diff options
Diffstat (limited to 'net')
111 files changed, 1086 insertions, 1004 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 3fe4fc86055..6567213959c 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -376,6 +376,7 @@ void vlan_setup(struct net_device *new_dev) new_dev->init = vlan_dev_init; new_dev->open = vlan_dev_open; new_dev->stop = vlan_dev_stop; + new_dev->set_mac_address = vlan_set_mac_address; new_dev->set_multicast_list = vlan_dev_set_multicast_list; new_dev->change_rx_flags = vlan_change_rx_flags; new_dev->destructor = free_netdev; @@ -636,6 +637,10 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (!vlandev) continue; + flgs = vlandev->flags; + if (!(flgs & IFF_UP)) + continue; + vlan_sync_address(dev, vlandev); } break; @@ -747,6 +752,7 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg) vlan_dev_set_ingress_priority(dev, args.u.skb_priority, args.vlan_qos); + err = 0; break; case SET_VLAN_EGRESS_PRIORITY_CMD: diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index cf4a80d06b3..2cd1393073e 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -60,6 +60,7 @@ int vlan_dev_hwaccel_hard_start_xmit(struct sk_buff *skb, struct net_device *dev int vlan_dev_change_mtu(struct net_device *dev, int new_mtu); int vlan_dev_open(struct net_device* dev); int vlan_dev_stop(struct net_device* dev); +int vlan_set_mac_address(struct net_device *dev, void *p); int vlan_dev_ioctl(struct net_device* dev, struct ifreq *ifr, int cmd); void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, short vlan_prio); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 1a1740aa9a8..7a36878241d 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -665,6 +665,32 @@ int vlan_dev_stop(struct net_device *dev) return 0; } +int vlan_set_mac_address(struct net_device *dev, void *p) +{ + struct net_device *real_dev = VLAN_DEV_INFO(dev)->real_dev; + struct sockaddr *addr = p; + int err; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + if (!(dev->flags & IFF_UP)) + goto out; + + if (compare_ether_addr(addr->sa_data, real_dev->dev_addr)) { + err = dev_unicast_add(real_dev, addr->sa_data, ETH_ALEN); + if (err < 0) + return err; + } + + if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) + dev_unicast_delete(real_dev, dev->dev_addr, ETH_ALEN); + +out: + memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); + return 0; +} + int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct net_device *real_dev = VLAN_DEV_INFO(dev)->real_dev; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index da22f900e89..c1757c79dfb 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -766,6 +766,9 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, if (!nf_bridge) return NF_ACCEPT; + if (!(nf_bridge->mask & (BRNF_BRIDGED | BRNF_BRIDGED_DNAT))) + return NF_ACCEPT; + if (!realoutdev) return NF_DROP; diff --git a/net/bridge/netfilter/ebt_arp.c b/net/bridge/netfilter/ebt_arp.c index 1a46952a56d..18141392a9b 100644 --- a/net/bridge/netfilter/ebt_arp.c +++ b/net/bridge/netfilter/ebt_arp.c @@ -34,7 +34,7 @@ static int ebt_filter_arp(const struct sk_buff *skb, const struct net_device *in ah->ar_pro, EBT_ARP_PTYPE)) return EBT_NOMATCH; - if (info->bitmask & (EBT_ARP_SRC_IP | EBT_ARP_DST_IP)) { + if (info->bitmask & (EBT_ARP_SRC_IP | EBT_ARP_DST_IP | EBT_ARP_GRAT)) { __be32 saddr, daddr, *sap, *dap; if (ah->ar_pln != sizeof(__be32) || ah->ar_pro != htons(ETH_P_IP)) diff --git a/net/core/dev.c b/net/core/dev.c index be6cedab5aa..86d62611f2f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1171,6 +1171,8 @@ rollback: nb->notifier_call(nb, NETDEV_UNREGISTER, dev); } } + + raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } @@ -2688,7 +2690,7 @@ static void __net_exit dev_proc_net_exit(struct net *net) proc_net_remove(net, "dev"); } -static struct pernet_operations dev_proc_ops = { +static struct pernet_operations __net_initdata dev_proc_ops = { .init = dev_proc_net_init, .exit = dev_proc_net_exit, }; @@ -4330,7 +4332,6 @@ static struct hlist_head *netdev_create_hash(void) static int __net_init netdev_init(struct net *net) { INIT_LIST_HEAD(&net->dev_base_head); - rwlock_init(&dev_base_lock); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) @@ -4354,7 +4355,7 @@ static void __net_exit netdev_exit(struct net *net) kfree(net->dev_index_head); } -static struct pernet_operations netdev_net_ops = { +static struct pernet_operations __net_initdata netdev_net_ops = { .init = netdev_init, .exit = netdev_exit, }; @@ -4385,7 +4386,7 @@ static void __net_exit default_device_exit(struct net *net) rtnl_unlock(); } -static struct pernet_operations default_device_ops = { +static struct pernet_operations __net_initdata default_device_ops = { .exit = default_device_exit, }; diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c index ae354057d84..69fff16ece1 100644 --- a/net/core/dev_mcast.c +++ b/net/core/dev_mcast.c @@ -168,13 +168,13 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) da = from->mc_list; while (da != NULL) { next = da->next; - if (!da->da_synced) - continue; - __dev_addr_delete(&to->mc_list, &to->mc_count, - da->da_addr, da->da_addrlen, 0); - da->da_synced = 0; - __dev_addr_delete(&from->mc_list, &from->mc_count, - da->da_addr, da->da_addrlen, 0); + if (da->da_synced) { + __dev_addr_delete(&to->mc_list, &to->mc_count, + da->da_addr, da->da_addrlen, 0); + da->da_synced = 0; + __dev_addr_delete(&from->mc_list, &from->mc_count, + da->da_addr, da->da_addrlen, 0); + } da = next; } __dev_set_rx_mode(to); @@ -285,7 +285,7 @@ static void __net_exit dev_mc_net_exit(struct net *net) proc_net_remove(net, "dev_mcast"); } -static struct pernet_operations dev_mc_net_ops = { +static struct pernet_operations __net_initdata dev_mc_net_ops = { .init = dev_mc_net_init, .exit = dev_mc_net_exit, }; diff --git a/net/core/dst.c b/net/core/dst.c index 16958e64e57..03daead3592 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -18,7 +18,6 @@ #include <linux/types.h> #include <net/net_namespace.h> -#include <net/net_namespace.h> #include <net/dst.h> /* diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 13de6f53f09..848132b6cb7 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -18,6 +18,28 @@ static LIST_HEAD(rules_ops); static DEFINE_SPINLOCK(rules_mod_lock); +int fib_default_rule_add(struct fib_rules_ops *ops, + u32 pref, u32 table, u32 flags) +{ + struct fib_rule *r; + + r = kzalloc(ops->rule_size, GFP_KERNEL); + if (r == NULL) + return -ENOMEM; + + atomic_set(&r->refcnt, 1); + r->action = FR_ACT_TO_TBL; + r->pref = pref; + r->table = table; + r->flags = flags; + + /* The lock is not required here, the list in unreacheable + * at the moment this function is called */ + list_add_tail(&r->list, &ops->rules_list); + return 0; +} +EXPORT_SYMBOL(fib_default_rule_add); + static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 05979e35696..29b8ee4e35d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1435,6 +1435,8 @@ int neigh_table_clear(struct neigh_table *tbl) kfree(tbl->phash_buckets); tbl->phash_buckets = NULL; + remove_proc_entry(tbl->id, init_net.proc_net_stat); + free_percpu(tbl->stats); tbl->stats = NULL; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index e9f0964ce70..383252b5041 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -64,6 +64,20 @@ static struct net *net_alloc(void) return kmem_cache_zalloc(net_cachep, GFP_KERNEL); } +static void net_free(struct net *net) +{ + if (!net) + return; + + if (unlikely(atomic_read(&net->use_count) != 0)) { + printk(KERN_EMERG "network namespace not free! Usage: %d\n", + atomic_read(&net->use_count)); + return; + } + + kmem_cache_free(net_cachep, net); +} + struct net *copy_net_ns(unsigned long flags, struct net *old_net) { struct net *new_net = NULL; @@ -100,20 +114,6 @@ out: return new_net; } -static void net_free(struct net *net) -{ - if (!net) - return; - - if (unlikely(atomic_read(&net->use_count) != 0)) { - printk(KERN_EMERG "network namespace not free! Usage: %d\n", - atomic_read(&net->use_count)); - return; - } - - kmem_cache_free(net_cachep, net); -} - static void cleanup_net(struct work_struct *work) { struct pernet_operations *ops; @@ -188,6 +188,7 @@ static int __init net_ns_init(void) pure_initcall(net_ns_init); +#ifdef CONFIG_NET_NS static int register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { @@ -228,6 +229,23 @@ static void unregister_pernet_operations(struct pernet_operations *ops) ops->exit(net); } +#else + +static int register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) +{ + if (ops->init == NULL) + return 0; + return ops->init(&init_net); +} + +static void unregister_pernet_operations(struct pernet_operations *ops) +{ + if (ops->exit) + ops->exit(&init_net); +} +#endif + /** * register_pernet_subsys - register a network namespace subsystem * @ops: pernet operations structure for the subsystem diff --git a/net/core/sock.c b/net/core/sock.c index 12ad2067a98..c519b439b8b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1801,11 +1801,65 @@ EXPORT_SYMBOL(sk_common_release); static DEFINE_RWLOCK(proto_list_lock); static LIST_HEAD(proto_list); +#ifdef CONFIG_SMP +/* + * Define default functions to keep track of inuse sockets per protocol + * Note that often used protocols use dedicated functions to get a speed increase. + * (see DEFINE_PROTO_INUSE/REF_PROTO_INUSE) + */ +static void inuse_add(struct proto *prot, int inc) +{ + per_cpu_ptr(prot->inuse_ptr, smp_processor_id())[0] += inc; +} + +static int inuse_get(const struct proto *prot) +{ + int res = 0, cpu; + for_each_possible_cpu(cpu) + res += per_cpu_ptr(prot->inuse_ptr, cpu)[0]; + return res; +} + +static int inuse_init(struct proto *prot) +{ + if (!prot->inuse_getval || !prot->inuse_add) { + prot->inuse_ptr = alloc_percpu(int); + if (prot->inuse_ptr == NULL) + return -ENOBUFS; + + prot->inuse_getval = inuse_get; + prot->inuse_add = inuse_add; + } + return 0; +} + +static void inuse_fini(struct proto *prot) +{ + if (prot->inuse_ptr != NULL) { + free_percpu(prot->inuse_ptr); + prot->inuse_ptr = NULL; + prot->inuse_getval = NULL; + prot->inuse_add = NULL; + } +} +#else +static inline int inuse_init(struct proto *prot) +{ + return 0; +} + +static inline void inuse_fini(struct proto *prot) +{ +} +#endif + int proto_register(struct proto *prot, int alloc_slab) { char *request_sock_slab_name = NULL; char *timewait_sock_slab_name; - int rc = -ENOBUFS; + + if (inuse_init(prot)) + goto out; if (alloc_slab) { prot->slab = kmem_cache_create(prot->name, prot->obj_size, 0, @@ -1814,7 +1868,7 @@ int proto_register(struct proto *prot, int alloc_slab) if (prot->slab == NULL) { printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n", prot->name); - goto out; + goto out_free_inuse; } if (prot->rsk_prot != NULL) { @@ -1858,9 +1912,8 @@ int proto_register(struct proto *prot, int alloc_slab) write_lock(&proto_list_lock); list_add(&prot->node, &proto_list); write_unlock(&proto_list_lock); - rc = 0; -out: - return rc; + return 0; + out_free_timewait_sock_slab_name: kfree(timewait_sock_slab_name); out_free_request_sock_slab: @@ -1873,7 +1926,10 @@ out_free_request_sock_slab_name: out_free_sock_slab: kmem_cache_destroy(prot->slab); prot->slab = NULL; - goto out; +out_free_inuse: + inuse_fini(prot); +out: + return -ENOBUFS; } EXPORT_SYMBOL(proto_register); @@ -1884,6 +1940,7 @@ void proto_unregister(struct proto *prot) list_del(&prot->node); write_unlock(&proto_list_lock); + inuse_fini(prot); if (prot->slab != NULL) { kmem_cache_destroy(prot->slab); prot->slab = NULL; @@ -2040,7 +2097,3 @@ EXPORT_SYMBOL(sock_wmalloc); EXPORT_SYMBOL(sock_i_uid); EXPORT_SYMBOL(sock_i_ino); EXPORT_SYMBOL(sysctl_optmem_max); -#ifdef CONFIG_SYSCTL -EXPORT_SYMBOL(sysctl_rmem_max); -EXPORT_SYMBOL(sysctl_wmem_max); -#endif diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 01a6a808bdb..db17b83e8d3 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -922,6 +922,8 @@ static struct timewait_sock_ops dccp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct inet_timewait_sock), }; +DEFINE_PROTO_INUSE(dccp_v4) + static struct proto dccp_v4_prot = { .name = "DCCP", .owner = THIS_MODULE, @@ -950,6 +952,7 @@ static struct proto dccp_v4_prot = { .compat_setsockopt = compat_dccp_setsockopt, .compat_getsockopt = compat_dccp_getsockopt, #endif + REF_PROTO_INUSE(dccp_v4) }; static struct net_protocol dccp_v4_protocol = { diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 62428ff137d..87c98fb86fa 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1107,6 +1107,8 @@ static struct timewait_sock_ops dccp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct dccp6_timewait_sock), }; +DEFINE_PROTO_INUSE(dccp_v6) + static struct proto dccp_v6_prot = { .name = "DCCPv6", .owner = THIS_MODULE, @@ -1135,6 +1137,7 @@ static struct proto dccp_v6_prot = { .compat_setsockopt = compat_dccp_setsockopt, .compat_getsockopt = compat_dccp_getsockopt, #endif + REF_PROTO_INUSE(dccp_v6) }; static struct inet6_protocol dccp_v6_protocol = { diff --git a/net/dccp/proto.c b/net/dccp/proto.c index d8497392803..7a3bea9c28c 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1072,11 +1072,13 @@ static int __init dccp_init(void) } for (i = 0; i < dccp_hashinfo.ehash_size; i++) { - rwlock_init(&dccp_hashinfo.ehash[i].lock); INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].chain); INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].twchain); } + if (inet_ehash_locks_alloc(&dccp_hashinfo)) + goto out_free_dccp_ehash; + bhash_order = ehash_order; do { @@ -1091,7 +1093,7 @@ static int __init dccp_init(void) if (!dccp_hashinfo.bhash) { DCCP_CRIT("Failed to allocate DCCP bind hash table"); - goto out_free_dccp_ehash; + goto out_free_dccp_locks; } for (i = 0; i < dccp_hashinfo.bhash_size; i++) { @@ -1121,6 +1123,8 @@ out_free_dccp_mib: out_free_dccp_bhash: free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); dccp_hashinfo.bhash = NULL; +out_free_dccp_locks: + inet_ehash_locks_free(&dccp_hashinfo); out_free_dccp_ehash: free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order); dccp_hashinfo.ehash = NULL; @@ -1139,6 +1143,7 @@ static void __exit dccp_fini(void) free_pages((unsigned long)dccp_hashinfo.ehash, get_order(dccp_hashinfo.ehash_size * sizeof(struct inet_ehash_bucket))); + inet_ehash_locks_free(&dccp_hashinfo); kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_ackvec_exit(); dccp_sysctl_exit(); diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 26130afd802..66e266fb590 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -1439,7 +1439,7 @@ static const struct file_operations dn_dev_seq_fops = { #endif /* CONFIG_PROC_FS */ -static int __initdata addr[2]; +static int addr[2]; module_param_array(addr, int, NULL, 0444); MODULE_PARM_DESC(addr, "The DECnet address of this machine: area,node"); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 97eee5e8fbb..66663e5d7ac 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -293,9 +293,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route * dn_rt_hash_table[hash].chain); rcu_assign_pointer(dn_rt_hash_table[hash].chain, rth); - rth->u.dst.__use++; - dst_hold(&rth->u.dst); - rth->u.dst.lastuse = now; + dst_use(&rth->u.dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); dnrt_drop(rt); @@ -308,9 +306,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route * rcu_assign_pointer(rt->u.dst.dn_next, dn_rt_hash_table[hash].chain); rcu_assign_pointer(dn_rt_hash_table[hash].chain, rt); - dst_hold(&rt->u.dst); - rt->u.dst.__use++; - rt->u.dst.lastuse = now; + dst_use(&rt->u.dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); *rp = rt; return 0; @@ -1182,9 +1178,7 @@ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowi *fl (flp->mark == rt->fl.mark) && (rt->fl.iif == 0) && (rt->fl.oif == flp->oif)) { - rt->u.dst.lastuse = jiffies; - dst_hold(&rt->u.dst); - rt->u.dst.__use++; + dst_use(&rt->u.dst, jiffies); rcu_read_unlock_bh(); *pprt = &rt->u.dst; return 0; @@ -1456,9 +1450,7 @@ int dn_route_input(struct sk_buff *skb) (rt->fl.oif == 0) && (rt->fl.mark == skb->mark) && (rt->fl.iif == cb->iif)) { - rt->u.dst.lastuse = jiffies; - dst_hold(&rt->u.dst); - rt->u.dst.__use++; + dst_use(&rt->u.dst, jiffies); rcu_read_unlock(); skb->dst = (struct dst_entry *)rt; return 0; diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index ddd3f04f091..ffebea04cc9 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -48,15 +48,6 @@ struct dn_fib_rule u8 flags; }; -static struct dn_fib_rule default_rule = { - .common = { - .refcnt = ATOMIC_INIT(2), - .pref = 0x7fff, - .table = RT_TABLE_MAIN, - .action = FR_ACT_TO_TBL, - }, -}; - int dn_fib_lookup(struct flowi *flp, struct dn_fib_res *res) { @@ -262,8 +253,8 @@ static struct fib_rules_ops dn_fib_rules_ops = { void __init dn_fib_rules_init(void) { - list_add_tail(&default_rule.common.list, - &dn_fib_rules_ops.rules_list); + BUG_ON(fib_default_rule_add(&dn_fib_rules_ops, 0x7fff, + RT_TABLE_MAIN, 0)); fib_rules_register(&dn_fib_rules_ops); } diff --git a/net/ieee80211/ieee80211_crypt_tkip.c b/net/ieee80211/ieee80211_crypt_tkip.c index 4cce3534e40..58b22619ab1 100644 --- a/net/ieee80211/ieee80211_crypt_tkip.c +++ b/net/ieee80211/ieee80211_crypt_tkip.c @@ -25,7 +25,6 @@ #include <net/ieee80211.h> #include <linux/crypto.h> -#include <linux/scatterlist.h> #include <linux/crc32.h> MODULE_AUTHOR("Jouni Malinen"); diff --git a/net/ieee80211/ieee80211_crypt_wep.c b/net/ieee80211/ieee80211_crypt_wep.c index 866fc04c44f..3fa30c40779 100644 --- a/net/ieee80211/ieee80211_crypt_wep.c +++ b/net/ieee80211/ieee80211_crypt_wep.c @@ -22,7 +22,6 @@ #include <net/ieee80211.h> #include <linux/crypto.h> -#include <linux/scatterlist.h> #include <linux/crc32.h> MODULE_AUTHOR("Jouni Malinen"); diff --git a/net/ieee80211/softmac/ieee80211softmac_wx.c b/net/ieee80211/softmac/ieee80211softmac_wx.c index ac36767b56e..e01b59aedc5 100644 --- a/net/ieee80211/softmac/ieee80211softmac_wx.c +++ b/net/ieee80211/softmac/ieee80211softmac_wx.c @@ -470,7 +470,7 @@ ieee80211softmac_wx_set_mlme(struct net_device *dev, { struct ieee80211softmac_device *mac = ieee80211_priv(dev); struct iw_mlme *mlme = (struct iw_mlme *)extra; - u16 reason = cpu_to_le16(mlme->reason_code); + u16 reason = mlme->reason_code; struct ieee80211softmac_network *net; int err = -EINVAL; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 60123905dbb..732d8f088b1 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -59,6 +59,13 @@ struct fib_table *ip_fib_main_table; #define FIB_TABLE_HASHSZ 1 static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ]; +static void __init fib4_rules_init(void) +{ + ip_fib_local_table = fib_hash_init(RT_TABLE_LOCAL); + hlist_add_head_rcu(&ip_fib_local_table->tb_hlist, &fib_table_hash[0]); + ip_fib_main_table = fib_hash_init(RT_TABLE_MAIN); + hlist_add_head_rcu(&ip_fib_main_table->tb_hlist, &fib_table_hash[0]); +} #else #define FIB_TABLE_HASHSZ 256 @@ -905,14 +912,8 @@ void __init ip_fib_init(void) for (i = 0; i < FIB_TABLE_HASHSZ; i++) INIT_HLIST_HEAD(&fib_table_hash[i]); -#ifndef CONFIG_IP_MULTIPLE_TABLES - ip_fib_local_table = fib_hash_init(RT_TABLE_LOCAL); - hlist_add_head_rcu(&ip_fib_local_table->tb_hlist, &fib_table_hash[0]); - ip_fib_main_table = fib_hash_init(RT_TABLE_MAIN); - hlist_add_head_rcu(&ip_fib_main_table->tb_hlist, &fib_table_hash[0]); -#else + fib4_rules_init(); -#endif register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index f16839c6a72..a0ada3a8d8d 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -49,33 +49,6 @@ struct fib4_rule #endif }; -static struct fib4_rule default_rule = { - .common = { - .refcnt = ATOMIC_INIT(2), - .pref = 0x7FFF, - .table = RT_TABLE_DEFAULT, - .action = FR_ACT_TO_TBL, - }, -}; - -static struct fib4_rule main_rule = { - .common = { - .refcnt = ATOMIC_INIT(2), - .pref = 0x7FFE, - .table = RT_TABLE_MAIN, - .action = FR_ACT_TO_TBL, - }, -}; - -static struct fib4_rule local_rule = { - .common = { - .refcnt = ATOMIC_INIT(2), - .table = RT_TABLE_LOCAL, - .action = FR_ACT_TO_TBL, - .flags = FIB_RULE_PERMANENT, - }, -}; - #ifdef CONFIG_NET_CLS_ROUTE u32 fib_rules_tclass(struct fib_result *res) { @@ -319,11 +292,27 @@ static struct fib_rules_ops fib4_rules_ops = { .owner = THIS_MODULE, }; -void __init fib4_rules_init(void) +static int __init fib_default_rules_init(void) { - list_add_tail(&local_rule.common.list, &fib4_rules_ops.rules_list); - list_add_tail(&main_rule.common.list, &fib4_rules_ops.rules_list); - list_add_tail(&default_rule.common.list, &fib4_rules_ops.rules_list); + int err; + + err = fib_default_rule_add(&fib4_rules_ops, 0, + RT_TABLE_LOCAL, FIB_RULE_PERMANENT); + if (err < 0) + return err; + err = fib_default_rule_add(&fib4_rules_ops, 0x7FFE, + RT_TABLE_MAIN, 0); + if (err < 0) + return err; + err = fib_default_rule_add(&fib4_rules_ops, 0x7FFF, + RT_TABLE_DEFAULT, 0); + if (err < 0) + return err; + return 0; +} +void __init fib4_rules_init(void) +{ + BUG_ON(fib_default_rules_init()); fib_rules_register(&fib4_rules_ops); } diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index dc429b6b0ba..b0170732b5e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -747,13 +747,14 @@ skip_listen_ht: for (i = s_i; i < hashinfo->ehash_size; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; + rwlock_t *lock = inet_ehash_lockp(hashinfo, i); struct sock *sk; struct hlist_node *node; if (i > s_i) s_num = 0; - read_lock_bh(&head->lock); + read_lock_bh(lock); num = 0; sk_for_each(sk, node, &head->chain) { struct inet_sock *inet = inet_sk(sk); @@ -769,7 +770,7 @@ skip_listen_ht: r->id.idiag_dport) goto next_normal; if (inet_csk_diag_dump(sk, skb, cb) < 0) { - read_unlock_bh(&head->lock); + read_unlock_bh(lock); goto done; } next_normal: @@ -791,14 +792,14 @@ next_normal: r->id.idiag_dport) goto next_dying; if (inet_twsk_diag_dump(tw, skb, cb) < 0) { - read_unlock_bh(&head->lock); + read_unlock_bh(lock); goto done; } next_dying: ++num; } } - read_unlock_bh(&head->lock); + read_unlock_bh(lock); } done: diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 16eecc7046a..67704da04fc 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -204,12 +204,13 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, const __portpair ports = INET_COMBINED_PORTS(inet->dport, lport); unsigned int hash = inet_ehashfn(daddr, lport, saddr, inet->dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); + rwlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; const struct hlist_node *node; struct inet_timewait_sock *tw; prefetch(head->chain.first); - write_lock(&head->lock); + write_lock(lock); /* Check TIME-WAIT sockets first. */ sk_for_each(sk2, node, &head->twchain) { @@ -239,7 +240,7 @@ unique: BUG_TRAP(sk_unhashed(sk)); __sk_add_node(sk, &head->chain); sock_prot_inc_use(sk->sk_prot); - write_unlock(&head->lock); + write_unlock(lock); if (twp) { *twp = tw; @@ -255,7 +256,7 @@ unique: return 0; not_unique: - write_unlock(&head->lock); + write_unlock(lock); return -EADDRNOTAVAIL; } diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 4e189e28f30..a60b99e0ebd 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -20,16 +20,16 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, struct inet_bind_hashbucket *bhead; struct inet_bind_bucket *tb; /* Unlink from established hashes. */ - struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, tw->tw_hash); + rwlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); - write_lock(&ehead->lock); + write_lock(lock); if (hlist_unhashed(&tw->tw_node)) { - write_unlock(&ehead->lock); + write_unlock(lock); return; } __hlist_del(&tw->tw_node); sk_node_init(&tw->tw_node); - write_unlock(&ehead->lock); + write_unlock(lock); /* Disassociate with bind bucket. */ bhead = &hashinfo->bhash[inet_bhashfn(tw->tw_num, hashinfo->bhash_size)]; @@ -59,6 +59,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, const struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash); + rwlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); struct inet_bind_hashbucket *bhead; /* Step 1: Put TW into bind hash. Original socket stays there too. Note, that any socket with inet->num != 0 MUST be bound in @@ -71,7 +72,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, inet_twsk_add_bind_node(tw, &tw->tw_tb->owners); spin_unlock(&bhead->lock); - write_lock(&ehead->lock); + write_lock(lock); /* Step 2: Remove SK from established hash. */ if (__sk_del_node_init(sk)) @@ -81,7 +82,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, inet_twsk_add_node(tw, &ehead->twchain); atomic_inc(&tw->tw_refcnt); - write_unlock(&ehead->lock); + write_unlock(lock); } EXPORT_SYMBOL_GPL(__inet_twsk_hashdance); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 771031dfbd0..af995198f64 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -61,7 +61,7 @@ * 4. Global variable peer_total is modified under the pool lock. * 5. struct inet_peer fields modification: * avl_left, avl_right, avl_parent, avl_height: pool lock - * unused_next, unused_prevp: unused node list 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 @@ -94,8 +94,7 @@ 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 inet_peer *inet_peer_unused_head; -static struct inet_peer **inet_peer_unused_tailp = &inet_peer_unused_head; +static LIST_HEAD(unused_peers); static DEFINE_SPINLOCK(inet_peer_unused_lock); static void peer_check_expire(unsigned long dummy); @@ -138,15 +137,7 @@ void __init inet_initpeers(void) static void unlink_from_unused(struct inet_peer *p) { spin_lock_bh(&inet_peer_unused_lock); - if (p->unused_prevp != NULL) { - /* On unused list. */ - *p->unused_prevp = p->unused_next; - if (p->unused_next != NULL) - p->unused_next->unused_prevp = p->unused_prevp; - else - inet_peer_unused_tailp = p->unused_prevp; - p->unused_prevp = NULL; /* mark it as removed */ - } + list_del_init(&p->unused); spin_unlock_bh(&inet_peer_unused_lock); } @@ -337,24 +328,24 @@ static void unlink_from_pool(struct inet_peer *p) /* May be called with local BH enabled. */ static int cleanup_once(unsigned long ttl) { - struct inet_peer *p; + struct inet_peer *p = NULL; /* Remove the first entry from the list of unused nodes. */ spin_lock_bh(&inet_peer_unused_lock); - p = inet_peer_unused_head; - if (p != NULL) { - __u32 delta = (__u32)jiffies - p->dtime; + if (!list_empty(&unused_peers)) { + __u32 delta; + + p = list_first_entry(&unused_peers, struct inet_peer, unused); + delta = (__u32)jiffies - p->dtime; + if (delta < ttl) { /* Do not prune fresh entries. */ spin_unlock_bh(&inet_peer_unused_lock); return -1; } - inet_peer_unused_head = p->unused_next; - if (p->unused_next != NULL) - p->unused_next->unused_prevp = p->unused_prevp; - else - inet_peer_unused_tailp = p->unused_prevp; - p->unused_prevp = NULL; /* mark as not on the list */ + + list_del_init(&p->unused); + /* Grab an extra reference to prevent node disappearing * before unlink_from_pool() call. */ atomic_inc(&p->refcnt); @@ -412,7 +403,7 @@ struct inet_peer *inet_getpeer(__be32 daddr, int create) /* Link the node. */ link_to_pool(n); - n->unused_prevp = NULL; /* not on the list */ + INIT_LIST_HEAD(&n->unused); peer_total++; write_unlock_bh(&peer_pool_lock); @@ -467,10 +458,7 @@ void inet_putpeer(struct inet_peer *p) { spin_lock_bh(&inet_peer_unused_lock); if (atomic_dec_and_test(&p->refcnt)) { - p->unused_prevp = inet_peer_unused_tailp; - p->unused_next = NULL; - *inet_peer_unused_tailp = p; - inet_peer_unused_tailp = &p->unused_next; + list_add_tail(&p->unused, &unused_peers); p->dtime = (__u32)jiffies; } spin_unlock_bh(&inet_peer_unused_lock); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e5f7dc2de30..fd99fbd685e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1183,6 +1183,17 @@ error: return err; } +static void ip_cork_release(struct inet_sock *inet) +{ + inet->cork.flags &= ~IPCORK_OPT; + kfree(inet->cork.opt); + inet->cork.opt = NULL; + if (inet->cork.rt) { + ip_rt_put(inet->cork.rt); + inet->cork.rt = NULL; + } +} + /* * Combined all pending IP fragments on the socket as one IP datagram * and push them out. @@ -1276,13 +1287,7 @@ int ip_push_pending_frames(struct sock *sk) } out: - inet->cork.flags &= ~IPCORK_OPT; - kfree(inet->cork.opt); - inet->cork.opt = NULL; - if (inet->cork.rt) { - ip_rt_put(inet->cork.rt); - inet->cork.rt = NULL; - } + ip_cork_release(inet); return err; error: @@ -1295,19 +1300,12 @@ error: */ void ip_flush_pending_frames(struct sock *sk) { - struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); - inet->cork.flags &= ~IPCORK_OPT; - kfree(inet->cork.opt); - inet->cork.opt = NULL; - if (inet->cork.rt) { - ip_rt_put(inet->cork.rt); - inet->cork.rt = NULL; - } + ip_cork_release(inet_sk(sk)); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index f51f20e487c..82817e55436 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -437,10 +437,8 @@ static int do_ip_setsockopt(struct sock *sk, int level, /* If optlen==0, it is equivalent to val == 0 */ -#ifdef CONFIG_IP_MROUTE - if (optname >= MRT_BASE && optname <= (MRT_BASE + 10)) + if (ip_mroute_opt(optname)) return ip_mroute_setsockopt(sk,optname,optval,optlen); -#endif err = 0; lock_sock(sk); @@ -909,11 +907,9 @@ int ip_setsockopt(struct sock *sk, int level, #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_HDRINCL && - optname != IP_IPSEC_POLICY && optname != IP_XFRM_POLICY -#ifdef CONFIG_IP_MROUTE - && (optname < MRT_BASE || optname > (MRT_BASE + 10)) -#endif - ) { + optname != IP_IPSEC_POLICY && + optname != IP_XFRM_POLICY && + !ip_mroute_opt(optname)) { lock_sock(sk); err = nf_setsockopt(sk, PF_INET, optname, optval, optlen); release_sock(sk); @@ -935,11 +931,9 @@ int compat_ip_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_HDRINCL && - optname != IP_IPSEC_POLICY && optname != IP_XFRM_POLICY -#ifdef CONFIG_IP_MROUTE - && (optname < MRT_BASE || optname > (MRT_BASE + 10)) -#endif - ) { + optname != IP_IPSEC_POLICY && + optname != IP_XFRM_POLICY && + !ip_mroute_opt(optname)) { lock_sock(sk); err = compat_nf_setsockopt(sk, PF_INET, optname, optval, optlen); @@ -967,11 +961,8 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, if (level != SOL_IP) return -EOPNOTSUPP; -#ifdef CONFIG_IP_MROUTE - if (optname >= MRT_BASE && optname <= MRT_BASE+10) { + if (ip_mroute_opt(optname)) return ip_mroute_getsockopt(sk,optname,optval,optlen); - } -#endif if (get_user(len,optlen)) return -EFAULT; @@ -1171,11 +1162,8 @@ int ip_getsockopt(struct sock *sk, int level, err = do_ip_getsockopt(sk, level, optname, optval, optlen); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ - if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS -#ifdef CONFIG_IP_MROUTE - && (optname < MRT_BASE || optname > MRT_BASE+10) -#endif - ) { + if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS && + !ip_mroute_opt(optname)) { int len; if (get_user(len,optlen)) @@ -1200,11 +1188,8 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, int err = do_ip_getsockopt(sk, level, optname, optval, optlen); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ - if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS -#ifdef CONFIG_IP_MROUTE - && (optname < MRT_BASE || optname > MRT_BASE+10) -#endif - ) { + if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS && + !ip_mroute_opt(optname)) { int len; if (get_user(len, optlen)) diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index ca1b5fdb8d3..2c44a94c213 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -16,6 +16,7 @@ #include <linux/module.h> #include <asm/semaphore.h> #include <linux/crypto.h> +#include <linux/err.h> #include <linux/pfkeyv2.h> #include <linux/percpu.h> #include <linux/smp.h> @@ -344,7 +345,7 @@ static struct crypto_comp **ipcomp_alloc_tfms(const char *alg_name) for_each_possible_cpu(cpu) { struct crypto_comp *tfm = crypto_alloc_comp(alg_name, 0, CRYPTO_ALG_ASYNC); - if (!tfm) + if (IS_ERR(tfm)) goto error; *per_cpu_ptr(tfms, cpu) = tfm; } diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c index 4b702f708d3..0a9f3c37e18 100644 --- a/net/ipv4/ipvs/ip_vs_conn.c +++ b/net/ipv4/ipvs/ip_vs_conn.c @@ -426,6 +426,24 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) /* + * Check if there is a destination for the connection, if so + * bind the connection to the destination. + */ +struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) +{ + struct ip_vs_dest *dest; + + if ((cp) && (!cp->dest)) { + dest = ip_vs_find_dest(cp->daddr, cp->dport, + cp->vaddr, cp->vport, cp->protocol); + ip_vs_bind_dest(cp, dest); + return dest; + } else + return NULL; +} + + +/* * Unbind a connection entry with its VS destination * Called by the ip_vs_conn_expire function. */ diff --git a/net/ipv4/ipvs/ip_vs_core.c b/net/ipv4/ipvs/ip_vs_core.c index c6ed7654e83..20c884a5772 100644 --- a/net/ipv4/ipvs/ip_vs_core.c +++ b/net/ipv4/ipvs/ip_vs_core.c @@ -979,15 +979,23 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, ret = NF_ACCEPT; } - /* increase its packet counter and check if it is needed - to be synchronized */ + /* Increase its packet counter and check if it is needed + * to be synchronized + * + * Sync connection if it is about to close to + * encorage the standby servers to update the connections timeout + */ atomic_inc(&cp->in_pkts); if ((ip_vs_sync_state & IP_VS_STATE_MASTER) && - (cp->protocol != IPPROTO_TCP || - cp->state == IP_VS_TCP_S_ESTABLISHED) && - (atomic_read(&cp->in_pkts) % sysctl_ip_vs_sync_threshold[1] - == sysctl_ip_vs_sync_threshold[0])) + (((cp->protocol != IPPROTO_TCP || + cp->state == IP_VS_TCP_S_ESTABLISHED) && + (atomic_read(&cp->in_pkts) % sysctl_ip_vs_sync_threshold[1] + == sysctl_ip_vs_sync_threshold[0])) || + ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) && + ((cp->state == IP_VS_TCP_S_FIN_WAIT) || + (cp->state == IP_VS_TCP_S_CLOSE))))) ip_vs_sync_conn(cp); + cp->old_state = cp->state; ip_vs_conn_put(cp); return ret; diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c index 7345fc252a2..b64cf45a9ea 100644 --- a/net/ipv4/ipvs/ip_vs_ctl.c +++ b/net/ipv4/ipvs/ip_vs_ctl.c @@ -579,6 +579,31 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, __be32 daddr, __be16 dport) return NULL; } +/* + * Find destination by {daddr,dport,vaddr,protocol} + * Cretaed to be used in ip_vs_process_message() in + * the backup synchronization daemon. It finds the + * destination to be bound to the received connection + * on the backup. + * + * ip_vs_lookup_real_service() looked promissing, but + * seems not working as expected. + */ +struct ip_vs_dest *ip_vs_find_dest(__be32 daddr, __be16 dport, + __be32 vaddr, __be16 vport, __u16 protocol) +{ + struct ip_vs_dest *dest; + struct ip_vs_service *svc; + + svc = ip_vs_service_get(0, protocol, vaddr, vport); + if (!svc) + return NULL; + dest = ip_vs_lookup_dest(svc, daddr, dport); + if (dest) + atomic_inc(&dest->refcnt); + ip_vs_service_put(svc); + return dest; +} /* * Lookup dest by {svc,addr,port} in the destination trash. diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c index 0d4d9721cbd..bd930efc18d 100644 --- a/net/ipv4/ipvs/ip_vs_sync.c +++ b/net/ipv4/ipvs/ip_vs_sync.c @@ -284,6 +284,7 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) struct ip_vs_sync_conn_options *opt; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; + struct ip_vs_dest *dest; char *p; int i; @@ -317,20 +318,34 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) s->caddr, s->cport, s->vaddr, s->vport); if (!cp) { + /* + * Find the appropriate destination for the connection. + * If it is not found the connection will remain unbound + * but still handled. + */ + dest = ip_vs_find_dest(s->daddr, s->dport, + s->vaddr, s->vport, + s->protocol); cp = ip_vs_conn_new(s->protocol, s->caddr, s->cport, s->vaddr, s->vport, s->daddr, s->dport, - flags, NULL); + flags, dest); + if (dest) + atomic_dec(&dest->refcnt); if (!cp) { IP_VS_ERR("ip_vs_conn_new failed\n"); return; } cp->state = ntohs(s->state); } else if (!cp->dest) { - /* it is an entry created by the synchronization */ - cp->state = ntohs(s->state); - cp->flags = flags | IP_VS_CONN_F_HASHED; + dest = ip_vs_try_bind_dest(cp); + if (!dest) { + /* it is an unbound entry created by + * synchronization */ + cp->flags = flags | IP_VS_CONN_F_HASHED; + } else + atomic_dec(&dest->refcnt); } /* Note that we don't touch its state and flags if it is a normal entry. */ @@ -342,6 +357,7 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) p += SIMPLE_CONN_SIZE; atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]); + cp->state = ntohs(s->state); pp = ip_vs_proto_get(s->protocol); cp->timeout = pp->timeout_table[cp->state]; ip_vs_conn_put(cp); diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 409d273f6f8..7456833d6ad 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -41,27 +41,27 @@ obj-$(CONFIG_NF_NAT) += iptable_nat.o obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o # matches +obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o +obj-$(CONFIG_IP_NF_MATCH_AH) += ipt_ah.o +obj-$(CONFIG_IP_NF_MATCH_ECN) += ipt_ecn.o obj-$(CONFIG_IP_NF_MATCH_IPRANGE) += ipt_iprange.o obj-$(CONFIG_IP_NF_MATCH_OWNER) += ipt_owner.o -obj-$(CONFIG_IP_NF_MATCH_TOS) += ipt_tos.o obj-$(CONFIG_IP_NF_MATCH_RECENT) += ipt_recent.o -obj-$(CONFIG_IP_NF_MATCH_ECN) += ipt_ecn.o -obj-$(CONFIG_IP_NF_MATCH_AH) += ipt_ah.o +obj-$(CONFIG_IP_NF_MATCH_TOS) += ipt_tos.o obj-$(CONFIG_IP_NF_MATCH_TTL) += ipt_ttl.o -obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o # targets -obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o -obj-$(CONFIG_IP_NF_TARGET_TOS) += ipt_TOS.o +obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o +obj-$(CONFIG_IP_NF_TARGET_LOG) += ipt_LOG.o obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o -obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o obj-$(CONFIG_IP_NF_TARGET_NETMAP) += ipt_NETMAP.o +obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o +obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o obj-$(CONFIG_IP_NF_TARGET_SAME) += ipt_SAME.o -obj-$(CONFIG_IP_NF_TARGET_LOG) += ipt_LOG.o -obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o -obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o +obj-$(CONFIG_IP_NF_TARGET_TOS) += ipt_TOS.o obj-$(CONFIG_IP_NF_TARGET_TTL) += ipt_TTL.o +obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o # generic ARP tables obj-$(CONFIG_IP_NF_ARPTABLES) += arp_tables.o diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index 10a2ce09fd8..14d64a383db 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -22,6 +22,7 @@ #include <linux/spinlock.h> #include <linux/sysctl.h> #include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <linux/security.h> #include <linux/mutex.h> #include <net/net_namespace.h> @@ -607,15 +608,11 @@ static ctl_table ipq_root_table[] = { { .ctl_name = 0 } }; -#ifdef CONFIG_PROC_FS -static int -ipq_get_info(char *buffer, char **start, off_t offset, int length) +static int ip_queue_show(struct seq_file *m, void *v) { - int len; - read_lock_bh(&queue_lock); - len = sprintf(buffer, + seq_printf(m, "Peer PID : %d\n" "Copy mode : %hu\n" "Copy range : %u\n" @@ -632,16 +629,21 @@ ipq_get_info(char *buffer, char **start, off_t offset, int length) queue_user_dropped); read_unlock_bh(&queue_lock); + return 0; +} - *start = buffer + offset; - len -= offset; - if (len > length) - len = length; - else if (len < 0) - len = 0; - return len; +static int ip_queue_open(struct inode *inode, struct file *file) +{ + return single_open(file, ip_queue_show, NULL); } -#endif /* CONFIG_PROC_FS */ + +static const struct file_operations ip_queue_proc_fops = { + .open = ip_queue_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .owner = THIS_MODULE, +}; static struct nf_queue_handler nfqh = { .name = "ip_queue", @@ -661,10 +663,11 @@ static int __init ip_queue_init(void) goto cleanup_netlink_notifier; } - proc = proc_net_create(&init_net, IPQ_PROC_FS_NAME, 0, ipq_get_info); - if (proc) + proc = create_proc_entry(IPQ_PROC_FS_NAME, 0, init_net.proc_net); + if (proc) { proc->owner = THIS_MODULE; - else { + proc->proc_fops = &ip_queue_proc_fops; + } else { printk(KERN_ERR "ip_queue: failed to create proc entry\n"); goto cleanup_ipqnl; } diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index 35a5aa69cd9..c31b8766825 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -69,7 +69,7 @@ static void __exit nf_nat_amanda_fini(void) static int __init nf_nat_amanda_init(void) { - BUG_ON(rcu_dereference(nf_nat_amanda_hook)); + BUG_ON(nf_nat_amanda_hook != NULL); rcu_assign_pointer(nf_nat_amanda_hook, help); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 56e93f692e8..70e7997ea28 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -681,7 +681,7 @@ static int clean_nat(struct nf_conn *i, void *data) if (!nat) return 0; - memset(nat, 0, sizeof(nat)); + memset(nat, 0, sizeof(*nat)); i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | IPS_SEQ_ADJUST); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_ftp.c b/net/ipv4/netfilter/nf_nat_ftp.c index e1a16d3ea4c..a1d5d58a58b 100644 --- a/net/ipv4/netfilter/nf_nat_ftp.c +++ b/net/ipv4/netfilter/nf_nat_ftp.c @@ -147,7 +147,7 @@ static void __exit nf_nat_ftp_fini(void) static int __init nf_nat_ftp_init(void) { - BUG_ON(rcu_dereference(nf_nat_ftp_hook)); + BUG_ON(nf_nat_ftp_hook != NULL); rcu_assign_pointer(nf_nat_ftp_hook, nf_nat_ftp); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index a868c8c4132..93e18ef114f 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -544,15 +544,15 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int __init init(void) { - BUG_ON(rcu_dereference(set_h245_addr_hook) != NULL); - BUG_ON(rcu_dereference(set_h225_addr_hook) != NULL); - BUG_ON(rcu_dereference(set_sig_addr_hook) != NULL); - BUG_ON(rcu_dereference(set_ras_addr_hook) != NULL); - BUG_ON(rcu_dereference(nat_rtp_rtcp_hook) != NULL); - BUG_ON(rcu_dereference(nat_t120_hook) != NULL); - BUG_ON(rcu_dereference(nat_h245_hook) != NULL); - BUG_ON(rcu_dereference(nat_callforwarding_hook) != NULL); - BUG_ON(rcu_dereference(nat_q931_hook) != NULL); + BUG_ON(set_h245_addr_hook != NULL); + BUG_ON(set_h225_addr_hook != NULL); + BUG_ON(set_sig_addr_hook != NULL); + BUG_ON(set_ras_addr_hook != NULL); + BUG_ON(nat_rtp_rtcp_hook != NULL); + BUG_ON(nat_t120_hook != NULL); + BUG_ON(nat_h245_hook != NULL); + BUG_ON(nat_callforwarding_hook != NULL); + BUG_ON(nat_q931_hook != NULL); rcu_assign_pointer(set_h245_addr_hook, set_h245_addr); rcu_assign_pointer(set_h225_addr_hook, set_h225_addr); diff --git a/net/ipv4/netfilter/nf_nat_irc.c b/net/ipv4/netfilter/nf_nat_irc.c index 766e2c16c6b..fe6f9cef6c8 100644 --- a/net/ipv4/netfilter/nf_nat_irc.c +++ b/net/ipv4/netfilter/nf_nat_irc.c @@ -74,7 +74,7 @@ static void __exit nf_nat_irc_fini(void) static int __init nf_nat_irc_init(void) { - BUG_ON(rcu_dereference(nf_nat_irc_hook)); + BUG_ON(nf_nat_irc_hook != NULL); rcu_assign_pointer(nf_nat_irc_hook, help); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index e1385a09907..6817e7995f3 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -281,16 +281,16 @@ static int __init nf_nat_helper_pptp_init(void) { nf_nat_need_gre(); - BUG_ON(rcu_dereference(nf_nat_pptp_hook_outbound)); + BUG_ON(nf_nat_pptp_hook_outbound != NULL); rcu_assign_pointer(nf_nat_pptp_hook_outbound, pptp_outbound_pkt); - BUG_ON(rcu_dereference(nf_nat_pptp_hook_inbound)); + BUG_ON(nf_nat_pptp_hook_inbound != NULL); rcu_assign_pointer(nf_nat_pptp_hook_inbound, pptp_inbound_pkt); - BUG_ON(rcu_dereference(nf_nat_pptp_hook_exp_gre)); + BUG_ON(nf_nat_pptp_hook_exp_gre != NULL); rcu_assign_pointer(nf_nat_pptp_hook_exp_gre, pptp_exp_gre); - BUG_ON(rcu_dereference(nf_nat_pptp_hook_expectfn)); + BUG_ON(nf_nat_pptp_hook_expectfn != NULL); rcu_assign_pointer(nf_nat_pptp_hook_expectfn, pptp_nat_expected); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index ce9edbcc01e..3ca98971a1e 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -293,8 +293,8 @@ static void __exit nf_nat_sip_fini(void) static int __init nf_nat_sip_init(void) { - BUG_ON(rcu_dereference(nf_nat_sip_hook)); - BUG_ON(rcu_dereference(nf_nat_sdp_hook)); + BUG_ON(nf_nat_sip_hook != NULL); + BUG_ON(nf_nat_sdp_hook != NULL); rcu_assign_pointer(nf_nat_sip_hook, ip_nat_sip); rcu_assign_pointer(nf_nat_sdp_hook, ip_nat_sdp); return 0; diff --git a/net/ipv4/netfilter/nf_nat_tftp.c b/net/ipv4/netfilter/nf_nat_tftp.c index 0ecec701cb4..1360a94766d 100644 --- a/net/ipv4/netfilter/nf_nat_tftp.c +++ b/net/ipv4/netfilter/nf_nat_tftp.c @@ -43,7 +43,7 @@ static void __exit nf_nat_tftp_fini(void) static int __init nf_nat_tftp_init(void) { - BUG_ON(rcu_dereference(nf_nat_tftp_hook)); + BUG_ON(nf_nat_tftp_hook != NULL); rcu_assign_pointer(nf_nat_tftp_hook, help); return 0; } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index ffdccc0972e..ce34b281803 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -46,17 +46,6 @@ #include <net/sock.h> #include <net/raw.h> -static int fold_prot_inuse(struct proto *proto) -{ - int res = 0; - int cpu; - - for_each_possible_cpu(cpu) - res += proto->stats[cpu].inuse; - - return res; -} - /* * Report socket allocation statistics [mea@utu.fi] */ @@ -64,12 +53,12 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) { socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n", - fold_prot_inuse(&tcp_prot), atomic_read(&tcp_orphan_count), + sock_prot_inuse(&tcp_prot), atomic_read(&tcp_orphan_count), tcp_death_row.tw_count, atomic_read(&tcp_sockets_allocated), atomic_read(&tcp_memory_allocated)); - seq_printf(seq, "UDP: inuse %d\n", fold_prot_inuse(&udp_prot)); - seq_printf(seq, "UDPLITE: inuse %d\n", fold_prot_inuse(&udplite_prot)); - seq_printf(seq, "RAW: inuse %d\n", fold_prot_inuse(&raw_prot)); + seq_printf(seq, "UDP: inuse %d\n", sock_prot_inuse(&udp_prot)); + seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse(&udplite_prot)); + seq_printf(seq, "RAW: inuse %d\n", sock_prot_inuse(&raw_prot)); seq_printf(seq, "FRAG: inuse %d memory %d\n", ip_frag_nqueues(), ip_frag_mem()); return 0; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 3916faca3af..66b42f547bf 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -760,6 +760,8 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg) } } +DEFINE_PROTO_INUSE(raw) + struct proto raw_prot = { .name = "RAW", .owner = THIS_MODULE, @@ -781,6 +783,7 @@ struct proto raw_prot = { .compat_setsockopt = compat_raw_setsockopt, .compat_getsockopt = compat_raw_getsockopt, #endif + REF_PROTO_INUSE(raw) }; #ifdef CONFIG_PROC_FS diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 21b12de9e65..1bff9ed349f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -578,6 +578,9 @@ static void rt_check_expire(struct work_struct *work) i = (i + 1) & rt_hash_mask; rthp = &rt_hash_table[i].chain; + if (need_resched()) + cond_resched(); + if (*rthp == NULL) continue; spin_lock_bh(rt_hash_lock_addr(i)); @@ -851,9 +854,7 @@ restart: */ rcu_assign_pointer(rt_hash_table[hash].chain, rth); - rth->u.dst.__use++; - dst_hold(&rth->u.dst); - rth->u.dst.lastuse = now; + dst_use(&rth->u.dst, now); spin_unlock_bh(rt_hash_lock_addr(hash)); rt_drop(rt); @@ -1813,11 +1814,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto martian_destination; err = ip_mkroute_input(skb, &res, &fl, in_dev, daddr, saddr, tos); - if (err == -ENOBUFS) - goto e_nobufs; - if (err == -EINVAL) - goto e_inval; - done: in_dev_put(in_dev); if (free_res) @@ -1935,9 +1931,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->fl.oif == 0 && rth->fl.mark == skb->mark && rth->fl.fl4_tos == tos) { - rth->u.dst.lastuse = jiffies; - dst_hold(&rth->u.dst); - rth->u.dst.__use++; + dst_use(&rth->u.dst, jiffies); RT_CACHE_STAT_INC(in_hit); rcu_read_unlock(); skb->dst = (struct dst_entry*)rth; @@ -2331,9 +2325,7 @@ int __ip_route_output_key(struct rtable **rp, const struct flowi *flp) rth->fl.mark == flp->mark && !((rth->fl.fl4_tos ^ flp->fl4_tos) & (IPTOS_RT_MASK | RTO_ONLINK))) { - rth->u.dst.lastuse = jiffies; - dst_hold(&rth->u.dst); - rth->u.dst.__use++; + dst_use(&rth->u.dst, jiffies); RT_CACHE_STAT_INC(out_hit); rcu_read_unlock_bh(); *rp = rth; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c64072bb504..8e65182f7af 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2456,11 +2456,11 @@ void __init tcp_init(void) thash_entries ? 0 : 512 * 1024); tcp_hashinfo.ehash_size = 1 << tcp_hashinfo.ehash_size; for (i = 0; i < tcp_hashinfo.ehash_size; i++) { - rwlock_init(&tcp_hashinfo.ehash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].chain); INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].twchain); } - + if (inet_ehash_locks_alloc(&tcp_hashinfo)) + panic("TCP: failed to alloc ehash_locks"); tcp_hashinfo.bhash = alloc_large_system_hash("TCP bind", sizeof(struct inet_bind_hashbucket), diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ca9590f4f52..0f0c1c9829a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1269,6 +1269,9 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window)) return 0; + if (!tp->packets_out) + goto out; + /* SACK fastpath: * if the only SACK change is the increase of the end_seq of * the first block then only apply that SACK block @@ -1400,11 +1403,9 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ /* DSACK info lost if out-of-mem, try SACK still */ if (in_sack <= 0) in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, end_seq); - if (in_sack < 0) + if (unlikely(in_sack < 0)) break; - fack_count += tcp_skb_pcount(skb); - sacked = TCP_SKB_CB(skb)->sacked; /* Account D-SACK for retransmitted packet. */ @@ -1419,19 +1420,17 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ if ((dup_sack && in_sack) && (sacked&TCPCB_SACKED_ACKED)) reord = min(fack_count, reord); - } else { - /* If it was in a hole, we detected reordering. */ - if (fack_count < prior_fackets && - !(sacked&TCPCB_SACKED_ACKED)) - reord = min(fack_count, reord); } /* Nothing to do; acked frame is about to be dropped. */ + fack_count += tcp_skb_pcount(skb); continue; } - if (!in_sack) + if (!in_sack) { + fack_count += tcp_skb_pcount(skb); continue; + } if (!(sacked&TCPCB_SACKED_ACKED)) { if (sacked & TCPCB_SACKED_RETRANS) { @@ -1448,12 +1447,17 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ tp->retransmit_skb_hint = NULL; } } else { - /* New sack for not retransmitted frame, - * which was in hole. It is reordering. - */ - if (!(sacked & TCPCB_RETRANS) && - fack_count < prior_fackets) - reord = min(fack_count, reord); + if (!(sacked & TCPCB_RETRANS)) { + /* New sack for not retransmitted frame, + * which was in hole. It is reordering. + */ + if (fack_count < prior_fackets) + reord = min(fack_count, reord); + + /* SACK enhanced F-RTO (RFC4138; Appendix B) */ + if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark)) + flag |= FLAG_ONLY_ORIG_SACKED; + } if (sacked & TCPCB_LOST) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; @@ -1462,24 +1466,13 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ /* clear lost hint */ tp->retransmit_skb_hint = NULL; } - /* SACK enhanced F-RTO detection. - * Set flag if and only if non-rexmitted - * segments below frto_highmark are - * SACKed (RFC4138; Appendix B). - * Clearing correct due to in-order walk - */ - if (after(end_seq, tp->frto_highmark)) { - flag &= ~FLAG_ONLY_ORIG_SACKED; - } else { - if (!(sacked & TCPCB_RETRANS)) - flag |= FLAG_ONLY_ORIG_SACKED; - } } TCP_SKB_CB(skb)->sacked |= TCPCB_SACKED_ACKED; flag |= FLAG_DATA_SACKED; tp->sacked_out += tcp_skb_pcount(skb); + fack_count += tcp_skb_pcount(skb); if (fack_count > tp->fackets_out) tp->fackets_out = fack_count; @@ -1490,6 +1483,8 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ } else { if (dup_sack && (sacked&TCPCB_RETRANS)) reord = min(fack_count, reord); + + fack_count += tcp_skb_pcount(skb); } /* D-SACK. We can detect redundant retransmission @@ -1504,6 +1499,12 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ tp->retransmit_skb_hint = NULL; } } + + /* SACK enhanced FRTO (RFC4138, Appendix B): Clearing correct + * due to in-order walk + */ + if (after(end_seq, tp->frto_highmark)) + flag &= ~FLAG_ONLY_ORIG_SACKED; } if (tp->retrans_out && @@ -1515,7 +1516,9 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ if ((reord < tp->fackets_out) && icsk->icsk_ca_state != TCP_CA_Loss && (!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark))) - tcp_update_reordering(sk, ((tp->fackets_out + 1) - reord), 0); + tcp_update_reordering(sk, tp->fackets_out - reord, 0); + +out: #if FASTRETRANS_DEBUG > 0 BUG_TRAP((int)tp->sacked_out >= 0); @@ -1671,6 +1674,9 @@ void tcp_enter_frto(struct sock *sk) } tcp_verify_left_out(tp); + /* Too bad if TCP was application limited */ + tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp) + 1); + /* Earlier loss recovery underway (see RFC4138; Appendix B). * The last condition is necessary at least in tp->frto_counter case. */ @@ -1703,6 +1709,8 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag) tcp_for_write_queue(skb, sk) { if (skb == tcp_send_head(sk)) break; + + TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; /* * Count the retransmission made on RTO correctly (only when * waiting for the first ACK and did not get it)... @@ -1716,7 +1724,7 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag) } else { if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) tp->undo_marker = 0; - TCP_SKB_CB(skb)->sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS); + TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; } /* Don't lost mark skbs that were fwd transmitted after RTO */ @@ -2630,7 +2638,8 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) * is before the ack sequence we can discard it as it's confirmed to have * arrived at the other end. */ -static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p) +static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p, + int prior_fackets) { struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -2639,6 +2648,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p) int fully_acked = 1; int flag = 0; int prior_packets = tp->packets_out; + u32 cnt = 0; + u32 reord = tp->packets_out; s32 seq_rtt = -1; ktime_t last_ackt = net_invalid_timestamp(); @@ -2679,10 +2690,14 @@ static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p) if ((flag & FLAG_DATA_ACKED) || (packets_acked > 1)) flag |= FLAG_NONHEAD_RETRANS_ACKED; - } else if (seq_rtt < 0) { - seq_rtt = now - scb->when; - if (fully_acked) - last_ackt = skb->tstamp; + } else { + if (seq_rtt < 0) { + seq_rtt = now - scb->when; + if (fully_acked) + last_ackt = skb->tstamp; + } + if (!(sacked & TCPCB_SACKED_ACKED)) + reord = min(cnt, reord); } if (sacked & TCPCB_SACKED_ACKED) @@ -2693,12 +2708,16 @@ static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p) if ((sacked & TCPCB_URG) && tp->urg_mode && !before(end_seq, tp->snd_up)) tp->urg_mode = 0; - } else if (seq_rtt < 0) { - seq_rtt = now - scb->when; - if (fully_acked) - last_ackt = skb->tstamp; + } else { + if (seq_rtt < 0) { + seq_rtt = now - scb->when; + if (fully_acked) + last_ackt = skb->tstamp; + } + reord = min(cnt, reord); } tp->packets_out -= packets_acked; + cnt += packets_acked; /* Initial outgoing SYN's get put onto the write_queue * just like anything else we transmit. It is not @@ -2730,13 +2749,18 @@ static int tcp_clean_rtx_queue(struct sock *sk, s32 *seq_rtt_p) tcp_ack_update_rtt(sk, flag, seq_rtt); tcp_rearm_rto(sk); + if (tcp_is_reno(tp)) { + tcp_remove_reno_sacks(sk, pkts_acked); + } else { + /* Non-retransmitted hole got filled? That's reordering */ + if (reord < prior_fackets) + tcp_update_reordering(sk, tp->fackets_out - reord, 0); + } + tp->fackets_out -= min(pkts_acked, tp->fackets_out); /* hint's skb might be NULL but we don't need to care */ tp->fastpath_cnt_hint -= min_t(u32, pkts_acked, tp->fastpath_cnt_hint); - if (tcp_is_reno(tp)) - tcp_remove_reno_sacks(sk, pkts_acked); - if (ca_ops->pkts_acked) { s32 rtt_us = -1; @@ -3019,6 +3043,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; u32 prior_in_flight; + u32 prior_fackets; s32 seq_rtt; int prior_packets; int frto_cwnd = 0; @@ -3043,6 +3068,8 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) tp->bytes_acked += min(ack - prior_snd_una, tp->mss_cache); } + prior_fackets = tp->fackets_out; + if (!(flag&FLAG_SLOWPATH) && after(ack, prior_snd_una)) { /* Window is constant, pure forward advance. * No more checks are required. @@ -3084,13 +3111,13 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) prior_in_flight = tcp_packets_in_flight(tp); /* See if we can take anything off of the retransmit queue. */ - flag |= tcp_clean_rtx_queue(sk, &seq_rtt); + flag |= tcp_clean_rtx_queue(sk, &seq_rtt, prior_fackets); + if (tp->frto_counter) + frto_cwnd = tcp_process_frto(sk, flag); /* Guarantee sacktag reordering detection against wrap-arounds */ if (before(tp->frto_highmark, tp->snd_una)) tp->frto_highmark = 0; - if (tp->frto_counter) - frto_cwnd = tcp_process_frto(sk, flag); if (tcp_ack_is_dubious(sk, flag)) { /* Advance CWND, if state allows this. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d438dfb0c8f..e566f3c6767 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2049,8 +2049,9 @@ static void *established_get_first(struct seq_file *seq) struct sock *sk; struct hlist_node *node; struct inet_timewait_sock *tw; + rwlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket); - read_lock_bh(&tcp_hashinfo.ehash[st->bucket].lock); + read_lock_bh(lock); sk_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { if (sk->sk_family != st->family) { continue; @@ -2067,7 +2068,7 @@ static void *established_get_first(struct seq_file *seq) rc = tw; goto out; } - read_unlock_bh(&tcp_hashinfo.ehash[st->bucket].lock); + read_unlock_bh(lock); st->state = TCP_SEQ_STATE_ESTABLISHED; } out: @@ -2094,11 +2095,11 @@ get_tw: cur = tw; goto out; } - read_unlock_bh(&tcp_hashinfo.ehash[st->bucket].lock); + read_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); st->state = TCP_SEQ_STATE_ESTABLISHED; if (++st->bucket < tcp_hashinfo.ehash_size) { - read_lock_bh(&tcp_hashinfo.ehash[st->bucket].lock); + read_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); sk = sk_head(&tcp_hashinfo.ehash[st->bucket].chain); } else { cur = NULL; @@ -2206,7 +2207,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v) case TCP_SEQ_STATE_TIME_WAIT: case TCP_SEQ_STATE_ESTABLISHED: if (v) - read_unlock_bh(&tcp_hashinfo.ehash[st->bucket].lock); + read_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); break; } } @@ -2417,6 +2418,8 @@ void tcp4_proc_exit(void) } #endif /* CONFIG_PROC_FS */ +DEFINE_PROTO_INUSE(tcp) + struct proto tcp_prot = { .name = "TCP", .owner = THIS_MODULE, @@ -2451,6 +2454,7 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif + REF_PROTO_INUSE(tcp) }; void __init tcp_v4_init(struct net_proto_family *ops) diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index a794a8ca8b4..978b3fd61e6 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -17,6 +17,11 @@ static struct xfrm_tunnel *tunnel4_handlers; static struct xfrm_tunnel *tunnel64_handlers; static DEFINE_MUTEX(tunnel4_mutex); +static inline struct xfrm_tunnel **fam_handlers(unsigned short family) +{ + return (family == AF_INET) ? &tunnel4_handlers : &tunnel64_handlers; +} + int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family) { struct xfrm_tunnel **pprev; @@ -25,8 +30,7 @@ int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family) mutex_lock(&tunnel4_mutex); - for (pprev = (family == AF_INET) ? &tunnel4_handlers : &tunnel64_handlers; - *pprev; pprev = &(*pprev)->next) { + for (pprev = fam_handlers(family); *pprev; pprev = &(*pprev)->next) { if ((*pprev)->priority > priority) break; if ((*pprev)->priority == priority) @@ -53,8 +57,7 @@ int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family) mutex_lock(&tunnel4_mutex); - for (pprev = (family == AF_INET) ? &tunnel4_handlers : &tunnel64_handlers; - *pprev; pprev = &(*pprev)->next) { + for (pprev = fam_handlers(family); *pprev; pprev = &(*pprev)->next) { if (*pprev == handler) { *pprev = handler->next; ret = 0; @@ -118,6 +121,17 @@ static void tunnel4_err(struct sk_buff *skb, u32 info) break; } +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +static void tunnel64_err(struct sk_buff *skb, u32 info) +{ + struct xfrm_tunnel *handler; + + for (handler = tunnel64_handlers; handler; handler = handler->next) + if (!handler->err_handler(skb, info)) + break; +} +#endif + static struct net_protocol tunnel4_protocol = { .handler = tunnel4_rcv, .err_handler = tunnel4_err, @@ -127,7 +141,7 @@ static struct net_protocol tunnel4_protocol = { #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) static struct net_protocol tunnel64_protocol = { .handler = tunnel64_rcv, - .err_handler = tunnel4_err, + .err_handler = tunnel64_err, .no_policy = 1, }; #endif diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 4bc25b46f33..03c400ca14c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1430,6 +1430,8 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) } +DEFINE_PROTO_INUSE(udp) + struct proto udp_prot = { .name = "UDP", .owner = THIS_MODULE, @@ -1452,6 +1454,7 @@ struct proto udp_prot = { .compat_setsockopt = compat_udp_setsockopt, .compat_getsockopt = compat_udp_getsockopt, #endif + REF_PROTO_INUSE(udp) }; /* ------------------------------------------------------------------------ */ diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 94977205abb..f5baeb3e8b8 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -44,6 +44,8 @@ static struct net_protocol udplite_protocol = { .no_policy = 1, }; +DEFINE_PROTO_INUSE(udplite) + struct proto udplite_prot = { .name = "UDP-Lite", .owner = THIS_MODULE, @@ -67,6 +69,7 @@ struct proto udplite_prot = { .compat_setsockopt = compat_udp_setsockopt, .compat_getsockopt = compat_udp_getsockopt, #endif + REF_PROTO_INUSE(udplite) }; static struct inet_protosw udplite4_protosw = { diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 706622af206..428c6b0e26d 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -31,25 +31,6 @@ struct fib6_rule static struct fib_rules_ops fib6_rules_ops; -static struct fib6_rule main_rule = { - .common = { - .refcnt = ATOMIC_INIT(2), - .pref = 0x7FFE, - .action = FR_ACT_TO_TBL, - .table = RT6_TABLE_MAIN, - }, -}; - -static struct fib6_rule local_rule = { - .common = { - .refcnt = ATOMIC_INIT(2), - .pref = 0, - .action = FR_ACT_TO_TBL, - .table = RT6_TABLE_LOCAL, - .flags = FIB_RULE_PERMANENT, - }, -}; - struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags, pol_lookup_t lookup) { @@ -270,11 +251,23 @@ static struct fib_rules_ops fib6_rules_ops = { .owner = THIS_MODULE, }; -void __init fib6_rules_init(void) +static int __init fib6_default_rules_init(void) { - list_add_tail(&local_rule.common.list, &fib6_rules_ops.rules_list); - list_add_tail(&main_rule.common.list, &fib6_rules_ops.rules_list); + int err; + + err = fib_default_rule_add(&fib6_rules_ops, 0, + RT6_TABLE_LOCAL, FIB_RULE_PERMANENT); + if (err < 0) + return err; + err = fib_default_rule_add(&fib6_rules_ops, 0x7FFE, RT6_TABLE_MAIN, 0); + if (err < 0) + return err; + return 0; +} +void __init fib6_rules_init(void) +{ + BUG_ON(fib6_default_rules_init()); fib_rules_register(&fib6_rules_ops); } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index d6f1026f194..adc73adadfa 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -37,9 +37,8 @@ void __inet6_hash(struct inet_hashinfo *hashinfo, } else { unsigned int hash; sk->sk_hash = hash = inet6_sk_ehashfn(sk); - hash &= (hashinfo->ehash_size - 1); - list = &hashinfo->ehash[hash].chain; - lock = &hashinfo->ehash[hash].lock; + list = &inet_ehash_bucket(hashinfo, hash)->chain; + lock = inet_ehash_lockp(hashinfo, hash); write_lock(lock); } @@ -70,9 +69,10 @@ struct sock *__inet6_lookup_established(struct inet_hashinfo *hashinfo, */ unsigned int hash = inet6_ehashfn(daddr, hnum, saddr, sport); struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash); + rwlock_t *lock = inet_ehash_lockp(hashinfo, hash); prefetch(head->chain.first); - read_lock(&head->lock); + read_lock(lock); sk_for_each(sk, node, &head->chain) { /* For IPV6 do the cheaper port and family tests first. */ if (INET6_MATCH(sk, hash, saddr, daddr, ports, dif)) @@ -92,12 +92,12 @@ struct sock *__inet6_lookup_established(struct inet_hashinfo *hashinfo, goto hit; } } - read_unlock(&head->lock); + read_unlock(lock); return NULL; hit: sock_hold(sk); - read_unlock(&head->lock); + read_unlock(lock); return sk; } EXPORT_SYMBOL(__inet6_lookup_established); @@ -175,12 +175,13 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, const unsigned int hash = inet6_ehashfn(daddr, lport, saddr, inet->dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); + rwlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; const struct hlist_node *node; struct inet_timewait_sock *tw; prefetch(head->chain.first); - write_lock(&head->lock); + write_lock(lock); /* Check TIME-WAIT sockets first. */ sk_for_each(sk2, node, &head->twchain) { @@ -216,7 +217,7 @@ unique: __sk_add_node(sk, &head->chain); sk->sk_hash = hash; sock_prot_inc_use(sk->sk_prot); - write_unlock(&head->lock); + write_unlock(lock); if (twp != NULL) { *twp = tw; @@ -231,7 +232,7 @@ unique: return 0; not_unique: - write_unlock(&head->lock); + write_unlock(lock); return -EADDRNOTAVAIL; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 653fc0a8235..86e1835ce4e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1339,6 +1339,19 @@ error: return err; } +static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np) +{ + inet->cork.flags &= ~IPCORK_OPT; + kfree(np->cork.opt); + np->cork.opt = NULL; + if (np->cork.rt) { + dst_release(&np->cork.rt->u.dst); + np->cork.rt = NULL; + inet->cork.flags &= ~IPCORK_ALLFRAG; + } + memset(&inet->cork.fl, 0, sizeof(inet->cork.fl)); +} + int ip6_push_pending_frames(struct sock *sk) { struct sk_buff *skb, *tmp_skb; @@ -1415,15 +1428,7 @@ int ip6_push_pending_frames(struct sock *sk) } out: - inet->cork.flags &= ~IPCORK_OPT; - kfree(np->cork.opt); - np->cork.opt = NULL; - if (np->cork.rt) { - dst_release(&np->cork.rt->u.dst); - np->cork.rt = NULL; - inet->cork.flags &= ~IPCORK_ALLFRAG; - } - memset(&inet->cork.fl, 0, sizeof(inet->cork.fl)); + ip6_cork_release(inet, np); return err; error: goto out; @@ -1431,8 +1436,6 @@ error: void ip6_flush_pending_frames(struct sock *sk) { - struct inet_sock *inet = inet_sk(sk); - struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) { @@ -1442,14 +1445,5 @@ void ip6_flush_pending_frames(struct sock *sk) kfree_skb(skb); } - inet->cork.flags &= ~IPCORK_OPT; - - kfree(np->cork.opt); - np->cork.opt = NULL; - if (np->cork.rt) { - dst_release(&np->cork.rt->u.dst); - np->cork.rt = NULL; - inet->cork.flags &= ~IPCORK_ALLFRAG; - } - memset(&inet->cork.fl, 0, sizeof(inet->cork.fl)); + ip6_cork_release(inet_sk(sk), inet6_sk(sk)); } diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 85eb4798d8d..0cd4056f912 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -36,6 +36,7 @@ #include <net/ipcomp.h> #include <asm/semaphore.h> #include <linux/crypto.h> +#include <linux/err.h> #include <linux/pfkeyv2.h> #include <linux/random.h> #include <linux/percpu.h> @@ -358,7 +359,7 @@ static struct crypto_comp **ipcomp6_alloc_tfms(const char *alg_name) for_each_possible_cpu(cpu) { struct crypto_comp *tfm = crypto_alloc_comp(alg_name, 0, CRYPTO_ALG_ASYNC); - if (!tfm) + if (IS_ERR(tfm)) goto error; *per_cpu_ptr(tfms, cpu) = tfm; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 36f7dbfb6db..67997a74ddc 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1037,6 +1037,7 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) ndmsg = nlmsg_data(nlh); ndmsg->nduseropt_family = AF_INET6; + ndmsg->nduseropt_ifindex = ra->dev->ifindex; ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type; ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code; ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3; diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 4513eab7739..e789ec44d23 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -4,25 +4,29 @@ # Link order matters here. obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o -obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o -obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o -obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o -obj-$(CONFIG_IP6_NF_MATCH_FRAG) += ip6t_frag.o -obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o -obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o -obj-$(CONFIG_IP6_NF_MATCH_OWNER) += ip6t_owner.o obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o -obj-$(CONFIG_IP6_NF_TARGET_HL) += ip6t_HL.o obj-$(CONFIG_IP6_NF_QUEUE) += ip6_queue.o -obj-$(CONFIG_IP6_NF_TARGET_LOG) += ip6t_LOG.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o -obj-$(CONFIG_IP6_NF_MATCH_HL) += ip6t_hl.o -obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o -obj-$(CONFIG_IP6_NF_MATCH_MH) += ip6t_mh.o # objects for l3 independent conntrack nf_conntrack_ipv6-objs := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o nf_conntrack_reasm.o # l3 independent conntrack obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o + +# matches +obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o +obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o +obj-$(CONFIG_IP6_NF_MATCH_FRAG) += ip6t_frag.o +obj-$(CONFIG_IP6_NF_MATCH_HL) += ip6t_hl.o +obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o +obj-$(CONFIG_IP6_NF_MATCH_MH) += ip6t_mh.o +obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o +obj-$(CONFIG_IP6_NF_MATCH_OWNER) += ip6t_owner.o +obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o + +# targets +obj-$(CONFIG_IP6_NF_TARGET_HL) += ip6t_HL.o +obj-$(CONFIG_IP6_NF_TARGET_LOG) += ip6t_LOG.o +obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 6413a30d9f6..e273605eef8 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -23,6 +23,7 @@ #include <linux/spinlock.h> #include <linux/sysctl.h> #include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <linux/mutex.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -596,15 +597,11 @@ static ctl_table ipq_root_table[] = { { .ctl_name = 0 } }; -#ifdef CONFIG_PROC_FS -static int -ipq_get_info(char *buffer, char **start, off_t offset, int length) +static int ip6_queue_show(struct seq_file *m, void *v) { - int len; - read_lock_bh(&queue_lock); - len = sprintf(buffer, + seq_printf(m, "Peer PID : %d\n" "Copy mode : %hu\n" "Copy range : %u\n" @@ -621,16 +618,21 @@ ipq_get_info(char *buffer, char **start, off_t offset, int length) queue_user_dropped); read_unlock_bh(&queue_lock); + return 0; +} - *start = buffer + offset; - len -= offset; - if (len > length) - len = length; - else if (len < 0) - len = 0; - return len; +static int ip6_queue_open(struct inode *inode, struct file *file) +{ + return single_open(file, ip6_queue_show, NULL); } -#endif /* CONFIG_PROC_FS */ + +static const struct file_operations ip6_queue_proc_fops = { + .open = ip6_queue_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .owner = THIS_MODULE, +}; static struct nf_queue_handler nfqh = { .name = "ip6_queue", @@ -650,10 +652,11 @@ static int __init ip6_queue_init(void) goto cleanup_netlink_notifier; } - proc = proc_net_create(&init_net, IPQ_PROC_FS_NAME, 0, ipq_get_info); - if (proc) + proc = create_proc_entry(IPQ_PROC_FS_NAME, 0, init_net.proc_net); + if (proc) { proc->owner = THIS_MODULE; - else { + proc->proc_fops = &ip6_queue_proc_fops; + } else { printk(KERN_ERR "ip6_queue: failed to create proc entry\n"); goto cleanup_ipqnl; } diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index be526ad9254..8631ed7fe8a 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -32,27 +32,16 @@ static struct proc_dir_entry *proc_net_devsnmp6; -static int fold_prot_inuse(struct proto *proto) -{ - int res = 0; - int cpu; - - for_each_possible_cpu(cpu) - res += proto->stats[cpu].inuse; - - return res; -} - static int sockstat6_seq_show(struct seq_file *seq, void *v) { seq_printf(seq, "TCP6: inuse %d\n", - fold_prot_inuse(&tcpv6_prot)); + sock_prot_inuse(&tcpv6_prot)); seq_printf(seq, "UDP6: inuse %d\n", - fold_prot_inuse(&udpv6_prot)); + sock_prot_inuse(&udpv6_prot)); seq_printf(seq, "UDPLITE6: inuse %d\n", - fold_prot_inuse(&udplitev6_prot)); + sock_prot_inuse(&udplitev6_prot)); seq_printf(seq, "RAW6: inuse %d\n", - fold_prot_inuse(&rawv6_prot)); + sock_prot_inuse(&rawv6_prot)); seq_printf(seq, "FRAG6: inuse %d memory %d\n", ip6_frag_nqueues(), ip6_frag_mem()); return 0; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ca24ef19cd8..807260d0358 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1144,6 +1144,8 @@ static int rawv6_init_sk(struct sock *sk) return(0); } +DEFINE_PROTO_INUSE(rawv6) + struct proto rawv6_prot = { .name = "RAWv6", .owner = THIS_MODULE, @@ -1166,6 +1168,7 @@ struct proto rawv6_prot = { .compat_setsockopt = compat_rawv6_setsockopt, .compat_getsockopt = compat_rawv6_getsockopt, #endif + REF_PROTO_INUSE(rawv6) }; #ifdef CONFIG_PROC_FS diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 95f8e4a62f6..6ecb5e6fae2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -38,12 +38,8 @@ #include <linux/in6.h> #include <linux/init.h> #include <linux/if_arp.h> - -#ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> -#endif - #include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> @@ -548,12 +544,8 @@ restart: rt = rt6_device_match(rt, fl->oif, flags); BACKTRACK(&fl->fl6_src); out: - dst_hold(&rt->u.dst); + dst_use(&rt->u.dst, jiffies); read_unlock_bh(&table->tb6_lock); - - rt->u.dst.lastuse = jiffies; - rt->u.dst.__use++; - return rt; } @@ -2288,71 +2280,50 @@ struct rt6_proc_arg static int rt6_info_route(struct rt6_info *rt, void *p_arg) { - struct rt6_proc_arg *arg = (struct rt6_proc_arg *) p_arg; - - if (arg->skip < arg->offset / RT6_INFO_LEN) { - arg->skip++; - return 0; - } - - if (arg->len >= arg->length) - return 0; + struct seq_file *m = p_arg; - arg->len += sprintf(arg->buffer + arg->len, - NIP6_SEQFMT " %02x ", - NIP6(rt->rt6i_dst.addr), - rt->rt6i_dst.plen); + seq_printf(m, NIP6_SEQFMT " %02x ", NIP6(rt->rt6i_dst.addr), + rt->rt6i_dst.plen); #ifdef CONFIG_IPV6_SUBTREES - arg->len += sprintf(arg->buffer + arg->len, - NIP6_SEQFMT " %02x ", - NIP6(rt->rt6i_src.addr), - rt->rt6i_src.plen); + seq_printf(m, NIP6_SEQFMT " %02x ", NIP6(rt->rt6i_src.addr), + rt->rt6i_src.plen); #else - arg->len += sprintf(arg->buffer + arg->len, - "00000000000000000000000000000000 00 "); + seq_puts(m, "00000000000000000000000000000000 00 "); #endif if (rt->rt6i_nexthop) { - arg->len += sprintf(arg->buffer + arg->len, - NIP6_SEQFMT, - NIP6(*((struct in6_addr *)rt->rt6i_nexthop->primary_key))); + seq_printf(m, NIP6_SEQFMT, + NIP6(*((struct in6_addr *)rt->rt6i_nexthop->primary_key))); } else { - arg->len += sprintf(arg->buffer + arg->len, - "00000000000000000000000000000000"); + seq_puts(m, "00000000000000000000000000000000"); } - arg->len += sprintf(arg->buffer + arg->len, - " %08x %08x %08x %08x %8s\n", - rt->rt6i_metric, atomic_read(&rt->u.dst.__refcnt), - rt->u.dst.__use, rt->rt6i_flags, - rt->rt6i_dev ? rt->rt6i_dev->name : ""); + seq_printf(m, " %08x %08x %08x %08x %8s\n", + rt->rt6i_metric, atomic_read(&rt->u.dst.__refcnt), + rt->u.dst.__use, rt->rt6i_flags, + rt->rt6i_dev ? rt->rt6i_dev->name : ""); return 0; } -static int rt6_proc_info(char *buffer, char **start, off_t offset, int length) +static int ipv6_route_show(struct seq_file *m, void *v) { - struct rt6_proc_arg arg = { - .buffer = buffer, - .offset = offset, - .length = length, - }; - - fib6_clean_all(rt6_info_route, 0, &arg); - - *start = buffer; - if (offset) - *start += offset % RT6_INFO_LEN; - - arg.len -= offset % RT6_INFO_LEN; - - if (arg.len > length) - arg.len = length; - if (arg.len < 0) - arg.len = 0; + fib6_clean_all(rt6_info_route, 0, m); + return 0; +} - return arg.len; +static int ipv6_route_open(struct inode *inode, struct file *file) +{ + return single_open(file, ipv6_route_show, NULL); } +static const struct file_operations ipv6_route_proc_fops = { + .owner = THIS_MODULE, + .open = ipv6_route_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int rt6_stats_seq_show(struct seq_file *seq, void *v) { seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", @@ -2489,22 +2460,14 @@ ctl_table ipv6_route_table[] = { void __init ip6_route_init(void) { -#ifdef CONFIG_PROC_FS - struct proc_dir_entry *p; -#endif ip6_dst_ops.kmem_cachep = kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops.kmem_cachep; fib6_init(); -#ifdef CONFIG_PROC_FS - p = proc_net_create(&init_net, "ipv6_route", 0, rt6_proc_info); - if (p) - p->owner = THIS_MODULE; - + proc_net_fops_create(&init_net, "ipv6_route", 0, &ipv6_route_proc_fops); proc_net_fops_create(&init_net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops); -#endif #ifdef CONFIG_XFRM xfrm6_init(); #endif diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 06be2a1f273..3aad861975a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2107,6 +2107,8 @@ void tcp6_proc_exit(void) } #endif +DEFINE_PROTO_INUSE(tcpv6) + struct proto tcpv6_prot = { .name = "TCPv6", .owner = THIS_MODULE, @@ -2141,6 +2143,7 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif + REF_PROTO_INUSE(tcpv6) }; static struct inet6_protocol tcpv6_protocol = { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index caebad6ee51..ee1cc3f8599 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -205,12 +205,11 @@ out: return err; csum_copy_err: + UDP6_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite); skb_kill_datagram(sk, skb, flags); - if (flags & MSG_DONTWAIT) { - UDP6_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite); + if (flags & MSG_DONTWAIT) return -EAGAIN; - } goto try_again; } @@ -971,6 +970,8 @@ void udp6_proc_exit(void) { /* ------------------------------------------------------------------------ */ +DEFINE_PROTO_INUSE(udpv6) + struct proto udpv6_prot = { .name = "UDPv6", .owner = THIS_MODULE, @@ -992,6 +993,7 @@ struct proto udpv6_prot = { .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, #endif + REF_PROTO_INUSE(udpv6) }; static struct inet_protosw udpv6_protosw = { diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 766566f7de4..5a0379f7141 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -40,6 +40,8 @@ static int udplite_v6_get_port(struct sock *sk, unsigned short snum) return udplite_get_port(sk, snum, ipv6_rcv_saddr_equal); } +DEFINE_PROTO_INUSE(udplitev6) + struct proto udplitev6_prot = { .name = "UDPLITEv6", .owner = THIS_MODULE, @@ -62,6 +64,7 @@ struct proto udplitev6_prot = { .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, #endif + REF_PROTO_INUSE(udplitev6) }; static struct inet_protosw udplite6_protosw = { diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index a195a66e0cc..c76a9523091 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -92,11 +92,6 @@ extern int ipxrtr_route_skb(struct sk_buff *skb); extern struct ipx_route *ipxrtr_lookup(__be32 net); extern int ipxrtr_ioctl(unsigned int cmd, void __user *arg); -#undef IPX_REFCNT_DEBUG -#ifdef IPX_REFCNT_DEBUG -atomic_t ipx_sock_nr; -#endif - struct ipx_interface *ipx_interfaces_head(void) { struct ipx_interface *rc = NULL; @@ -151,14 +146,7 @@ static void ipx_destroy_socket(struct sock *sk) { ipx_remove_socket(sk); skb_queue_purge(&sk->sk_receive_queue); -#ifdef IPX_REFCNT_DEBUG - atomic_dec(&ipx_sock_nr); - printk(KERN_DEBUG "IPX socket %p released, %d are still alive\n", sk, - atomic_read(&ipx_sock_nr)); - if (atomic_read(&sk->sk_refcnt) != 1) - printk(KERN_DEBUG "Destruction sock ipx %p delayed, cnt=%d\n", - sk, atomic_read(&sk->sk_refcnt)); -#endif + sk_refcnt_debug_dec(sk); sock_put(sk); } @@ -1384,11 +1372,8 @@ static int ipx_create(struct net *net, struct socket *sock, int protocol) sk = sk_alloc(net, PF_IPX, GFP_KERNEL, &ipx_proto); if (!sk) goto out; -#ifdef IPX_REFCNT_DEBUG - atomic_inc(&ipx_sock_nr); - printk(KERN_DEBUG "IPX socket %p created, now we have %d alive\n", sk, - atomic_read(&ipx_sock_nr)); -#endif + + sk_refcnt_debug_inc(sk); sock_init_data(sock, sk); sk->sk_no_check = 1; /* Checksum off by default */ sock->ops = &ipx_dgram_ops; @@ -1409,6 +1394,7 @@ static int ipx_release(struct socket *sock) sock_set_flag(sk, SOCK_DEAD); sock->sk = NULL; + sk_refcnt_debug_release(sk); ipx_destroy_socket(sk); out: return 0; diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 6fffb3845ab..ce176e691af 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -13,6 +13,18 @@ config MAC80211 This option enables the hardware independent IEEE 802.11 networking stack. +config MAC80211_RCSIMPLE + bool "'simple' rate control algorithm" if EMBEDDED + default y + depends on MAC80211 + help + This option allows you to turn off the 'simple' rate + control algorithm in mac80211. If you do turn it off, + you absolutely need another rate control algorithm. + + Say Y unless you know you will have another algorithm + available. + config MAC80211_LEDS bool "Enable LED triggers" depends on MAC80211 && LEDS_TRIGGERS diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 219cd9f9341..1e6237b3484 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -1,8 +1,9 @@ -obj-$(CONFIG_MAC80211) += mac80211.o rc80211_simple.o +obj-$(CONFIG_MAC80211) += mac80211.o mac80211-objs-$(CONFIG_MAC80211_LEDS) += ieee80211_led.o mac80211-objs-$(CONFIG_MAC80211_DEBUGFS) += debugfs.o debugfs_sta.o debugfs_netdev.o debugfs_key.o mac80211-objs-$(CONFIG_NET_SCHED) += wme.o +mac80211-objs-$(CONFIG_MAC80211_RCSIMPLE) += rc80211_simple.o mac80211-objs := \ ieee80211.o \ diff --git a/net/mac80211/ieee80211.c b/net/mac80211/ieee80211.c index f484ca7ade9..e0ee65a969b 100644 --- a/net/mac80211/ieee80211.c +++ b/net/mac80211/ieee80211.c @@ -1072,7 +1072,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) ieee80211_debugfs_add_netdev(IEEE80211_DEV_TO_SUB_IF(local->mdev)); ieee80211_if_set_type(local->mdev, IEEE80211_IF_TYPE_AP); - result = ieee80211_init_rate_ctrl_alg(local, NULL); + result = ieee80211_init_rate_ctrl_alg(local, + hw->rate_control_algorithm); if (result < 0) { printk(KERN_DEBUG "%s: Failed to initialize rate control " "algorithm\n", wiphy_name(local->hw.wiphy)); @@ -1233,8 +1234,17 @@ static int __init ieee80211_init(void) BUILD_BUG_ON(sizeof(struct ieee80211_tx_packet_data) > sizeof(skb->cb)); +#ifdef CONFIG_MAC80211_RCSIMPLE + ret = ieee80211_rate_control_register(&mac80211_rcsimple); + if (ret) + return ret; +#endif + ret = ieee80211_wme_register(); if (ret) { +#ifdef CONFIG_MAC80211_RCSIMPLE + ieee80211_rate_control_unregister(&mac80211_rcsimple); +#endif printk(KERN_DEBUG "ieee80211_init: failed to " "initialize WME (err=%d)\n", ret); return ret; @@ -1248,6 +1258,10 @@ static int __init ieee80211_init(void) static void __exit ieee80211_exit(void) { +#ifdef CONFIG_MAC80211_RCSIMPLE + ieee80211_rate_control_unregister(&mac80211_rcsimple); +#endif + ieee80211_wme_unregister(); ieee80211_debugfs_netdev_exit(); } diff --git a/net/mac80211/ieee80211_common.h b/net/mac80211/ieee80211_common.h deleted file mode 100644 index c15295d43d8..00000000000 --- a/net/mac80211/ieee80211_common.h +++ /dev/null @@ -1,91 +0,0 @@ -/* - * IEEE 802.11 driver (80211.o) -- hostapd interface - * Copyright 2002-2004, Instant802 Networks, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef IEEE80211_COMMON_H -#define IEEE80211_COMMON_H - -#include <linux/types.h> - -/* - * This is common header information with user space. It is used on all - * frames sent to wlan#ap interface. - */ - -#define IEEE80211_FI_VERSION 0x80211001 - -struct ieee80211_frame_info { - __be32 version; - __be32 length; - __be64 mactime; - __be64 hosttime; - __be32 phytype; - __be32 channel; - __be32 datarate; - __be32 antenna; - __be32 priority; - __be32 ssi_type; - __be32 ssi_signal; - __be32 ssi_noise; - __be32 preamble; - __be32 encoding; - - /* Note: this structure is otherwise identical to capture format used - * in linux-wlan-ng, but this additional field is used to provide meta - * data about the frame to hostapd. This was the easiest method for - * providing this information, but this might change in the future. */ - __be32 msg_type; -} __attribute__ ((packed)); - - -enum ieee80211_msg_type { - ieee80211_msg_normal = 0, - ieee80211_msg_tx_callback_ack = 1, - ieee80211_msg_tx_callback_fail = 2, - /* hole at 3, was ieee80211_msg_passive_scan but unused */ - /* hole at 4, was ieee80211_msg_wep_frame_unknown_key but now unused */ - ieee80211_msg_michael_mic_failure = 5, - /* hole at 6, was monitor but never sent to userspace */ - ieee80211_msg_sta_not_assoc = 7, - /* 8 was ieee80211_msg_set_aid_for_sta */ - /* 9 was ieee80211_msg_key_threshold_notification */ - /* 11 was ieee80211_msg_radar */ -}; - -struct ieee80211_msg_key_notification { - int tx_rx_count; - char ifname[IFNAMSIZ]; - u8 addr[ETH_ALEN]; /* ff:ff:ff:ff:ff:ff for broadcast keys */ -}; - - -enum ieee80211_phytype { - ieee80211_phytype_fhss_dot11_97 = 1, - ieee80211_phytype_dsss_dot11_97 = 2, - ieee80211_phytype_irbaseband = 3, - ieee80211_phytype_dsss_dot11_b = 4, - ieee80211_phytype_pbcc_dot11_b = 5, - ieee80211_phytype_ofdm_dot11_g = 6, - ieee80211_phytype_pbcc_dot11_g = 7, - ieee80211_phytype_ofdm_dot11_a = 8, -}; - -enum ieee80211_ssi_type { - ieee80211_ssi_none = 0, - ieee80211_ssi_norm = 1, /* normalized, 0-1000 */ - ieee80211_ssi_dbm = 2, - ieee80211_ssi_raw = 3, /* raw SSI */ -}; - -struct ieee80211_radar_info { - int channel; - int radar; - int radar_type; -}; - -#endif /* IEEE80211_COMMON_H */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index d575ccd67e9..72e1c93dd87 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -230,6 +230,7 @@ struct ieee80211_if_vlan { #define IEEE80211_STA_AUTO_SSID_SEL BIT(10) #define IEEE80211_STA_AUTO_BSSID_SEL BIT(11) #define IEEE80211_STA_AUTO_CHANNEL_SEL BIT(12) +#define IEEE80211_STA_PRIVACY_INVOKED BIT(13) struct ieee80211_if_sta { enum { IEEE80211_DISABLED, IEEE80211_AUTHENTICATE, @@ -261,7 +262,6 @@ struct ieee80211_if_sta { unsigned long request; struct sk_buff_head skb_queue; - int key_management_enabled; unsigned long last_probe; #define IEEE80211_AUTH_ALG_OPEN BIT(0) diff --git a/net/mac80211/ieee80211_ioctl.c b/net/mac80211/ieee80211_ioctl.c index 6caa3ec2cff..7027eed4d4a 100644 --- a/net/mac80211/ieee80211_ioctl.c +++ b/net/mac80211/ieee80211_ioctl.c @@ -917,7 +917,6 @@ static int ieee80211_ioctl_siwauth(struct net_device *dev, struct iw_request_info *info, struct iw_param *data, char *extra) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); int ret = 0; @@ -927,18 +926,21 @@ static int ieee80211_ioctl_siwauth(struct net_device *dev, case IW_AUTH_CIPHER_GROUP: case IW_AUTH_WPA_ENABLED: case IW_AUTH_RX_UNENCRYPTED_EAPOL: - break; case IW_AUTH_KEY_MGMT: + break; + case IW_AUTH_PRIVACY_INVOKED: if (sdata->type != IEEE80211_IF_TYPE_STA) ret = -EINVAL; else { + sdata->u.sta.flags &= ~IEEE80211_STA_PRIVACY_INVOKED; /* - * Key management was set by wpa_supplicant, - * we only need this to associate to a network - * that has privacy enabled regardless of not - * having a key. + * Privacy invoked by wpa_supplicant, store the + * value and allow associating to a protected + * network without having a key up front. */ - sdata->u.sta.key_management_enabled = !!data->value; + if (data->value) + sdata->u.sta.flags |= + IEEE80211_STA_PRIVACY_INVOKED; } break; case IW_AUTH_80211_AUTH_ALG: @@ -948,11 +950,6 @@ static int ieee80211_ioctl_siwauth(struct net_device *dev, else ret = -EOPNOTSUPP; break; - case IW_AUTH_PRIVACY_INVOKED: - if (local->ops->set_privacy_invoked) - ret = local->ops->set_privacy_invoked( - local_to_hw(local), data->value); - break; default: ret = -EOPNOTSUPP; break; diff --git a/net/mac80211/ieee80211_rate.c b/net/mac80211/ieee80211_rate.c index 93abb8fff14..7254bd60983 100644 --- a/net/mac80211/ieee80211_rate.c +++ b/net/mac80211/ieee80211_rate.c @@ -25,13 +25,25 @@ int ieee80211_rate_control_register(struct rate_control_ops *ops) { struct rate_control_alg *alg; + if (!ops->name) + return -EINVAL; + + mutex_lock(&rate_ctrl_mutex); + list_for_each_entry(alg, &rate_ctrl_algs, list) { + if (!strcmp(alg->ops->name, ops->name)) { + /* don't register an algorithm twice */ + WARN_ON(1); + return -EALREADY; + } + } + alg = kzalloc(sizeof(*alg), GFP_KERNEL); if (alg == NULL) { + mutex_unlock(&rate_ctrl_mutex); return -ENOMEM; } alg->ops = ops; - mutex_lock(&rate_ctrl_mutex); list_add_tail(&alg->list, &rate_ctrl_algs); mutex_unlock(&rate_ctrl_mutex); @@ -61,9 +73,12 @@ ieee80211_try_rate_control_ops_get(const char *name) struct rate_control_alg *alg; struct rate_control_ops *ops = NULL; + if (!name) + return NULL; + mutex_lock(&rate_ctrl_mutex); list_for_each_entry(alg, &rate_ctrl_algs, list) { - if (!name || !strcmp(alg->ops->name, name)) + if (!strcmp(alg->ops->name, name)) if (try_module_get(alg->ops->module)) { ops = alg->ops; break; @@ -80,9 +95,12 @@ ieee80211_rate_control_ops_get(const char *name) { struct rate_control_ops *ops; + if (!name) + name = "simple"; + ops = ieee80211_try_rate_control_ops_get(name); if (!ops) { - request_module("rc80211_%s", name ? name : "default"); + request_module("rc80211_%s", name); ops = ieee80211_try_rate_control_ops_get(name); } return ops; diff --git a/net/mac80211/ieee80211_rate.h b/net/mac80211/ieee80211_rate.h index 7cd1ebab4f8..23688139ffb 100644 --- a/net/mac80211/ieee80211_rate.h +++ b/net/mac80211/ieee80211_rate.h @@ -65,6 +65,9 @@ struct rate_control_ref { struct kref kref; }; +/* default 'simple' algorithm */ +extern struct rate_control_ops mac80211_rcsimple; + int ieee80211_rate_control_register(struct rate_control_ops *ops); void ieee80211_rate_control_unregister(struct rate_control_ops *ops); diff --git a/net/mac80211/ieee80211_sta.c b/net/mac80211/ieee80211_sta.c index fc6a3ff3d90..015b3f879aa 100644 --- a/net/mac80211/ieee80211_sta.c +++ b/net/mac80211/ieee80211_sta.c @@ -704,10 +704,11 @@ static int ieee80211_privacy_mismatch(struct net_device *dev, { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_sta_bss *bss; - int res = 0; + int bss_privacy; + int wep_privacy; + int privacy_invoked; - if (!ifsta || (ifsta->flags & IEEE80211_STA_MIXED_CELL) || - ifsta->key_management_enabled) + if (!ifsta || (ifsta->flags & IEEE80211_STA_MIXED_CELL)) return 0; bss = ieee80211_rx_bss_get(dev, ifsta->bssid, local->hw.conf.channel, @@ -715,13 +716,16 @@ static int ieee80211_privacy_mismatch(struct net_device *dev, if (!bss) return 0; - if (ieee80211_sta_wep_configured(dev) != - !!(bss->capability & WLAN_CAPABILITY_PRIVACY)) - res = 1; + bss_privacy = !!(bss->capability & WLAN_CAPABILITY_PRIVACY); + wep_privacy = !!ieee80211_sta_wep_configured(dev); + privacy_invoked = !!(ifsta->flags & IEEE80211_STA_PRIVACY_INVOKED); ieee80211_rx_bss_put(dev, bss); - return res; + if ((bss_privacy == wep_privacy) || (bss_privacy == privacy_invoked)) + return 0; + + return 1; } diff --git a/net/mac80211/rc80211_simple.c b/net/mac80211/rc80211_simple.c index 314b8de8886..da72737364e 100644 --- a/net/mac80211/rc80211_simple.c +++ b/net/mac80211/rc80211_simple.c @@ -7,7 +7,6 @@ * published by the Free Software Foundation. */ -#include <linux/module.h> #include <linux/init.h> #include <linux/netdevice.h> #include <linux/types.h> @@ -29,8 +28,6 @@ #define RATE_CONTROL_INTERVAL (HZ / 20) #define RATE_CONTROL_MIN_TX 10 -MODULE_ALIAS("rc80211_default"); - static void rate_control_rate_inc(struct ieee80211_local *local, struct sta_info *sta) { @@ -394,8 +391,7 @@ static void rate_control_simple_remove_sta_debugfs(void *priv, void *priv_sta) } #endif -static struct rate_control_ops rate_control_simple = { - .module = THIS_MODULE, +struct rate_control_ops mac80211_rcsimple = { .name = "simple", .tx_status = rate_control_simple_tx_status, .get_rate = rate_control_simple_get_rate, @@ -410,22 +406,3 @@ static struct rate_control_ops rate_control_simple = { .remove_sta_debugfs = rate_control_simple_remove_sta_debugfs, #endif }; - - -static int __init rate_control_simple_init(void) -{ - return ieee80211_rate_control_register(&rate_control_simple); -} - - -static void __exit rate_control_simple_exit(void) -{ - ieee80211_rate_control_unregister(&rate_control_simple); -} - - -subsys_initcall(rate_control_simple_init); -module_exit(rate_control_simple_exit); - -MODULE_DESCRIPTION("Simple rate control algorithm for ieee80211"); -MODULE_LICENSE("GPL"); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index ece77766ea2..428a9fcf57d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -509,9 +509,11 @@ ieee80211_rx_h_decrypt(struct ieee80211_txrx_data *rx) rx->key->tx_rx_count++; /* TODO: add threshold stuff again */ } else { +#ifdef CONFIG_MAC80211_DEBUG if (net_ratelimit()) printk(KERN_DEBUG "%s: RX protected frame," " but have no key\n", rx->dev->name); +#endif /* CONFIG_MAC80211_DEBUG */ return TXRX_DROP; } diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index a84a23310ff..9bf0e1cc530 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -314,9 +314,11 @@ ieee80211_crypto_wep_decrypt(struct ieee80211_txrx_data *rx) if (!(rx->u.rx.status->flag & RX_FLAG_DECRYPTED)) { if (ieee80211_wep_decrypt(rx->local, rx->skb, rx->key)) { +#ifdef CONFIG_MAC80211_DEBUG if (net_ratelimit()) printk(KERN_DEBUG "%s: RX WEP frame, decrypt " "failed\n", rx->dev->name); +#endif /* CONFIG_MAC80211_DEBUG */ return TXRX_DROP; } } else if (!(rx->u.rx.status->flag & RX_FLAG_IV_STRIPPED)) { diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 6695efba57e..20cec1cb956 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -323,9 +323,12 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_txrx_data *rx) &rx->u.rx.tkip_iv32, &rx->u.rx.tkip_iv16); if (res != TKIP_DECRYPT_OK || wpa_test) { - printk(KERN_DEBUG "%s: TKIP decrypt failed for RX frame from " - "%s (res=%d)\n", - rx->dev->name, print_mac(mac, rx->sta->addr), res); +#ifdef CONFIG_MAC80211_DEBUG + if (net_ratelimit()) + printk(KERN_DEBUG "%s: TKIP decrypt failed for RX " + "frame from %s (res=%d)\n", rx->dev->name, + print_mac(mac, rx->sta->addr), res); +#endif /* CONFIG_MAC80211_DEBUG */ return TXRX_DROP; } @@ -594,9 +597,12 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_txrx_data *rx) skb->data + hdrlen + CCMP_HDR_LEN, data_len, skb->data + skb->len - CCMP_MIC_LEN, skb->data + hdrlen + CCMP_HDR_LEN)) { - printk(KERN_DEBUG "%s: CCMP decrypt failed for RX " - "frame from %s\n", rx->dev->name, - print_mac(mac, rx->sta->addr)); +#ifdef CONFIG_MAC80211_DEBUG + if (net_ratelimit()) + printk(KERN_DEBUG "%s: CCMP decrypt failed " + "for RX frame from %s\n", rx->dev->name, + print_mac(mac, rx->sta->addr)); +#endif /* CONFIG_MAC80211_DEBUG */ return TXRX_DROP; } } diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 93c58f97383..ad0e36ebea3 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -40,15 +40,15 @@ obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o # targets obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o obj-$(CONFIG_NETFILTER_XT_TARGET_CONNMARK) += xt_CONNMARK.o +obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o obj-$(CONFIG_NETFILTER_XT_TARGET_DSCP) += xt_DSCP.o obj-$(CONFIG_NETFILTER_XT_TARGET_MARK) += xt_MARK.o -obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o +obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o obj-$(CONFIG_NETFILTER_XT_TARGET_NOTRACK) += xt_NOTRACK.o -obj-$(CONFIG_NETFILTER_XT_TARGET_TRACE) += xt_TRACE.o obj-$(CONFIG_NETFILTER_XT_TARGET_SECMARK) += xt_SECMARK.o obj-$(CONFIG_NETFILTER_XT_TARGET_TCPMSS) += xt_TCPMSS.o -obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o +obj-$(CONFIG_NETFILTER_XT_TARGET_TRACE) += xt_TRACE.o # matches obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o @@ -59,22 +59,22 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o obj-$(CONFIG_NETFILTER_XT_MATCH_DCCP) += xt_dccp.o obj-$(CONFIG_NETFILTER_XT_MATCH_DSCP) += xt_dscp.o obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o +obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o obj-$(CONFIG_NETFILTER_XT_MATCH_MARK) += xt_mark.o obj-$(CONFIG_NETFILTER_XT_MATCH_MULTIPORT) += xt_multiport.o -obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o +obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o +obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA) += xt_quota.o obj-$(CONFIG_NETFILTER_XT_MATCH_REALM) += xt_realm.o obj-$(CONFIG_NETFILTER_XT_MATCH_SCTP) += xt_sctp.o obj-$(CONFIG_NETFILTER_XT_MATCH_STATE) += xt_state.o obj-$(CONFIG_NETFILTER_XT_MATCH_STATISTIC) += xt_statistic.o obj-$(CONFIG_NETFILTER_XT_MATCH_STRING) += xt_string.o -obj-$(CONFIG_NETFILTER_XT_MATCH_TIME) += xt_time.o obj-$(CONFIG_NETFILTER_XT_MATCH_TCPMSS) += xt_tcpmss.o -obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o +obj-$(CONFIG_NETFILTER_XT_MATCH_TIME) += xt_time.o obj-$(CONFIG_NETFILTER_XT_MATCH_U32) += xt_u32.o -obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o diff --git a/net/netfilter/nf_sockopt.c b/net/netfilter/nf_sockopt.c index aa2831587b8..87bc1443c52 100644 --- a/net/netfilter/nf_sockopt.c +++ b/net/netfilter/nf_sockopt.c @@ -23,14 +23,13 @@ static inline int overlap(int min1, int max1, int min2, int max2) /* Functions to register sockopt ranges (exclusive). */ int nf_register_sockopt(struct nf_sockopt_ops *reg) { - struct list_head *i; + struct nf_sockopt_ops *ops; int ret = 0; if (mutex_lock_interruptible(&nf_sockopt_mutex) != 0) return -EINTR; - list_for_each(i, &nf_sockopts) { - struct nf_sockopt_ops *ops = (struct nf_sockopt_ops *)i; + list_for_each_entry(ops, &nf_sockopts, list) { if (ops->pf == reg->pf && (overlap(ops->set_optmin, ops->set_optmax, reg->set_optmin, reg->set_optmax) @@ -61,48 +60,57 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg) } EXPORT_SYMBOL(nf_unregister_sockopt); -/* Call get/setsockopt() */ -static int nf_sockopt(struct sock *sk, int pf, int val, - char __user *opt, int *len, int get) +static struct nf_sockopt_ops *nf_sockopt_find(struct sock *sk, int pf, + int val, int get) { - struct list_head *i; struct nf_sockopt_ops *ops; - int ret; if (sk->sk_net != &init_net) - return -ENOPROTOOPT; + return ERR_PTR(-ENOPROTOOPT); if (mutex_lock_interruptible(&nf_sockopt_mutex) != 0) - return -EINTR; + return ERR_PTR(-EINTR); - list_for_each(i, &nf_sockopts) { - ops = (struct nf_sockopt_ops *)i; + list_for_each_entry(ops, &nf_sockopts, list) { if (ops->pf == pf) { if (!try_module_get(ops->owner)) goto out_nosup; + if (get) { - if (val >= ops->get_optmin - && val < ops->get_optmax) { - mutex_unlock(&nf_sockopt_mutex); - ret = ops->get(sk, val, opt, len); + if (val >= ops->get_optmin && + val < ops->get_optmax) goto out; - } } else { - if (val >= ops->set_optmin - && val < ops->set_optmax) { - mutex_unlock(&nf_sockopt_mutex); - ret = ops->set(sk, val, opt, *len); + if (val >= ops->set_optmin && + val < ops->set_optmax) goto out; - } } module_put(ops->owner); } } - out_nosup: +out_nosup: + ops = ERR_PTR(-ENOPROTOOPT); +out: mutex_unlock(&nf_sockopt_mutex); - return -ENOPROTOOPT; + return ops; +} + +/* Call get/setsockopt() */ +static int nf_sockopt(struct sock *sk, int pf, int val, + char __user *opt, int *len, int get) +{ + struct nf_sockopt_ops *ops; + int ret; + + ops = nf_sockopt_find(sk, pf, val, get); + if (IS_ERR(ops)) + return PTR_ERR(ops); + + if (get) + ret = ops->get(sk, val, opt, len); + else + ret = ops->set(sk, val, opt, *len); - out: module_put(ops->owner); return ret; } @@ -124,56 +132,25 @@ EXPORT_SYMBOL(nf_getsockopt); static int compat_nf_sockopt(struct sock *sk, int pf, int val, char __user *opt, int *len, int get) { - struct list_head *i; struct nf_sockopt_ops *ops; int ret; - if (sk->sk_net != &init_net) - return -ENOPROTOOPT; - - - if (mutex_lock_interruptible(&nf_sockopt_mutex) != 0) - return -EINTR; - - list_for_each(i, &nf_sockopts) { - ops = (struct nf_sockopt_ops *)i; - if (ops->pf == pf) { - if (!try_module_get(ops->owner)) - goto out_nosup; - - if (get) { - if (val >= ops->get_optmin - && val < ops->get_optmax) { - mutex_unlock(&nf_sockopt_mutex); - if (ops->compat_get) - ret = ops->compat_get(sk, - val, opt, len); - else - ret = ops->get(sk, - val, opt, len); - goto out; - } - } else { - if (val >= ops->set_optmin - && val < ops->set_optmax) { - mutex_unlock(&nf_sockopt_mutex); - if (ops->compat_set) - ret = ops->compat_set(sk, - val, opt, *len); - else - ret = ops->set(sk, - val, opt, *len); - goto out; - } - } - module_put(ops->owner); - } + ops = nf_sockopt_find(sk, pf, val, get); + if (IS_ERR(ops)) + return PTR_ERR(ops); + + if (get) { + if (ops->compat_get) + ret = ops->compat_get(sk, val, opt, len); + else + ret = ops->get(sk, val, ops, len); + } else { + if (ops->compat_set) + ret = ops->compat_set(sk, val, ops, *len); + else + ret = ops->set(sk, val, ops, *len); } - out_nosup: - mutex_unlock(&nf_sockopt_mutex); - return -ENOPROTOOPT; - out: module_put(ops->owner); return ret; } diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 06cff1d1369..d7becf08a93 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -4,7 +4,8 @@ * (c) 2000 Gerd Knorr <kraxel@bytesex.org> * Nov 2002: Martin Bene <martin.bene@icomedias.com>: * only ignore TIME_WAIT or gone connections - * Copyright © Jan Engelhardt <jengelh@gmx.de>, 2007 + * (C) CC Computer Consultants GmbH, 2007 + * Contact: <jengelh@computergmbh.de> * * based on ... * @@ -306,7 +307,7 @@ static void __exit xt_connlimit_exit(void) module_init(xt_connlimit_init); module_exit(xt_connlimit_exit); -MODULE_AUTHOR("Jan Engelhardt <jengelh@gmx.de>"); +MODULE_AUTHOR("Jan Engelhardt <jengelh@computergmbh.de>"); MODULE_DESCRIPTION("netfilter xt_connlimit match module"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_connlimit"); diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c index ef48bbd9357..f9c55dcd894 100644 --- a/net/netfilter/xt_time.c +++ b/net/netfilter/xt_time.c @@ -1,6 +1,7 @@ /* * xt_time - * Copyright © Jan Engelhardt <jengelh@computergmbh.de>, 2007 + * Copyright © CC Computer Consultants GmbH, 2007 + * Contact: <jengelh@computergmbh.de> * * based on ipt_time by Fabrice MARIE <fabrice@netfilter.org> * This is a module which is used for time matching @@ -169,7 +170,7 @@ static bool xt_time_match(const struct sk_buff *skb, if (skb->tstamp.tv64 == 0) __net_timestamp((struct sk_buff *)skb); - stamp = skb->tstamp.tv64; + stamp = ktime_to_ns(skb->tstamp); do_div(stamp, NSEC_PER_SEC); if (info->flags & XT_TIME_LOCAL_TZ) diff --git a/net/netfilter/xt_u32.c b/net/netfilter/xt_u32.c index bec427915b3..af75b8c3f20 100644 --- a/net/netfilter/xt_u32.c +++ b/net/netfilter/xt_u32.c @@ -2,7 +2,8 @@ * xt_u32 - kernel module to match u32 packet content * * Original author: Don Cohen <don@isis.cs3-inc.com> - * © Jan Engelhardt <jengelh@gmx.de>, 2007 + * (C) CC Computer Consultants GmbH, 2007 + * Contact: <jengelh@computergmbh.de> */ #include <linux/module.h> @@ -129,7 +130,7 @@ static void __exit xt_u32_exit(void) module_init(xt_u32_init); module_exit(xt_u32_exit); -MODULE_AUTHOR("Jan Engelhardt <jengelh@gmx.de>"); +MODULE_AUTHOR("Jan Engelhardt <jengelh@computergmbh.de>"); MODULE_DESCRIPTION("netfilter u32 match module"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_u32"); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 26017125557..de3988ba1f4 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -752,7 +752,7 @@ struct sock *netlink_getsockbyfilp(struct file *filp) * 1: repeat lookup - reference dropped while waiting for socket memory. */ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, - long timeo, struct sock *ssk) + long *timeo, struct sock *ssk) { struct netlink_sock *nlk; @@ -761,7 +761,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || test_bit(0, &nlk->state)) { DECLARE_WAITQUEUE(wait, current); - if (!timeo) { + if (!*timeo) { if (!ssk || netlink_is_kernel(ssk)) netlink_overrun(sk); sock_put(sk); @@ -775,7 +775,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || test_bit(0, &nlk->state)) && !sock_flag(sk, SOCK_DEAD)) - timeo = schedule_timeout(timeo); + *timeo = schedule_timeout(*timeo); __set_current_state(TASK_RUNNING); remove_wait_queue(&nlk->wait, &wait); @@ -783,7 +783,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, if (signal_pending(current)) { kfree_skb(skb); - return sock_intr_errno(timeo); + return sock_intr_errno(*timeo); } return 1; } @@ -877,7 +877,7 @@ retry: if (netlink_is_kernel(sk)) return netlink_unicast_kernel(sk, skb); - err = netlink_attachskb(sk, skb, nonblock, timeo, ssk); + err = netlink_attachskb(sk, skb, nonblock, &timeo, ssk); if (err == 1) goto retry; if (err) @@ -1888,7 +1888,7 @@ static void __net_exit netlink_net_exit(struct net *net) #endif } -static struct pernet_operations netlink_net_ops = { +static struct pernet_operations __net_initdata netlink_net_ops = { .init = netlink_net_init, .exit = netlink_net_exit, }; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 4cb2dfba099..8a7807dbba0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -139,9 +139,6 @@ dev->hard_header == NULL (ll header is added by device, we cannot control it) static HLIST_HEAD(packet_sklist); static DEFINE_RWLOCK(packet_sklist_lock); -static atomic_t packet_socks_nr; - - /* Private packet socket structures. */ struct packet_mclist @@ -236,10 +233,7 @@ static void packet_sock_destruct(struct sock *sk) return; } - atomic_dec(&packet_socks_nr); -#ifdef PACKET_REFCNT_DEBUG - printk(KERN_DEBUG "PACKET socket %p is free, %d are alive\n", sk, atomic_read(&packet_socks_nr)); -#endif + sk_refcnt_debug_dec(sk); } @@ -515,7 +509,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet sll->sll_hatype = dev->type; sll->sll_protocol = skb->protocol; sll->sll_pkttype = skb->pkt_type; - if (unlikely(po->origdev) && skb->pkt_type == PACKET_HOST) + if (unlikely(po->origdev)) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; @@ -661,7 +655,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe sll->sll_hatype = dev->type; sll->sll_protocol = skb->protocol; sll->sll_pkttype = skb->pkt_type; - if (unlikely(po->origdev) && skb->pkt_type == PACKET_HOST) + if (unlikely(po->origdev)) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; @@ -849,6 +843,7 @@ static int packet_release(struct socket *sock) /* Purge queues */ skb_queue_purge(&sk->sk_receive_queue); + sk_refcnt_debug_release(sk); sock_put(sk); return 0; @@ -886,20 +881,14 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc if (protocol == 0) goto out_unlock; - if (dev) { - if (dev->flags&IFF_UP) { - dev_add_pack(&po->prot_hook); - sock_hold(sk); - po->running = 1; - } else { - sk->sk_err = ENETDOWN; - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); - } - } else { + if (!dev || (dev->flags & IFF_UP)) { dev_add_pack(&po->prot_hook); sock_hold(sk); po->running = 1; + } else { + sk->sk_err = ENETDOWN; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); } out_unlock: @@ -1010,7 +999,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol) po->num = proto; sk->sk_destruct = packet_sock_destruct; - atomic_inc(&packet_socks_nr); + sk_refcnt_debug_inc(sk); /* * Attach a protocol block diff --git a/net/rfkill/rfkill.c b/net/rfkill/rfkill.c index 51d151c0e96..73d60a30712 100644 --- a/net/rfkill/rfkill.c +++ b/net/rfkill/rfkill.c @@ -27,6 +27,10 @@ #include <linux/mutex.h> #include <linux/rfkill.h> +/* Get declaration of rfkill_switch_all() to shut up sparse. */ +#include "rfkill-input.h" + + MODULE_AUTHOR("Ivo van Doorn <IvDoorn@gmail.com>"); MODULE_VERSION("1.0"); MODULE_DESCRIPTION("RF switch support"); @@ -276,21 +280,17 @@ static struct class rfkill_class = { static int rfkill_add_switch(struct rfkill *rfkill) { - int retval; - - retval = mutex_lock_interruptible(&rfkill_mutex); - if (retval) - return retval; + int error; - retval = rfkill_toggle_radio(rfkill, rfkill_states[rfkill->type]); - if (retval) - goto out; + mutex_lock(&rfkill_mutex); - list_add_tail(&rfkill->node, &rfkill_list); + error = rfkill_toggle_radio(rfkill, rfkill_states[rfkill->type]); + if (!error) + list_add_tail(&rfkill->node, &rfkill_list); - out: mutex_unlock(&rfkill_mutex); - return retval; + + return error; } static void rfkill_remove_switch(struct rfkill *rfkill) @@ -387,20 +387,23 @@ int rfkill_register(struct rfkill *rfkill) if (!rfkill->toggle_radio) return -EINVAL; + if (rfkill->type >= RFKILL_TYPE_MAX) + return -EINVAL; + + snprintf(dev->bus_id, sizeof(dev->bus_id), + "rfkill%ld", (long)atomic_inc_return(&rfkill_no) - 1); + + rfkill_led_trigger_register(rfkill); error = rfkill_add_switch(rfkill); if (error) return error; - snprintf(dev->bus_id, sizeof(dev->bus_id), - "rfkill%ld", (long)atomic_inc_return(&rfkill_no) - 1); - error = device_add(dev); if (error) { rfkill_remove_switch(rfkill); return error; } - rfkill_led_trigger_register(rfkill); return 0; } @@ -416,9 +419,9 @@ EXPORT_SYMBOL(rfkill_register); */ void rfkill_unregister(struct rfkill *rfkill) { - rfkill_led_trigger_unregister(rfkill); device_del(&rfkill->dev); rfkill_remove_switch(rfkill); + rfkill_led_trigger_unregister(rfkill); put_device(&rfkill->dev); } EXPORT_SYMBOL(rfkill_unregister); @@ -448,5 +451,5 @@ static void __exit rfkill_exit(void) class_unregister(&rfkill_class); } -module_init(rfkill_init); +subsys_initcall(rfkill_init); module_exit(rfkill_exit); diff --git a/net/rxrpc/ar-local.c b/net/rxrpc/ar-local.c index fe03f71f17d..f3a2bd747a8 100644 --- a/net/rxrpc/ar-local.c +++ b/net/rxrpc/ar-local.c @@ -114,7 +114,7 @@ static int rxrpc_create_local(struct rxrpc_local *local) return 0; error: - local->socket->ops->shutdown(local->socket, 2); + kernel_sock_shutdown(local->socket, SHUT_RDWR); local->socket->sk->sk_user_data = NULL; sock_release(local->socket); local->socket = NULL; @@ -267,7 +267,7 @@ static void rxrpc_destroy_local(struct work_struct *work) /* finish cleaning up the local descriptor */ rxrpc_purge_queue(&local->accept_queue); rxrpc_purge_queue(&local->reject_queue); - local->socket->ops->shutdown(local->socket, 2); + kernel_sock_shutdown(local->socket, SHUT_RDWR); sock_release(local->socket); up_read(&rxrpc_local_sem); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 9e98c6e567d..c3900820916 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -91,7 +91,7 @@ static struct tc_u_common *u32_list; static __inline__ unsigned u32_hash_fold(u32 key, struct tc_u32_sel *sel, u8 fshift) { - unsigned h = (key & sel->hmask)>>fshift; + unsigned h = ntohl(key & sel->hmask)>>fshift; return h; } @@ -613,17 +613,7 @@ static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle, memcpy(&n->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key)); n->ht_up = ht; n->handle = handle; -{ - u8 i = 0; - u32 mask = s->hmask; - if (mask) { - while (!(mask & 1)) { - i++; - mask>>=1; - } - } - n->fshift = i; -} + n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; #ifdef CONFIG_CLS_U32_MARK if (tb[TCA_U32_MARK-1]) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index fa1a6f45dc4..e595e6570ce 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -134,7 +134,7 @@ static inline int qdisc_restart(struct net_device *dev) { struct Qdisc *q = dev->qdisc; struct sk_buff *skb; - int ret; + int ret = NETDEV_TX_BUSY; /* Dequeue packet */ if (unlikely((skb = dev_dequeue_skb(dev, q)) == NULL)) @@ -145,7 +145,8 @@ static inline int qdisc_restart(struct net_device *dev) spin_unlock(&dev->queue_lock); HARD_TX_LOCK(dev, smp_processor_id()); - ret = dev_hard_start_xmit(skb, dev); + if (!netif_subqueue_stopped(dev, skb)) + ret = dev_hard_start_xmit(skb, dev); HARD_TX_UNLOCK(dev); spin_lock(&dev->queue_lock); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 421281d9dd1..c0ed06d4a50 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -252,6 +252,9 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device * static inline int teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *dev) { + if (dev->qdisc == &noop_qdisc) + return -ENODEV; + if (dev->header_ops == NULL || skb->dst == NULL || skb->dst->neighbour == NULL) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 03158e3665d..013e3d3ab0f 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -262,10 +262,14 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a */ asoc->peer.sack_needed = 1; - /* Assume that the peer recongizes ASCONF until reported otherwise - * via an ERROR chunk. + /* Assume that the peer will tell us if he recognizes ASCONF + * as part of INIT exchange. + * The sctp_addip_noauth option is there for backward compatibilty + * and will revert old behavior. */ - asoc->peer.asconf_capable = 1; + asoc->peer.asconf_capable = 0; + if (sctp_addip_noauth) + asoc->peer.asconf_capable = 1; /* Create an input queue. */ sctp_inq_init(&asoc->base.inqueue); diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index dfffa94fb9f..cae95af9a8c 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -180,9 +180,7 @@ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new, /* Delete an address from the bind address list in the SCTP_bind_addr * structure. */ -int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr, - void fastcall (*rcu_call)(struct rcu_head *head, - void (*func)(struct rcu_head *head))) +int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr) { struct sctp_sockaddr_entry *addr, *temp; @@ -198,15 +196,10 @@ int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr, } } - /* Call the rcu callback provided in the args. This function is - * called by both BH packet processing and user side socket option - * processing, but it works on different lists in those 2 contexts. - * Each context provides it's own callback, whether call_rcu_bh() - * or call_rcu(), to make sure that we wait for an appropriate time. - */ if (addr && !addr->valid) { - rcu_call(&addr->rcu, sctp_local_addr_free); + call_rcu(&addr->rcu, sctp_local_addr_free); SCTP_DBG_OBJCNT_DEC(addr); + return 0; } return -EINVAL; diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 2d2d81ef4a6..de6f505d6ff 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -328,24 +328,35 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( const union sctp_addr *paddr, struct sctp_transport **transport) { + struct sctp_association *asoc = NULL; + struct sctp_transport *t = NULL; + struct sctp_hashbucket *head; + struct sctp_ep_common *epb; + struct hlist_node *node; + int hash; int rport; - struct sctp_association *asoc; - struct list_head *pos; + *transport = NULL; rport = ntohs(paddr->v4.sin_port); - list_for_each(pos, &ep->asocs) { - asoc = list_entry(pos, struct sctp_association, asocs); - if (rport == asoc->peer.port) { - *transport = sctp_assoc_lookup_paddr(asoc, paddr); - - if (*transport) - return asoc; + hash = sctp_assoc_hashfn(ep->base.bind_addr.port, rport); + head = &sctp_assoc_hashtable[hash]; + read_lock(&head->lock); + sctp_for_each_hentry(epb, node, &head->chain) { + asoc = sctp_assoc(epb); + if (asoc->ep != ep || rport != asoc->peer.port) + goto next; + + t = sctp_assoc_lookup_paddr(asoc, paddr); + if (t) { + *transport = t; + break; } +next: + asoc = NULL; } - - *transport = NULL; - return NULL; + read_unlock(&head->lock); + return asoc; } /* Lookup association on an endpoint based on a peer address. BH-safe. */ diff --git a/net/sctp/input.c b/net/sctp/input.c index 86503e7fa21..91ae463b079 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -656,7 +656,6 @@ discard: /* Insert endpoint into the hash table. */ static void __sctp_hash_endpoint(struct sctp_endpoint *ep) { - struct sctp_ep_common **epp; struct sctp_ep_common *epb; struct sctp_hashbucket *head; @@ -666,12 +665,7 @@ static void __sctp_hash_endpoint(struct sctp_endpoint *ep) head = &sctp_ep_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - epp = &head->chain; - epb->next = *epp; - if (epb->next) - (*epp)->pprev = &epb->next; - *epp = epb; - epb->pprev = epp; + hlist_add_head(&epb->node, &head->chain); sctp_write_unlock(&head->lock); } @@ -691,19 +685,15 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) epb = &ep->base; + if (hlist_unhashed(&epb->node)) + return; + epb->hashent = sctp_ep_hashfn(epb->bind_addr.port); head = &sctp_ep_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - - if (epb->pprev) { - if (epb->next) - epb->next->pprev = epb->pprev; - *epb->pprev = epb->next; - epb->pprev = NULL; - } - + __hlist_del(&epb->node); sctp_write_unlock(&head->lock); } @@ -721,12 +711,13 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(const union sctp_addr *l struct sctp_hashbucket *head; struct sctp_ep_common *epb; struct sctp_endpoint *ep; + struct hlist_node *node; int hash; hash = sctp_ep_hashfn(ntohs(laddr->v4.sin_port)); head = &sctp_ep_hashtable[hash]; read_lock(&head->lock); - for (epb = head->chain; epb; epb = epb->next) { + sctp_for_each_hentry(epb, node, &head->chain) { ep = sctp_ep(epb); if (sctp_endpoint_is_match(ep, laddr)) goto hit; @@ -744,7 +735,6 @@ hit: /* Insert association into the hash table. */ static void __sctp_hash_established(struct sctp_association *asoc) { - struct sctp_ep_common **epp; struct sctp_ep_common *epb; struct sctp_hashbucket *head; @@ -756,12 +746,7 @@ static void __sctp_hash_established(struct sctp_association *asoc) head = &sctp_assoc_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - epp = &head->chain; - epb->next = *epp; - if (epb->next) - (*epp)->pprev = &epb->next; - *epp = epb; - epb->pprev = epp; + hlist_add_head(&epb->node, &head->chain); sctp_write_unlock(&head->lock); } @@ -790,14 +775,7 @@ static void __sctp_unhash_established(struct sctp_association *asoc) head = &sctp_assoc_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - - if (epb->pprev) { - if (epb->next) - epb->next->pprev = epb->pprev; - *epb->pprev = epb->next; - epb->pprev = NULL; - } - + __hlist_del(&epb->node); sctp_write_unlock(&head->lock); } @@ -822,6 +800,7 @@ static struct sctp_association *__sctp_lookup_association( struct sctp_ep_common *epb; struct sctp_association *asoc; struct sctp_transport *transport; + struct hlist_node *node; int hash; /* Optimize here for direct hit, only listening connections can @@ -830,7 +809,7 @@ static struct sctp_association *__sctp_lookup_association( hash = sctp_assoc_hashfn(ntohs(local->v4.sin_port), ntohs(peer->v4.sin_port)); head = &sctp_assoc_hashtable[hash]; read_lock(&head->lock); - for (epb = head->chain; epb; epb = epb->next) { + sctp_for_each_hentry(epb, node, &head->chain) { asoc = sctp_assoc(epb); transport = sctp_assoc_is_match(asoc, local, peer); if (transport) diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index f10fe7fbf24..cf4b7eb023b 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -90,6 +90,10 @@ void sctp_inq_free(struct sctp_inq *queue) void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk) { /* Directly call the packet handling routine. */ + if (chunk->rcvr->dead) { + sctp_chunk_free(chunk); + return; + } /* We are now calling this either from the soft interrupt * or from the backlog processing. diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 28f4fe77cee..fa76f235169 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -382,7 +382,7 @@ static void sctp_insert_list(struct list_head *head, struct list_head *new) /* Mark all the eligible packets on a transport for retransmission. */ void sctp_retransmit_mark(struct sctp_outq *q, struct sctp_transport *transport, - __u8 fast_retransmit) + __u8 reason) { struct list_head *lchunk, *ltemp; struct sctp_chunk *chunk; @@ -412,20 +412,20 @@ void sctp_retransmit_mark(struct sctp_outq *q, continue; } - /* If we are doing retransmission due to a fast retransmit, - * only the chunk's that are marked for fast retransmit - * should be added to the retransmit queue. If we are doing - * retransmission due to a timeout or pmtu discovery, only the - * chunks that are not yet acked should be added to the - * retransmit queue. + /* If we are doing retransmission due to a timeout or pmtu + * discovery, only the chunks that are not yet acked should + * be added to the retransmit queue. */ - if ((fast_retransmit && (chunk->fast_retransmit > 0)) || - (!fast_retransmit && !chunk->tsn_gap_acked)) { + if ((reason == SCTP_RTXR_FAST_RTX && + (chunk->fast_retransmit > 0)) || + (reason != SCTP_RTXR_FAST_RTX && !chunk->tsn_gap_acked)) { /* If this chunk was sent less then 1 rto ago, do not * retransmit this chunk, but give the peer time - * to acknowlege it. + * to acknowlege it. Do this only when + * retransmitting due to T3 timeout. */ - if ((jiffies - chunk->sent_at) < transport->rto) + if (reason == SCTP_RTXR_T3_RTX && + (jiffies - chunk->sent_at) < transport->last_rto) continue; /* RFC 2960 6.2.1 Processing a Received SACK @@ -467,10 +467,10 @@ void sctp_retransmit_mark(struct sctp_outq *q, } } - SCTP_DEBUG_PRINTK("%s: transport: %p, fast_retransmit: %d, " + SCTP_DEBUG_PRINTK("%s: transport: %p, reason: %d, " "cwnd: %d, ssthresh: %d, flight_size: %d, " "pba: %d\n", __FUNCTION__, - transport, fast_retransmit, + transport, reason, transport->cwnd, transport->ssthresh, transport->flight_size, transport->partial_bytes_acked); @@ -484,7 +484,6 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, sctp_retransmit_reason_t reason) { int error = 0; - __u8 fast_retransmit = 0; switch(reason) { case SCTP_RTXR_T3_RTX: @@ -499,16 +498,18 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, case SCTP_RTXR_FAST_RTX: SCTP_INC_STATS(SCTP_MIB_FAST_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX); - fast_retransmit = 1; break; case SCTP_RTXR_PMTUD: SCTP_INC_STATS(SCTP_MIB_PMTUD_RETRANSMITS); break; + case SCTP_RTXR_T1_RTX: + SCTP_INC_STATS(SCTP_MIB_T1_RETRANSMITS); + break; default: BUG(); } - sctp_retransmit_mark(q, transport, fast_retransmit); + sctp_retransmit_mark(q, transport, reason); /* PR-SCTP A5) Any time the T3-rtx timer expires, on any destination, * the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by @@ -641,7 +642,8 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, /* If we are here due to a retransmit timeout or a fast * retransmit and if there are any chunks left in the retransmit - * queue that could not fit in the PMTU sized packet, they need * to be marked as ineligible for a subsequent fast retransmit. + * queue that could not fit in the PMTU sized packet, they need + * to be marked as ineligible for a subsequent fast retransmit. */ if (rtx_timeout && !lchunk) { list_for_each(lchunk1, lqueue) { @@ -660,10 +662,9 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, int sctp_outq_uncork(struct sctp_outq *q) { int error = 0; - if (q->cork) { + if (q->cork) q->cork = 0; - error = sctp_outq_flush(q, 0); - } + error = sctp_outq_flush(q, 0); return error; } diff --git a/net/sctp/proc.c b/net/sctp/proc.c index e4cd841a22e..24997320407 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -225,6 +225,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_endpoint *ep; struct sock *sk; + struct hlist_node *node; int hash = *(loff_t *)v; if (hash >= sctp_ep_hashsize) @@ -233,7 +234,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) head = &sctp_ep_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); - for (epb = head->chain; epb; epb = epb->next) { + sctp_for_each_hentry(epb, node, &head->chain) { ep = sctp_ep(epb); sk = epb->sk; seq_printf(seq, "%8p %8p %-3d %-3d %-4d %-5d %5d %5lu ", ep, sk, @@ -328,6 +329,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_association *assoc; struct sock *sk; + struct hlist_node *node; int hash = *(loff_t *)v; if (hash >= sctp_assoc_hashsize) @@ -336,7 +338,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) head = &sctp_assoc_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); - for (epb = head->chain; epb; epb = epb->next) { + sctp_for_each_hentry(epb, node, &head->chain) { assoc = sctp_assoc(epb); sk = epb->sk; seq_printf(seq, diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 40c1a47d1b8..d50f610d1b0 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1137,7 +1137,7 @@ SCTP_STATIC __init int sctp_init(void) } for (i = 0; i < sctp_assoc_hashsize; i++) { rwlock_init(&sctp_assoc_hashtable[i].lock); - sctp_assoc_hashtable[i].chain = NULL; + INIT_HLIST_HEAD(&sctp_assoc_hashtable[i].chain); } /* Allocate and initialize the endpoint hash table. */ @@ -1151,7 +1151,7 @@ SCTP_STATIC __init int sctp_init(void) } for (i = 0; i < sctp_ep_hashsize; i++) { rwlock_init(&sctp_ep_hashtable[i].lock); - sctp_ep_hashtable[i].chain = NULL; + INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain); } /* Allocate and initialize the SCTP port hash table. */ @@ -1170,7 +1170,7 @@ SCTP_STATIC __init int sctp_init(void) } for (i = 0; i < sctp_port_hashsize; i++) { spin_lock_init(&sctp_port_hashtable[i].lock); - sctp_port_hashtable[i].chain = NULL; + INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); } printk(KERN_INFO "SCTP: Hash tables configured " @@ -1179,6 +1179,7 @@ SCTP_STATIC __init int sctp_init(void) /* Disable ADDIP by default. */ sctp_addip_enable = 0; + sctp_addip_noauth = 0; /* Enable PR-SCTP by default. */ sctp_prsctp_enable = 1; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index c377e4e8f65..5a9783c38de 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1788,9 +1788,14 @@ static int sctp_process_inv_paramlength(const struct sctp_association *asoc, sizeof(sctp_paramhdr_t); + /* This is a fatal error. Any accumulated non-fatal errors are + * not reported. + */ + if (*errp) + sctp_chunk_free(*errp); + /* Create an error chunk and fill it in with our payload. */ - if (!*errp) - *errp = sctp_make_op_error_space(asoc, chunk, payload_len); + *errp = sctp_make_op_error_space(asoc, chunk, payload_len); if (*errp) { sctp_init_cause(*errp, SCTP_ERROR_PROTO_VIOLATION, @@ -1813,9 +1818,15 @@ static int sctp_process_hn_param(const struct sctp_association *asoc, { __u16 len = ntohs(param.p->length); - /* Make an ERROR chunk. */ - if (!*errp) - *errp = sctp_make_op_error_space(asoc, chunk, len); + /* Processing of the HOST_NAME parameter will generate an + * ABORT. If we've accumulated any non-fatal errors, they + * would be unrecognized parameters and we should not include + * them in the ABORT. + */ + if (*errp) + sctp_chunk_free(*errp); + + *errp = sctp_make_op_error_space(asoc, chunk, len); if (*errp) { sctp_init_cause(*errp, SCTP_ERROR_DNS_FAILED, len); @@ -1847,7 +1858,7 @@ static void sctp_process_ext_param(struct sctp_association *asoc, break; case SCTP_CID_ASCONF: case SCTP_CID_ASCONF_ACK: - asoc->peer.addip_capable = 1; + asoc->peer.asconf_capable = 1; break; default: break; @@ -1862,56 +1873,40 @@ static void sctp_process_ext_param(struct sctp_association *asoc, * taken if the processing endpoint does not recognize the * Parameter Type. * - * 00 - Stop processing this SCTP chunk and discard it, - * do not process any further chunks within it. + * 00 - Stop processing this parameter; do not process any further + * parameters within this chunk * - * 01 - Stop processing this SCTP chunk and discard it, - * do not process any further chunks within it, and report - * the unrecognized parameter in an 'Unrecognized - * Parameter Type' (in either an ERROR or in the INIT ACK). + * 01 - Stop processing this parameter, do not process any further + * parameters within this chunk, and report the unrecognized + * parameter in an 'Unrecognized Parameter' ERROR chunk. * * 10 - Skip this parameter and continue processing. * * 11 - Skip this parameter and continue processing but * report the unrecognized parameter in an - * 'Unrecognized Parameter Type' (in either an ERROR or in - * the INIT ACK). + * 'Unrecognized Parameter' ERROR chunk. * * Return value: - * 0 - discard the chunk - * 1 - continue with the chunk + * SCTP_IERROR_NO_ERROR - continue with the chunk + * SCTP_IERROR_ERROR - stop and report an error. + * SCTP_IERROR_NOMEME - out of memory. */ -static int sctp_process_unk_param(const struct sctp_association *asoc, - union sctp_params param, - struct sctp_chunk *chunk, - struct sctp_chunk **errp) +static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc, + union sctp_params param, + struct sctp_chunk *chunk, + struct sctp_chunk **errp) { - int retval = 1; + int retval = SCTP_IERROR_NO_ERROR; switch (param.p->type & SCTP_PARAM_ACTION_MASK) { case SCTP_PARAM_ACTION_DISCARD: - retval = 0; - break; - case SCTP_PARAM_ACTION_DISCARD_ERR: - retval = 0; - /* Make an ERROR chunk, preparing enough room for - * returning multiple unknown parameters. - */ - if (NULL == *errp) - *errp = sctp_make_op_error_space(asoc, chunk, - ntohs(chunk->chunk_hdr->length)); - - if (*errp) { - sctp_init_cause(*errp, SCTP_ERROR_UNKNOWN_PARAM, - WORD_ROUND(ntohs(param.p->length))); - sctp_addto_chunk(*errp, - WORD_ROUND(ntohs(param.p->length)), - param.v); - } - + retval = SCTP_IERROR_ERROR; break; case SCTP_PARAM_ACTION_SKIP: break; + case SCTP_PARAM_ACTION_DISCARD_ERR: + retval = SCTP_IERROR_ERROR; + /* Fall through */ case SCTP_PARAM_ACTION_SKIP_ERR: /* Make an ERROR chunk, preparing enough room for * returning multiple unknown parameters. @@ -1932,9 +1927,8 @@ static int sctp_process_unk_param(const struct sctp_association *asoc, * to the peer and the association won't be * established. */ - retval = 0; + retval = SCTP_IERROR_NOMEM; } - break; default: break; @@ -1943,18 +1937,20 @@ static int sctp_process_unk_param(const struct sctp_association *asoc, return retval; } -/* Find unrecognized parameters in the chunk. +/* Verify variable length parameters * Return values: - * 0 - discard the chunk - * 1 - continue with the chunk + * SCTP_IERROR_ABORT - trigger an ABORT + * SCTP_IERROR_NOMEM - out of memory (abort) + * SCTP_IERROR_ERROR - stop processing, trigger an ERROR + * SCTP_IERROR_NO_ERROR - continue with the chunk */ -static int sctp_verify_param(const struct sctp_association *asoc, - union sctp_params param, - sctp_cid_t cid, - struct sctp_chunk *chunk, - struct sctp_chunk **err_chunk) +static sctp_ierror_t sctp_verify_param(const struct sctp_association *asoc, + union sctp_params param, + sctp_cid_t cid, + struct sctp_chunk *chunk, + struct sctp_chunk **err_chunk) { - int retval = 1; + int retval = SCTP_IERROR_NO_ERROR; /* FIXME - This routine is not looking at each parameter per the * chunk type, i.e., unrecognized parameters should be further @@ -1976,7 +1972,9 @@ static int sctp_verify_param(const struct sctp_association *asoc, case SCTP_PARAM_HOST_NAME_ADDRESS: /* Tell the peer, we won't support this param. */ - return sctp_process_hn_param(asoc, param, chunk, err_chunk); + sctp_process_hn_param(asoc, param, chunk, err_chunk); + retval = SCTP_IERROR_ABORT; + break; case SCTP_PARAM_FWD_TSN_SUPPORT: if (sctp_prsctp_enable) @@ -1993,9 +1991,11 @@ static int sctp_verify_param(const struct sctp_association *asoc, * cause 'Protocol Violation'. */ if (SCTP_AUTH_RANDOM_LENGTH != - ntohs(param.p->length) - sizeof(sctp_paramhdr_t)) - return sctp_process_inv_paramlength(asoc, param.p, + ntohs(param.p->length) - sizeof(sctp_paramhdr_t)) { + sctp_process_inv_paramlength(asoc, param.p, chunk, err_chunk); + retval = SCTP_IERROR_ABORT; + } break; case SCTP_PARAM_CHUNKS: @@ -2007,9 +2007,11 @@ static int sctp_verify_param(const struct sctp_association *asoc, * INIT-ACK chunk if the sender wants to receive authenticated * chunks. Its maximum length is 260 bytes. */ - if (260 < ntohs(param.p->length)) - return sctp_process_inv_paramlength(asoc, param.p, - chunk, err_chunk); + if (260 < ntohs(param.p->length)) { + sctp_process_inv_paramlength(asoc, param.p, + chunk, err_chunk); + retval = SCTP_IERROR_ABORT; + } break; case SCTP_PARAM_HMAC_ALGO: @@ -2020,8 +2022,7 @@ fallthrough: default: SCTP_DEBUG_PRINTK("Unrecognized param: %d for chunk %d.\n", ntohs(param.p->type), cid); - return sctp_process_unk_param(asoc, param, chunk, err_chunk); - + retval = sctp_process_unk_param(asoc, param, chunk, err_chunk); break; } return retval; @@ -2036,6 +2037,7 @@ int sctp_verify_init(const struct sctp_association *asoc, { union sctp_params param; int has_cookie = 0; + int result; /* Verify stream values are non-zero. */ if ((0 == peer_init->init_hdr.num_outbound_streams) || @@ -2043,8 +2045,7 @@ int sctp_verify_init(const struct sctp_association *asoc, (0 == peer_init->init_hdr.init_tag) || (SCTP_DEFAULT_MINWINDOW > ntohl(peer_init->init_hdr.a_rwnd))) { - sctp_process_inv_mandatory(asoc, chunk, errp); - return 0; + return sctp_process_inv_mandatory(asoc, chunk, errp); } /* Check for missing mandatory parameters. */ @@ -2062,29 +2063,29 @@ int sctp_verify_init(const struct sctp_association *asoc, * VIOLATION error. We build the ERROR chunk here and let the normal * error handling code build and send the packet. */ - if (param.v != (void*)chunk->chunk_end) { - sctp_process_inv_paramlength(asoc, param.p, chunk, errp); - return 0; - } + if (param.v != (void*)chunk->chunk_end) + return sctp_process_inv_paramlength(asoc, param.p, chunk, errp); /* The only missing mandatory param possible today is * the state cookie for an INIT-ACK chunk. */ - if ((SCTP_CID_INIT_ACK == cid) && !has_cookie) { - sctp_process_missing_param(asoc, SCTP_PARAM_STATE_COOKIE, - chunk, errp); - return 0; - } - - /* Find unrecognized parameters. */ + if ((SCTP_CID_INIT_ACK == cid) && !has_cookie) + return sctp_process_missing_param(asoc, SCTP_PARAM_STATE_COOKIE, + chunk, errp); + /* Verify all the variable length parameters */ sctp_walk_params(param, peer_init, init_hdr.params) { - if (!sctp_verify_param(asoc, param, cid, chunk, errp)) { - if (SCTP_PARAM_HOST_NAME_ADDRESS == param.p->type) + result = sctp_verify_param(asoc, param, cid, chunk, errp); + switch (result) { + case SCTP_IERROR_ABORT: + case SCTP_IERROR_NOMEM: return 0; - else + case SCTP_IERROR_ERROR: return 1; + case SCTP_IERROR_NO_ERROR: + default: + break; } } /* for (loop through all parameters) */ @@ -2137,11 +2138,14 @@ int sctp_process_init(struct sctp_association *asoc, sctp_cid_t cid, /* If the peer claims support for ADD-IP without support * for AUTH, disable support for ADD-IP. + * Do this only if backward compatible mode is turned off. */ - if (asoc->peer.addip_capable && !asoc->peer.auth_capable) { + if (!sctp_addip_noauth && + (asoc->peer.asconf_capable && !asoc->peer.auth_capable)) { asoc->peer.addip_disabled_mask |= (SCTP_PARAM_ADD_IP | SCTP_PARAM_DEL_IP | SCTP_PARAM_SET_PRIMARY); + asoc->peer.asconf_capable = 0; } /* Walk list of transports, removing transports in the UNKNOWN state. */ @@ -2848,10 +2852,11 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, __be16 err_code; int length = 0; - int chunk_len = asconf->skb->len; + int chunk_len; __u32 serial; int all_param_pass = 1; + chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); hdr = (sctp_addiphdr_t *)asconf->skb->data; serial = ntohl(hdr->serial); @@ -2952,13 +2957,17 @@ static int sctp_asconf_param_success(struct sctp_association *asoc, /* This is always done in BH context with a socket lock * held, so the list can not change. */ + local_bh_disable(); list_for_each_entry(saddr, &bp->address_list, list) { if (sctp_cmp_addr_exact(&saddr->a, &addr)) saddr->use_as_src = 1; } + local_bh_enable(); break; case SCTP_PARAM_DEL_IP: - retval = sctp_del_bind_addr(bp, &addr, call_rcu_bh); + local_bh_disable(); + retval = sctp_del_bind_addr(bp, &addr); + local_bh_enable(); list_for_each(pos, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); @@ -2990,7 +2999,7 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, sctp_addip_param_t *asconf_ack_param; sctp_errhdr_t *err_param; int length; - int asconf_ack_len = asconf_ack->skb->len; + int asconf_ack_len; __be16 err_code; if (no_err) @@ -2998,6 +3007,9 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, else err_code = SCTP_ERROR_REQ_REFUSED; + asconf_ack_len = ntohs(asconf_ack->chunk_hdr->length) - + sizeof(sctp_chunkhdr_t); + /* Skip the addiphdr from the asconf_ack chunk and store a pointer to * the first asconf_ack parameter. */ diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index bbdc938da86..78d1a8a49bd 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -453,6 +453,7 @@ static void sctp_do_8_2_transport_strike(struct sctp_association *asoc, * maximum value discussed in rule C7 above (RTO.max) may be * used to provide an upper bound to this doubling operation. */ + transport->last_rto = transport->rto; transport->rto = min((transport->rto * 2), transport->asoc->rto_max); } @@ -1267,6 +1268,12 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, sctp_ootb_pkt_free(packet); break; + case SCTP_CMD_T1_RETRAN: + /* Mark a transport for retransmission. */ + sctp_retransmit(&asoc->outqueue, cmd->obj.transport, + SCTP_RTXR_T1_RTX); + break; + case SCTP_CMD_RETRAN: /* Mark a transport for retransmission. */ sctp_retransmit(&asoc->outqueue, cmd->obj.transport, @@ -1393,7 +1400,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, list_for_each(pos, &asoc->peer.transport_addr_list) { t = list_entry(pos, struct sctp_transport, transports); - sctp_retransmit_mark(&asoc->outqueue, t, 0); + sctp_retransmit_mark(&asoc->outqueue, t, + SCTP_RTXR_T1_RTX); } sctp_add_cmd_sf(commands, diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index f01b408508f..5ebbe808d80 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -2305,7 +2305,7 @@ static sctp_disposition_t sctp_sf_do_5_2_6_stale(const struct sctp_endpoint *ep, /* If we've sent any data bundled with COOKIE-ECHO we will need to * resend */ - sctp_add_cmd_sf(commands, SCTP_CMD_RETRAN, + sctp_add_cmd_sf(commands, SCTP_CMD_T1_RETRAN, SCTP_TRANSPORT(asoc->peer.primary_path)); /* Cast away the const modifier, as we want to just @@ -4064,11 +4064,6 @@ static sctp_disposition_t sctp_sf_abort_violation( struct sctp_chunk *chunk = arg; struct sctp_chunk *abort = NULL; - /* Make the abort chunk. */ - abort = sctp_make_abort_violation(asoc, chunk, payload, paylen); - if (!abort) - goto nomem; - /* SCTP-AUTH, Section 6.3: * It should be noted that if the receiver wants to tear * down an association in an authenticated way only, the @@ -4083,6 +4078,11 @@ static sctp_disposition_t sctp_sf_abort_violation( if (sctp_auth_recv_cid(SCTP_CID_ABORT, asoc)) goto discard; + /* Make the abort chunk. */ + abort = sctp_make_abort_violation(asoc, chunk, payload, paylen); + if (!abort) + goto nomem; + if (asoc) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index bd6f42a15a4..ff8bc95670e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -660,7 +660,7 @@ static int sctp_bindx_rem(struct sock *sk, struct sockaddr *addrs, int addrcnt) * socket routing and failover schemes. Refer to comments in * sctp_do_bind(). -daisy */ - retval = sctp_del_bind_addr(bp, sa_addr, call_rcu); + retval = sctp_del_bind_addr(bp, sa_addr); addr_buf += af->sockaddr_len; err_bindx_rem: @@ -5307,6 +5307,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) { struct sctp_bind_hashbucket *head; /* hash list */ struct sctp_bind_bucket *pp; /* hash list port iterator */ + struct hlist_node *node; unsigned short snum; int ret; @@ -5331,7 +5332,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) index = sctp_phashfn(rover); head = &sctp_port_hashtable[index]; sctp_spin_lock(&head->lock); - for (pp = head->chain; pp; pp = pp->next) + sctp_for_each_hentry(pp, node, &head->chain) if (pp->port == rover) goto next; break; @@ -5358,7 +5359,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) */ head = &sctp_port_hashtable[sctp_phashfn(snum)]; sctp_spin_lock(&head->lock); - for (pp = head->chain; pp; pp = pp->next) { + sctp_for_each_hentry(pp, node, &head->chain) { if (pp->port == snum) goto pp_found; } @@ -5702,10 +5703,7 @@ static struct sctp_bind_bucket *sctp_bucket_create( pp->port = snum; pp->fastreuse = 0; INIT_HLIST_HEAD(&pp->owner); - if ((pp->next = head->chain) != NULL) - pp->next->pprev = &pp->next; - head->chain = pp; - pp->pprev = &head->chain; + hlist_add_head(&pp->node, &head->chain); } return pp; } @@ -5714,9 +5712,7 @@ static struct sctp_bind_bucket *sctp_bucket_create( static void sctp_bucket_destroy(struct sctp_bind_bucket *pp) { if (pp && hlist_empty(&pp->owner)) { - if (pp->next) - pp->next->pprev = pp->pprev; - *(pp->pprev) = pp->next; + __hlist_del(&pp->node); kmem_cache_free(sctp_bucket_cachep, pp); SCTP_DBG_OBJCNT_DEC(bind_bucket); } @@ -6455,6 +6451,8 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, } +DEFINE_PROTO_INUSE(sctp) + /* This proto struct describes the ULP interface for SCTP. */ struct proto sctp_prot = { .name = "SCTP", @@ -6483,9 +6481,12 @@ struct proto sctp_prot = { .memory_pressure = &sctp_memory_pressure, .enter_memory_pressure = sctp_enter_memory_pressure, .memory_allocated = &sctp_memory_allocated, + REF_PROTO_INUSE(sctp) }; #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +DEFINE_PROTO_INUSE(sctpv6) + struct proto sctpv6_prot = { .name = "SCTPv6", .owner = THIS_MODULE, @@ -6513,5 +6514,6 @@ struct proto sctpv6_prot = { .memory_pressure = &sctp_memory_pressure, .enter_memory_pressure = sctp_enter_memory_pressure, .memory_allocated = &sctp_memory_allocated, + REF_PROTO_INUSE(sctpv6) }; #endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 0669778e433..da4f15734fb 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -263,6 +263,15 @@ static ctl_table sctp_table[] = { .proc_handler = &proc_dointvec, .strategy = &sysctl_intvec }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "addip_noauth_enable", + .data = &sctp_addip_noauth, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + .strategy = &sysctl_intvec + }, { .ctl_name = 0 } }; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 5f467c914f8..d55ce83a020 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -74,8 +74,8 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, * given destination transport address, set RTO to the protocol * parameter 'RTO.Initial'. */ + peer->last_rto = peer->rto = msecs_to_jiffies(sctp_rto_initial); peer->rtt = 0; - peer->rto = msecs_to_jiffies(sctp_rto_initial); peer->rttvar = 0; peer->srtt = 0; peer->rto_pending = 0; @@ -385,6 +385,7 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) tp->rto = tp->asoc->rto_max; tp->rtt = rtt; + tp->last_rto = tp->rto; /* Reset rto_pending so that a new RTT measurement is started when a * new data chunk is sent. @@ -578,7 +579,7 @@ void sctp_transport_reset(struct sctp_transport *t) */ t->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); t->ssthresh = asoc->peer.i.a_rwnd; - t->rto = asoc->rto_initial; + t->last_rto = t->rto = asoc->rto_initial; t->rtt = 0; t->srtt = 0; t->rttvar = 0; diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 4be92d0a2ca..4908041ffb3 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -862,7 +862,7 @@ static inline void sctp_ulpq_reap_ordered(struct sctp_ulpq *ulpq, __u16 sid) continue; /* see if this ssn has been marked by skipping */ - if (!SSN_lt(cssn, sctp_ssn_peek(in, csid))) + if (!SSN_lte(cssn, sctp_ssn_peek(in, csid))) break; __skb_unlink(pos, &ulpq->lobby); diff --git a/net/socket.c b/net/socket.c index 5d879fd3d01..74784dfe8e5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2319,6 +2319,11 @@ int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg) return err; } +int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) +{ + return sock->ops->shutdown(sock, how); +} + /* ABI emulation layers need these two */ EXPORT_SYMBOL(move_addr_to_kernel); EXPORT_SYMBOL(move_addr_to_user); @@ -2345,3 +2350,4 @@ EXPORT_SYMBOL(kernel_getsockopt); EXPORT_SYMBOL(kernel_setsockopt); EXPORT_SYMBOL(kernel_sendpage); EXPORT_SYMBOL(kernel_sock_ioctl); +EXPORT_SYMBOL(kernel_sock_shutdown); diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index dc55cc974c9..1afeb3eb8e4 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -320,9 +320,9 @@ xprt_setup_rdma(struct xprt_create *args) xprt->slot = kcalloc(xprt->max_reqs, sizeof(struct rpc_rqst), GFP_KERNEL); if (xprt->slot == NULL) { - kfree(xprt); dprintk("RPC: %s: couldn't allocate %d slots\n", __func__, xprt->max_reqs); + kfree(xprt); return ERR_PTR(-ENOMEM); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 515e7a692f9..e835da8fc09 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -457,7 +457,7 @@ static int unix_release_sock (struct sock *sk, int embrion) * What the above comment does talk about? --ANK(980817) */ - if (atomic_read(&unix_tot_inflight)) + if (unix_tot_inflight) unix_gc(); /* Garbage collect fds */ return 0; @@ -599,15 +599,14 @@ static struct sock * unix_create1(struct net *net, struct socket *sock) struct sock *sk = NULL; struct unix_sock *u; - if (atomic_read(&unix_nr_socks) >= 2*get_max_files()) + atomic_inc(&unix_nr_socks); + if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) goto out; sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto); if (!sk) goto out; - atomic_inc(&unix_nr_socks); - sock_init_data(sock,sk); lockdep_set_class(&sk->sk_receive_queue.lock, &af_unix_sk_receive_queue_lock_key); @@ -625,6 +624,8 @@ static struct sock * unix_create1(struct net *net, struct socket *sock) init_waitqueue_head(&u->peer_wait); unix_insert_socket(unix_sockets_unbound, sk); out: + if (sk == NULL) + atomic_dec(&unix_nr_socks); return sk; } diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 406b6433e46..ebdff3d877a 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -92,7 +92,7 @@ static LIST_HEAD(gc_inflight_list); static LIST_HEAD(gc_candidates); static DEFINE_SPINLOCK(unix_gc_lock); -atomic_t unix_tot_inflight = ATOMIC_INIT(0); +unsigned int unix_tot_inflight; static struct sock *unix_get_socket(struct file *filp) @@ -133,7 +133,7 @@ void unix_inflight(struct file *fp) } else { BUG_ON(list_empty(&u->link)); } - atomic_inc(&unix_tot_inflight); + unix_tot_inflight++; spin_unlock(&unix_gc_lock); } } @@ -147,7 +147,7 @@ void unix_notinflight(struct file *fp) BUG_ON(list_empty(&u->link)); if (atomic_dec_and_test(&u->inflight)) list_del_init(&u->link); - atomic_dec(&unix_tot_inflight); + unix_tot_inflight--; spin_unlock(&unix_gc_lock); } } @@ -161,7 +161,7 @@ static inline struct sk_buff *sock_queue_head(struct sock *sk) for (skb = sock_queue_head(sk)->next, next = skb->next; \ skb != sock_queue_head(sk); skb = next, next = skb->next) -static void scan_inflight(struct sock *x, void (*func)(struct sock *), +static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) { struct sk_buff *skb; @@ -185,9 +185,9 @@ static void scan_inflight(struct sock *x, void (*func)(struct sock *), * if it indeed does so */ struct sock *sk = unix_get_socket(*fp++); - if(sk) { + if (sk) { hit = true; - func(sk); + func(unix_sk(sk)); } } if (hit && hitlist != NULL) { @@ -199,7 +199,7 @@ static void scan_inflight(struct sock *x, void (*func)(struct sock *), spin_unlock(&x->sk_receive_queue.lock); } -static void scan_children(struct sock *x, void (*func)(struct sock *), +static void scan_children(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) { if (x->sk_state != TCP_LISTEN) @@ -235,20 +235,18 @@ static void scan_children(struct sock *x, void (*func)(struct sock *), } } -static void dec_inflight(struct sock *sk) +static void dec_inflight(struct unix_sock *usk) { - atomic_dec(&unix_sk(sk)->inflight); + atomic_dec(&usk->inflight); } -static void inc_inflight(struct sock *sk) +static void inc_inflight(struct unix_sock *usk) { - atomic_inc(&unix_sk(sk)->inflight); + atomic_inc(&usk->inflight); } -static void inc_inflight_move_tail(struct sock *sk) +static void inc_inflight_move_tail(struct unix_sock *u) { - struct unix_sock *u = unix_sk(sk); - atomic_inc(&u->inflight); /* * If this is still a candidate, move it to the end of the |