diff options
Diffstat (limited to 'net/ipv4')
33 files changed, 492 insertions, 693 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index eae1f67..1b745d4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -465,8 +465,10 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len < sizeof(struct sockaddr_in)) goto out; - if (addr->sin_family != AF_INET) + if (addr->sin_family != AF_INET) { + err = -EAFNOSUPPORT; goto out; + } chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); @@ -1438,11 +1440,11 @@ EXPORT_SYMBOL_GPL(inet_ctl_sock_create); unsigned long snmp_fold_field(void __percpu *mib[], int offt) { unsigned long res = 0; - int i; + int i, j; for_each_possible_cpu(i) { - res += *(((unsigned long *) per_cpu_ptr(mib[0], i)) + offt); - res += *(((unsigned long *) per_cpu_ptr(mib[1], i)) + offt); + for (j = 0; j < SNMP_ARRAY_SZ; j++) + res += *(((unsigned long *) per_cpu_ptr(mib[j], i)) + offt); } return res; } @@ -1456,28 +1458,19 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset) int cpu; for_each_possible_cpu(cpu) { - void *bhptr, *userptr; + void *bhptr; struct u64_stats_sync *syncp; - u64 v_bh, v_user; + u64 v; unsigned int start; - /* first mib used by softirq context, we must use _bh() accessors */ - bhptr = per_cpu_ptr(SNMP_STAT_BHPTR(mib), cpu); + bhptr = per_cpu_ptr(mib[0], cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { start = u64_stats_fetch_begin_bh(syncp); - v_bh = *(((u64 *) bhptr) + offt); + v = *(((u64 *) bhptr) + offt); } while (u64_stats_fetch_retry_bh(syncp, start)); - /* second mib used in USER context */ - userptr = per_cpu_ptr(SNMP_STAT_USRPTR(mib), cpu); - syncp = (struct u64_stats_sync *)(userptr + syncp_offset); - do { - start = u64_stats_fetch_begin(syncp); - v_user = *(((u64 *) userptr) + offt); - } while (u64_stats_fetch_retry(syncp, start)); - - res += v_bh + v_user; + res += v; } return res; } @@ -1489,25 +1482,28 @@ int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align) BUG_ON(ptr == NULL); ptr[0] = __alloc_percpu(mibsize, align); if (!ptr[0]) - goto err0; + return -ENOMEM; +#if SNMP_ARRAY_SZ == 2 ptr[1] = __alloc_percpu(mibsize, align); - if (!ptr[1]) - goto err1; + if (!ptr[1]) { + free_percpu(ptr[0]); + ptr[0] = NULL; + return -ENOMEM; + } +#endif return 0; -err1: - free_percpu(ptr[0]); - ptr[0] = NULL; -err0: - return -ENOMEM; } EXPORT_SYMBOL_GPL(snmp_mib_init); -void snmp_mib_free(void __percpu *ptr[2]) +void snmp_mib_free(void __percpu *ptr[SNMP_ARRAY_SZ]) { + int i; + BUG_ON(ptr == NULL); - free_percpu(ptr[0]); - free_percpu(ptr[1]); - ptr[0] = ptr[1] = NULL; + for (i = 0; i < SNMP_ARRAY_SZ; i++) { + free_percpu(ptr[i]); + ptr[i] = NULL; + } } EXPORT_SYMBOL_GPL(snmp_mib_free); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 1b74d3b..96a164a 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -97,7 +97,6 @@ #include <linux/init.h> #include <linux/net.h> #include <linux/rcupdate.h> -#include <linux/jhash.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> @@ -139,8 +138,6 @@ static const struct neigh_ops arp_generic_ops = { .error_report = arp_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; static const struct neigh_ops arp_hh_ops = { @@ -149,16 +146,12 @@ static const struct neigh_ops arp_hh_ops = { .error_report = arp_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; static const struct neigh_ops arp_direct_ops = { .family = AF_INET, - .output = dev_queue_xmit, - .connected_output = dev_queue_xmit, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, + .output = neigh_direct_output, + .connected_output = neigh_direct_output, }; static const struct neigh_ops arp_broken_ops = { @@ -167,8 +160,6 @@ static const struct neigh_ops arp_broken_ops = { .error_report = arp_error_report, .output = neigh_compat_output, .connected_output = neigh_compat_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; struct neigh_table arp_tbl = { @@ -232,7 +223,7 @@ static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 hash_rnd) { - return jhash_2words(*(u32 *)pkey, dev->ifindex, hash_rnd); + return arp_hashfn(*(u32 *)pkey, dev, hash_rnd); } static int arp_constructor(struct neighbour *neigh) @@ -259,7 +250,7 @@ static int arp_constructor(struct neighbour *neigh) if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &arp_direct_ops; - neigh->output = neigh->ops->queue_xmit; + neigh->output = neigh_direct_output; } else { /* Good devices (checked by reading texts, but only Ethernet is tested) @@ -518,30 +509,6 @@ EXPORT_SYMBOL(arp_find); /* END OF OBSOLETE FUNCTIONS */ -int arp_bind_neighbour(struct dst_entry *dst) -{ - struct net_device *dev = dst->dev; - struct neighbour *n = dst->neighbour; - - if (dev == NULL) - return -EINVAL; - if (n == NULL) { - __be32 nexthop = ((struct rtable *)dst)->rt_gateway; - if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) - nexthop = 0; - n = __neigh_lookup_errno( -#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE) - dev->type == ARPHRD_ATM ? - clip_tbl_hook : -#endif - &arp_tbl, &nexthop, dev); - if (IS_ERR(n)) - return PTR_ERR(n); - dst->neighbour = n; - } - return 0; -} - /* * Check if we can use proxy ARP for this path */ diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 0d4a184..37b3c18 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1833,8 +1833,8 @@ void __init devinet_init(void) rtnl_af_register(&inet_af_ops); - rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL); - rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL); - rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr); + rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL); + rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL); + rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 2252471..92fc5f6 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1124,9 +1124,9 @@ static struct pernet_operations fib_net_ops = { void __init ip_fib_init(void) { - rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL); - rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL); - rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib); + rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); + rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); + rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); register_pernet_subsys(&fib_net_ops); register_netdevice_notifier(&fib_netdev_notifier); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 58c25ea..de9e297 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -110,9 +110,10 @@ struct leaf { struct leaf_info { struct hlist_node hlist; - struct rcu_head rcu; int plen; + u32 mask_plen; /* ntohl(inet_make_mask(plen)) */ struct list_head falh; + struct rcu_head rcu; }; struct tnode { @@ -451,6 +452,7 @@ static struct leaf_info *leaf_info_new(int plen) struct leaf_info *li = kmalloc(sizeof(struct leaf_info), GFP_KERNEL); if (li) { li->plen = plen; + li->mask_plen = ntohl(inet_make_mask(plen)); INIT_LIST_HEAD(&li->falh); } return li; @@ -1359,10 +1361,8 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, hlist_for_each_entry_rcu(li, node, hhead, hlist) { struct fib_alias *fa; - int plen = li->plen; - __be32 mask = inet_make_mask(plen); - if (l->key != (key & ntohl(mask))) + if (l->key != (key & li->mask_plen)) continue; list_for_each_entry_rcu(fa, &li->falh, fa_list) { @@ -1394,7 +1394,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, #ifdef CONFIG_IP_FIB_TRIE_STATS t->stats.semantic_match_passed++; #endif - res->prefixlen = plen; + res->prefixlen = li->plen; res->nh_sel = nhsel; res->type = fa->fa_type; res->scope = fa->fa_info->fib_scope; @@ -1402,7 +1402,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, res->table = tb; res->fa_head = &li->falh; if (!(fib_flags & FIB_LOOKUP_NOREF)) - atomic_inc(&res->fi->fib_clntref); + atomic_inc(&fi->fib_clntref); return 0; } } diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c index c6933f2..9dbe108 100644 --- a/net/ipv4/gre.c +++ b/net/ipv4/gre.c @@ -16,7 +16,6 @@ #include <linux/skbuff.h> #include <linux/in.h> #include <linux/netdevice.h> -#include <linux/version.h> #include <linux/spinlock.h> #include <net/protocol.h> #include <net/gre.h> diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 5395e45..23ef31b 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -380,6 +380,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct icmp_bxm *param) { struct rtable *rt, *rt2; + struct flowi4 fl4_dec; int err; memset(fl4, 0, sizeof(*fl4)); @@ -408,19 +409,19 @@ static struct rtable *icmp_route_lookup(struct net *net, } else return rt; - err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(fl4), AF_INET); + err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(&fl4_dec), AF_INET); if (err) goto relookup_failed; - if (inet_addr_type(net, fl4->saddr) == RTN_LOCAL) { - rt2 = __ip_route_output_key(net, fl4); + if (inet_addr_type(net, fl4_dec.saddr) == RTN_LOCAL) { + rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) err = PTR_ERR(rt2); } else { struct flowi4 fl4_2 = {}; unsigned long orefdst; - fl4_2.daddr = fl4->saddr; + fl4_2.daddr = fl4_dec.saddr; rt2 = ip_route_output_key(net, &fl4_2); if (IS_ERR(rt2)) { err = PTR_ERR(rt2); @@ -428,7 +429,7 @@ static struct rtable *icmp_route_lookup(struct net *net, } /* Ugh! */ orefdst = skb_in->_skb_refdst; /* save old refdst */ - err = ip_route_input(skb_in, fl4->daddr, fl4->saddr, + err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, RT_TOS(tos), rt2->dst.dev); dst_release(&rt2->dst); @@ -440,10 +441,11 @@ static struct rtable *icmp_route_lookup(struct net *net, goto relookup_failed; rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst, - flowi4_to_flowi(fl4), NULL, + flowi4_to_flowi(&fl4_dec), NULL, XFRM_LOOKUP_ICMP); if (!IS_ERR(rt2)) { dst_release(&rt->dst); + memcpy(fl4, &fl4_dec, sizeof(*fl4)); rt = rt2; } else if (PTR_ERR(rt2) == -EPERM) { if (rt) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 3267d38..389a2e6 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -869,7 +869,7 @@ static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } return netlink_dump_start(idiagnl, skb, nlh, - inet_diag_dump, NULL); + inet_diag_dump, NULL, 0); } return inet_diag_get_exact(skb, nlh); diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index 85a0f75..ef7ae60 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -146,8 +146,7 @@ static __wsum lro_tcp_data_csum(struct iphdr *iph, struct tcphdr *tcph, int len) } static void lro_init_desc(struct net_lro_desc *lro_desc, struct sk_buff *skb, - struct iphdr *iph, struct tcphdr *tcph, - u16 vlan_tag, struct vlan_group *vgrp) + struct iphdr *iph, struct tcphdr *tcph) { int nr_frags; __be32 *ptr; @@ -173,8 +172,6 @@ static void lro_init_desc(struct net_lro_desc *lro_desc, struct sk_buff *skb, } lro_desc->mss = tcp_data_len; - lro_desc->vgrp = vgrp; - lro_desc->vlan_tag = vlan_tag; lro_desc->active = 1; lro_desc->data_csum = lro_tcp_data_csum(iph, tcph, @@ -309,29 +306,17 @@ static void lro_flush(struct net_lro_mgr *lro_mgr, skb_shinfo(lro_desc->parent)->gso_size = lro_desc->mss; - if (lro_desc->vgrp) { - if (lro_mgr->features & LRO_F_NAPI) - vlan_hwaccel_receive_skb(lro_desc->parent, - lro_desc->vgrp, - lro_desc->vlan_tag); - else - vlan_hwaccel_rx(lro_desc->parent, - lro_desc->vgrp, - lro_desc->vlan_tag); - - } else { - if (lro_mgr->features & LRO_F_NAPI) - netif_receive_skb(lro_desc->parent); - else - netif_rx(lro_desc->parent); - } + if (lro_mgr->features & LRO_F_NAPI) + netif_receive_skb(lro_desc->parent); + else + netif_rx(lro_desc->parent); LRO_INC_STATS(lro_mgr, flushed); lro_clear_desc(lro_desc); } static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, - struct vlan_group *vgrp, u16 vlan_tag, void *priv) + void *priv) { struct net_lro_desc *lro_desc; struct iphdr *iph; @@ -360,7 +345,7 @@ static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, goto out; skb->ip_summed = lro_mgr->ip_summed_aggr; - lro_init_desc(lro_desc, skb, iph, tcph, vlan_tag, vgrp); + lro_init_desc(lro_desc, skb, iph, tcph); LRO_INC_STATS(lro_mgr, aggregated); return 0; } @@ -433,8 +418,7 @@ static struct sk_buff *lro_gen_skb(struct net_lro_mgr *lro_mgr, static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, struct skb_frag_struct *frags, int len, int true_size, - struct vlan_group *vgrp, - u16 vlan_tag, void *priv, __wsum sum) + void *priv, __wsum sum) { struct net_lro_desc *lro_desc; struct iphdr *iph; @@ -480,7 +464,7 @@ static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, tcph = (void *)((u8 *)skb->data + vlan_hdr_len + IP_HDR_LEN(iph)); - lro_init_desc(lro_desc, skb, iph, tcph, 0, NULL); + lro_init_desc(lro_desc, skb, iph, tcph); LRO_INC_STATS(lro_mgr, aggregated); return NULL; } @@ -514,7 +498,7 @@ void lro_receive_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, void *priv) { - if (__lro_proc_skb(lro_mgr, skb, NULL, 0, priv)) { + if (__lro_proc_skb(lro_mgr, skb, priv)) { if (lro_mgr->features & LRO_F_NAPI) netif_receive_skb(skb); else @@ -523,29 +507,13 @@ void lro_receive_skb(struct net_lro_mgr *lro_mgr, } EXPORT_SYMBOL(lro_receive_skb); -void lro_vlan_hwaccel_receive_skb(struct net_lro_mgr *lro_mgr, - struct sk_buff *skb, - struct vlan_group *vgrp, - u16 vlan_tag, - void *priv) -{ - if (__lro_proc_skb(lro_mgr, skb, vgrp, vlan_tag, priv)) { - if (lro_mgr->features & LRO_F_NAPI) - vlan_hwaccel_receive_skb(skb, vgrp, vlan_tag); - else - vlan_hwaccel_rx(skb, vgrp, vlan_tag); - } -} -EXPORT_SYMBOL(lro_vlan_hwaccel_receive_skb); - void lro_receive_frags(struct net_lro_mgr *lro_mgr, struct skb_frag_struct *frags, int len, int true_size, void *priv, __wsum sum) { struct sk_buff *skb; - skb = __lro_proc_segment(lro_mgr, frags, len, true_size, NULL, 0, - priv, sum); + skb = __lro_proc_segment(lro_mgr, frags, len, true_size, priv, sum); if (!skb) return; @@ -556,26 +524,6 @@ void lro_receive_frags(struct net_lro_mgr *lro_mgr, } EXPORT_SYMBOL(lro_receive_frags); -void lro_vlan_hwaccel_receive_frags(struct net_lro_mgr *lro_mgr, - struct skb_frag_struct *frags, - int len, int true_size, - struct vlan_group *vgrp, - u16 vlan_tag, void *priv, __wsum sum) -{ - struct sk_buff *skb; - - skb = __lro_proc_segment(lro_mgr, frags, len, true_size, vgrp, - vlan_tag, priv, sum); - if (!skb) - return; - - if (lro_mgr->features & LRO_F_NAPI) - vlan_hwaccel_receive_skb(skb, vgrp, vlan_tag); - else - vlan_hwaccel_rx(skb, vgrp, vlan_tag); -} -EXPORT_SYMBOL(lro_vlan_hwaccel_receive_frags); - void lro_flush_all(struct net_lro_mgr *lro_mgr) { int i; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index ce616d9..e382138 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -54,15 +54,11 @@ * 1. Nodes may appear in the tree only with the pool lock held. * 2. Nodes may disappear from the tree only with the pool lock held * AND reference count being 0. - * 3. Nodes appears and disappears from unused node list only under - * "inet_peer_unused_lock". - * 4. Global variable peer_total is modified under the pool lock. - * 5. struct inet_peer fields modification: + * 3. Global variable peer_total is modified under the pool lock. + * 4. struct inet_peer fields modification: * avl_left, avl_right, avl_parent, avl_height: pool lock - * unused: unused node list lock * refcnt: atomically against modifications on other CPU; * usually under some other lock to prevent node disappearing - * dtime: unused node list lock * daddr: unchangeable * ip_id_count: atomic value (no lock needed) */ @@ -104,19 +100,6 @@ int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries m * aggressively at this stage */ int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */ -int inet_peer_gc_mintime __read_mostly = 10 * HZ; -int inet_peer_gc_maxtime __read_mostly = 120 * HZ; - -static struct { - struct list_head list; - spinlock_t lock; -} unused_peers = { - .list = LIST_HEAD_INIT(unused_peers.list), - .lock = __SPIN_LOCK_UNLOCKED(unused_peers.lock), -}; - -static void peer_check_expire(unsigned long dummy); -static DEFINE_TIMER(peer_periodic_timer, peer_check_expire, 0, 0); /* Called from ip_output.c:ip_init */ @@ -142,21 +125,6 @@ void __init inet_initpeers(void) 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); - /* All the timers, started at system startup tend - to synchronize. Perturb it a bit. - */ - peer_periodic_timer.expires = jiffies - + net_random() % inet_peer_gc_maxtime - + inet_peer_gc_maxtime; - add_timer(&peer_periodic_timer); -} - -/* Called with or without local BH being disabled. */ -static void unlink_from_unused(struct inet_peer *p) -{ - spin_lock_bh(&unused_peers.lock); - list_del_init(&p->unused); - spin_unlock_bh(&unused_peers.lock); } static int addr_compare(const struct inetpeer_addr *a, @@ -203,20 +171,6 @@ static int addr_compare(const struct inetpeer_addr *a, u; \ }) -static bool atomic_add_unless_return(atomic_t *ptr, int a, int u, int *newv) -{ - int cur, old = atomic_read(ptr); - - while (old != u) { - *newv = old + a; - cur = atomic_cmpxchg(ptr, old, *newv); - if (cur == old) - return true; - old = cur; - } - return false; -} - /* * Called with rcu_read_lock() * Because we hold no lock against a writer, its quite possible we fall @@ -225,8 +179,7 @@ static bool atomic_add_unless_return(atomic_t *ptr, int a, int u, int *newv) * We exit from this function if number of links exceeds PEER_MAXDEPTH */ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, - struct inet_peer_base *base, - int *newrefcnt) + struct inet_peer_base *base) { struct inet_peer *u = rcu_dereference(base->root); int count = 0; @@ -235,11 +188,9 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, int cmp = addr_compare(daddr, &u->daddr); if (cmp == 0) { /* Before taking a reference, check if this entry was - * deleted, unlink_from_pool() sets refcnt=-1 to make - * distinction between an unused entry (refcnt=0) and - * a freed one. + * deleted (refcnt=-1) */ - if (!atomic_add_unless_return(&u->refcnt, 1, -1, newrefcnt)) + if (!atomic_add_unless(&u->refcnt, 1, -1)) u = NULL; return u; } @@ -366,137 +317,99 @@ static void inetpeer_free_rcu(struct rcu_head *head) kmem_cache_free(peer_cachep, container_of(head, struct inet_peer, rcu)); } -/* May be called with local BH enabled. */ static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base, struct inet_peer __rcu **stack[PEER_MAXDEPTH]) { - int do_free; - - do_free = 0; - - write_seqlock_bh(&base->lock); - /* Check the reference counter. It was artificially incremented by 1 - * in cleanup() function to prevent sudden disappearing. If we can - * atomically (because of lockless readers) take this last reference, - * it's safe to remove the node and free it later. - * We use refcnt=-1 to alert lockless readers this entry is deleted. - */ - if (atomic_cmpxchg(&p->refcnt, 1, -1) == 1) { - struct inet_peer __rcu ***stackptr, ***delp; - if (lookup(&p->daddr, stack, base) != p) - BUG(); - delp = stackptr - 1; /* *delp[0] == p */ - if (p->avl_left == peer_avl_empty_rcu) { - *delp[0] = p->avl_right; - --stackptr; - } else { - /* look for a node to insert instead of p */ - struct inet_peer *t; - t = lookup_rightempty(p, base); - BUG_ON(rcu_deref_locked(*stackptr[-1], base) != t); - **--stackptr = t->avl_left; - /* t is removed, t->daddr > x->daddr for any - * x in p->avl_left subtree. - * Put t in the old place of p. */ - RCU_INIT_POINTER(*delp[0], t); - t->avl_left = p->avl_left; - t->avl_right = p->avl_right; - t->avl_height = p->avl_height; - BUG_ON(delp[1] != &p->avl_left); - delp[1] = &t->avl_left; /* was &p->avl_left */ - } - peer_avl_rebalance(stack, stackptr, base); - base->total--; - do_free = 1; + struct inet_peer __rcu ***stackptr, ***delp; + + if (lookup(&p->daddr, stack, base) != p) + BUG(); + delp = stackptr - 1; /* *delp[0] == p */ + if (p->avl_left == peer_avl_empty_rcu) { + *delp[0] = p->avl_right; + --stackptr; + } else { + /* look for a node to insert instead of p */ + struct inet_peer *t; + t = lookup_rightempty(p, base); + BUG_ON(rcu_deref_locked(*stackptr[-1], base) != t); + **--stackptr = t->avl_left; + /* t is removed, t->daddr > x->daddr for any + * x in p->avl_left subtree. + * Put t in the old place of p. */ + RCU_INIT_POINTER(*delp[0], t); + t->avl_left = p->avl_left; + t->avl_right = p->avl_right; + t->avl_height = p->avl_height; + BUG_ON(delp[1] != &p->avl_left); + delp[1] = &t->avl_left; /* was &p->avl_left */ } - write_sequnlock_bh(&base->lock); - - if (do_free) - call_rcu(&p->rcu, inetpeer_free_rcu); - else - /* The node is used again. Decrease the reference counter - * back. The loop "cleanup -> unlink_from_unused - * -> unlink_from_pool -> putpeer -> link_to_unused - * -> cleanup (for the same node)" - * doesn't really exist because the entry will have a - * recent deletion time and will not be cleaned again soon. - */ - inet_putpeer(p); + peer_avl_rebalance(stack, stackptr, base); + base->total--; + call_rcu(&p->rcu, inetpeer_free_rcu); } static struct inet_peer_base *family_to_base(int family) { - return (family == AF_INET ? &v4_peers : &v6_peers); -} - -static struct inet_peer_base *peer_to_base(struct inet_peer *p) -{ - return family_to_base(p->daddr.family); + return family == AF_INET ? &v4_peers : &v6_peers; } -/* May be called with local BH enabled. */ -static int cleanup_once(unsigned long ttl, struct inet_peer __rcu **stack[PEER_MAXDEPTH]) +/* perform garbage collect on all items stacked during a lookup */ +static int inet_peer_gc(struct inet_peer_base *base, + struct inet_peer __rcu **stack[PEER_MAXDEPTH], + struct inet_peer __rcu ***stackptr) { - struct inet_peer *p = NULL; - - /* Remove the first entry from the list of unused nodes. */ - spin_lock_bh(&unused_peers.lock); - if (!list_empty(&unused_peers.list)) { - __u32 delta; - - p = list_first_entry(&unused_peers.list, struct inet_peer, unused); - delta = (__u32)jiffies - p->dtime; + struct inet_peer *p, *gchead = NULL; + __u32 delta, ttl; + int cnt = 0; - if (delta < ttl) { - /* Do not prune fresh entries. */ - spin_unlock_bh(&unused_peers.lock); - return -1; + if (base->total >= inet_peer_threshold) + ttl = 0; /* be aggressive */ + else + ttl = inet_peer_maxttl + - (inet_peer_maxttl - inet_peer_minttl) / HZ * + base->total / inet_peer_threshold * HZ; + stackptr--; /* last stack slot is peer_avl_empty */ + while (stackptr > stack) { + stackptr--; + p = rcu_deref_locked(**stackptr, base); + if (atomic_read(&p->refcnt) == 0) { + smp_rmb(); + delta = (__u32)jiffies - p->dtime; + if (delta >= ttl && + atomic_cmpxchg(&p->refcnt, 0, -1) == 0) { + p->gc_next = gchead; + gchead = p; + } } - - list_del_init(&p->unused); - - /* Grab an extra reference to prevent node disappearing - * before unlink_from_pool() call. */ - atomic_inc(&p->refcnt); } - spin_unlock_bh(&unused_peers.lock); - - if (p == NULL) - /* It means that the total number of USED entries has - * grown over inet_peer_threshold. It shouldn't really - * happen because of entry limits in route cache. */ - return -1; - - unlink_from_pool(p, peer_to_base(p), stack); - return 0; + while ((p = gchead) != NULL) { + gchead = p->gc_next; + cnt++; + unlink_from_pool(p, base, stack); + } + return cnt; } -/* Called with or without local BH being disabled. */ -struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) +struct inet_peer *inet_getpeer(const struct inetpeer_addr *daddr, int create) { struct inet_peer __rcu **stack[PEER_MAXDEPTH], ***stackptr; struct inet_peer_base *base = family_to_base(daddr->family); struct inet_peer *p; unsigned int sequence; - int invalidated, newrefcnt = 0; + int invalidated, gccnt = 0; - /* Look up for the address quickly, lockless. + /* Attempt a lockless lookup first. * Because of a concurrent writer, we might not find an existing entry. */ rcu_read_lock(); sequence = read_seqbegin(&base->lock); - p = lookup_rcu(daddr, base, &newrefcnt); + p = lookup_rcu(daddr, base); invalidated = read_seqretry(&base->lock, sequence); rcu_read_unlock(); - if (p) { -found: /* The existing node has been found. - * Remove the entry from unused list if it was there. - */ - if (newrefcnt == 1) - unlink_from_unused(p); + if (p) return p; - } /* If no writer did a change during our lookup, we can return early. */ if (!create && !invalidated) @@ -506,18 +419,27 @@ found: /* The existing node has been found. * At least, nodes should be hot in our cache. */ write_seqlock_bh(&base->lock); +relookup: p = lookup(daddr, stack, base); if (p != peer_avl_empty) { - newrefcnt = atomic_inc_return(&p->refcnt); + atomic_inc(&p->refcnt); write_sequnlock_bh(&base->lock); - goto found; + return p; + } + if (!gccnt) { + gccnt = inet_peer_gc(base, stack, stackptr); + if (gccnt && create) + goto relookup; } p = create ? kmem_cache_alloc(peer_cachep, GFP_ATOMIC) : NULL; if (p) { p->daddr = *daddr; atomic_set(&p->refcnt, 1); atomic_set(&p->rid, 0); - atomic_set(&p->ip_id_count, secure_ip_id(daddr->addr.a4)); + atomic_set(&p->ip_id_count, + (daddr->family == AF_INET) ? + secure_ip_id(daddr->addr.a4) : + secure_ipv6_id(daddr->addr.a6)); p->tcp_ts_stamp = 0; p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; @@ -525,7 +447,6 @@ found: /* The existing node has been found. p->pmtu_expires = 0; p->pmtu_orig = 0; memset(&p->redirect_learned, 0, sizeof(p->redirect_learned)); - INIT_LIST_HEAD(&p->unused); /* Link the node. */ @@ -534,63 +455,15 @@ found: /* The existing node has been found. } write_sequnlock_bh(&base->lock); - if (base->total >= inet_peer_threshold) - /* Remove one less-recently-used entry. */ - cleanup_once(0, stack); - return p; } - -static int compute_total(void) -{ - return v4_peers.total + v6_peers.total; -} EXPORT_SYMBOL_GPL(inet_getpeer); -/* Called with local BH disabled. */ -static void peer_check_expire(unsigned long dummy) -{ - unsigned long now = jiffies; - int ttl, total; - struct inet_peer __rcu **stack[PEER_MAXDEPTH]; - - total = compute_total(); - if (total >= inet_peer_threshold) - ttl = inet_peer_minttl; - else - ttl = inet_peer_maxttl - - (inet_peer_maxttl - inet_peer_minttl) / HZ * - total / inet_peer_threshold * HZ; - while (!cleanup_once(ttl, stack)) { - if (jiffies != now) - break; - } - - /* Trigger the timer after inet_peer_gc_mintime .. inet_peer_gc_maxtime - * interval depending on the total number of entries (more entries, - * less interval). */ - total = compute_total(); - if (total >= inet_peer_threshold) - peer_periodic_timer.expires = jiffies + inet_peer_gc_mintime; - else - peer_periodic_timer.expires = jiffies - + inet_peer_gc_maxtime - - (inet_peer_gc_maxtime - inet_peer_gc_mintime) / HZ * - total / inet_peer_threshold * HZ; - add_timer(&peer_periodic_timer); -} - void inet_putpeer(struct inet_peer *p) { - local_bh_disable(); - - if (atomic_dec_and_lock(&p->refcnt, &unused_peers.lock)) { - list_add_tail(&p->unused, &unused_peers.list); - p->dtime = (__u32)jiffies; - spin_unlock(&unused_peers.lock); - } - - local_bh_enable(); + p->dtime = (__u32)jiffies; + smp_mb__before_atomic_dec(); + atomic_dec(&p->refcnt); } EXPORT_SYMBOL_GPL(inet_putpeer); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 0ad6035..0e0ab98 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -261,8 +261,9 @@ static void ip_expire(unsigned long arg) * Only an end host needs to send an ICMP * "Fragment Reassembly Timeout" message, per RFC792. */ - if (qp->user == IP_DEFRAG_CONNTRACK_IN && - skb_rtable(head)->rt_type != RTN_LOCAL) + if (qp->user == IP_DEFRAG_AF_PACKET || + (qp->user == IP_DEFRAG_CONNTRACK_IN && + skb_rtable(head)->rt_type != RTN_LOCAL)) goto out_rcu_unlock; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 8871067..d7bb94c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -731,9 +731,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { + struct neighbour *neigh = dst_get_neighbour(skb_dst(skb)); const struct in6_addr *addr6; int addr_type; - struct neighbour *neigh = skb_dst(skb)->neighbour; if (neigh == NULL) goto tx_error; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index c8f48ef..073a9b0 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -165,7 +165,7 @@ int ip_call_ra_chain(struct sk_buff *skb) (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) && net_eq(sock_net(sk), dev_net(dev))) { - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) return 1; } @@ -256,7 +256,7 @@ int ip_local_deliver(struct sk_buff *skb) * Reassemble IP fragments. */ - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { if (ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER)) return 0; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a8024ea..ccaaa85 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -182,6 +182,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); + struct neighbour *neigh; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTMCAST, skb->len); @@ -203,10 +204,9 @@ static inline int ip_finish_output2(struct sk_buff *skb) skb = skb2; } - if (dst->hh) - return neigh_hh_output(dst->hh, skb); - else if (dst->neighbour) - return dst->neighbour->output(skb); + neigh = dst_get_neighbour(dst); + if (neigh) + return neigh_output(neigh, skb); if (net_ratelimit()) printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n"); @@ -489,7 +489,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (first_len - hlen > mtu || ((first_len - hlen) & 7) || - (iph->frag_off & htons(IP_MF|IP_OFFSET)) || + ip_is_fragment(iph) || skb_cloned(skb)) goto slow_path; @@ -734,7 +734,7 @@ static inline int ip_ufo_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int hh_len, int fragheaderlen, - int transhdrlen, int mtu, unsigned int flags) + int transhdrlen, int maxfraglen, unsigned int flags) { struct sk_buff *skb; int err; @@ -767,7 +767,7 @@ static inline int ip_ufo_append_data(struct sock *sk, skb->csum = 0; /* specify the length of each IP datagram fragment */ - skb_shinfo(skb)->gso_size = mtu - fragheaderlen; + skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; __skb_queue_tail(queue, skb); } @@ -802,8 +802,6 @@ static int __ip_append_data(struct sock *sk, skb = skb_peek_tail(queue); exthdrlen = !skb ? rt->dst.header_len : 0; - length += exthdrlen; - transhdrlen += exthdrlen; mtu = cork->fragsize; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -830,10 +828,10 @@ static int __ip_append_data(struct sock *sk, cork->length += length; if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO)) { + (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, - mtu, flags); + maxfraglen, flags); if (err) goto error; return 0; @@ -883,17 +881,16 @@ alloc_new_skb: else alloclen = fraglen; + alloclen += exthdrlen; + /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, * because we have no idea what fragment will be * the last. */ - if (datalen == length + fraggap) { + if (datalen == length + fraggap) alloclen += rt->dst.trailer_len; - /* make sure mtu is not reached */ - if (datalen > mtu - fragheaderlen - rt->dst.trailer_len) - datalen -= ALIGN(rt->dst.trailer_len, 8); - } + if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen + hh_len + 15, @@ -926,11 +923,11 @@ alloc_new_skb: /* * Find where to start putting bytes. */ - data = skb_put(skb, fraglen); + data = skb_put(skb, fraglen + exthdrlen); skb_set_network_header(skb, exthdrlen); skb->transport_header = (skb->network_header + fragheaderlen); - data += fragheaderlen; + data += fragheaderlen + exthdrlen; if (fraggap) { skb->csum = skb_copy_and_csum_bits( @@ -1064,7 +1061,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, */ *rtp = NULL; cork->fragsize = inet->pmtudisc == IP_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(rt->dst.path); + rt->dst.dev->mtu : dst_mtu(&rt->dst); cork->dst = &rt->dst; cork->length = 0; cork->tx_flags = ipc->tx_flags; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index ab7e554..472a8c4 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -861,41 +861,44 @@ static void __init ic_do_bootp_ext(u8 *ext) #endif switch (*ext++) { - case 1: /* Subnet mask */ - if (ic_netmask == NONE) - memcpy(&ic_netmask, ext+1, 4); - break; - case 3: /* Default gateway */ - if (ic_gateway == NONE) - memcpy(&ic_gateway, ext+1, 4); - break; - case 6: /* DNS server */ - servers= *ext/4; - if (servers > CONF_NAMESERVERS_MAX) - servers = CONF_NAMESERVERS_MAX; - for (i = 0; i < servers; i++) { - if (ic_nameservers[i] == NONE) - memcpy(&ic_nameservers[i], ext+1+4*i, 4); - } - break; - case 12: /* Host name */ - ic_bootp_string(utsname()->nodename, ext+1, *ext, __NEW_UTS_LEN); - ic_host_name_set = 1; - break; - case 15: /* Domain name (DNS) */ - ic_bootp_string(ic_domain, ext+1, *ext, sizeof(ic_domain)); - break; - case 17: /* Root path */ - if (!root_server_path[0]) - ic_bootp_string(root_server_path, ext+1, *ext, sizeof(root_server_path)); - break; - case 26: /* Interface MTU */ - memcpy(&mtu, ext+1, sizeof(mtu)); - ic_dev_mtu = ntohs(mtu); - break; - case 40: /* NIS Domain name (_not_ DNS) */ - ic_bootp_string(utsname()->domainname, ext+1, *ext, __NEW_UTS_LEN); - break; + case 1: /* Subnet mask */ + if (ic_netmask == NONE) + memcpy(&ic_netmask, ext+1, 4); + break; + case 3: /* Default gateway */ + if (ic_gateway == NONE) + memcpy(&ic_gateway, ext+1, 4); + break; + case 6: /* DNS server */ + servers= *ext/4; + if (servers > CONF_NAMESERVERS_MAX) + servers = CONF_NAMESERVERS_MAX; + for (i = 0; i < servers; i++) { + if (ic_nameservers[i] == NONE) + memcpy(&ic_nameservers[i], ext+1+4*i, 4); + } + break; + case 12: /* Host name */ + ic_bootp_string(utsname()->nodename, ext+1, *ext, + __NEW_UTS_LEN); + ic_host_name_set = 1; + break; + case 15: /* Domain name (DNS) */ + ic_bootp_string(ic_domain, ext+1, *ext, sizeof(ic_domain)); + break; + case 17: /* Root path */ + if (!root_server_path[0]) + ic_bootp_string(root_server_path, ext+1, *ext, + sizeof(root_server_path)); + break; + case 26: /* Interface MTU */ + memcpy(&mtu, ext+1, sizeof(mtu)); + ic_dev_mtu = ntohs(mtu); + break; + case 40: /* NIS Domain name (_not_ DNS) */ + ic_bootp_string(utsname()->domainname, ext+1, *ext, + __NEW_UTS_LEN); + break; } } @@ -932,7 +935,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str goto drop; /* Fragments are not supported */ - if (h->frag_off & htons(IP_OFFSET | IP_MF)) { + if (ip_is_fragment(h)) { if (net_ratelimit()) printk(KERN_ERR "DHCP/BOOTP: Ignoring fragmented " "reply.\n"); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 30a7763..aae2bd8 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2544,7 +2544,8 @@ int __init ip_mr_init(void) goto add_proto_fail; } #endif - rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, NULL, ipmr_rtm_dumproute); + rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, + NULL, ipmr_rtm_dumproute, NULL); return 0; #ifdef CONFIG_IP_PIMSM_V2 diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 4614bab..2e97e3e 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -17,51 +17,35 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi4 fl4 = {}; - unsigned long orefdst; + __be32 saddr = iph->saddr; + __u8 flags = 0; unsigned int hh_len; - unsigned int type; - type = inet_addr_type(net, iph->saddr); - if (skb->sk && inet_sk(skb->sk)->transparent) - type = RTN_LOCAL; - if (addr_type == RTN_UNSPEC) - addr_type = type; + if (!skb->sk && addr_type != RTN_LOCAL) { + if (addr_type == RTN_UNSPEC) + addr_type = inet_addr_type(net, saddr); + if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) + flags |= FLOWI_FLAG_ANYSRC; + else + saddr = 0; + } /* some non-standard hacks like ipt_REJECT.c:send_reset() can cause * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook. */ - if (addr_type == RTN_LOCAL) { - fl4.daddr = iph->daddr; - if (type == RTN_LOCAL) - fl4.saddr = iph->saddr; - fl4.flowi4_tos = RT_TOS(iph->tos); - fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; - fl4.flowi4_mark = skb->mark; - fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; - rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - return -1; - - /* Drop old route. */ - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - } else { - /* non-local src, find valid iif to satisfy - * rp-filter when calling ip_route_input. */ - fl4.daddr = iph->saddr; - rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - return -1; + fl4.daddr = iph->daddr; + fl4.saddr = saddr; + fl4.flowi4_tos = RT_TOS(iph->tos); + fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; + fl4.flowi4_mark = skb->mark; + fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : flags; + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + return -1; - orefdst = skb->_skb_refdst; - if (ip_route_input(skb, iph->daddr, iph->saddr, - RT_TOS(iph->tos), rt->dst.dev) != 0) { - dst_release(&rt->dst); - return -1; - } - dst_release(&rt->dst); - refdst_drop(orefdst); - } + /* Drop old route. */ + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); if (skb_dst(skb)->error) return -1; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 5c9e97c..db8d22d 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -317,19 +317,19 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) hash = clusterip_hashfn(skb, cipinfo->config); switch (ctinfo) { - case IP_CT_NEW: - ct->mark = hash; - break; - case IP_CT_RELATED: - case IP_CT_RELATED_REPLY: - /* FIXME: we don't handle expectations at the - * moment. they can arrive on a different node than - * the master connection (e.g. FTP passive mode) */ - case IP_CT_ESTABLISHED: - case IP_CT_ESTABLISHED_REPLY: - break; - default: - break; + case IP_CT_NEW: + ct->mark = hash; + break; + case IP_CT_RELATED: + case IP_CT_RELATED_REPLY: + /* FIXME: we don't handle expectations at the moment. + * They can arrive on a different node than + * the master connection (e.g. FTP passive mode) */ + case IP_CT_ESTABLISHED: + case IP_CT_ESTABLISHED_REPLY: + break; + default: /* Prevent gcc warnings */ + break; } #ifdef DEBUG diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 1ff79e5..51f13f8 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -40,7 +40,6 @@ static void send_reset(struct sk_buff *oldskb, int hook) struct iphdr *niph; const struct tcphdr *oth; struct tcphdr _otcph, *tcph; - unsigned int addr_type; /* IP header checks: fragment. */ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) @@ -55,6 +54,9 @@ static void send_reset(struct sk_buff *oldskb, int hook) if (oth->rst) return; + if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) + return; + /* Check checksum */ if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP)) return; @@ -101,19 +103,11 @@ static void send_reset(struct sk_buff *oldskb, int hook) nskb->csum_start = (unsigned char *)tcph - nskb->head; nskb->csum_offset = offsetof(struct tcphdr, check); - addr_type = RTN_UNSPEC; - if (hook != NF_INET_FORWARD -#ifdef CONFIG_BRIDGE_NETFILTER - || (nskb->nf_bridge && nskb->nf_bridge->mask & BRNF_BRIDGED) -#endif - ) - addr_type = RTN_LOCAL; - /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set_noref(nskb, skb_dst(oldskb)); nskb->protocol = htons(ETH_P_IP); - if (ip_route_me_harder(nskb, addr_type)) + if (ip_route_me_harder(nskb, RTN_UNSPEC)) goto free_nskb; niph->ttl = ip4_dst_hoplimit(skb_dst(nskb)); diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index f3a9b42..9bb1b8a 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -82,7 +82,7 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, #endif #endif /* Gather fragments. */ - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { enum ip_defrag_users user = nf_ct_defrag_user(hooknum, skb); if (nf_ct_ipv4_gather_frags(skb, user)) return NF_STOLEN; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 8812a02..076b7c8 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -719,117 +719,115 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, l = 0; switch (type) { - case SNMP_INTEGER: - len = sizeof(long); - if (!asn1_long_decode(ctx, end, &l)) { - kfree(id); - return 0; - } - *obj = kmalloc(sizeof(struct snmp_object) + len, - GFP_ATOMIC); - if (*obj == NULL) { - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - (*obj)->syntax.l[0] = l; - break; - case SNMP_OCTETSTR: - case SNMP_OPAQUE: - if (!asn1_octets_decode(ctx, end, &p, &len)) { - kfree(id); - return 0; - } - *obj = kmalloc(sizeof(struct snmp_object) + len, - GFP_ATOMIC); - if (*obj == NULL) { - kfree(p); - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - memcpy((*obj)->syntax.c, p, len); + case SNMP_INTEGER: + len = sizeof(long); + if (!asn1_long_decode(ctx, end, &l)) { + kfree(id); + return 0; + } + *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); + if (*obj == NULL) { + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + (*obj)->syntax.l[0] = l; + break; + case SNMP_OCTETSTR: + case SNMP_OPAQUE: + if (!asn1_octets_decode(ctx, end, &p, &len)) { + kfree(id); + return 0; + } + *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); + if (*obj == NULL) { kfree(p); - break; - case SNMP_NULL: - case SNMP_NOSUCHOBJECT: - case SNMP_NOSUCHINSTANCE: - case SNMP_ENDOFMIBVIEW: - len = 0; - *obj = kmalloc(sizeof(struct snmp_object), GFP_ATOMIC); - if (*obj == NULL) { - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - if (!asn1_null_decode(ctx, end)) { - kfree(id); - kfree(*obj); - *obj = NULL; - return 0; - } - break; - case SNMP_OBJECTID: - if (!asn1_oid_decode(ctx, end, (unsigned long **)&lp, &len)) { - kfree(id); - return 0; - } - len *= sizeof(unsigned long); - *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); - if (*obj == NULL) { - kfree(lp); - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - memcpy((*obj)->syntax.ul, lp, len); + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + memcpy((*obj)->syntax.c, p, len); + kfree(p); + break; + case SNMP_NULL: + case SNMP_NOSUCHOBJECT: + case SNMP_NOSUCHINSTANCE: + case SNMP_ENDOFMIBVIEW: + len = 0; + *obj = kmalloc(sizeof(struct snmp_object), GFP_ATOMIC); + if (*obj == NULL) { + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + if (!asn1_null_decode(ctx, end)) { + kfree(id); + kfree(*obj); + *obj = NULL; + return 0; + } + break; + case SNMP_OBJECTID: + if (!asn1_oid_decode(ctx, end, (unsigned long **)&lp, &len)) { + kfree(id); + return 0; + } + len *= sizeof(unsigned long); + *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); + if (*obj == NULL) { kfree(lp); - break; - case SNMP_IPADDR: - if (!asn1_octets_decode(ctx, end, &p, &len)) { - kfree(id); - return 0; - } - if (len != 4) { - kfree(p); - kfree(id); - return 0; - } - *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); - if (*obj == NULL) { - kfree(p); - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - memcpy((*obj)->syntax.uc, p, len); + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + memcpy((*obj)->syntax.ul, lp, len); + kfree(lp); + break; + case SNMP_IPADDR: + if (!asn1_octets_decode(ctx, end, &p, &len)) { + kfree(id); + return 0; + } + if (len != 4) { kfree(p); - break; - case SNMP_COUNTER: - case SNMP_GAUGE: - case SNMP_TIMETICKS: - len = sizeof(unsigned long); - if (!asn1_ulong_decode(ctx, end, &ul)) { - kfree(id); - return 0; - } - *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); - if (*obj == NULL) { - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - (*obj)->syntax.ul[0] = ul; - break; - default: kfree(id); return 0; + } + *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); + if (*obj == NULL) { + kfree(p); + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + memcpy((*obj)->syntax.uc, p, len); + kfree(p); + break; + case SNMP_COUNTER: + case SNMP_GAUGE: + case SNMP_TIMETICKS: + len = sizeof(unsigned long); + if (!asn1_ulong_decode(ctx, end, &ul)) { + kfree(id); + return 0; + } + *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); + if (*obj == NULL) { + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + (*obj)->syntax.ul[0] = ul; + break; + default: + kfree(id); + return 0; } (*obj)->syntax_len = len; diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 483b76d..a6e606e 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -88,7 +88,7 @@ nf_nat_fn(unsigned int hooknum, /* We never see fragments: conntrack defrags on pre-routing and local-out, and nf_nat_out protects post-routing. */ - NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET))); + NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb))); ct = nf_ct_get(skb, &ctinfo); /* Can't track? It's not due to stress, or conntrack would diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index c9893d4..0852678 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -825,28 +825,28 @@ static int compat_raw_getsockopt(struct sock *sk, int level, int optname, static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch (cmd) { - case SIOCOUTQ: { - int amount = sk_wmem_alloc_get(sk); + case SIOCOUTQ: { + int amount = sk_wmem_alloc_get(sk); - return put_user(amount, (int __user *)arg); - } - case SIOCINQ: { - struct sk_buff *skb; - int amount = 0; - - spin_lock_bh(&sk->sk_receive_queue.lock); - skb = skb_peek(&sk->sk_receive_queue); - if (skb != NULL) - amount = skb->len; - spin_unlock_bh(&sk->sk_receive_queue.lock); - return put_user(amount, (int __user *)arg); - } + return put_user(amount, (int __user *)arg); + } + case SIOCINQ: { + struct sk_buff *skb; + int amount = 0; + + spin_lock_bh(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); + if (skb != NULL) + amount = skb->len; + spin_unlock_bh(&sk->sk_receive_queue.lock); + return put_user(amount, (int __user *)arg); + } - default: + default: #ifdef CONFIG_IP_MROUTE - return ipmr_ioctl(sk, cmd, (void __user *)arg); + return ipmr_ioctl(sk, cmd, (void __user *)arg); #else - return -ENOIOCTLCMD; + return -ENOIOCTLCMD; #endif } } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index aa13ef1..3313730 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -108,6 +108,7 @@ #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif +#include <net/atmclip.h> #define RT_FL_TOS(oldflp4) \ ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))) @@ -184,6 +185,8 @@ static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) return p; } +static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr); + static struct dst_ops ipv4_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), @@ -198,6 +201,7 @@ static struct dst_ops ipv4_dst_ops = { .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .local_out = __ip_local_out, + .neigh_lookup = ipv4_neigh_lookup, }; #define ECN_OR_COST(class) TC_PRIO_##class @@ -411,8 +415,10 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) "HHUptod\tSpecDst"); else { struct rtable *r = v; + struct neighbour *n; int len; + n = dst_get_neighbour(&r->dst); seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t" "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", r->dst.dev ? r->dst.dev->name : "*", @@ -425,9 +431,8 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) (int)((dst_metric(&r->dst, RTAX_RTT) >> 3) + dst_metric(&r->dst, RTAX_RTTVAR)), r->rt_key_tos, - r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1, - r->dst.hh ? (r->dst.hh->hh_output == - dev_queue_xmit) : 0, + -1, + (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0, r->rt_spec_dst, &len); seq_printf(seq, "%*s\n", 127 - len, ""); @@ -1006,6 +1011,37 @@ static int slow_chain_length(const struct rtable *head) return length >> FRACT_BITS; } +static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr) +{ + struct neigh_table *tbl = &arp_tbl; + static const __be32 inaddr_any = 0; + struct net_device *dev = dst->dev; + const __be32 *pkey = daddr; + struct neighbour *n; + +#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE) + if (dev->type == ARPHRD_ATM) + tbl = clip_tbl_hook; +#endif + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + pkey = &inaddr_any; + + n = __ipv4_neigh_lookup(tbl, dev, *(__force u32 *)pkey); + if (n) + return n; + return neigh_create(tbl, pkey, dev); +} + +static int rt_bind_neighbour(struct rtable *rt) +{ + struct neighbour *n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); + if (IS_ERR(n)) + return PTR_ERR(n); + dst_set_neighbour(&rt->dst, n); + + return 0; +} + static struct rtable *rt_intern_hash(unsigned hash, struct rtable *rt, struct sk_buff *skb, int ifindex) { @@ -1042,7 +1078,7 @@ restart: rt->dst.flags |= DST_NOCACHE; if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { - int err = arp_bind_neighbour(&rt->dst); + int err = rt_bind_neighbour(rt); if (err) { if (net_ratelimit()) printk(KERN_WARNING @@ -1138,7 +1174,7 @@ restart: route or unicast forwarding path. */ if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { - int err = arp_bind_neighbour(&rt->dst); + int err = rt_bind_neighbour(rt); if (err) { spin_unlock_bh(rt_hash_lock_addr(hash)); @@ -1439,20 +1475,20 @@ static int ip_error(struct sk_buff *skb) int code; switch (rt->dst.error) { - case EINVAL: - default: - goto out; - case EHOSTUNREACH: - code = ICMP_HOST_UNREACH; - break; - case ENETUNREACH: - code = ICMP_NET_UNREACH; - IP_INC_STATS_BH(dev_net(rt->dst.dev), - IPSTATS_MIB_INNOROUTES); - break; - case EACCES: - code = ICMP_PKT_FILTERED; - break; + case EINVAL: + default: + goto out; + case EHOSTUNREACH: + code = ICMP_HOST_UNREACH; + break; + case ENETUNREACH: + code = ICMP_NET_UNREACH; + IP_INC_STATS_BH(dev_net(rt->dst.dev), + IPSTATS_MIB_INNOROUTES); + break; + case EACCES: + code = ICMP_PKT_FILTERED; + break; } if (!rt->peer) @@ -1592,23 +1628,24 @@ static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) { struct rtable *rt = (struct rtable *) dst; __be32 orig_gw = rt->rt_gateway; + struct neighbour *n; dst_confirm(&rt->dst); - neigh_release(rt->dst.neighbour); - rt->dst.neighbour = NULL; + neigh_release(dst_get_neighbour(&rt->dst)); + dst_set_neighbour(&rt->dst, NULL); rt->rt_gateway = peer->redirect_learned.a4; - if (arp_bind_neighbour(&rt->dst) || - !(rt->dst.neighbour->nud_state & NUD_VALID)) { - if (rt->dst.neighbour) - neigh_event_send(rt->dst.neighbour, NULL); + rt_bind_neighbour(rt); + n = dst_get_neighbour(&rt->dst); + if (!n || !(n->nud_state & NUD_VALID)) { + if (n) + neigh_event_send(n, NULL); rt->rt_gateway = orig_gw; return -EAGAIN; } else { rt->rt_flags |= RTCF_REDIRECTED; - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, - rt->dst.neighbour); + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } return 0; } @@ -2708,6 +2745,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .cow_metrics = ipv4_rt_blackhole_cow_metrics, + .neigh_lookup = ipv4_neigh_lookup, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) @@ -3303,7 +3341,7 @@ int __init ip_rt_init(void) xfrm_init(); xfrm4_init(ip_rt_max_size); #endif - rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL); + rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL); #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 2646149..92bb943 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -316,6 +316,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; + treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; /* 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) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 57d0752..69fd720 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -398,20 +398,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec_jiffies, }, { - .procname = "inet_peer_gc_mintime", - .data = &inet_peer_gc_mintime, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "inet_peer_gc_maxtime", - .data = &inet_peer_gc_maxtime, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { .procname = "tcp_orphan_retries", .data = &sysctl_tcp_orphan_retries, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 054a59d..46febca 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3220,7 +3220,7 @@ __setup("thash_entries=", set_thash_entries); void __init tcp_init(void) { struct sk_buff *skb = NULL; - unsigned long nr_pages, limit; + unsigned long limit; int i, max_share, cnt; unsigned long jiffy = jiffies; @@ -3277,13 +3277,7 @@ void __init tcp_init(void) sysctl_tcp_max_orphans = cnt / 2; sysctl_max_syn_backlog = max(128, cnt / 256); - /* Set the pressure threshold to be a fraction of global memory that - * is up to 1/2 at 256 MB, decreasing toward zero with the amount of - * memory, with a floor of 128 pages. - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_tcp_mem[0] = limit / 4 * 3; sysctl_tcp_mem[1] = limit; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bef9f04..ea0d218 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -880,6 +880,11 @@ static void tcp_init_metrics(struct sock *sk) tp->snd_ssthresh = dst_metric(dst, RTAX_SSTHRESH); if (tp->snd_ssthresh > tp->snd_cwnd_clamp) tp->snd_ssthresh = tp->snd_cwnd_clamp; + } else { + /* ssthresh may have been reduced unnecessarily during. + * 3WHS. Restore it back to its initial default. + */ + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; } if (dst_metric(dst, RTAX_REORDERING) && tp->reordering != dst_metric(dst, RTAX_REORDERING)) { @@ -887,10 +892,7 @@ static void tcp_init_metrics(struct sock *sk) tp->reordering = dst_metric(dst, RTAX_REORDERING); } - if (dst_metric(dst, RTAX_RTT) == 0) - goto reset; - - if (!tp->srtt && dst_metric_rtt(dst, RTAX_RTT) < (TCP_TIMEOUT_INIT << 3)) + if (dst_metric(dst, RTAX_RTT) == 0 || tp->srtt == 0) goto reset; /* Initial rtt is determined from SYN,SYN-ACK. @@ -916,19 +918,26 @@ static void tcp_init_metrics(struct sock *sk) tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); } tcp_set_rto(sk); - if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp) { reset: - /* Play conservative. If timestamps are not - * supported, TCP will fail to recalculate correct - * rtt, if initial rto is too small. FORGET ALL AND RESET! + if (tp->srtt == 0) { + /* RFC2988bis: We've failed to get a valid RTT sample from + * 3WHS. This is most likely due to retransmission, + * including spurious one. Reset the RTO back to 3secs + * from the more aggressive 1sec to avoid more spurious + * retransmission. */ - if (!tp->rx_opt.saw_tstamp && tp->srtt) { - tp->srtt = 0; - tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT; - inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; - } + tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK; + inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK; } - tp->snd_cwnd = tcp_init_cwnd(tp, dst); + /* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been + * retransmitted. In light of RFC2988bis' more aggressive 1sec + * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK + * retransmission has occurred. + */ + if (tp->total_retrans > 1) + tp->snd_cwnd = 1; + else + tp->snd_cwnd = tcp_init_cwnd(tp, dst); tp->snd_cwnd_stamp = tcp_time_stamp; } @@ -3112,12 +3121,13 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) tcp_xmit_retransmit_queue(sk); } -static void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt) +void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt) { tcp_rtt_estimator(sk, seq_rtt); tcp_set_rto(sk); inet_csk(sk)->icsk_backoff = 0; } +EXPORT_SYMBOL(tcp_valid_rtt_meas); /* Read draft-ietf-tcplw-high-performance before mucking * with this code. (Supersedes RFC1323) @@ -5806,12 +5816,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); - /* tcp_ack considers this ACK as duplicate - * and does not calculate rtt. - * Force it here. - */ - tcp_ack_update_rtt(sk, 0, 0); - if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 708dc20..955b8e6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -429,8 +429,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) break; icsk->icsk_backoff--; - inet_csk(sk)->icsk_rto = __tcp_set_rto(tp) << - icsk->icsk_backoff; + inet_csk(sk)->icsk_rto = (tp->srtt ? __tcp_set_rto(tp) : + TCP_TIMEOUT_INIT) << icsk->icsk_backoff; tcp_bound_rto(sk); skb = tcp_write_queue_head(sk); @@ -1384,6 +1384,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) isn = tcp_v4_init_sequence(skb); } tcp_rsk(req)->snt_isn = isn; + tcp_rsk(req)->snt_synack = tcp_time_stamp; if (tcp_v4_send_synack(sk, dst, req, (struct request_values *)&tmp_ext) || @@ -1458,6 +1459,10 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; tcp_initialize_rcv_mss(newsk); + if (tcp_rsk(req)->snt_synack) + tcp_valid_rtt_meas(newsk, + tcp_time_stamp - tcp_rsk(req)->snt_synack); + newtp->total_retrans = req->retrans; #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ @@ -1855,7 +1860,7 @@ static int tcp_v4_init_sock(struct sock *sk) * algorithms that we must have the following bandaid to talk * efficiently to them. -DaveM */ - tp->snd_cwnd = 2; + tp->snd_cwnd = TCP_INIT_CWND; /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 80b1f80..d2fe4e0 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -486,7 +486,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, * algorithms that we must have the following bandaid to talk * efficiently to them. -DaveM */ - newtp->snd_cwnd = 2; + newtp->snd_cwnd = TCP_INIT_CWND; newtp->snd_cwnd_cnt = 0; newtp->bytes_acked = 0; @@ -720,6 +720,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDEFERACCEPTDROP); return NULL; } + if (tmp_opt.saw_tstamp && tmp_opt.rcv_tsecr) + tcp_rsk(req)->snt_synack = tmp_opt.rcv_tsecr; + else if (req->retrans) /* don't take RTT sample if retrans && ~TS */ + tcp_rsk(req)->snt_synack = 0; /* OK, ACK is valid, create big socket and * feed this segment to it. It will repeat all diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index abca870..1b5a193 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -105,6 +105,7 @@ #include <net/route.h> #include <net/checksum.h> #include <net/xfrm.h> +#include <trace/events/udp.h> #include "udp_impl.h" struct udp_table udp_table __read_mostly; @@ -1249,6 +1250,9 @@ csum_copy_err: if (noblock) return -EAGAIN; + + /* starting over for a new packet */ + msg->msg_flags &= ~MSG_TRUNC; goto try_again; } @@ -1363,6 +1367,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) is_udplite); UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); + trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } @@ -2206,16 +2211,10 @@ void __init udp_table_init(struct udp_table *table, const char *name) void __init udp_init(void) { - unsigned long nr_pages, limit; + unsigned long limit; udp_table_init(&udp_table, "UDP"); - /* Set the pressure threshold up by the same strategy of TCP. It is a - * fraction of global memory that is up to 1/2 at 256 MB, decreasing - * toward zero with the amount of memory, with a floor of 128 pages. - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_udp_mem[0] = limit / 4 * 3; sysctl_udp_mem[1] = limit; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 2d51840..327a617 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -32,7 +32,12 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) dst = skb_dst(skb); mtu = dst_mtu(dst); if (skb->len > mtu) { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); + if (skb->sk) + ip_local_error(skb->sk, EMSGSIZE, ip_hdr(skb)->daddr, + inet_sk(skb->sk)->inet_dport, mtu); + else + icmp_send(skb, ICMP_DEST_UNREACH, + ICMP_FRAG_NEEDED, htonl(mtu)); ret = -EMSGSIZE; } out: diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 981e43e..fc5368a 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -117,7 +117,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; - if (!(iph->frag_off & htons(IP_MF | IP_OFFSET))) { + if (!ip_is_fragment(iph)) { switch (iph->protocol) { case IPPROTO_UDP: case IPPROTO_UDPLITE: |