diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/fib_rules.c | 27 | ||||
-rw-r--r-- | net/ipv4/icmp.c | 2 | ||||
-rw-r--r-- | net/ipv4/inet_hashtables.c | 2 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 6 | ||||
-rw-r--r-- | net/ipv4/netfilter/arp_tables.c | 6 | ||||
-rw-r--r-- | net/ipv4/netfilter/ip_conntrack_core.c | 4 | ||||
-rw-r--r-- | net/ipv4/netfilter/ip_conntrack_helper_h323.c | 4 | ||||
-rw-r--r-- | net/ipv4/netfilter/ip_conntrack_netlink.c | 72 | ||||
-rw-r--r-- | net/ipv4/netfilter/ip_nat_standalone.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/ip_tables.c | 15 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 1 | ||||
-rw-r--r-- | net/ipv4/route.c | 45 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 28 |
13 files changed, 136 insertions, 78 deletions
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 768e8f5d7daa..ec566f3e66c7 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -104,6 +104,8 @@ static struct hlist_head fib_rules; /* writer func called from netlink -- rtnl_sem hold*/ +static void rtmsg_rule(int, struct fib_rule *); + int inet_rtm_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { struct rtattr **rta = arg; @@ -131,6 +133,7 @@ int inet_rtm_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) hlist_del_rcu(&r->hlist); r->r_dead = 1; + rtmsg_rule(RTM_DELRULE, r); fib_rule_put(r); err = 0; break; @@ -253,6 +256,7 @@ int inet_rtm_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) else hlist_add_before_rcu(&new_r->hlist, &r->hlist); + rtmsg_rule(RTM_NEWRULE, new_r); return 0; } @@ -382,14 +386,14 @@ static struct notifier_block fib_rules_notifier = { static __inline__ int inet_fill_rule(struct sk_buff *skb, struct fib_rule *r, - struct netlink_callback *cb, + u32 pid, u32 seq, int event, unsigned int flags) { struct rtmsg *rtm; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWRULE, sizeof(*rtm), flags); + nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*rtm), flags); rtm = NLMSG_DATA(nlh); rtm->rtm_family = AF_INET; rtm->rtm_dst_len = r->r_dst_len; @@ -430,6 +434,21 @@ rtattr_failure: /* callers should hold rtnl semaphore */ +static void rtmsg_rule(int event, struct fib_rule *r) +{ + int size = NLMSG_SPACE(sizeof(struct rtmsg) + 128); + struct sk_buff *skb = alloc_skb(size, GFP_KERNEL); + + if (!skb) + netlink_set_err(rtnl, 0, RTNLGRP_IPV4_RULE, ENOBUFS); + else if (inet_fill_rule(skb, r, 0, 0, event, 0) < 0) { + kfree_skb(skb); + netlink_set_err(rtnl, 0, RTNLGRP_IPV4_RULE, EINVAL); + } else { + netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV4_RULE, GFP_KERNEL); + } +} + int inet_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) { int idx = 0; @@ -442,7 +461,9 @@ int inet_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) if (idx < s_idx) continue; - if (inet_fill_rule(skb, r, cb, NLM_F_MULTI) < 0) + if (inet_fill_rule(skb, r, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWRULE, NLM_F_MULTI) < 0) break; idx++; } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index e7bbff4340bb..9831fd2c73a0 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -753,7 +753,7 @@ static void icmp_redirect(struct sk_buff *skb) case ICMP_REDIR_HOST: case ICMP_REDIR_HOSTTOS: ip_rt_redirect(skb->nh.iph->saddr, ip, skb->h.icmph->un.gateway, - iph->saddr, iph->tos, skb->dev); + iph->saddr, skb->dev); break; } out: diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 33228115cda4..ef7366fc132f 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -315,7 +315,7 @@ ok: spin_unlock(&head->lock); if (tw) { - inet_twsk_deschedule(tw, death_row);; + inet_twsk_deschedule(tw, death_row); inet_twsk_put(tw); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8ee4d016740d..f75ff1d96551 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1249,11 +1249,7 @@ int ip_push_pending_frames(struct sock *sk) iph->tos = inet->tos; iph->tot_len = htons(skb->len); iph->frag_off = df; - if (!df) { - __ip_select_ident(iph, &rt->u.dst, 0); - } else { - iph->id = htons(inet->id++); - } + ip_select_ident(iph, &rt->u.dst, sk); iph->ttl = ttl; iph->protocol = sk->sk_protocol; iph->saddr = rt->rt_src; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index f7efb3f27bf5..ff0c594a4198 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1146,12 +1146,14 @@ void arpt_unregister_table(struct arpt_table *table) static struct arpt_target arpt_standard_target = { .name = ARPT_STANDARD_TARGET, .targetsize = sizeof(int), + .family = NF_ARP, }; static struct arpt_target arpt_error_target = { .name = ARPT_ERROR_TARGET, .target = arpt_error, .targetsize = ARPT_FUNCTION_MAXNAMELEN, + .family = NF_ARP, }; static struct nf_sockopt_ops arpt_sockopts = { @@ -1171,8 +1173,8 @@ static int __init init(void) xt_proto_init(NF_ARP); /* Noone else will be downing sem now, so we won't sleep */ - xt_register_target(NF_ARP, &arpt_standard_target); - xt_register_target(NF_ARP, &arpt_error_target); + xt_register_target(&arpt_standard_target); + xt_register_target(&arpt_error_target); /* Register setsockopt */ ret = nf_register_sockopt(&arpt_sockopts); diff --git a/net/ipv4/netfilter/ip_conntrack_core.c b/net/ipv4/netfilter/ip_conntrack_core.c index 84c66dbfedaf..9e34034729a6 100644 --- a/net/ipv4/netfilter/ip_conntrack_core.c +++ b/net/ipv4/netfilter/ip_conntrack_core.c @@ -77,8 +77,8 @@ unsigned int ip_ct_log_invalid; static LIST_HEAD(unconfirmed); static int ip_conntrack_vmalloc; -static unsigned int ip_conntrack_next_id = 1; -static unsigned int ip_conntrack_expect_next_id = 1; +static unsigned int ip_conntrack_next_id; +static unsigned int ip_conntrack_expect_next_id; #ifdef CONFIG_IP_NF_CONNTRACK_EVENTS struct notifier_block *ip_conntrack_chain; struct notifier_block *ip_conntrack_expect_chain; diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323.c b/net/ipv4/netfilter/ip_conntrack_helper_h323.c index 20da6730b860..daeb1395faa4 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_h323.c +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323.c @@ -639,8 +639,8 @@ void ip_conntrack_h245_expect(struct ip_conntrack *new, } /****************************************************************************/ -static int get_h225_addr(unsigned char *data, TransportAddress * addr, - u_int32_t * ip, u_int16_t * port) +int get_h225_addr(unsigned char *data, TransportAddress * addr, + u_int32_t * ip, u_int16_t * port) { unsigned char *p; diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c index 5ce2e3fc2c7f..9b6e19bae90f 100644 --- a/net/ipv4/netfilter/ip_conntrack_netlink.c +++ b/net/ipv4/netfilter/ip_conntrack_netlink.c @@ -4,7 +4,7 @@ * (C) 2001 by Jay Schulist <jschlst@samba.org> * (C) 2002-2005 by Harald Welte <laforge@gnumonks.org> * (C) 2003 by Patrick Mchardy <kaber@trash.net> - * (C) 2005 by Pablo Neira Ayuso <pablo@eurodev.net> + * (C) 2005-2006 by Pablo Neira Ayuso <pablo@eurodev.net> * * I've reworked this stuff to use attributes instead of conntrack * structures. 5.44 am. I need more tea. --pablo 05/07/11. @@ -53,20 +53,18 @@ static char __initdata version[] = "0.90"; static inline int ctnetlink_dump_tuples_proto(struct sk_buff *skb, - const struct ip_conntrack_tuple *tuple) + const struct ip_conntrack_tuple *tuple, + struct ip_conntrack_protocol *proto) { - struct ip_conntrack_protocol *proto; int ret = 0; + struct nfattr *nest_parms = NFA_NEST(skb, CTA_TUPLE_PROTO); NFA_PUT(skb, CTA_PROTO_NUM, sizeof(u_int8_t), &tuple->dst.protonum); - /* If no protocol helper is found, this function will return the - * generic protocol helper, so proto won't *ever* be NULL */ - proto = ip_conntrack_proto_find_get(tuple->dst.protonum); if (likely(proto->tuple_to_nfattr)) ret = proto->tuple_to_nfattr(skb, tuple); - ip_conntrack_proto_put(proto); + NFA_NEST_END(skb, nest_parms); return ret; @@ -75,28 +73,41 @@ nfattr_failure: } static inline int -ctnetlink_dump_tuples(struct sk_buff *skb, - const struct ip_conntrack_tuple *tuple) +ctnetlink_dump_tuples_ip(struct sk_buff *skb, + const struct ip_conntrack_tuple *tuple) { - struct nfattr *nest_parms; - int ret; + struct nfattr *nest_parms = NFA_NEST(skb, CTA_TUPLE_IP); - nest_parms = NFA_NEST(skb, CTA_TUPLE_IP); NFA_PUT(skb, CTA_IP_V4_SRC, sizeof(u_int32_t), &tuple->src.ip); NFA_PUT(skb, CTA_IP_V4_DST, sizeof(u_int32_t), &tuple->dst.ip); - NFA_NEST_END(skb, nest_parms); - nest_parms = NFA_NEST(skb, CTA_TUPLE_PROTO); - ret = ctnetlink_dump_tuples_proto(skb, tuple); NFA_NEST_END(skb, nest_parms); - return ret; + return 0; nfattr_failure: return -1; } static inline int +ctnetlink_dump_tuples(struct sk_buff *skb, + const struct ip_conntrack_tuple *tuple) +{ + int ret; + struct ip_conntrack_protocol *proto; + + ret = ctnetlink_dump_tuples_ip(skb, tuple); + if (unlikely(ret < 0)) + return ret; + + proto = ip_conntrack_proto_find_get(tuple->dst.protonum); + ret = ctnetlink_dump_tuples_proto(skb, tuple, proto); + ip_conntrack_proto_put(proto); + + return ret; +} + +static inline int ctnetlink_dump_status(struct sk_buff *skb, const struct ip_conntrack *ct) { u_int32_t status = htonl((u_int32_t) ct->status); @@ -1135,6 +1146,33 @@ nfattr_failure: } static inline int +ctnetlink_exp_dump_mask(struct sk_buff *skb, + const struct ip_conntrack_tuple *tuple, + const struct ip_conntrack_tuple *mask) +{ + int ret; + struct ip_conntrack_protocol *proto; + struct nfattr *nest_parms = NFA_NEST(skb, CTA_EXPECT_MASK); + + ret = ctnetlink_dump_tuples_ip(skb, mask); + if (unlikely(ret < 0)) + goto nfattr_failure; + + proto = ip_conntrack_proto_find_get(tuple->dst.protonum); + ret = ctnetlink_dump_tuples_proto(skb, mask, proto); + ip_conntrack_proto_put(proto); + if (unlikely(ret < 0)) + goto nfattr_failure; + + NFA_NEST_END(skb, nest_parms); + + return 0; + +nfattr_failure: + return -1; +} + +static inline int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct ip_conntrack_expect *exp) { @@ -1144,7 +1182,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, if (ctnetlink_exp_dump_tuple(skb, &exp->tuple, CTA_EXPECT_TUPLE) < 0) goto nfattr_failure; - if (ctnetlink_exp_dump_tuple(skb, &exp->mask, CTA_EXPECT_MASK) < 0) + if (ctnetlink_exp_dump_mask(skb, &exp->tuple, &exp->mask) < 0) goto nfattr_failure; if (ctnetlink_exp_dump_tuple(skb, &master->tuplehash[IP_CT_DIR_ORIGINAL].tuple, diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index ab1f88fa21ec..380aef3d7865 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -394,7 +394,7 @@ static int init_or_cleanup(int init) ret = nf_register_hook(&ip_nat_local_out_ops); if (ret < 0) { printk("ip_nat_init: can't register local out hook.\n"); - goto cleanup_adjustout_ops;; + goto cleanup_adjustout_ops; } ret = nf_register_hook(&ip_nat_local_in_ops); if (ret < 0) { diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 39705f9bc154..a7b194c4d79d 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1335,12 +1335,14 @@ icmp_checkentry(const char *tablename, static struct ipt_target ipt_standard_target = { .name = IPT_STANDARD_TARGET, .targetsize = sizeof(int), + .family = AF_INET, }; static struct ipt_target ipt_error_target = { .name = IPT_ERROR_TARGET, .target = ipt_error, .targetsize = IPT_FUNCTION_MAXNAMELEN, + .family = AF_INET, }; static struct nf_sockopt_ops ipt_sockopts = { @@ -1358,6 +1360,7 @@ static struct ipt_match icmp_matchstruct = { .match = icmp_match, .matchsize = sizeof(struct ipt_icmp), .proto = IPPROTO_ICMP, + .family = AF_INET, .checkentry = icmp_checkentry, }; @@ -1368,9 +1371,9 @@ static int __init init(void) xt_proto_init(AF_INET); /* Noone else will be downing sem now, so we won't sleep */ - xt_register_target(AF_INET, &ipt_standard_target); - xt_register_target(AF_INET, &ipt_error_target); - xt_register_match(AF_INET, &icmp_matchstruct); + xt_register_target(&ipt_standard_target); + xt_register_target(&ipt_error_target); + xt_register_match(&icmp_matchstruct); /* Register setsockopt */ ret = nf_register_sockopt(&ipt_sockopts); @@ -1387,9 +1390,9 @@ static void __exit fini(void) { nf_unregister_sockopt(&ipt_sockopts); - xt_unregister_match(AF_INET, &icmp_matchstruct); - xt_unregister_target(AF_INET, &ipt_error_target); - xt_unregister_target(AF_INET, &ipt_standard_target); + xt_unregister_match(&icmp_matchstruct); + xt_unregister_target(&ipt_error_target); + xt_unregister_target(&ipt_standard_target); xt_proto_fini(AF_INET); } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index cb9c661f3f33..c8abc9d859b9 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -568,6 +568,7 @@ static int init_or_cleanup(int init) return ret; } +MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET)); MODULE_LICENSE("GPL"); static int __init init(void) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index fca5fe0cf94a..94fcbc5e5a1b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -55,6 +55,8 @@ * Robert Olsson : Added rt_cache statistics * Arnaldo C. Melo : Convert proc stuff to seq_file * Eric Dumazet : hashed spinlocks and rt_check_expire() fixes. + * Ilia Sotnikov : Ignore TOS on PMTUD and Redirect + * Ilia Sotnikov : Removed TOS from hash calculations * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -247,9 +249,9 @@ static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); static int rt_intern_hash(unsigned hash, struct rtable *rth, struct rtable **res); -static unsigned int rt_hash_code(u32 daddr, u32 saddr, u8 tos) +static unsigned int rt_hash_code(u32 daddr, u32 saddr) { - return (jhash_3words(daddr, saddr, (u32) tos, rt_hash_rnd) + return (jhash_2words(daddr, saddr, rt_hash_rnd) & rt_hash_mask); } @@ -1111,7 +1113,7 @@ static void rt_del(unsigned hash, struct rtable *rt) } void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw, - u32 saddr, u8 tos, struct net_device *dev) + u32 saddr, struct net_device *dev) { int i, k; struct in_device *in_dev = in_dev_get(dev); @@ -1119,8 +1121,6 @@ void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw, u32 skeys[2] = { saddr, 0 }; int ikeys[2] = { dev->ifindex, 0 }; - tos &= IPTOS_RT_MASK; - if (!in_dev) return; @@ -1141,8 +1141,7 @@ void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw, for (i = 0; i < 2; i++) { for (k = 0; k < 2; k++) { unsigned hash = rt_hash_code(daddr, - skeys[i] ^ (ikeys[k] << 5), - tos); + skeys[i] ^ (ikeys[k] << 5)); rthp=&rt_hash_table[hash].chain; @@ -1152,7 +1151,6 @@ void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw, if (rth->fl.fl4_dst != daddr || rth->fl.fl4_src != skeys[i] || - rth->fl.fl4_tos != tos || rth->fl.oif != ikeys[k] || rth->fl.iif != 0) { rthp = &rth->u.rt_next; @@ -1232,10 +1230,9 @@ reject_redirect: if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) printk(KERN_INFO "Redirect from %u.%u.%u.%u on %s about " "%u.%u.%u.%u ignored.\n" - " Advised path = %u.%u.%u.%u -> %u.%u.%u.%u, " - "tos %02x\n", + " Advised path = %u.%u.%u.%u -> %u.%u.%u.%u\n", NIPQUAD(old_gw), dev->name, NIPQUAD(new_gw), - NIPQUAD(saddr), NIPQUAD(daddr), tos); + NIPQUAD(saddr), NIPQUAD(daddr)); #endif in_dev_put(in_dev); } @@ -1253,8 +1250,7 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) rt->u.dst.expires) { unsigned hash = rt_hash_code(rt->fl.fl4_dst, rt->fl.fl4_src ^ - (rt->fl.oif << 5), - rt->fl.fl4_tos); + (rt->fl.oif << 5)); #if RT_CACHE_DEBUG >= 1 printk(KERN_DEBUG "ip_rt_advice: redirect to " "%u.%u.%u.%u/%02x dropped\n", @@ -1391,14 +1387,13 @@ unsigned short ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu) struct rtable *rth; u32 skeys[2] = { iph->saddr, 0, }; u32 daddr = iph->daddr; - u8 tos = iph->tos & IPTOS_RT_MASK; unsigned short est_mtu = 0; if (ipv4_config.no_pmtu_disc) return 0; for (i = 0; i < 2; i++) { - unsigned hash = rt_hash_code(daddr, skeys[i], tos); + unsigned hash = rt_hash_code(daddr, skeys[i]); rcu_read_lock(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; @@ -1407,7 +1402,6 @@ unsigned short ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu) rth->fl.fl4_src == skeys[i] && rth->rt_dst == daddr && rth->rt_src == iph->saddr && - rth->fl.fl4_tos == tos && rth->fl.iif == 0 && !(dst_metric_locked(&rth->u.dst, RTAX_MTU))) { unsigned short mtu = new_mtu; @@ -1658,7 +1652,7 @@ static int ip_route_input_mc(struct sk_buff *skb, u32 daddr, u32 saddr, RT_CACHE_STAT_INC(in_slow_mc); in_dev_put(in_dev); - hash = rt_hash_code(daddr, saddr ^ (dev->ifindex << 5), tos); + hash = rt_hash_code(daddr, saddr ^ (dev->ifindex << 5)); return rt_intern_hash(hash, rth, (struct rtable**) &skb->dst); e_nobufs: @@ -1823,7 +1817,7 @@ static inline int ip_mkroute_input_def(struct sk_buff *skb, return err; /* put it into the cache */ - hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5), tos); + hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5)); return rt_intern_hash(hash, rth, (struct rtable**)&skb->dst); } @@ -1864,7 +1858,7 @@ static inline int ip_mkroute_input(struct sk_buff *skb, return err; /* put it into the cache */ - hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5), tos); + hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5)); err = rt_intern_hash(hash, rth, &rtres); if (err) return err; @@ -2041,7 +2035,7 @@ local_input: rth->rt_flags &= ~RTCF_LOCAL; } rth->rt_type = res.type; - hash = rt_hash_code(daddr, saddr ^ (fl.iif << 5), tos); + hash = rt_hash_code(daddr, saddr ^ (fl.iif << 5)); err = rt_intern_hash(hash, rth, (struct rtable**)&skb->dst); goto done; @@ -2088,7 +2082,7 @@ int ip_route_input(struct sk_buff *skb, u32 daddr, u32 saddr, int iif = dev->ifindex; tos &= IPTOS_RT_MASK; - hash = rt_hash_code(daddr, saddr ^ (iif << 5), tos); + hash = rt_hash_code(daddr, saddr ^ (iif << 5)); rcu_read_lock(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; @@ -2286,10 +2280,8 @@ static inline int ip_mkroute_output_def(struct rtable **rp, int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags); unsigned hash; if (err == 0) { - u32 tos = RT_FL_TOS(oldflp); - hash = rt_hash_code(oldflp->fl4_dst, - oldflp->fl4_src ^ (oldflp->oif << 5), tos); + oldflp->fl4_src ^ (oldflp->oif << 5)); err = rt_intern_hash(hash, rth, rp); } @@ -2304,7 +2296,6 @@ static inline int ip_mkroute_output(struct rtable** rp, unsigned flags) { #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - u32 tos = RT_FL_TOS(oldflp); unsigned char hop; unsigned hash; int err = -EINVAL; @@ -2334,7 +2325,7 @@ static inline int ip_mkroute_output(struct rtable** rp, hash = rt_hash_code(oldflp->fl4_dst, oldflp->fl4_src ^ - (oldflp->oif << 5), tos); + (oldflp->oif << 5)); err = rt_intern_hash(hash, rth, rp); /* forward hop information to multipath impl. */ @@ -2563,7 +2554,7 @@ int __ip_route_output_key(struct rtable **rp, const struct flowi *flp) unsigned hash; struct rtable *rth; - hash = rt_hash_code(flp->fl4_dst, flp->fl4_src ^ (flp->oif << 5), flp->fl4_tos); + hash = rt_hash_code(flp->fl4_dst, flp->fl4_src ^ (flp->oif << 5)); rcu_read_lock_bh(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4b0272c92d66..87f68e787d0c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -257,6 +257,7 @@ #include <linux/fs.h> #include <linux/random.h> #include <linux/bootmem.h> +#include <linux/cache.h> #include <net/icmp.h> #include <net/tcp.h> @@ -275,9 +276,9 @@ atomic_t tcp_orphan_count = ATOMIC_INIT(0); EXPORT_SYMBOL_GPL(tcp_orphan_count); -int sysctl_tcp_mem[3]; -int sysctl_tcp_wmem[3] = { 4 * 1024, 16 * 1024, 128 * 1024 }; -int sysctl_tcp_rmem[3] = { 4 * 1024, 87380, 87380 * 2 }; +int sysctl_tcp_mem[3] __read_mostly; +int sysctl_tcp_wmem[3] __read_mostly; +int sysctl_tcp_rmem[3] __read_mostly; EXPORT_SYMBOL(sysctl_tcp_mem); EXPORT_SYMBOL(sysctl_tcp_rmem); @@ -365,7 +366,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE) mask |= POLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLIN | POLLRDNORM; + mask |= POLLIN | POLLRDNORM | POLLRDHUP; /* Connected? */ if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) { @@ -2081,7 +2082,8 @@ __setup("thash_entries=", set_thash_entries); void __init tcp_init(void) { struct sk_buff *skb = NULL; - int order, i; + unsigned long limit; + int order, i, max_share; if (sizeof(struct tcp_skb_cb) > sizeof(skb->cb)) __skb_cb_too_small_for_tcp(sizeof(struct tcp_skb_cb), @@ -2155,12 +2157,16 @@ void __init tcp_init(void) sysctl_tcp_mem[1] = 1024 << order; sysctl_tcp_mem[2] = 1536 << order; - if (order < 3) { - sysctl_tcp_wmem[2] = 64 * 1024; - sysctl_tcp_rmem[0] = PAGE_SIZE; - sysctl_tcp_rmem[1] = 43689; - sysctl_tcp_rmem[2] = 2 * 43689; - } + limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7); + max_share = min(4UL*1024*1024, limit); + + sysctl_tcp_wmem[0] = SK_STREAM_MEM_QUANTUM; + sysctl_tcp_wmem[1] = 16*1024; + sysctl_tcp_wmem[2] = max(64*1024, max_share); + + sysctl_tcp_rmem[0] = SK_STREAM_MEM_QUANTUM; + sysctl_tcp_rmem[1] = 87380; + sysctl_tcp_rmem[2] = max(87380, max_share); printk(KERN_INFO "TCP: Hash tables configured " "(established %d bind %d)\n", |