diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/batman-adv/icmp_socket.c | 1 | ||||
-rw-r--r-- | net/batman-adv/icmp_socket.h | 2 | ||||
-rw-r--r-- | net/batman-adv/main.c | 1 | ||||
-rw-r--r-- | net/batman-adv/routing.c | 1 | ||||
-rw-r--r-- | net/batman-adv/routing.h | 2 | ||||
-rw-r--r-- | net/batman-adv/send.c | 1 | ||||
-rw-r--r-- | net/batman-adv/send.h | 2 | ||||
-rw-r--r-- | net/batman-adv/soft-interface.c | 1 | ||||
-rw-r--r-- | net/batman-adv/translation-table.c | 1 | ||||
-rw-r--r-- | net/batman-adv/translation-table.h | 2 | ||||
-rw-r--r-- | net/batman-adv/unicast.c | 19 | ||||
-rw-r--r-- | net/bridge/br_device.c | 17 | ||||
-rw-r--r-- | net/bridge/br_if.c | 11 | ||||
-rw-r--r-- | net/core/dev.c | 53 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 2 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 43 | ||||
-rw-r--r-- | net/ipv4/fib_semantics.c | 2 | ||||
-rw-r--r-- | net/ipv4/inetpeer.c | 8 | ||||
-rw-r--r-- | net/ipv4/route.c | 417 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 2 | ||||
-rw-r--r-- | net/ipv6/route.c | 18 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 2 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_proto_sctp.c | 2 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_sync.c | 2 | ||||
-rw-r--r-- | net/packet/af_packet.c | 31 | ||||
-rw-r--r-- | net/rose/af_rose.c | 7 | ||||
-rw-r--r-- | net/rose/rose_route.c | 28 |
27 files changed, 335 insertions, 343 deletions
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 5e86d6f..319a7cc 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -24,7 +24,6 @@ #include <linux/slab.h> #include "icmp_socket.h" #include "send.h" -#include "types.h" #include "hash.h" #include "originator.h" #include "hard-interface.h" diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 08b1859..462b190 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -22,8 +22,6 @@ #ifndef _NET_BATMAN_ADV_ICMP_SOCKET_H_ #define _NET_BATMAN_ADV_ICMP_SOCKET_H_ -#include "types.h" - #define ICMP_SOCKET "socket" void bat_socket_init(void); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index dc9248d..06d956c 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -30,7 +30,6 @@ #include "translation-table.h" #include "hard-interface.h" #include "gateway_client.h" -#include "types.h" #include "vis.h" #include "hash.h" diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 028f739..8274140 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -28,7 +28,6 @@ #include "icmp_socket.h" #include "translation-table.h" #include "originator.h" -#include "types.h" #include "ring_buffer.h" #include "vis.h" #include "aggregation.h" diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index ceeca6f..a09d16f 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -22,8 +22,6 @@ #ifndef _NET_BATMAN_ADV_ROUTING_H_ #define _NET_BATMAN_ADV_ROUTING_H_ -#include "types.h" - void slide_own_bcast_window(struct batman_if *batman_if); void receive_bat_packet(struct ethhdr *ethhdr, struct batman_packet *batman_packet, diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 7cc620e..8314276 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -25,7 +25,6 @@ #include "translation-table.h" #include "soft-interface.h" #include "hard-interface.h" -#include "types.h" #include "vis.h" #include "aggregation.h" #include "gateway_common.h" diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index bc53ade..b68c272 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -22,8 +22,6 @@ #ifndef _NET_BATMAN_ADV_SEND_H_ #define _NET_BATMAN_ADV_SEND_H_ -#include "types.h" - int send_skb_packet(struct sk_buff *skb, struct batman_if *batman_if, uint8_t *dst_addr); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 145e0f7..bd088f8 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -26,7 +26,6 @@ #include "send.h" #include "bat_debugfs.h" #include "translation-table.h" -#include "types.h" #include "hash.h" #include "gateway_common.h" #include "gateway_client.h" diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index f6917dd..7fb6726 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -22,7 +22,6 @@ #include "main.h" #include "translation-table.h" #include "soft-interface.h" -#include "types.h" #include "hash.h" #include "originator.h" diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index a4f3a37..f19931c 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -22,8 +22,6 @@ #ifndef _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ #define _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ -#include "types.h" - int hna_local_init(struct bat_priv *bat_priv); void hna_local_add(struct net_device *soft_iface, uint8_t *addr); void hna_local_remove(struct bat_priv *bat_priv, diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index bedf294..121b11d 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -39,8 +39,8 @@ static struct sk_buff *frag_merge_packet(struct list_head *head, (struct unicast_frag_packet *)skb->data; struct sk_buff *tmp_skb; struct unicast_packet *unicast_packet; - int hdr_len = sizeof(struct unicast_packet), - uni_diff = sizeof(struct unicast_frag_packet) - hdr_len; + int hdr_len = sizeof(struct unicast_packet); + int uni_diff = sizeof(struct unicast_frag_packet) - hdr_len; /* set skb to the first part and tmp_skb to the second part */ if (up->flags & UNI_FRAG_HEAD) { @@ -231,6 +231,7 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, int ucf_hdr_len = sizeof(struct unicast_frag_packet); int data_len = skb->len - uc_hdr_len; int large_tail = 0; + uint16_t seqno; if (!bat_priv->primary_if) goto dropped; @@ -266,10 +267,9 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, frag1->flags = UNI_FRAG_HEAD | large_tail; frag2->flags = large_tail; - frag1->seqno = htons((uint16_t)atomic_inc_return( - &batman_if->frag_seqno)); - frag2->seqno = htons((uint16_t)atomic_inc_return( - &batman_if->frag_seqno)); + seqno = atomic_add_return(2, &batman_if->frag_seqno); + frag1->seqno = htons(seqno - 1); + frag2->seqno = htons(seqno); send_skb_packet(skb, batman_if, dstaddr); send_skb_packet(frag_skb, batman_if, dstaddr); @@ -286,7 +286,7 @@ int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct unicast_packet *unicast_packet; - struct orig_node *orig_node; + struct orig_node *orig_node = NULL; struct batman_if *batman_if; struct neigh_node *router; int data_len = skb->len; @@ -297,11 +297,6 @@ int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv) /* get routing information */ if (is_multicast_ether_addr(ethhdr->h_dest)) orig_node = (struct orig_node *)gw_get_selected(bat_priv); - else - orig_node = ((struct orig_node *)hash_find(bat_priv->orig_hash, - compare_orig, - choose_orig, - ethhdr->h_dest)); /* check for hna host */ if (!orig_node) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 5564435..1461b19 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -297,6 +297,21 @@ void br_netpoll_disable(struct net_bridge_port *p) #endif +static int br_add_slave(struct net_device *dev, struct net_device *slave_dev) + +{ + struct net_bridge *br = netdev_priv(dev); + + return br_add_if(br, slave_dev); +} + +static int br_del_slave(struct net_device *dev, struct net_device *slave_dev) +{ + struct net_bridge *br = netdev_priv(dev); + + return br_del_if(br, slave_dev); +} + static const struct ethtool_ops br_ethtool_ops = { .get_drvinfo = br_getinfo, .get_link = ethtool_op_get_link, @@ -326,6 +341,8 @@ static const struct net_device_ops br_netdev_ops = { .ndo_netpoll_cleanup = br_netpoll_cleanup, .ndo_poll_controller = br_poll_controller, #endif + .ndo_add_slave = br_add_slave, + .ndo_del_slave = br_del_slave, }; static void br_dev_free(struct net_device *dev) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 2a6801d..dce8f00 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -148,6 +148,8 @@ static void del_nbp(struct net_bridge_port *p) netdev_rx_handler_unregister(dev); + netdev_set_master(dev, NULL); + br_multicast_del_port(p); kobject_uevent(&p->kobj, KOBJ_REMOVE); @@ -429,10 +431,14 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (br_netpoll_info(br) && ((err = br_netpoll_enable(p)))) goto err3; - err = netdev_rx_handler_register(dev, br_handle_frame, p); + err = netdev_set_master(dev, br->dev); if (err) goto err3; + err = netdev_rx_handler_register(dev, br_handle_frame, p); + if (err) + goto err4; + dev->priv_flags |= IFF_BRIDGE_PORT; dev_disable_lro(dev); @@ -455,6 +461,9 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) kobject_uevent(&p->kobj, KOBJ_ADD); return 0; + +err4: + netdev_set_master(dev, NULL); err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: diff --git a/net/core/dev.c b/net/core/dev.c index 30c71f9..4580460 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3106,7 +3106,8 @@ static inline void skb_bond_set_mac_by_master(struct sk_buff *skb, * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and * ARP on active-backup slaves with arp_validate enabled. */ -int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master) +static int __skb_bond_should_drop(struct sk_buff *skb, + struct net_device *master) { struct net_device *dev = skb->dev; @@ -3140,14 +3141,12 @@ int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master) } return 0; } -EXPORT_SYMBOL(__skb_bond_should_drop); static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; struct net_device *orig_dev; - struct net_device *master; struct net_device *null_or_orig; struct net_device *orig_or_bond; int ret = NET_RX_DROP; @@ -3174,15 +3173,19 @@ static int __netif_receive_skb(struct sk_buff *skb) */ null_or_orig = NULL; orig_dev = skb->dev; - master = ACCESS_ONCE(orig_dev->master); if (skb->deliver_no_wcard) null_or_orig = orig_dev; - else if (master) { - if (skb_bond_should_drop(skb, master)) { - skb->deliver_no_wcard = 1; - null_or_orig = orig_dev; /* deliver only exact match */ - } else - skb->dev = master; + else if (netif_is_bond_slave(orig_dev)) { + struct net_device *bond_master = ACCESS_ONCE(orig_dev->master); + + if (likely(bond_master)) { + if (__skb_bond_should_drop(skb, bond_master)) { + skb->deliver_no_wcard = 1; + /* deliver only exact match */ + null_or_orig = orig_dev; + } else + skb->dev = bond_master; + } } __this_cpu_inc(softnet_data.processed); @@ -4347,15 +4350,14 @@ static int __init dev_proc_init(void) /** - * netdev_set_master - set up master/slave pair + * netdev_set_master - set up master pointer * @slave: slave device * @master: new master device * * Changes the master device of the slave. Pass %NULL to break the * bonding. The caller must hold the RTNL semaphore. On a failure * a negative errno code is returned. On success the reference counts - * are adjusted, %RTM_NEWLINK is sent to the routing socket and the - * function returns zero. + * are adjusted and the function returns zero. */ int netdev_set_master(struct net_device *slave, struct net_device *master) { @@ -4375,6 +4377,29 @@ int netdev_set_master(struct net_device *slave, struct net_device *master) synchronize_net(); dev_put(old); } + return 0; +} +EXPORT_SYMBOL(netdev_set_master); + +/** + * netdev_set_bond_master - set up bonding master/slave pair + * @slave: slave device + * @master: new master device + * + * Changes the master device of the slave. Pass %NULL to break the + * bonding. The caller must hold the RTNL semaphore. On a failure + * a negative errno code is returned. On success %RTM_NEWLINK is sent + * to the routing socket and the function returns zero. + */ +int netdev_set_bond_master(struct net_device *slave, struct net_device *master) +{ + int err; + + ASSERT_RTNL(); + + err = netdev_set_master(slave, master); + if (err) + return err; if (master) slave->flags |= IFF_SLAVE; else @@ -4383,7 +4408,7 @@ int netdev_set_master(struct net_device *slave, struct net_device *master) rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE); return 0; } -EXPORT_SYMBOL(netdev_set_master); +EXPORT_SYMBOL(netdev_set_bond_master); static void dev_change_rx_flags(struct net_device *dev, int flags) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 2e4a393..5ceb257 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -330,7 +330,7 @@ static struct device_attribute net_class_attributes[] = { __ATTR(flags, S_IRUGO | S_IWUSR, show_flags, store_flags), __ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len, store_tx_queue_len), - __ATTR(group, S_IRUGO | S_IWUSR, show_group, store_group), + __ATTR(netdev_group, S_IRUGO | S_IWUSR, show_group, store_group), {} }; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index da0fe45..49f7ea5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1036,6 +1036,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) }, [IFLA_MTU] = { .type = NLA_U32 }, [IFLA_LINK] = { .type = NLA_U32 }, + [IFLA_MASTER] = { .type = NLA_U32 }, [IFLA_TXQLEN] = { .type = NLA_U32 }, [IFLA_WEIGHT] = { .type = NLA_U32 }, [IFLA_OPERSTATE] = { .type = NLA_U8 }, @@ -1178,6 +1179,41 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) return err; } +static int do_set_master(struct net_device *dev, int ifindex) +{ + struct net_device *master_dev; + const struct net_device_ops *ops; + int err; + + if (dev->master) { + if (dev->master->ifindex == ifindex) + return 0; + ops = dev->master->netdev_ops; + if (ops->ndo_del_slave) { + err = ops->ndo_del_slave(dev->master, dev); + if (err) + return err; + } else { + return -EOPNOTSUPP; + } + } + + if (ifindex) { + master_dev = __dev_get_by_index(dev_net(dev), ifindex); + if (!master_dev) + return -EINVAL; + ops = master_dev->netdev_ops; + if (ops->ndo_add_slave) { + err = ops->ndo_add_slave(master_dev, dev); + if (err) + return err; + } else { + return -EOPNOTSUPP; + } + } + return 0; +} + static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { @@ -1301,6 +1337,13 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, goto errout; } + if (tb[IFLA_MASTER]) { + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER])); + if (err) + goto errout; + modified = 1; + } + if (tb[IFLA_TXQLEN]) dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 146bd82..562f34c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1189,7 +1189,7 @@ void fib_select_default(struct fib_result *res) fib_result_assign(res, last_resort); tb->tb_default = last_idx; out: - rcu_read_unlock(); + return; } #ifdef CONFIG_IP_ROUTE_MULTIPATH diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 709fbb4..48f8d45 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -167,9 +167,9 @@ static int addr_compare(const struct inetpeer_addr *a, int i, n = (a->family == AF_INET ? 1 : 4); for (i = 0; i < n; i++) { - if (a->a6[i] == b->a6[i]) + if (a->addr.a6[i] == b->addr.a6[i]) continue; - if (a->a6[i] < b->a6[i]) + if (a->addr.a6[i] < b->addr.a6[i]) return -1; return 1; } @@ -510,11 +510,13 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) p->daddr = *daddr; atomic_set(&p->refcnt, 1); atomic_set(&p->rid, 0); - atomic_set(&p->ip_id_count, secure_ip_id(daddr->a4)); + atomic_set(&p->ip_id_count, secure_ip_id(daddr->addr.a4)); p->tcp_ts_stamp = 0; p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; p->rate_last = 0; + p->pmtu_expires = 0; + memset(&p->redirect_learned, 0, sizeof(p->redirect_learned)); INIT_LIST_HEAD(&p->unused); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0455af8..756f544 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -131,9 +131,6 @@ static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int rt_chain_length_max __read_mostly = 20; -static struct delayed_work expires_work; -static unsigned long expires_ljiffies; - /* * Interface to generic destination cache. */ @@ -668,7 +665,7 @@ static inline int rt_fast_clean(struct rtable *rth) static inline int rt_valuable(struct rtable *rth) { return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) || - rth->dst.expires; + (rth->peer && rth->peer->pmtu_expires); } static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2) @@ -679,13 +676,7 @@ static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long t if (atomic_read(&rth->dst.__refcnt)) goto out; - ret = 1; - if (rth->dst.expires && - time_after_eq(jiffies, rth->dst.expires)) - goto out; - age = jiffies - rth->dst.lastuse; - ret = 0; if ((age <= tmo1 && !rt_fast_clean(rth)) || (age <= tmo2 && rt_valuable(rth))) goto out; @@ -829,97 +820,6 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth) return ONE; } -static void rt_check_expire(void) -{ - static unsigned int rover; - unsigned int i = rover, goal; - struct rtable *rth; - struct rtable __rcu **rthp; - unsigned long samples = 0; - unsigned long sum = 0, sum2 = 0; - unsigned long delta; - u64 mult; - - delta = jiffies - expires_ljiffies; - expires_ljiffies = jiffies; - mult = ((u64)delta) << rt_hash_log; - if (ip_rt_gc_timeout > 1) - do_div(mult, ip_rt_gc_timeout); - goal = (unsigned int)mult; - if (goal > rt_hash_mask) - goal = rt_hash_mask + 1; - for (; goal > 0; goal--) { - unsigned long tmo = ip_rt_gc_timeout; - unsigned long length; - - i = (i + 1) & rt_hash_mask; - rthp = &rt_hash_table[i].chain; - - if (need_resched()) - cond_resched(); - - samples++; - - if (rcu_dereference_raw(*rthp) == NULL) - continue; - length = 0; - spin_lock_bh(rt_hash_lock_addr(i)); - while ((rth = rcu_dereference_protected(*rthp, - lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) { - prefetch(rth->dst.rt_next); - if (rt_is_expired(rth)) { - *rthp = rth->dst.rt_next; - rt_free(rth); - continue; - } - if (rth->dst.expires) { - /* Entry is expired even if it is in use */ - if (time_before_eq(jiffies, rth->dst.expires)) { -nofree: - tmo >>= 1; - rthp = &rth->dst.rt_next; - /* - * We only count entries on - * a chain with equal hash inputs once - * so that entries for different QOS - * levels, and other non-hash input - * attributes don't unfairly skew - * the length computation - */ - length += has_noalias(rt_hash_table[i].chain, rth); - continue; - } - } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) - goto nofree; - - /* Cleanup aged off entries. */ - *rthp = rth->dst.rt_next; - rt_free(rth); - } - spin_unlock_bh(rt_hash_lock_addr(i)); - sum += length; - sum2 += length*length; - } - if (samples) { - unsigned long avg = sum / samples; - unsigned long sd = int_sqrt(sum2 / samples - avg*avg); - rt_chain_length_max = max_t(unsigned long, - ip_rt_gc_elasticity, - (avg + 4*sd) >> FRACT_BITS); - } - rover = i; -} - -/* - * rt_worker_func() is run in process context. - * we call rt_check_expire() to scan part of the hash table - */ -static void rt_worker_func(struct work_struct *work) -{ - rt_check_expire(); - schedule_delayed_work(&expires_work, ip_rt_gc_interval); -} - /* * Pertubation of rt_genid by a small quantity [1..256] * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() @@ -1308,6 +1208,13 @@ skip_hashing: return 0; } +static atomic_t __rt_peer_genid = ATOMIC_INIT(0); + +static u32 rt_peer_genid(void) +{ + return atomic_read(&__rt_peer_genid); +} + void rt_bind_peer(struct rtable *rt, int create) { struct inet_peer *peer; @@ -1316,6 +1223,8 @@ void rt_bind_peer(struct rtable *rt, int create) if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL) inet_putpeer(peer); + else + rt->rt_peer_genid = rt_peer_genid(); } /* @@ -1385,13 +1294,8 @@ static void rt_del(unsigned hash, struct rtable *rt) void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, __be32 saddr, struct net_device *dev) { - int i, k; struct in_device *in_dev = __in_dev_get_rcu(dev); - struct rtable *rth; - struct rtable __rcu **rthp; - __be32 skeys[2] = { saddr, 0 }; - int ikeys[2] = { dev->ifindex, 0 }; - struct netevent_redirect netevent; + struct inet_peer *peer; struct net *net; if (!in_dev) @@ -1403,9 +1307,6 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, ipv4_is_zeronet(new_gw)) goto reject_redirect; - if (!rt_caching(net)) - goto reject_redirect; - if (!IN_DEV_SHARED_MEDIA(in_dev)) { if (!inet_addr_onlink(in_dev, new_gw, old_gw)) goto reject_redirect; @@ -1416,93 +1317,13 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - for (i = 0; i < 2; i++) { - for (k = 0; k < 2; k++) { - unsigned hash = rt_hash(daddr, skeys[i], ikeys[k], - rt_genid(net)); - - rthp = &rt_hash_table[hash].chain; - - while ((rth = rcu_dereference(*rthp)) != NULL) { - struct rtable *rt; - - if (rth->fl.fl4_dst != daddr || - rth->fl.fl4_src != skeys[i] || - rth->fl.oif != ikeys[k] || - rt_is_input_route(rth) || - rt_is_expired(rth) || - !net_eq(dev_net(rth->dst.dev), net)) { - rthp = &rth->dst.rt_next; - continue; - } - - if (rth->rt_dst != daddr || - rth->rt_src != saddr || - rth->dst.error || - rth->rt_gateway != old_gw || - rth->dst.dev != dev) - break; - - dst_hold(&rth->dst); - - rt = dst_alloc(&ipv4_dst_ops); - if (rt == NULL) { - ip_rt_put(rth); - return; - } - - /* Copy all the information. */ - *rt = *rth; - rt->dst.__use = 1; - atomic_set(&rt->dst.__refcnt, 1); - rt->dst.child = NULL; - if (rt->dst.dev) - dev_hold(rt->dst.dev); - rt->dst.obsolete = -1; - rt->dst.lastuse = jiffies; - rt->dst.path = &rt->dst; - rt->dst.neighbour = NULL; - rt->dst.hh = NULL; -#ifdef CONFIG_XFRM - rt->dst.xfrm = NULL; -#endif - rt->rt_genid = rt_genid(net); - rt->rt_flags |= RTCF_REDIRECTED; - - /* Gateway is different ... */ - rt->rt_gateway = new_gw; - - /* Redirect received -> path was valid */ - dst_confirm(&rth->dst); - - if (rt->peer) - atomic_inc(&rt->peer->refcnt); - if (rt->fi) - atomic_inc(&rt->fi->fib_clntref); - - if (arp_bind_neighbour(&rt->dst) || - !(rt->dst.neighbour->nud_state & - NUD_VALID)) { - if (rt->dst.neighbour) - neigh_event_send(rt->dst.neighbour, NULL); - ip_rt_put(rth); - rt_drop(rt); - goto do_next; - } + peer = inet_getpeer_v4(daddr, 1); + if (peer) { + peer->redirect_learned.a4 = new_gw; - netevent.old = &rth->dst; - netevent.new = &rt->dst; - call_netevent_notifiers(NETEVENT_REDIRECT, - &netevent); + inet_putpeer(peer); - rt_del(hash, rth); - if (!rt_intern_hash(hash, rt, &rt, NULL, rt->fl.oif)) - ip_rt_put(rt); - goto do_next; - } - do_next: - ; - } + atomic_inc(&__rt_peer_genid); } return; @@ -1526,9 +1347,7 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) if (dst->obsolete > 0) { ip_rt_put(rt); ret = NULL; - } else if ((rt->rt_flags & RTCF_REDIRECTED) || - (rt->dst.expires && - time_after_eq(jiffies, rt->dst.expires))) { + } else if (rt->rt_flags & RTCF_REDIRECTED) { unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, rt->fl.oif, rt_genid(dev_net(dst->dev))); @@ -1538,6 +1357,14 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) #endif rt_del(hash, rt); ret = NULL; + } else if (rt->peer && + rt->peer->pmtu_expires && + time_after_eq(jiffies, rt->peer->pmtu_expires)) { + unsigned long orig = rt->peer->pmtu_expires; + + if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig) + dst_metric_set(dst, RTAX_MTU, + rt->peer->pmtu_orig); } } return ret; @@ -1688,87 +1515,130 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, unsigned short new_mtu, struct net_device *dev) { - int i, k; unsigned short old_mtu = ntohs(iph->tot_len); - struct rtable *rth; - int ikeys[2] = { dev->ifindex, 0 }; - __be32 skeys[2] = { iph->saddr, 0, }; - __be32 daddr = iph->daddr; unsigned short est_mtu = 0; + struct inet_peer *peer; - for (k = 0; k < 2; k++) { - for (i = 0; i < 2; i++) { - unsigned hash = rt_hash(daddr, skeys[i], ikeys[k], - rt_genid(net)); - - rcu_read_lock(); - for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; - rth = rcu_dereference(rth->dst.rt_next)) { - unsigned short mtu = new_mtu; - - if (rth->fl.fl4_dst != daddr || - rth->fl.fl4_src != skeys[i] || - rth->rt_dst != daddr || - rth->rt_src != iph->saddr || - rth->fl.oif != ikeys[k] || - rt_is_input_route(rth) || - dst_metric_locked(&rth->dst, RTAX_MTU) || - !net_eq(dev_net(rth->dst.dev), net) || - rt_is_expired(rth)) - continue; - - if (new_mtu < 68 || new_mtu >= old_mtu) { + peer = inet_getpeer_v4(iph->daddr, 1); + if (peer) { + unsigned short mtu = new_mtu; - /* BSD 4.2 compatibility hack :-( */ - if (mtu == 0 && - old_mtu >= dst_mtu(&rth->dst) && - old_mtu >= 68 + (iph->ihl << 2)) - old_mtu -= iph->ihl << 2; + if (new_mtu < 68 || new_mtu >= old_mtu) { + /* BSD 4.2 derived systems incorrectly adjust + * tot_len by the IP header length, and report + * a zero MTU in the ICMP message. + */ + if (mtu == 0 && + old_mtu >= 68 + (iph->ihl << 2)) + old_mtu -= iph->ihl << 2; + mtu = guess_mtu(old_mtu); + } - mtu = guess_mtu(old_mtu); - } - if (mtu <= dst_mtu(&rth->dst)) { - if (mtu < dst_mtu(&rth->dst)) { - dst_confirm(&rth->dst); - if (mtu < ip_rt_min_pmtu) { - u32 lock = dst_metric(&rth->dst, - RTAX_LOCK); - mtu = ip_rt_min_pmtu; - lock |= (1 << RTAX_MTU); - dst_metric_set(&rth->dst, RTAX_LOCK, - lock); - } - dst_metric_set(&rth->dst, RTAX_MTU, mtu); - dst_set_expires(&rth->dst, - ip_rt_mtu_expires); - } - est_mtu = mtu; - } - } - rcu_read_unlock(); + if (mtu < ip_rt_min_pmtu) + mtu = ip_rt_min_pmtu; + if (!peer->pmtu_expires || mtu < peer->pmtu_learned) { + est_mtu = mtu; + peer->pmtu_learned = mtu; + peer->pmtu_expires = jiffies + ip_rt_mtu_expires; } + + inet_putpeer(peer); + + atomic_inc(&__rt_peer_genid); } return est_mtu ? : new_mtu; } +static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer) +{ + unsigned long expires = peer->pmtu_expires; + + if (time_before(expires, jiffies)) { + u32 orig_dst_mtu = dst_mtu(dst); + if (peer->pmtu_learned < orig_dst_mtu) { + if (!peer->pmtu_orig) + peer->pmtu_orig = dst_metric_raw(dst, RTAX_MTU); + dst_metric_set(dst, RTAX_MTU, peer->pmtu_learned); + } + } else if (cmpxchg(&peer->pmtu_expires, expires, 0) == expires) + dst_metric_set(dst, RTAX_MTU, peer->pmtu_orig); +} + static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) { - if (dst_mtu(dst) > mtu && mtu >= 68 && - !(dst_metric_locked(dst, RTAX_MTU))) { - if (mtu < ip_rt_min_pmtu) { - u32 lock = dst_metric(dst, RTAX_LOCK); + struct rtable *rt = (struct rtable *) dst; + struct inet_peer *peer; + + dst_confirm(dst); + + if (!rt->peer) + rt_bind_peer(rt, 1); + peer = rt->peer; + if (peer) { + if (mtu < ip_rt_min_pmtu) mtu = ip_rt_min_pmtu; - dst_metric_set(dst, RTAX_LOCK, lock | (1 << RTAX_MTU)); + if (!peer->pmtu_expires || mtu < peer->pmtu_learned) { + peer->pmtu_learned = mtu; + peer->pmtu_expires = jiffies + ip_rt_mtu_expires; + + atomic_inc(&__rt_peer_genid); + rt->rt_peer_genid = rt_peer_genid(); + + check_peer_pmtu(dst, peer); } - dst_metric_set(dst, RTAX_MTU, mtu); - dst_set_expires(dst, ip_rt_mtu_expires); + inet_putpeer(peer); } } +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; + + dst_confirm(&rt->dst); + + neigh_release(rt->dst.neighbour); + rt->dst.neighbour = 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->rt_gateway = orig_gw; + return -EAGAIN; + } else { + rt->rt_flags |= RTCF_REDIRECTED; + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, + rt->dst.neighbour); + } + return 0; +} + static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { - if (rt_is_expired((struct rtable *)dst)) + struct rtable *rt = (struct rtable *) dst; + + if (rt_is_expired(rt)) return NULL; + if (rt->rt_peer_genid != rt_peer_genid()) { + struct inet_peer *peer; + + if (!rt->peer) + rt_bind_peer(rt, 0); + + peer = rt->peer; + if (peer && peer->pmtu_expires) + check_peer_pmtu(dst, peer); + + if (peer && peer->redirect_learned.a4 && + peer->redirect_learned.a4 != rt->rt_gateway) { + if (check_peer_redir(dst, peer)) + return NULL; + } + + rt->rt_peer_genid = rt_peer_genid(); + } return dst; } @@ -1795,8 +1665,14 @@ static void ipv4_link_failure(struct sk_buff *skb) icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); rt = skb_rtable(skb); - if (rt) - dst_set_expires(&rt->dst, 0); + if (rt && + rt->peer && + rt->peer->pmtu_expires) { + unsigned long orig = rt->peer->pmtu_expires; + + if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig) + dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig); + } } static int ip_rt_bug(struct sk_buff *skb) @@ -1894,6 +1770,14 @@ static void rt_init_metrics(struct rtable *rt, struct fib_info *fi) memcpy(peer->metrics, fi->fib_metrics, sizeof(u32) * RTAX_MAX); dst_init_metrics(&rt->dst, peer->metrics, false); + + if (peer->pmtu_expires) + check_peer_pmtu(&rt->dst, peer); + if (peer->redirect_learned.a4 && + peer->redirect_learned.a4 != rt->rt_gateway) { + rt->rt_gateway = peer->redirect_learned.a4; + rt->rt_flags |= RTCF_REDIRECTED; + } } else { if (fi->fib_metrics != (u32 *) dst_default_metrics) { rt->fi = fi; @@ -2944,7 +2828,8 @@ static int rt_fill_info(struct net *net, NLA_PUT_BE32(skb, RTA_MARK, rt->fl.mark); error = rt->dst.error; - expires = rt->dst.expires ? rt->dst.expires - jiffies : 0; + expires = (rt->peer && rt->peer->pmtu_expires) ? + rt->peer->pmtu_expires - jiffies : 0; if (rt->peer) { inet_peer_refcheck(rt->peer); id = atomic_read(&rt->peer->ip_id_count) & 0xffff; @@ -3401,14 +3286,6 @@ int __init ip_rt_init(void) devinet_init(); ip_fib_init(); - /* All the timers, started at system startup tend - to synchronize. Perturb it a bit. - */ - INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func); - expires_ljiffies = jiffies; - schedule_delayed_work(&expires_work, - net_random() % ip_rt_gc_interval + ip_rt_gc_interval); - if (ip_rt_proc_init()) printk(KERN_ERR "Unable to create route proc files\n"); #ifdef CONFIG_XFRM diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 02f583b..e2b9be2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1341,7 +1341,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_death_row.sysctl_tw_recycle && (dst = inet_csk_route_req(sk, req)) != NULL && (peer = rt_get_peer((struct rtable *)dst)) != NULL && - peer->daddr.a4 == saddr) { + peer->daddr.addr.a4 == saddr) { inet_peer_refcheck(peer); if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && (s32)(peer->tcp_ts - req->ts_recent) > diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 12ec83d..ad8556e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -240,6 +240,13 @@ static void ip6_dst_destroy(struct dst_entry *dst) } } +static atomic_t __rt6_peer_genid = ATOMIC_INIT(0); + +static u32 rt6_peer_genid(void) +{ + return atomic_read(&__rt6_peer_genid); +} + void rt6_bind_peer(struct rt6_info *rt, int create) { struct inet_peer *peer; @@ -247,6 +254,8 @@ void rt6_bind_peer(struct rt6_info *rt, int create) peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create); if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL) inet_putpeer(peer); + else + rt->rt6i_peer_genid = rt6_peer_genid(); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -912,9 +921,14 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = (struct rt6_info *) dst; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) + if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { + if (rt->rt6i_peer_genid != rt6_peer_genid()) { + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 0); + rt->rt6i_peer_genid = rt6_peer_genid(); + } return dst; - + } return NULL; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 20aa95e..d6954e3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1323,7 +1323,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_death_row.sysctl_tw_recycle && (dst = inet6_csk_route_req(sk, req)) != NULL && (peer = rt6_get_peer((struct rt6_info *)dst)) != NULL && - ipv6_addr_equal((struct in6_addr *)peer->daddr.a6, + ipv6_addr_equal((struct in6_addr *)peer->daddr.addr.a6, &treq->rmt_addr)) { inet_peer_refcheck(peer); if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index fb2d04a..b027ccc 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -1101,7 +1101,7 @@ static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) struct netns_ipvs *ipvs = net_ipvs(net); ip_vs_init_hash_table(ipvs->sctp_apps, SCTP_APP_TAB_SIZE); - spin_lock_init(&ipvs->tcp_app_lock); + spin_lock_init(&ipvs->sctp_app_lock); pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts, sizeof(sctp_timeouts)); } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 2a2a836..d1b7298 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -392,7 +392,7 @@ void ip_vs_sync_switch_mode(struct net *net, int mode) { struct netns_ipvs *ipvs = net_ipvs(net); - if (!ipvs->sync_state & IP_VS_STATE_MASTER) + if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) return; if (mode == ipvs->sysctl_sync_ver || !ipvs->sync_buff) return; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c60649e..5efef5b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -465,7 +465,7 @@ retry: */ err = -EMSGSIZE; - if (len > dev->mtu + dev->hard_header_len) + if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN) goto out_unlock; if (!skb) { @@ -496,6 +496,19 @@ retry: goto retry; } + if (len > (dev->mtu + dev->hard_header_len)) { + /* Earlier code assumed this would be a VLAN pkt, + * double-check this now that we have the actual + * packet in hand. + */ + struct ethhdr *ehdr; + skb_reset_mac_header(skb); + ehdr = eth_hdr(skb); + if (ehdr->h_proto != htons(ETH_P_8021Q)) { + err = -EMSGSIZE; + goto out_unlock; + } + } skb->protocol = proto; skb->dev = dev; @@ -1199,7 +1212,7 @@ static int packet_snd(struct socket *sock, } err = -EMSGSIZE; - if (!gso_type && (len > dev->mtu+reserve)) + if (!gso_type && (len > dev->mtu + reserve + VLAN_HLEN)) goto out_unlock; err = -ENOBUFS; @@ -1224,6 +1237,20 @@ static int packet_snd(struct socket *sock, if (err < 0) goto out_free; + if (!gso_type && (len > dev->mtu + reserve)) { + /* Earlier code assumed this would be a VLAN pkt, + * double-check this now that we have the actual + * packet in hand. + */ + struct ethhdr *ehdr; + skb_reset_mac_header(skb); + ehdr = eth_hdr(skb); + if (ehdr->h_proto != htons(ETH_P_8021Q)) { + err = -EMSGSIZE; + goto out_free; + } + } + skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index d952e7e..5ee0c62 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -803,7 +803,6 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le rose_insert_socket(sk); /* Finish the bind */ } -rose_try_next_neigh: rose->dest_addr = addr->srose_addr; rose->dest_call = addr->srose_call; rose->rand = ((long)rose & 0xFFFF) + rose->lci; @@ -865,12 +864,6 @@ rose_try_next_neigh: } if (sk->sk_state != TCP_ESTABLISHED) { - /* Try next neighbour */ - rose->neighbour = rose_get_neigh(&addr->srose_addr, &cause, &diagnostic, 0); - if (rose->neighbour) - goto rose_try_next_neigh; - - /* No more neighbours */ sock->state = SS_UNCONNECTED; err = sock_error(sk); /* Always set at this point */ goto out_release; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index b4fdaac..88a77e9 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -674,29 +674,34 @@ struct rose_route *rose_route_free_lci(unsigned int lci, struct rose_neigh *neig * Find a neighbour or a route given a ROSE address. */ struct rose_neigh *rose_get_neigh(rose_address *addr, unsigned char *cause, - unsigned char *diagnostic, int new) + unsigned char *diagnostic, int route_frame) { struct rose_neigh *res = NULL; struct rose_node *node; int failed = 0; int i; - if (!new) spin_lock_bh(&rose_node_list_lock); + if (!route_frame) spin_lock_bh(&rose_node_list_lock); for (node = rose_node_list; node != NULL; node = node->next) { if (rosecmpm(addr, &node->address, node->mask) == 0) { for (i = 0; i < node->count; i++) { - if (new) { - if (node->neighbour[i]->restarted) { - res = node->neighbour[i]; - goto out; - } + if (node->neighbour[i]->restarted) { + res = node->neighbour[i]; + goto out; } - else { + } + } + } + if (!route_frame) { /* connect request */ + for (node = rose_node_list; node != NULL; node = node->next) { + if (rosecmpm(addr, &node->address, node->mask) == 0) { + for (i = 0; i < node->count; i++) { if (!rose_ftimer_running(node->neighbour[i])) { res = node->neighbour[i]; + failed = 0; goto out; - } else - failed = 1; + } + failed = 1; } } } @@ -711,8 +716,7 @@ struct rose_neigh *rose_get_neigh(rose_address *addr, unsigned char *cause, } out: - if (!new) spin_unlock_bh(&rose_node_list_lock); - + if (!route_frame) spin_unlock_bh(&rose_node_list_lock); return res; } |