been moved to the netns loopback interface, so the namespace + * can finish exiting. This condition is only possible if we are a kernel + * socket, as those do not hold references to the namespace. + * * Criteria is still not confirmed experimentally and may change. * We kill the socket, if: * 1. If number of orphaned sockets exceeds an administratively configured * limit. * 2. If we have strong memory pressure. + * 3. If our net namespace is exiting. */ static int tcp_out_of_resources(struct sock *sk, bool do_reset) { @@ -79,6 +87,13 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; } + + if (!check_net(sock_net(sk))) { + /* Not possible to send reset; just close */ + tcp_done(sk); + return 1; + } + return 0; } diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index a6cea1d5e20d..33c0879612f5 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -158,7 +158,7 @@ EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event); static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp) { - return min(tp->snd_ssthresh, tp->snd_cwnd-1); + return min(tp->snd_ssthresh, tp->snd_cwnd); } static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e0fed822855d..ed6eca1c7cdf 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1733,6 +1733,11 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, err = udplite_checksum_init(skb, uh); if (err) return err; + + if (UDP_SKB_CB(skb)->partial_cov) { + skb->csum = inet_compute_pseudo(skb, proto); + return 0; + } } return skb_checksum_init_zero_check(skb, proto, uh->check, |