diff options
Diffstat (limited to 'net')
74 files changed, 609 insertions, 363 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 77f04e49a1a..480ea90e7dc 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -382,7 +382,7 @@ static int vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) vlan_dev_info(dev)->cnt_encap_on_xmit++; pr_debug("%s: proto to encap: 0x%hx\n", - __FUNCTION__, htons(veth->h_vlan_proto)); + __FUNCTION__, ntohs(veth->h_vlan_proto)); /* Construct the second two bytes. This field looks something * like: * usr_priority: 3 bits (high bits) @@ -660,7 +660,7 @@ static int vlan_dev_init(struct net_device *dev) int subclass = 0; /* IFF_BROADCAST|IFF_MULTICAST; ??? */ - dev->flags = real_dev->flags & ~IFF_UP; + dev->flags = real_dev->flags & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI); dev->iflink = real_dev->ifindex; dev->state = (real_dev->state & ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))) | diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 1aa9d517539..4e8d4e724b9 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -861,7 +861,6 @@ static void p9_mux_free_request(struct p9_conn *m, struct p9_req *req) static void p9_mux_flush_cb(struct p9_req *freq, void *a) { - p9_conn_req_callback cb; int tag; struct p9_conn *m; struct p9_req *req, *rreq, *rptr; @@ -872,7 +871,6 @@ static void p9_mux_flush_cb(struct p9_req *freq, void *a) freq->tcall->params.tflush.oldtag); spin_lock(&m->lock); - cb = NULL; tag = freq->tcall->params.tflush.oldtag; req = NULL; list_for_each_entry_safe(rreq, rptr, &m->req_list, req_list) { diff --git a/net/atm/clip.c b/net/atm/clip.c index d30167c0b48..2ab1e36098f 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -947,6 +947,8 @@ static const struct file_operations arp_seq_fops = { }; #endif +static void atm_clip_exit_noproc(void); + static int __init atm_clip_init(void) { neigh_table_init_no_netlink(&clip_tbl); @@ -963,18 +965,22 @@ static int __init atm_clip_init(void) struct proc_dir_entry *p; p = proc_create("arp", S_IRUGO, atm_proc_root, &arp_seq_fops); + if (!p) { + printk(KERN_ERR "Unable to initialize " + "/proc/net/atm/arp\n"); + atm_clip_exit_noproc(); + return -ENOMEM; + } } #endif return 0; } -static void __exit atm_clip_exit(void) +static void atm_clip_exit_noproc(void) { struct net_device *dev, *next; - remove_proc_entry("arp", atm_proc_root); - unregister_inetaddr_notifier(&clip_inet_notifier); unregister_netdevice_notifier(&clip_dev_notifier); @@ -1005,6 +1011,13 @@ static void __exit atm_clip_exit(void) clip_tbl_hook = NULL; } +static void __exit atm_clip_exit(void) +{ + remove_proc_entry("arp", atm_proc_root); + + atm_clip_exit_noproc(); +} + module_init(atm_clip_init); module_exit(atm_clip_exit); MODULE_AUTHOR("Werner Almesberger"); diff --git a/net/atm/lec.c b/net/atm/lec.c index 0e450d12f03..a2efa7ff41f 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1250,6 +1250,10 @@ static int __init lane_module_init(void) struct proc_dir_entry *p; p = proc_create("lec", S_IRUGO, atm_proc_root, &lec_seq_fops); + if (!p) { + printk(KERN_ERR "Unable to initialize /proc/net/atm/lec\n"); + return -ENOMEM; + } #endif register_atm_ioctl(&lane_ioctl_ops); diff --git a/net/ax25/TODO b/net/ax25/TODO index 4089c49e45c..69fb4e368d9 100644 --- a/net/ax25/TODO +++ b/net/ax25/TODO @@ -9,10 +9,6 @@ being used. Routes to a device being taken down might be deleted by ax25_rt_device_down but added by somebody else before the device has been deleted fully. -Massive amounts of lock_kernel / unlock_kernel are just a temporary solution to -get around the removal of SOCKOPS_WRAP. A serious locking strategy has to be -implemented. - The ax25_rt_find_route synopsys is pervert but I somehow had to deal with the race caused by the static variable in it's previous implementation. diff --git a/net/bluetooth/bnep/bnep.h b/net/bluetooth/bnep/bnep.h index a2992280c3d..e69244dd8de 100644 --- a/net/bluetooth/bnep/bnep.h +++ b/net/bluetooth/bnep/bnep.h @@ -174,7 +174,7 @@ struct bnep_session { void bnep_net_setup(struct net_device *dev); int bnep_sock_init(void); -int bnep_sock_cleanup(void); +void bnep_sock_cleanup(void); static inline int bnep_mc_hash(__u8 *addr) { diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index 81065e548a1..201e5b1ce47 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -257,12 +257,10 @@ error: return err; } -int __exit bnep_sock_cleanup(void) +void __exit bnep_sock_cleanup(void) { if (bt_sock_unregister(BTPROTO_BNEP) < 0) BT_ERR("Can't unregister BNEP socket"); proto_unregister(&bnep_proto); - - return 0; } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 930b58e7149..aec6929f5c1 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -902,8 +902,6 @@ int hci_unregister_dev(struct hci_dev *hdev) BT_DBG("%p name %s type %d", hdev, hdev->name, hdev->type); - hci_unregister_sysfs(hdev); - write_lock_bh(&hci_dev_list_lock); list_del(&hdev->list); write_unlock_bh(&hci_dev_list_lock); @@ -915,6 +913,8 @@ int hci_unregister_dev(struct hci_dev *hdev) hci_notify(hdev, HCI_DEV_UNREG); + hci_unregister_sysfs(hdev); + __hci_dev_put(hdev); return 0; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 14991323c27..b5d4019d357 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -734,7 +734,7 @@ error: return err; } -int __exit hci_sock_cleanup(void) +void __exit hci_sock_cleanup(void) { if (bt_sock_unregister(BTPROTO_HCI) < 0) BT_ERR("HCI socket unregistration failed"); @@ -742,6 +742,4 @@ int __exit hci_sock_cleanup(void) hci_unregister_notifier(&hci_sock_nblock); proto_unregister(&hci_sk_proto); - - return 0; } diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 7c5459c8e8e..34f8bf98bc0 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -417,7 +417,8 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) l2cap_sock_kill(sk); } - del_timer_sync(&conn->info_timer); + if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) + del_timer_sync(&conn->info_timer); hcon->l2cap_data = NULL; kfree(conn); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index bc40377136a..9326c377822 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -136,7 +136,7 @@ void br_fdb_cleanup(unsigned long _data) this_timer = f->ageing_timer + delay; if (time_before_eq(this_timer, jiffies)) fdb_delete(f); - else if (this_timer < next_timer) + else if (time_before(this_timer, next_timer)) next_timer = this_timer; } } diff --git a/net/core/dev.c b/net/core/dev.c index fcdf03cf3b3..460e7f99ce3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3329,7 +3329,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) return -EOPNOTSUPP; case SIOCADDMULTI: - if (!dev->set_multicast_list || + if ((!dev->set_multicast_list && !dev->set_rx_mode) || ifr->ifr_hwaddr.sa_family != AF_UNSPEC) return -EINVAL; if (!netif_device_present(dev)) @@ -3338,7 +3338,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) dev->addr_len, 1); case SIOCDELMULTI: - if (!dev->set_multicast_list || + if ((!dev->set_multicast_list && !dev->set_rx_mode) || ifr->ifr_hwaddr.sa_family != AF_UNSPEC) return -EINVAL; if (!netif_device_present(dev)) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index aef01533dfb..19b8e003f15 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -466,6 +466,28 @@ out_neigh_release: goto out; } +struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, + struct net *net, const void *pkey, struct net_device *dev) +{ + struct pneigh_entry *n; + int key_len = tbl->key_len; + u32 hash_val = *(u32 *)(pkey + key_len - 4); + + hash_val ^= (hash_val >> 16); + hash_val ^= hash_val >> 8; + hash_val ^= hash_val >> 4; + hash_val &= PNEIGH_HASHMASK; + + for (n = tbl->phash_buckets[hash_val]; n; n = n->next) { + if (!memcmp(n->key, pkey, key_len) && + (n->net == net) && + (n->dev == dev || !n->dev)) + break; + } + + return n; +} + struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev, int creat) @@ -839,7 +861,7 @@ static void neigh_timer_handler(unsigned long arg) struct sk_buff *skb = skb_peek(&neigh->arp_queue); /* keep skb alive even if arp_queue overflows */ if (skb) - skb_get(skb); + skb = skb_copy(skb, GFP_ATOMIC); write_unlock(&neigh->lock); neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); @@ -2803,6 +2825,7 @@ EXPORT_SYMBOL(neigh_table_init_no_netlink); EXPORT_SYMBOL(neigh_update); EXPORT_SYMBOL(pneigh_enqueue); EXPORT_SYMBOL(pneigh_lookup); +EXPORT_SYMBOL_GPL(__pneigh_lookup); #ifdef CONFIG_ARPD EXPORT_SYMBOL(neigh_app_ns); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 6faa128a4c8..c635de52526 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -39,6 +39,8 @@ static struct sk_buff_head skb_pool; static atomic_t trapped; #define USEC_PER_POLL 50 +#define NETPOLL_RX_ENABLED 1 +#define NETPOLL_RX_DROP 2 #define MAX_SKB_SIZE \ (MAX_UDP_CHUNK + sizeof(struct udphdr) + \ @@ -126,11 +128,13 @@ static int poll_one_napi(struct netpoll_info *npinfo, if (!test_bit(NAPI_STATE_SCHED, &napi->state)) return budget; + npinfo->rx_flags |= NETPOLL_RX_DROP; atomic_inc(&trapped); work = napi->poll(napi, budget); atomic_dec(&trapped); + npinfo->rx_flags &= ~NETPOLL_RX_DROP; return budget - work; } @@ -211,10 +215,12 @@ static void zap_completion_queue(void) while (clist != NULL) { struct sk_buff *skb = clist; clist = clist->next; - if (skb->destructor) + if (skb->destructor) { + atomic_inc(&skb->users); dev_kfree_skb_any(skb); /* put this one back */ - else + } else { __kfree_skb(skb); + } } } @@ -472,7 +478,7 @@ int __netpoll_rx(struct sk_buff *skb) if (skb->dev->type != ARPHRD_ETHER) goto out; - /* if receive ARP during middle of NAPI poll, then queue */ + /* check if netpoll clients need ARP */ if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) { skb_queue_tail(&npi->arp_tx, skb); @@ -534,9 +540,6 @@ int __netpoll_rx(struct sk_buff *skb) return 1; out: - /* If packet received while already in poll then just - * silently drop. - */ if (atomic_read(&trapped)) { kfree_skb(skb); return 1; @@ -675,6 +678,7 @@ int netpoll_setup(struct netpoll *np) goto release; } + npinfo->rx_flags = 0; npinfo->rx_np = NULL; spin_lock_init(&npinfo->rx_lock); @@ -756,6 +760,7 @@ int netpoll_setup(struct netpoll *np) if (np->rx_hook) { spin_lock_irqsave(&npinfo->rx_lock, flags); + npinfo->rx_flags |= NETPOLL_RX_ENABLED; npinfo->rx_np = np; spin_unlock_irqrestore(&npinfo->rx_lock, flags); } @@ -797,6 +802,7 @@ void netpoll_cleanup(struct netpoll *np) if (npinfo->rx_np == np) { spin_lock_irqsave(&npinfo->rx_lock, flags); npinfo->rx_np = NULL; + npinfo->rx_flags &= ~NETPOLL_RX_ENABLED; spin_unlock_irqrestore(&npinfo->rx_lock, flags); } diff --git a/net/core/sock.c b/net/core/sock.c index 09cb3a74de7..2654c147c00 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1621,7 +1621,7 @@ static void sock_def_readable(struct sock *sk, int len) { read_lock(&sk->sk_callback_lock); if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible_sync(sk->sk_sleep); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); read_unlock(&sk->sk_callback_lock); } @@ -1635,7 +1635,7 @@ static void sock_def_write_space(struct sock *sk) */ if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible_sync(sk->sk_sleep); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 19880b086e7..9c7e5ffb223 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -343,7 +343,7 @@ config INET_ESP tristate "IP: ESP transformation" select XFRM select CRYPTO - select CRYPTO_AEAD + select CRYPTO_AUTHENC select CRYPTO_HMAC select CRYPTO_MD5 select CRYPTO_CBC diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 09ca5293d08..0d109504ed8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -458,7 +458,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = -EADDRNOTAVAIL; if (!sysctl_ip_nonlocal_bind && !inet->freebind && - addr->sin_addr.s_addr != INADDR_ANY && + addr->sin_addr.s_addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 091e6709f83..f3ceca31aa4 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -168,7 +168,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_encap_tmpl *encap = x->encap; struct udphdr *uh; __be32 *udpdata32; - unsigned int sport, dport; + __be16 sport, dport; int encap_type; spin_lock_bh(&x->lock); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 1ff446d0fa8..f6cdc012eec 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -177,10 +177,13 @@ static inline struct tnode *node_parent_rcu(struct node *node) return rcu_dereference(ret); } +/* Same as rcu_assign_pointer + * but that macro() assumes that value is a pointer. + */ static inline void node_set_parent(struct node *node, struct tnode *ptr) { - rcu_assign_pointer(node->parent, - (unsigned long)ptr | NODE_TYPE(node)); + smp_wmb(); + node->parent = (unsigned long)ptr | NODE_TYPE(node); } static inline struct node *tnode_get_child(struct tnode *tn, unsigned int i) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index a13c074dac0..a944e8053e2 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -591,7 +591,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) } if (xfrm_decode_session_reverse(skb_in, &fl, AF_INET)) - goto out_unlock; + goto ende; if (inet_addr_type(net, fl.fl4_src) == RTN_LOCAL) err = __ip_route_output_key(net, &rt2, &fl); @@ -601,7 +601,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) fl2.fl4_dst = fl.fl4_src; if (ip_route_output_key(net, &rt2, &fl2)) - goto out_unlock; + goto ende; /* Ugh! */ odst = skb_in->dst; @@ -614,7 +614,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) } if (err) - goto out_unlock; + goto ende; err = xfrm_lookup((struct dst_entry **)&rt2, &fl, NULL, XFRM_LOOKUP_ICMP); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index a2e92f9709d..3b2e5adca83 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -568,7 +568,7 @@ int ip_defrag(struct sk_buff *skb, u32 user) IP_INC_STATS_BH(IPSTATS_MIB_REASMREQDS); - net = skb->dev->nd_net; + net = skb->dev ? skb->dev->nd_net : skb->dst->dev->nd_net; /* Start by cleaning up the memory. */ if (atomic_read(&net->ipv4.frags.mem) > net->ipv4.frags.high_thresh) ip_evictor(net); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index de0572c8885..f72457b4b0a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -583,7 +583,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, } if (!mreq.imr_ifindex) { - if (mreq.imr_address.s_addr == INADDR_ANY) { + if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) { inet->mc_index = 0; inet->mc_addr = 0; err = 0; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 10013ccee8d..7c992fbbc2c 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -103,6 +103,7 @@ - '3' from resolv.h */ #define NONE __constant_htonl(INADDR_NONE) +#define ANY __constant_htonl(INADDR_ANY) /* * Public IP configuration @@ -753,9 +754,9 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d printk("Unknown ARP type 0x%04x for device %s\n", dev->type, dev->name); b->htype = dev->type; /* can cause undefined behavior */ } + + /* server_ip and your_ip address are both already zero per RFC2131 */ b->hlen = dev->addr_len; - b->your_ip = NONE; - b->server_ip = NONE; memcpy(b->hw_addr, dev->dev_addr, dev->addr_len); b->secs = htons(jiffies_diff / HZ); b->xid = d->xid; @@ -1479,19 +1480,19 @@ static int __init ip_auto_config_setup(char *addrs) DBG(("IP-Config: Parameter #%d: `%s'\n", num, ip)); switch (num) { case 0: - if ((ic_myaddr = in_aton(ip)) == INADDR_ANY) + if ((ic_myaddr = in_aton(ip)) == ANY) ic_myaddr = NONE; break; case 1: - if ((ic_servaddr = in_aton(ip)) == INADDR_ANY) + if ((ic_servaddr = in_aton(ip)) == ANY) ic_servaddr = NONE; break; case 2: - if ((ic_gateway = in_aton(ip)) == INADDR_ANY) + if ((ic_gateway = in_aton(ip)) == ANY) ic_gateway = NONE; break; case 3: - if ((ic_netmask = in_aton(ip)) == INADDR_ANY) + if ((ic_netmask = in_aton(ip)) == ANY) ic_netmask = NONE; break; case 4: diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 68cbe3ca01c..8e8f0425a8e 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -252,6 +252,8 @@ recent_mt_check(const char *tablename, const void *ip, if ((info->check_set & (IPT_RECENT_SET | IPT_RECENT_REMOVE)) && (info->seconds || info->hit_count)) return false; + if (info->hit_count > ip_pkt_list_tot) + return false; if (info->name[0] == '\0' || strnlen(info->name, IPT_RECENT_NAME_LEN) == IPT_RECENT_NAME_LEN) return false; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 071e83a894a..39b629ac240 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -735,7 +735,7 @@ new_segment: if (!(psize -= copy)) goto out; - if (skb->len < mss_now || (flags & MSG_OOB)) + if (skb->len < size_goal || (flags & MSG_OOB)) continue; if (forced_push(tp)) { @@ -981,7 +981,7 @@ new_segment: if ((seglen -= copy) == 0 && iovlen == 0) goto out; - if (skb->len < mss_now || (flags & MSG_OOB)) + if (skb->len < size_goal || (flags & MSG_OOB)) continue; if (forced_push(tp)) { diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index 5212ed9b0c9..7eb7636db0d 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -1,12 +1,13 @@ /* * Binary Increase Congestion control for TCP - * + * Home page: + * http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC * This is from the implementation of BICTCP in * Lison-Xu, Kahaled Harfoush, and Injong Rhee. * "Binary Increase Congestion Control for Fast, Long Distance * Networks" in InfoComm 2004 * Available from: - * http://www.csc.ncsu.edu/faculty/rhee/export/bitcp.pdf + * http://netsrv.csc.ncsu.edu/export/bitcp.pdf * * Unless BIC is enabled and congestion window is large * this behaves the same as the original Reno. diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 19c449f6267..7facdb0f696 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1367,7 +1367,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, * a normal way */ static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk, - u32 skip_to_seq) + u32 skip_to_seq, int *fack_count) { tcp_for_write_queue_from(skb, sk) { if (skb == tcp_send_head(sk)) @@ -1375,6 +1375,8 @@ static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk, if (!before(TCP_SKB_CB(skb)->end_seq, skip_to_seq)) break; + + *fack_count += tcp_skb_pcount(skb); } return skb; } @@ -1390,7 +1392,7 @@ static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, return skb; if (before(next_dup->start_seq, skip_to_seq)) { - skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq); + skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq, fack_count); tcp_sacktag_walk(skb, sk, NULL, next_dup->start_seq, next_dup->end_seq, 1, fack_count, reord, flag); @@ -1537,7 +1539,8 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, /* Head todo? */ if (before(start_seq, cache->start_seq)) { - skb = tcp_sacktag_skip(skb, sk, start_seq); + skb = tcp_sacktag_skip(skb, sk, start_seq, + &fack_count); skb = tcp_sacktag_walk(skb, sk, next_dup, start_seq, cache->start_seq, @@ -1565,7 +1568,8 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, goto walk; } - skb = tcp_sacktag_skip(skb, sk, cache->end_seq); + skb = tcp_sacktag_skip(skb, sk, cache->end_seq, + &fack_count); /* Check overlap against next cached too (past this one already) */ cache++; continue; @@ -1577,7 +1581,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, break; fack_count = tp->fackets_out; } - skb = tcp_sacktag_skip(skb, sk, start_seq); + skb = tcp_sacktag_skip(skb, sk, start_seq, &fack_count); walk: skb = tcp_sacktag_walk(skb, sk, next_dup, start_seq, end_seq, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index ed750f9ceb0..72b9350006f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -255,7 +255,7 @@ static u16 tcp_select_window(struct sock *sk) * * Relax Will Robinson. */ - new_win = cur_win; + new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } tp->rcv_wnd = new_win; tp->rcv_wup = tp->rcv_nxt; @@ -1035,6 +1035,13 @@ static void tcp_cwnd_validate(struct sock *sk) * introducing MSS oddities to segment boundaries. In rare cases where * mss_now != mss_cache, we will request caller to create a small skb * per input skb which could be mostly avoided here (if desired). + * + * We explicitly want to create a request for splitting write queue tail + * to a small skb for Nagle purposes while avoiding unnecessary modulos, + * thus all the complexity (cwnd_len is always MSS multiple which we + * return whenever allowed by the other factors). Basically we need the + * modulo only when the receiver window alone is the limiting factor or + * when we would be allowed to send the split-due-to-Nagle skb fully. */ static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb, unsigned int mss_now, unsigned int cwnd) @@ -1048,10 +1055,11 @@ static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb, if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk))) return cwnd_len; - if (skb == tcp_write_queue_tail(sk) && cwnd_len <= skb->len) + needed = min(skb->len, window); + + if (skb == tcp_write_queue_tail(sk) && cwnd_len <= needed) return cwnd_len; - needed = min(skb->len, window); return needed - needed % mss_now; } diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index b47030ba162..9c798abce73 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -39,13 +39,11 @@ static void xfrm4_beet_make_header(struct sk_buff *skb) static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) { struct ip_beet_phdr *ph; - struct iphdr *iph, *top_iph; + struct iphdr *top_iph; int hdrlen, optlen; - iph = ip_hdr(skb); - hdrlen = 0; - optlen = iph->ihl * 4 - sizeof(*iph); + optlen = XFRM_MODE_SKB_CB(skb)->optlen; if (unlikely(optlen)) hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4); @@ -53,11 +51,12 @@ static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) hdrlen); skb->mac_header = skb->network_header + offsetof(struct iphdr, protocol); - skb->transport_header = skb->network_header + sizeof(*iph); + skb->transport_header = skb->network_header + sizeof(*top_iph); xfrm4_beet_make_header(skb); - ph = (struct ip_beet_phdr *)__skb_pull(skb, sizeof(*iph) - hdrlen); + ph = (struct ip_beet_phdr *) + __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen); top_iph = ip_hdr(skb); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 8dee617ee90..584e6d74e3a 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -41,7 +41,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->ihl = 5; top_iph->version = 4; - top_iph->protocol = x->inner_mode->afinfo->proto; + top_iph->protocol = xfrm_af2proto(skb->dst->ops->family); /* DS disclosed */ top_iph->tos = INET_ECN_encapsulate(XFRM_MODE_SKB_CB(skb)->tos, diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index d5a58a81802..8c3180adddb 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -56,7 +56,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) { int err; - err = x->inner_mode->afinfo->extract_output(x, skb); + err = xfrm_inner_extract_output(x, skb); if (err) return err; diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index fdeebe68a37..07735ed280d 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -52,10 +52,12 @@ int xfrm4_extract_header(struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); + XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph); XFRM_MODE_SKB_CB(skb)->id = iph->id; XFRM_MODE_SKB_CB(skb)->frag_off = iph->frag_off; XFRM_MODE_SKB_CB(skb)->tos = iph->tos; XFRM_MODE_SKB_CB(skb)->ttl = iph->ttl; + XFRM_MODE_SKB_CB(skb)->optlen = iph->ihl * 4 - sizeof(*iph); memset(XFRM_MODE_SKB_CB(skb)->flow_lbl, 0, sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl)); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 3ffb0323668..47263e45bac 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -85,7 +85,7 @@ config INET6_ESP depends on IPV6 select XFRM select CRYPTO - select CRYPTO_AEAD + select CRYPTO_AUTHENC select CRYPTO_HMAC select CRYPTO_MD5 select CRYPTO_CBC @@ -179,11 +179,12 @@ config IPV6_SIT Saying M here will produce a module called sit.ko. If unsure, say Y. config IPV6_TUNNEL - tristate "IPv6: IPv6-in-IPv6 tunnel" + tristate "IPv6: IP-in-IPv6 tunnel (RFC2473)" select INET6_TUNNEL depends on IPV6 ---help--- - Support for IPv6-in-IPv6 tunnels described in RFC 2473. + Support for IPv6-in-IPv6 and IPv4-in-IPv6 tunnels described in + RFC 2473. If unsure, say N. diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0d33a7d3212..452a2ac4eec 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -676,6 +676,20 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) } } +static struct pneigh_entry *pndisc_check_router(struct net_device *dev, + struct in6_addr *addr, int *is_router) +{ + struct pneigh_entry *n; + + read_lock_bh(&nd_tbl.lock); + n = __pneigh_lookup(&nd_tbl, &init_net, addr, dev); + if (n != NULL) + *is_router = (n->flags & NTF_ROUTER); + read_unlock_bh(&nd_tbl.lock); + + return n; +} + static void ndisc_recv_ns(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); @@ -692,7 +706,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) struct pneigh_entry *pneigh = NULL; int dad = ipv6_addr_any(saddr); int inc; - int is_router; + int is_router = 0; if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK2(KERN_WARNING @@ -790,8 +804,8 @@ static void ndisc_recv_ns(struct sk_buff *skb) if (ipv6_chk_acast_addr(dev, &msg->target) || (idev->cnf.forwarding && (ipv6_devconf.proxy_ndp || idev->cnf.proxy_ndp) && - (pneigh = pneigh_lookup(&nd_tbl, &init_net, - &msg->target, dev, 0)) != NULL)) { + (pneigh = pndisc_check_router(dev, &msg->target, + &is_router)) != NULL)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && inc != 0 && @@ -812,7 +826,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) goto out; } - is_router = !!(pneigh ? pneigh->flags & NTF_ROUTER : idev->cnf.forwarding); + is_router = !!(pneigh ? is_router : idev->cnf.forwarding); if (dad) { struct in6_addr maddr; @@ -1420,7 +1434,6 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, u8 *opt; int rd_len; int err; - int hlen; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; dev = skb->dev; @@ -1491,7 +1504,6 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, return; } - hlen = 0; skb_reserve(buff, LL_RESERVED_SPACE(dev)); ip6_nd_hdr(sk, buff, dev, &saddr_buf, &ipv6_hdr(skb)->saddr, diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index 0527d11c1ae..d6ce400f585 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -45,6 +45,7 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) skb->mac_header = skb->network_header + offsetof(struct ipv6hdr, nexthdr); skb->transport_header = skb->network_header + sizeof(*top_iph); + __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl); xfrm6_beet_make_header(skb); diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 0c742faaa30..e20529b4c82 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -45,7 +45,7 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl, sizeof(top_iph->flow_lbl)); - top_iph->nexthdr = x->inner_mode->afinfo->proto; + top_iph->nexthdr = xfrm_af2proto(skb->dst->ops->family); dsfield = XFRM_MODE_SKB_CB(skb)->tos; dsfield = INET_ECN_encapsulate(dsfield, dsfield); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 79ccfb08073..0af823cf7f1 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -62,7 +62,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) { int err; - err = x->inner_mode->afinfo->extract_output(x, skb); + err = xfrm_inner_extract_output(x, skb); if (err) return err; diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index dc817e035e2..ff1e1db8e23 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -174,10 +174,12 @@ int xfrm6_extract_header(struct sk_buff *skb) { struct ipv6hdr *iph = ipv6_hdr(skb); + XFRM_MODE_SKB_CB(skb)->ihl = sizeof(*iph); XFRM_MODE_SKB_CB(skb)->id = 0; XFRM_MODE_SKB_CB(skb)->frag_off = htons(IP_DF); XFRM_MODE_SKB_CB(skb)->tos = ipv6_get_dsfield(iph); XFRM_MODE_SKB_CB(skb)->ttl = iph->hop_limit; + XFRM_MODE_SKB_CB(skb)->optlen = 0; memcpy(XFRM_MODE_SKB_CB(skb)->flow_lbl, iph->flow_lbl, sizeof(XFRM_MODE_SKB_CB(skb)->flow_lbl)); diff --git a/net/irda/ircomm/ircomm_core.c b/net/irda/ircomm/ircomm_core.c index b825399fc16..6eef1f2a755 100644 --- a/net/irda/ircomm/ircomm_core.c +++ b/net/irda/ircomm/ircomm_core.c @@ -76,9 +76,11 @@ static int __init ircomm_init(void) #ifdef CONFIG_PROC_FS { struct proc_dir_entry *ent; - ent = create_proc_entry("ircomm", 0, proc_irda); - if (ent) - ent->proc_fops = &ircomm_proc_fops; + ent = proc_create("ircomm", 0, proc_irda, &ircomm_proc_fops); + if (!ent) { + printk(KERN_ERR "ircomm_init: can't create /proc entry!\n"); + return -ENODEV; + } } #endif /* CONFIG_PROC_FS */ diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c index a4b56e25a91..1eb4bbcb1c9 100644 --- a/net/irda/irlan/irlan_common.c +++ b/net/irda/irlan/irlan_common.c @@ -128,13 +128,11 @@ static int __init irlan_init(void) #ifdef CONFIG_PROC_FS { struct proc_dir_entry *proc; - proc = create_proc_entry("irlan", 0, proc_irda); + proc = proc_create("irlan", 0, proc_irda, &irlan_fops); if (!proc) { printk(KERN_ERR "irlan_init: can't create /proc entry!\n"); return -ENODEV; } - - proc->proc_fops = &irlan_fops; } #endif /* CONFIG_PROC_FS */ diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h index bc2e15ce700..7873c392ab4 100644 --- a/net/irda/irnet/irnet.h +++ b/net/irda/irnet/irnet.h @@ -405,7 +405,7 @@ typedef struct irnet_socket /* "pppd" interact directly with us on a /dev/ file */ struct file * file; /* File descriptor of this instance */ /* TTY stuff - to keep "pppd" happy */ - struct termios termios; /* Various tty flags */ + struct ktermios termios; /* Various tty flags */ /* Stuff for the control channel */ int event_index; /* Last read in the event log */ diff --git a/net/irda/irproc.c b/net/irda/irproc.c index cae24fbda96..88e80a31273 100644 --- a/net/irda/irproc.c +++ b/net/irda/irproc.c @@ -72,11 +72,9 @@ void __init irda_proc_register(void) return; proc_irda->owner = THIS_MODULE; - for (i=0; i<ARRAY_SIZE(irda_dirs); i++) { - d = create_proc_entry(irda_dirs[i].name, 0, proc_irda); - if (d) - d->proc_fops = irda_dirs[i].fops; - } + for (i = 0; i < ARRAY_SIZE(irda_dirs); i++) + d = proc_create(irda_dirs[i].name, 0, proc_irda, + irda_dirs[i].fops); } /* diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 2753b0c448f..d764f4c1b7e 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -621,7 +621,6 @@ static int iucv_sever_pathid(u16 pathid, u8 userdata[16]) return iucv_call_b2f0(IUCV_SEVER, parm); } -#ifdef CONFIG_SMP /** * __iucv_cleanup_queue * @dummy: unused dummy argument @@ -632,7 +631,6 @@ static int iucv_sever_pathid(u16 pathid, u8 userdata[16]) static void __iucv_cleanup_queue(void *dummy) { } -#endif /** * iucv_cleanup_queue diff --git a/net/key/af_key.c b/net/key/af_key.c index 8b5f486ac80..e9ef9af4a53 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1219,7 +1219,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr, x->sel.prefixlen_s = addr->sadb_address_prefixlen; } - if (!x->sel.family) + if (x->props.mode == XFRM_MODE_TRANSPORT) x->sel.family = x->props.family; if (ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1]) { diff --git a/net/mac80211/rc80211_pid_algo.c b/net/mac80211/rc80211_pid_algo.c index c339571632b..3b77410588e 100644 --- a/net/mac80211/rc80211_pid_algo.c +++ b/net/mac80211/rc80211_pid_algo.c @@ -2,7 +2,7 @@ * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005, Devicescape Software, Inc. * Copyright 2007, Mattias Nissler <mattias.nissler@gmx.de> - * Copyright 2007, Stefano Brivio <stefano.brivio@polimi.it> + * Copyright 2007-2008, Stefano Brivio <stefano.brivio@polimi.it> * * 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 @@ -63,72 +63,66 @@ * RC_PID_ARITH_SHIFT. */ - -/* Shift the adjustment so that we won't switch to a lower rate if it exhibited - * a worse failed frames behaviour and we'll choose the highest rate whose - * failed frames behaviour is not worse than the one of the original rate - * target. While at it, check that the adjustment is within the ranges. Then, - * provide the new rate index. */ -static int rate_control_pid_shift_adjust(struct rc_pid_rateinfo *r, - int adj, int cur, int l) -{ - int i, j, k, tmp; - - j = r[cur].rev_index; - i = j + adj; - - if (i < 0) - return r[0].index; - if (i >= l - 1) - return r[l - 1].index; - - tmp = i; - - if (adj < 0) { - for (k = j; k >= i; k--) - if (r[k].diff <= r[j].diff) - tmp = k; - } else { - for (k = i + 1; k + i < l; k++) - if (r[k].diff <= r[i].diff) - tmp = k; - } - - return r[tmp].index; -} - +/* Adjust the rate while ensuring that we won't switch to a lower rate if it + * exhibited a worse failed frames behaviour and we'll choose the highest rate + * whose failed frames behaviour is not worse than the one of the original rate + * target. While at it, check that the new rate is valid. */ static void rate_control_pid_adjust_rate(struct ieee80211_local *local, struct sta_info *sta, int adj, struct rc_pid_rateinfo *rinfo) { struct ieee80211_sub_if_data *sdata; struct ieee80211_hw_mode *mode; - int newidx; - int maxrate; - int back = (adj > 0) ? 1 : -1; + int cur_sorted, new_sorted, probe, tmp, n_bitrates; + int cur = sta->txrate; sdata = IEEE80211_DEV_TO_SUB_IF(sta->dev); mode = local->oper_hw_mode; - maxrate = sdata->bss ? sdata->bss->max_ratectrl_rateidx : -1; + n_bitrates = mode->num_rates; - newidx = rate_control_pid_shift_adjust(rinfo, adj, sta->txrate, - mode->num_rates); + /* Map passed arguments to sorted values. */ + cur_sorted = rinfo[cur].rev_index; + new_sorted = cur_sorted + adj; - while (newidx != sta->txrate) { - if (rate_supported(sta, mode, newidx) && - (maxrate < 0 || newidx <= maxrate)) { - sta->txrate = newidx; - break; - } + /* Check limits. */ + if (new_sorted < 0) + new_sorted = rinfo[0].rev_index; + else if (new_sorted >= n_bitrates) + new_sorted = rinfo[n_bitrates - 1].rev_index; - newidx += back; + tmp = new_sorted; + + if (adj < 0) { + /* Ensure that the rate decrease isn't disadvantageous. */ + for (probe = cur_sorted; probe >= new_sorted; probe--) + if (rinfo[probe].diff <= rinfo[cur_sorted].diff && + rate_supported(sta, mode, rinfo[probe].index)) + tmp = probe; + } else { + /* Look for rate increase with zero (or below) cost. */ + for (probe = new_sorted + 1; probe < n_bitrates; probe++) + if (rinfo[probe].diff <= rinfo[new_sorted].diff && + rate_supported(sta, mode, rinfo[probe].index)) + tmp = probe; } + /* Fit the rate found to the nearest supported rate. */ + do { + if (rate_supported(sta, mode, rinfo[tmp].index)) { + sta->txrate = rinfo[tmp].index; + break; + } + if (adj < 0) + tmp--; + else + tmp++; + } while (tmp < n_bitrates && tmp >= 0); + #ifdef CONFIG_MAC80211_DEBUGFS rate_control_pid_event_rate_change( &((struct rc_pid_sta_info *)sta->rate_ctrl_priv)->events, - newidx, mode->rates[newidx].rate); + cur, mode->rates[cur].rate); #endif } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index e06bf0028bb..684ec9c1ad3 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -381,7 +381,7 @@ int nf_ct_expect_related(struct nf_conntrack_expect *expect) if (nf_ct_expect_count >= nf_ct_expect_max) { if (net_ratelimit()) printk(KERN_WARNING - "nf_conntrack: expectation table full"); + "nf_conntrack: expectation table full\n"); ret = -EMFILE; goto out; } diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 8b9be1e978c..2bd9963b5b3 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -19,14 +19,6 @@ static struct nf_ct_ext_type *nf_ct_ext_types[NF_CT_EXT_NUM]; static DEFINE_MUTEX(nf_ct_ext_type_mutex); -/* Horrible trick to figure out smallest amount worth kmallocing. */ -#define CACHE(x) (x) + 0 * -enum { - NF_CT_EXT_MIN_SIZE = -#include <linux/kmalloc_sizes.h> - 1 }; -#undef CACHE - void __nf_ct_ext_destroy(struct nf_conn *ct) { unsigned int i; @@ -53,7 +45,7 @@ EXPORT_SYMBOL(__nf_ct_ext_destroy); static void * nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) { - unsigned int off, len, real_len; + unsigned int off, len; struct nf_ct_ext_type *t; rcu_read_lock(); @@ -61,16 +53,14 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) BUG_ON(t == NULL); off = ALIGN(sizeof(struct nf_ct_ext), t->align); len = off + t->len; - real_len = t->alloc_size; rcu_read_unlock(); - *ext = kzalloc(real_len, gfp); + *ext = kzalloc(t->alloc_size, gfp); if (!*ext) return NULL; (*ext)->offset[id] = off; (*ext)->len = len; - (*ext)->real_len = real_len; return (void *)(*ext) + off; } @@ -95,7 +85,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) newlen = newoff + t->len; rcu_read_unlock(); - if (newlen >= ct->ext->real_len) { + if (newlen >= ksize(ct->ext)) { new = kmalloc(newlen, gfp); if (!new) return NULL; @@ -114,7 +104,6 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) rcu_read_unlock(); } kfree(ct->ext); - new->real_len = newlen; ct->ext = new; } @@ -156,8 +145,6 @@ static void update_alloc_size(struct nf_ct_ext_type *type) t1->alloc_size = ALIGN(t1->alloc_size, t2->align) + t2->len; } - if (t1->alloc_size < NF_CT_EXT_MIN_SIZE) - t1->alloc_size = NF_CT_EXT_MIN_SIZE; } } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 62137879e6a..898f1922b5b 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -842,7 +842,7 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, set_h225_addr = rcu_dereference(set_h225_addr_hook); if ((setup->options & eSetup_UUIE_destCallSignalAddress) && - (set_h225_addr) && ct->status && IPS_NAT_MASK && + (set_h225_addr) && ct->status & IPS_NAT_MASK && get_h225_addr(ct, *data, &setup->destCallSignalAddress, &addr, &port) && memcmp(&addr, &ct->tuplehash[!dir].tuple.src.u3, sizeof(addr))) { diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index bfc2928c191..ddc80ea114c 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -51,7 +51,7 @@ int nf_unregister_queue_handler(int pf, const struct nf_queue_handler *qh) return -EINVAL; mutex_lock(&queue_handler_mutex); - if (queue_handler[pf] != qh) { + if (queue_handler[pf] && queue_handler[pf] != qh) { mutex_unlock(&queue_handler_mutex); return -EINVAL; } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 7efa40d4739..bf3f19b21fe 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -556,7 +556,7 @@ nfulnl_log_packet(unsigned int pf, /* FIXME: do we want to make the size calculation conditional based on * what is actually present? way more branches and checks, but more * memory efficient... */ - size = NLMSG_ALIGN(sizeof(struct nfgenmsg)) + size = NLMSG_SPACE(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfulnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ @@ -702,20 +702,30 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); u_int16_t group_num = ntohs(nfmsg->res_id); struct nfulnl_instance *inst; + struct nfulnl_msg_config_cmd *cmd = NULL; int ret = 0; + if (nfula[NFULA_CFG_CMD]) { + u_int8_t pf = nfmsg->nfgen_family; + cmd = nla_data(nfula[NFULA_CFG_CMD]); + + /* Commands without queue context */ + switch (cmd->command) { + case NFULNL_CFG_CMD_PF_BIND: + return nf_log_register(pf, &nfulnl_logger); + case NFULNL_CFG_CMD_PF_UNBIND: + nf_log_unregister_pf(pf); + return 0; + } + } + inst = instance_lookup_get(group_num); if (inst && inst->peer_pid != NETLINK_CB(skb).pid) { ret = -EPERM; goto out_put; } - if (nfula[NFULA_CFG_CMD]) { - u_int8_t pf = nfmsg->nfgen_family; - struct nfulnl_msg_config_cmd *cmd; - - cmd = nla_data(nfula[NFULA_CFG_CMD]); - + if (cmd != NULL) { switch (cmd->command) { case NFULNL_CFG_CMD_BIND: if (inst) { @@ -738,14 +748,6 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, instance_destroy(inst); goto out; - case NFULNL_CFG_CMD_PF_BIND: - ret = nf_log_register(pf, &nfulnl_logger); - break; - case NFULNL_CFG_CMD_PF_UNBIND: - /* This is a bug and a feature. We cannot unregister - * other handlers, like nfnetlink_inst can */ - nf_log_unregister_pf(pf); - break; default: ret = -ENOTSUPP; break; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 0043d3a9f87..012cb691082 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -224,7 +224,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, struct net_device *indev; struct net_device *outdev; - size = NLMSG_ALIGN(sizeof(struct nfgenmsg)) + size = NLMSG_SPACE(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfqnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ @@ -703,19 +703,12 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, /* Commands without queue context - might sleep */ switch (cmd->command) { case NFQNL_CFG_CMD_PF_BIND: - ret = nf_register_queue_handler(ntohs(cmd->pf), - &nfqh); - break; + return nf_register_queue_handler(ntohs(cmd->pf), + &nfqh); case NFQNL_CFG_CMD_PF_UNBIND: - ret = nf_unregister_queue_handler(ntohs(cmd->pf), - &nfqh); - break; - default: - break; + return nf_unregister_queue_handler(ntohs(cmd->pf), + &nfqh); } - - if (ret < 0) - return ret; } rcu_read_lock(); diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c index e9a8794bc3a..9fa2e082470 100644 --- a/net/netfilter/xt_time.c +++ b/net/netfilter/xt_time.c @@ -95,8 +95,11 @@ static inline void localtime_2(struct xtm *r, time_t time) */ r->dse = time / 86400; - /* 1970-01-01 (w=0) was a Thursday (4). */ - r->weekday = (4 + r->dse) % 7; + /* + * 1970-01-01 (w=0) was a Thursday (4). + * -1 and +1 map Sunday properly onto 7. + */ + r->weekday = (4 + r->dse - 1) % 7 + 1; } static void localtime_3(struct xtm *r, time_t time) diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index f19121d4795..a39bf97f883 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -143,7 +143,8 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, /* copy the peer address and timestamp */ if (!continue_call) { if (msg->msg_name && msg->msg_namelen > 0) - memcpy(&msg->msg_name, &call->conn->trans->peer->srx, + memcpy(msg->msg_name, + &call->conn->trans->peer->srx, sizeof(call->conn->trans->peer->srx)); sock_recv_timestamp(msg, &rx->sk, skb); } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index b18fa95ef24..c5c16b4b6e9 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -89,7 +89,7 @@ static const struct tcf_ext_map u32_ext_map = { static struct tc_u_common *u32_list; -static __inline__ unsigned u32_hash_fold(u32 key, struct tc_u32_sel *sel, u8 fshift) +static __inline__ unsigned u32_hash_fold(__be32 key, struct tc_u32_sel *sel, u8 fshift) { unsigned h = ntohl(key & sel->hmask)>>fshift; @@ -137,7 +137,7 @@ next_knode: for (i = n->sel.nkeys; i>0; i--, key++) { - if ((*(u32*)(ptr+key->off+(off2&key->offmask))^key->val)&key->mask) { + if ((*(__be32*)(ptr+key->off+(off2&key->offmask))^key->val)&key->mask) { n = n->next; goto next_knode; } @@ -182,7 +182,7 @@ check_terminal: ht = n->ht_down; sel = 0; if (ht->divisor) - sel = ht->divisor&u32_hash_fold(*(u32*)(ptr+n->sel.hoff), &n->sel,n->fshift); + sel = ht->divisor&u32_hash_fold(*(__be32*)(ptr+n->sel.hoff), &n->sel,n->fshift); if (!(n->sel.flags&(TC_U32_VAROFFSET|TC_U32_OFFSET|TC_U32_EAT))) goto next_ht; @@ -190,7 +190,7 @@ check_terminal: if (n->sel.flags&(TC_U32_OFFSET|TC_U32_VAROFFSET)) { off2 = n->sel.off + 3; if (n->sel.flags&TC_U32_VAROFFSET) - off2 += ntohs(n->sel.offmask & *(u16*)(ptr+n->sel.offoff)) >>n->sel.offshift; + off2 += ntohs(n->sel.offmask & *(__be16*)(ptr+n->sel.offoff)) >>n->sel.offshift; off2 &= ~3; } if (n->sel.flags&TC_U32_EAT) { diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c index 112796e4a7c..953f1479f7d 100644 --- a/net/sched/em_u32.c +++ b/net/sched/em_u32.c @@ -35,7 +35,7 @@ static int em_u32_match(struct sk_buff *skb, struct tcf_ematch *em, if (!tcf_valid_offset(skb, ptr, sizeof(u32))) return 0; - return !(((*(u32*) ptr) ^ key->val) & key->mask); + return !(((*(__be32*) ptr) ^ key->val) & key->mask); } static struct tcf_ematch_ops em_u32_ops = { diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 795c761ad99..66148cc4759 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -711,9 +711,11 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl, */ static psched_time_t htb_do_events(struct htb_sched *q, int level) { - int i; - - for (i = 0; i < 500; i++) { + /* don't run for longer than 2 jiffies; 2 is used instead of + 1 to simplify things when jiffy is going to be incremented + too soon */ + unsigned long stop_at = jiffies + 2; + while (time_before(jiffies, stop_at)) { struct htb_class *cl; long diff; struct rb_node *p = rb_first(&q->wait_pq[level]); @@ -731,9 +733,8 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level) if (cl->cmode != HTB_CAN_SEND) htb_add_to_wait_tree(q, cl, diff); } - if (net_ratelimit()) - printk(KERN_WARNING "htb: too many events !\n"); - return q->now + PSCHED_TICKS_PER_SEC / 10; + /* too much load - let's continue on next jiffie */ + return q->now + PSCHED_TICKS_PER_SEC / HZ; } /* Returns class->node+prio from id-tree where classe's id is >= id. NULL diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index a27511ebc4c..ceefda025e2 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -209,6 +209,7 @@ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new, int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr) { struct sctp_sockaddr_entry *addr, *temp; + int found = 0; /* We hold the socket lock when calling this function, * and that acts as a writer synchronizing lock. @@ -216,13 +217,14 @@ int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr) list_for_each_entry_safe(addr, temp, &bp->address_list, list) { if (sctp_cmp_addr_exact(&addr->a, del_addr)) { /* Found the exact match. */ + found = 1; addr->valid = 0; list_del_rcu(&addr->list); break; } } - if (addr && !addr->valid) { + if (found) { call_rcu(&addr->rcu, sctp_local_addr_free); SCTP_DBG_OBJCNT_DEC(addr); return 0; diff --git a/net/sctp/input.c b/net/sctp/input.c index 57fe2f81eca..812ff1756c3 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -944,7 +944,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct sk_buff *skb, static struct sctp_association *__sctp_rcv_asconf_lookup( sctp_chunkhdr_t *ch, const union sctp_addr *laddr, - __be32 peer_port, + __be16 peer_port, struct sctp_transport **transportp) { sctp_addip_chunk_t *asconf = (struct sctp_addip_chunk *)ch; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 87f940587d5..b1e05d719f9 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -89,6 +89,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; struct sctp_sockaddr_entry *addr = NULL; struct sctp_sockaddr_entry *temp; + int found = 0; switch (ev) { case NETDEV_UP: @@ -111,13 +112,14 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, &sctp_local_addr_list, list) { if (ipv6_addr_equal(&addr->a.v6.sin6_addr, &ifa->addr)) { + found = 1; addr->valid = 0; list_del_rcu(&addr->list); break; } } spin_unlock_bh(&sctp_local_addr_lock); - if (addr && !addr->valid) + if (found) call_rcu(&addr->rcu, sctp_local_addr_free); break; } @@ -1012,15 +1014,24 @@ static struct sctp_pf sctp_pf_inet6 = { }; /* Initialize IPv6 support and register with socket layer. */ -int sctp_v6_init(void) +void sctp_v6_pf_init(void) { - int rc; - /* Register the SCTP specific PF_INET6 functions. */ sctp_register_pf(&sctp_pf_inet6, PF_INET6); /* Register the SCTP specific AF_INET6 functions. */ sctp_register_af(&sctp_af_inet6); +} + +void sctp_v6_pf_exit(void) +{ + list_del(&sctp_af_inet6.list); +} + +/* Initialize IPv6 support and register with socket layer. */ +int sctp_v6_protosw_init(void) +{ + int rc; rc = proto_register(&sctpv6_prot, 1); if (rc) @@ -1033,6 +1044,14 @@ int sctp_v6_init(void) return 0; } +void sctp_v6_protosw_exit(void) +{ + inet6_unregister_protosw(&sctpv6_seqpacket_protosw); + inet6_unregister_protosw(&sctpv6_stream_protosw); + proto_unregister(&sctpv6_prot); +} + + /* Register with inet6 layer. */ int sctp_v6_add_protocol(void) { @@ -1045,15 +1064,6 @@ int sctp_v6_add_protocol(void) return 0; } -/* IPv6 specific exit support. */ -void sctp_v6_exit(void) -{ - inet6_unregister_protosw(&sctpv6_seqpacket_protosw); - inet6_unregister_protosw(&sctpv6_stream_protosw); - proto_unregister(&sctpv6_prot); - list_del(&sctp_af_inet6.list); -} - /* Unregister with inet6 layer. */ void sctp_v6_del_protocol(void) { diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 9e214da82d9..973f1dbc2ec 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -256,12 +256,10 @@ int __init sctp_eps_proc_init(void) { struct proc_dir_entry *p; - p = create_proc_entry("eps", S_IRUGO, proc_net_sctp); + p = proc_create("eps", S_IRUGO, proc_net_sctp, &sctp_eps_seq_fops); if (!p) return -ENOMEM; - p->proc_fops = &sctp_eps_seq_fops; - return 0; } @@ -367,12 +365,11 @@ int __init sctp_assocs_proc_init(void) { struct proc_dir_entry *p; - p = create_proc_entry("assocs", S_IRUGO, proc_net_sctp); + p = proc_create("assocs", S_IRUGO, proc_net_sctp, + &sctp_assocs_seq_fops); if (!p) return -ENOMEM; - p->proc_fops = &sctp_assocs_seq_fops; - return 0; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 688546dccd8..f90091a1b9c 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -337,14 +337,14 @@ static int sctp_v4_cmp_addr(const union sctp_addr *addr1, static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port) { addr->v4.sin_family = AF_INET; - addr->v4.sin_addr.s_addr = INADDR_ANY; + addr->v4.sin_addr.s_addr = htonl(INADDR_ANY); addr->v4.sin_port = port; } /* Is this a wildcard address? */ static int sctp_v4_is_any(const union sctp_addr *addr) { - return INADDR_ANY == addr->v4.sin_addr.s_addr; + return htonl(INADDR_ANY) == addr->v4.sin_addr.s_addr; } /* This function checks if the address is a valid address to be used for @@ -375,7 +375,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) int ret = inet_addr_type(&init_net, addr->v4.sin_addr.s_addr); - if (addr->v4.sin_addr.s_addr != INADDR_ANY && + if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && !sp->inet.freebind && !sysctl_ip_nonlocal_bind) @@ -628,6 +628,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; struct sctp_sockaddr_entry *addr = NULL; struct sctp_sockaddr_entry *temp; + int found = 0; switch (ev) { case NETDEV_UP: @@ -647,13 +648,14 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, list_for_each_entry_safe(addr, temp, &sctp_local_addr_list, list) { if (addr->a.v4.sin_addr.s_addr == ifa->ifa_local) { + found = 1; addr->valid = 0; list_del_rcu(&addr->list); break; } } spin_unlock_bh(&sctp_local_addr_lock); - if (addr && !addr->valid) + if (found) call_rcu(&addr->rcu, sctp_local_addr_free); break; } @@ -783,8 +785,8 @@ static int sctp_inet_cmp_addr(const union sctp_addr *addr1, /* PF_INET only supports AF_INET addresses. */ if (addr1->sa.sa_family != addr2->sa.sa_family) return 0; - if (INADDR_ANY == addr1->v4.sin_addr.s_addr || - INADDR_ANY == addr2->v4.sin_addr.s_addr) + if (htonl(INADDR_ANY) == addr1->v4.sin_addr.s_addr || + htonl(INADDR_ANY) == addr2->v4.sin_addr.s_addr) return 1; if (addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr) return 1; @@ -990,6 +992,58 @@ static void cleanup_sctp_mibs(void) free_percpu(sctp_statistics[1]); } +static void sctp_v4_pf_init(void) +{ + /* Initialize the SCTP specific PF functions. */ + sctp_register_pf(&sctp_pf_inet, PF_INET); + sctp_register_af(&sctp_af_inet); +} + +static void sctp_v4_pf_exit(void) +{ + list_del(&sctp_af_inet.list); +} + +static int sctp_v4_protosw_init(void) +{ + int rc; + + rc = proto_register(&sctp_prot, 1); + if (rc) + return rc; + + /* Register SCTP(UDP and TCP style) with socket layer. */ + inet_register_protosw(&sctp_seqpacket_protosw); + inet_register_protosw(&sctp_stream_protosw); + + return 0; +} + +static void sctp_v4_protosw_exit(void) +{ + inet_unregister_protosw(&sctp_stream_protosw); + inet_unregister_protosw(&sctp_seqpacket_protosw); + proto_unregister(&sctp_prot); +} + +static int sctp_v4_add_protocol(void) +{ + /* Register notifier for inet address additions/deletions. */ + register_inetaddr_notifier(&sctp_inetaddr_notifier); + + /* Register SCTP with inet layer. */ + if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0) + return -EAGAIN; + + return 0; +} + +static void sctp_v4_del_protocol(void) +{ + inet_del_protocol(&sctp_protocol, IPPROTO_SCTP); + unregister_inetaddr_notifier(&sctp_inetaddr_notifier); +} + /* Initialize the universe into something sensible. */ SCTP_STATIC __init int sctp_init(void) { @@ -1033,8 +1087,6 @@ SCTP_STATIC __init int sctp_init(void) /* Initialize object count debugging. */ sctp_dbg_objcnt_init(); - /* Initialize the SCTP specific PF functions. */ - sctp_register_pf(&sctp_pf_inet, PF_INET); /* * 14. Suggested SCTP Protocol Parameter Values */ @@ -1192,19 +1244,22 @@ SCTP_STATIC __init int sctp_init(void) sctp_sysctl_register(); INIT_LIST_HEAD(&sctp_address_families); - sctp_register_af(&sctp_af_inet); + sctp_v4_pf_init(); + sctp_v6_pf_init(); - status = proto_register(&sctp_prot, 1); - if (status) - goto err_proto_register; + /* Initialize the local address list. */ + INIT_LIST_HEAD(&sctp_local_addr_list); + spin_lock_init(&sctp_local_addr_lock); + sctp_get_local_addr_list(); - /* Register SCTP(UDP and TCP style) with socket layer. */ - inet_register_protosw(&sctp_seqpacket_protosw); - inet_register_protosw(&sctp_stream_protosw); + status = sctp_v4_protosw_init(); - status = sctp_v6_init(); if (status) - goto err_v6_init; + goto err_protosw_init; + + status = sctp_v6_protosw_init(); + if (status) + goto err_v6_protosw_init; /* Initialize the control inode/socket for handling OOTB packets. */ if ((status = sctp_ctl_sock_init())) { @@ -1213,19 +1268,9 @@ SCTP_STATIC __init int sctp_init(void) goto err_ctl_sock_init; } - /* Initialize the local address list. */ - INIT_LIST_HEAD(&sctp_local_addr_list); - spin_lock_init(&sctp_local_addr_lock); - sctp_get_local_addr_list(); - - /* Register notifier for inet address additions/deletions. */ - register_inetaddr_notifier(&sctp_inetaddr_notifier); - - /* Register SCTP with inet layer. */ - if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0) { - status = -EAGAIN; + status = sctp_v4_add_protocol(); + if (status) goto err_add_protocol; - } /* Register SCTP with inet6 layer. */ status = sctp_v6_add_protocol(); @@ -1236,18 +1281,18 @@ SCTP_STATIC __init int sctp_init(void) out: return status; err_v6_add_protocol: - inet_del_protocol(&sctp_protocol, IPPROTO_SCTP); - unregister_inetaddr_notifier(&sctp_inetaddr_notifier); + sctp_v6_del_protocol(); err_add_protocol: - sctp_free_local_addr_list(); + sctp_v4_del_protocol(); sock_release(sctp_ctl_socket); err_ctl_sock_init: - sctp_v6_exit(); -err_v6_init: - inet_unregister_protosw(&sctp_stream_protosw); - inet_unregister_protosw(&sctp_seqpacket_protosw); - proto_unregister(&sctp_prot); -err_proto_register: + sctp_v6_protosw_exit(); +err_v6_protosw_init: + sctp_v4_protosw_exit(); +err_protosw_init: + sctp_free_local_addr_list(); + sctp_v4_pf_exit(); + sctp_v6_pf_exit(); sctp_sysctl_unregister(); list_del(&sctp_af_inet.list); free_pages((unsigned long)sctp_port_hashtable, @@ -1280,23 +1325,21 @@ SCTP_STATIC __exit void sctp_exit(void) /* Unregister with inet6/inet layers. */ sctp_v6_del_protocol(); - inet_del_protocol(&sctp_protocol, IPPROTO_SCTP); - - /* Unregister notifier for inet address additions/deletions. */ - unregister_inetaddr_notifier(&sctp_inetaddr_notifier); - - /* Free the local address list. */ - sctp_free_local_addr_list(); + sctp_v4_del_protocol(); /* Free the control endpoint. */ sock_release(sctp_ctl_socket); - /* Cleanup v6 initializations. */ - sctp_v6_exit(); + /* Free protosw registrations */ + sctp_v6_protosw_exit(); + sctp_v4_protosw_exit(); + + /* Free the local address list. */ + sctp_free_local_addr_list(); /* Unregister with socket layer. */ - inet_unregister_protosw(&sctp_stream_protosw); - inet_unregister_protosw(&sctp_seqpacket_protosw); + sctp_v6_pf_exit(); + sctp_v4_pf_exit(); sctp_sysctl_unregister(); list_del(&sctp_af_inet.list); @@ -1315,8 +1358,6 @@ SCTP_STATIC __exit void sctp_exit(void) kmem_cache_destroy(sctp_chunk_cachep); kmem_cache_destroy(sctp_bucket_cachep); - - proto_unregister(&sctp_prot); } module_init(sctp_init); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index e45be4e3f80..578630e8e00 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2375,6 +2375,14 @@ static int sctp_process_param(struct sctp_association *asoc, asoc->peer.ipv4_address = 0; asoc->peer.ipv6_address = 0; + /* Assume that peer supports the address family + * by which it sends a packet. + */ + if (peer_addr->sa.sa_family == AF_INET6) + asoc->peer.ipv6_address = 1; + else if (peer_addr->sa.sa_family == AF_INET) + asoc->peer.ipv4_address = 1; + /* Cycle through address types; avoid divide by 0. */ sat = ntohs(param.p->length) - sizeof(sctp_paramhdr_t); if (sat) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 939892691a2..d994d822900 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2933,17 +2933,39 @@ static int sctp_setsockopt_maxburst(struct sock *sk, char __user *optval, int optlen) { + struct sctp_assoc_value params; + struct sctp_sock *sp; + struct sctp_association *asoc; int val; + int assoc_id = 0; - if (optlen != sizeof(int)) + if (optlen < sizeof(int)) return -EINVAL; - if (get_user(val, (int __user *)optval)) - return -EFAULT; - if (val < 0) + if (optlen == sizeof(int)) { + printk(KERN_WARNING + "SCTP: Use of int in max_burst socket option deprecated\n"); + printk(KERN_WARNING + "SCTP: Use struct sctp_assoc_value instead\n"); + if (copy_from_user(&val, optval, optlen)) + return -EFAULT; + } else if (optlen == sizeof(struct sctp_assoc_value)) { + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; + val = params.assoc_value; + assoc_id = params.assoc_id; + } else return -EINVAL; - sctp_sk(sk)->max_burst = val; + sp = sctp_sk(sk); + + if (assoc_id != 0) { + asoc = sctp_id2assoc(sk, assoc_id); + if (!asoc) + return -EINVAL; + asoc->max_burst = val; + } else + sp->max_burst = val; return 0; } @@ -5005,20 +5027,45 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, char __user *optval, int __user *optlen) { - int val; + struct sctp_assoc_value params; + struct sctp_sock *sp; + struct sctp_association *asoc; if (len < sizeof(int)) return -EINVAL; - len = sizeof(int); + if (len == sizeof(int)) { + printk(KERN_WARNING + "SCTP: Use of int in max_burst socket option deprecated\n"); + printk(KERN_WARNING + "SCTP: Use struct sctp_assoc_value instead\n"); + params.assoc_id = 0; + } else if (len == sizeof (struct sctp_assoc_value)) { + if (copy_from_user(¶ms, optval, len)) + return -EFAULT; + } else + return -EINVAL; - val = sctp_sk(sk)->max_burst; - if (put_user(len, optlen)) - return -EFAULT; - if (copy_to_user(optval, &val, len)) - return -EFAULT; + sp = sctp_sk(sk); + + if (params.assoc_id != 0) { + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) + return -EINVAL; + params.assoc_value = asoc->max_burst; + } else + params.assoc_value = sp->max_burst; + + if (len == sizeof(int)) { + if (copy_to_user(optval, ¶ms.assoc_value, len)) + return -EFAULT; + } else { + if (copy_to_user(optval, ¶ms, len)) + return -EFAULT; + } + + return 0; - return -ENOTSUPP; } static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, diff --git a/net/socket.c b/net/socket.c index b6d35cd72a5..9d3fbfbc853 100644 --- a/net/socket.c +++ b/net/socket.c @@ -909,11 +909,10 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) if (!dlci_ioctl_hook) request_module("dlci"); - if (dlci_ioctl_hook) { - mutex_lock(&dlci_ioctl_mutex); + mutex_lock(&dlci_ioctl_mutex); + if (dlci_ioctl_hook) err = dlci_ioctl_hook(cmd, argp); - mutex_unlock(&dlci_ioctl_mutex); - } + mutex_unlock(&dlci_ioctl_mutex); break; default: err = sock->ops->ioctl(sock, cmd, arg); diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 61801a069ff..bce9d527af0 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -317,7 +317,7 @@ gss_delete_sec_context(struct gss_ctx **context_handle) if (!*context_handle) return(GSS_S_NO_CONTEXT); - if ((*context_handle)->internal_ctx_id != 0) + if ((*context_handle)->internal_ctx_id) (*context_handle)->mech_type->gm_ops ->gss_delete_sec_context((*context_handle) ->internal_ctx_id); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index ea377e06afa..332eb47539e 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -185,7 +185,7 @@ int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port, struct svc_xprt_class *xcl; struct sockaddr_in sin = { .sin_family = AF_INET, - .sin_addr.s_addr = INADDR_ANY, + .sin_addr.s_addr = htonl(INADDR_ANY), .sin_port = htons(port), }; dprintk("svc: creating transport %s[%d]\n", xprt_name, port); diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index ab54a736486..c22d6b6f2db 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -237,14 +237,12 @@ static void rdma_set_ctxt_sge(struct svc_rdma_op_ctxt *ctxt, static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count) { -#ifdef RDMA_TRANSPORT_IWARP if ((RDMA_TRANSPORT_IWARP == rdma_node_get_transport(xprt->sc_cm_id-> device->node_type)) && sge_count > 1) return 1; else -#endif return min_t(int, sge_count, xprt->sc_max_sge); } @@ -324,15 +322,6 @@ next_sge: ctxt->direction = DMA_FROM_DEVICE; clear_bit(RDMACTXT_F_READ_DONE, &ctxt->flags); clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - if ((ch+1)->rc_discrim == 0) { - /* - * Checked in sq_cq_reap to see if we need to - * be enqueued - */ - set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - ctxt->next = hdr_ctxt; - hdr_ctxt->next = head; - } /* Prepare READ WR */ memset(&read_wr, 0, sizeof read_wr); @@ -350,7 +339,17 @@ next_sge: rdma_set_ctxt_sge(ctxt, &sge[ch_sge_ary[ch_no].start], &sgl_offset, read_wr.num_sge); - + if (((ch+1)->rc_discrim == 0) && + (read_wr.num_sge == ch_sge_ary[ch_no].count)) { + /* + * Mark the last RDMA_READ with a bit to + * indicate all RPC data has been fetched from + * the client and the RPC needs to be enqueued. + */ + set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); + ctxt->next = hdr_ctxt; + hdr_ctxt->next = head; + } /* Post the read */ err = svc_rdma_send(xprt, &read_wr); if (err) { diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 0598b229c11..981f190c1b3 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -156,7 +156,7 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *ctxt; int ret = 0; - BUG_ON(sge_count >= 32); + BUG_ON(sge_count > RPCSVC_MAXPAGES); dprintk("svcrdma: RDMA_WRITE rmr=%x, to=%llx, xdr_off=%d, " "write_len=%d, xdr_sge=%p, sge_count=%d\n", rmr, (unsigned long long)to, xdr_off, diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index f09444c451b..16fd3f6718f 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -54,7 +54,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, int flags); static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt); static void svc_rdma_release_rqst(struct svc_rqst *); -static void rdma_destroy_xprt(struct svcxprt_rdma *xprt); static void dto_tasklet_func(unsigned long data); static void svc_rdma_detach(struct svc_xprt *xprt); static void svc_rdma_free(struct svc_xprt *xprt); @@ -247,6 +246,7 @@ static void dto_tasklet_func(unsigned long data) sq_cq_reap(xprt); } + svc_xprt_put(&xprt->sc_xprt); spin_lock_irqsave(&dto_lock, flags); } spin_unlock_irqrestore(&dto_lock, flags); @@ -275,8 +275,10 @@ static void rq_comp_handler(struct ib_cq *cq, void *cq_context) * add it */ spin_lock_irqsave(&dto_lock, flags); - if (list_empty(&xprt->sc_dto_q)) + if (list_empty(&xprt->sc_dto_q)) { + svc_xprt_get(&xprt->sc_xprt); list_add_tail(&xprt->sc_dto_q, &dto_xprt_q); + } spin_unlock_irqrestore(&dto_lock, flags); /* Tasklet does all the work to avoid irqsave locks. */ @@ -386,8 +388,10 @@ static void sq_comp_handler(struct ib_cq *cq, void *cq_context) * add it */ spin_lock_irqsave(&dto_lock, flags); - if (list_empty(&xprt->sc_dto_q)) + if (list_empty(&xprt->sc_dto_q)) { + svc_xprt_get(&xprt->sc_xprt); list_add_tail(&xprt->sc_dto_q, &dto_xprt_q); + } spin_unlock_irqrestore(&dto_lock, flags); /* Tasklet does all the work to avoid irqsave locks. */ @@ -611,6 +615,7 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id, switch (event->event) { case RDMA_CM_EVENT_ESTABLISHED: /* Accept complete */ + svc_xprt_get(xprt); dprintk("svcrdma: Connection completed on DTO xprt=%p, " "cm_id=%p\n", xprt, cma_id); clear_bit(RDMAXPRT_CONN_PENDING, &rdma->sc_flags); @@ -661,15 +666,15 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, listen_id = rdma_create_id(rdma_listen_handler, cma_xprt, RDMA_PS_TCP); if (IS_ERR(listen_id)) { - rdma_destroy_xprt(cma_xprt); + svc_xprt_put(&cma_xprt->sc_xprt); dprintk("svcrdma: rdma_create_id failed = %ld\n", PTR_ERR(listen_id)); return (void *)listen_id; } ret = rdma_bind_addr(listen_id, sa); if (ret) { - rdma_destroy_xprt(cma_xprt); rdma_destroy_id(listen_id); + svc_xprt_put(&cma_xprt->sc_xprt); dprintk("svcrdma: rdma_bind_addr failed = %d\n", ret); return ERR_PTR(ret); } @@ -678,8 +683,9 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, ret = rdma_listen(listen_id, RPCRDMA_LISTEN_BACKLOG); if (ret) { rdma_destroy_id(listen_id); - rdma_destroy_xprt(cma_xprt); + svc_xprt_put(&cma_xprt->sc_xprt); dprintk("svcrdma: rdma_listen failed = %d\n", ret); + return ERR_PTR(ret); } /* @@ -820,6 +826,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) newxprt->sc_sq_depth = qp_attr.cap.max_send_wr; newxprt->sc_max_requests = qp_attr.cap.max_recv_wr; } + svc_xprt_get(&newxprt->sc_xprt); newxprt->sc_qp = newxprt->sc_cm_id->qp; /* Register all of physical memory */ @@ -891,8 +898,15 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) errout: dprintk("svcrdma: failure accepting new connection rc=%d.\n", ret); + /* Take a reference in case the DTO handler runs */ + svc_xprt_get(&newxprt->sc_xprt); + if (newxprt->sc_qp && !IS_ERR(newxprt->sc_qp)) { + ib_destroy_qp(newxprt->sc_qp); + svc_xprt_put(&newxprt->sc_xprt); + } rdma_destroy_id(newxprt->sc_cm_id); - rdma_destroy_xprt(newxprt); + /* This call to put will destroy the transport */ + svc_xprt_put(&newxprt->sc_xprt); return NULL; } @@ -919,54 +933,60 @@ static void svc_rdma_release_rqst(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = NULL; } -/* Disable data ready events for this connection */ +/* + * When connected, an svc_xprt has at least three references: + * + * - A reference held by the QP. We still hold that here because this + * code deletes the QP and puts the reference. + * + * - A reference held by the cm_id between the ESTABLISHED and + * DISCONNECTED events. If the remote peer disconnected first, this + * reference could be gone. + * + * - A reference held by the svc_recv code that called this function + * as part of close processing. + * + * At a minimum two references should still be held. + */ static void svc_rdma_detach(struct svc_xprt *xprt) { struct svcxprt_rdma *rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt); - unsigned long flags; - dprintk("svc: svc_rdma_detach(%p)\n", xprt); - /* - * Shutdown the connection. This will ensure we don't get any - * more events from the provider. - */ + + /* Disconnect and flush posted WQE */ rdma_disconnect(rdma->sc_cm_id); - rdma_destroy_id(rdma->sc_cm_id); - /* We may already be on the DTO list */ - spin_lock_irqsave(&dto_lock, flags); - if (!list_empty(&rdma->sc_dto_q)) - list_del_init(&rdma->sc_dto_q); - spin_unlock_irqrestore(&dto_lock, flags); + /* Destroy the QP if present (not a listener) */ + if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) { + ib_destroy_qp(rdma->sc_qp); + svc_xprt_put(xprt); + } + + /* Destroy the CM ID */ + rdma_destroy_id(rdma->sc_cm_id); } static void svc_rdma_free(struct svc_xprt *xprt) { struct svcxprt_rdma *rdma = (struct svcxprt_rdma *)xprt; dprintk("svcrdma: svc_rdma_free(%p)\n", rdma); - rdma_destroy_xprt(rdma); - kfree(rdma); -} - -static void rdma_destroy_xprt(struct svcxprt_rdma *xprt) -{ - if (xprt->sc_qp && !IS_ERR(xprt->sc_qp)) - ib_destroy_qp(xprt->sc_qp); - - if (xprt->sc_sq_cq && !IS_ERR(xprt->sc_sq_cq)) - ib_destroy_cq(xprt->sc_sq_cq); + /* We should only be called from kref_put */ + BUG_ON(atomic_read(&xprt->xpt_ref.refcount) != 0); + if (rdma->sc_sq_cq && !IS_ERR(rdma->sc_sq_cq)) + ib_destroy_cq(rdma->sc_sq_cq); - if (xprt->sc_rq_cq && !IS_ERR(xprt->sc_rq_cq)) - ib_destroy_cq(xprt->sc_rq_cq); + if (rdma->sc_rq_cq && !IS_ERR(rdma->sc_rq_cq)) + ib_destroy_cq(rdma->sc_rq_cq); - if (xprt->sc_phys_mr && !IS_ERR(xprt->sc_phys_mr)) - ib_dereg_mr(xprt->sc_phys_mr); + if (rdma->sc_phys_mr && !IS_ERR(rdma->sc_phys_mr)) + ib_dereg_mr(rdma->sc_phys_mr); - if (xprt->sc_pd && !IS_ERR(xprt->sc_pd)) - ib_dealloc_pd(xprt->sc_pd); + if (rdma->sc_pd && !IS_ERR(rdma->sc_pd)) + ib_dealloc_pd(rdma->sc_pd); - destroy_context_cache(xprt->sc_ctxt_head); + destroy_context_cache(rdma->sc_ctxt_head); + kfree(rdma); } static int svc_rdma_has_wspace(struct svc_xprt *xprt) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 02c522c17de..a564c1a39ec 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -614,7 +614,11 @@ xprt_rdma_free(void *buffer) return; req = container_of(buffer, struct rpcrdma_req, rl_xdr_buf[0]); - r_xprt = container_of(req->rl_buffer, struct rpcrdma_xprt, rx_buf); + if (req->rl_iov.length == 0) { /* see allocate above */ + r_xprt = container_of(((struct rpcrdma_req *) req->rl_buffer)->rl_buffer, + struct rpcrdma_xprt, rx_buf); + } else + r_xprt = container_of(req->rl_buffer, struct rpcrdma_xprt, rx_buf); rep = req->rl_reply; dprintk("RPC: %s: called on 0x%p%s\n", diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 62188c6a06d..75279402ccf 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -84,14 +84,21 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) { + struct xfrm_mode *inner_mode = x->inner_mode; int err; err = x->outer_mode->afinfo->extract_input(x, skb); if (err) return err; - skb->protocol = x->inner_mode->afinfo->eth_proto; - return x->inner_mode->input2(x, skb); + if (x->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); + if (inner_mode == NULL) + return -EAFNOSUPPORT; + } + + skb->protocol = inner_mode->afinfo->eth_proto; + return inner_mode->input2(x, skb); } EXPORT_SYMBOL(xfrm_prepare_input); @@ -101,6 +108,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) __be32 seq; struct xfrm_state *x; xfrm_address_t *daddr; + struct xfrm_mode *inner_mode; unsigned int family; int decaps = 0; int async = 0; @@ -207,7 +215,15 @@ resume: XFRM_MODE_SKB_CB(skb)->protocol = nexthdr; - if (x->inner_mode->input(x, skb)) { + inner_mode = x->inner_mode; + + if (x->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); + if (inner_mode == NULL) + goto drop; + } + + if (inner_mode->input(x, skb)) { XFRM_INC_STATS(LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 569d377932c..2519129c6d2 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -124,7 +124,7 @@ int xfrm_output_resume(struct sk_buff *skb, int err) if (!x) return dst_output(skb); - err = nf_hook(x->inner_mode->afinfo->family, + err = nf_hook(skb->dst->ops->family, NF_INET_POST_ROUTING, skb, NULL, skb->dst->dev, xfrm_output2); if (unlikely(err != 1)) @@ -193,4 +193,20 @@ int xfrm_output(struct sk_buff *skb) return xfrm_output2(skb); } + +int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct xfrm_mode *inner_mode; + if (x->sel.family == AF_UNSPEC) + inner_mode = xfrm_ip2inner_mode(x, + xfrm_af2proto(skb->dst->ops->family)); + else + inner_mode = x->inner_mode; + + if (inner_mode == NULL) + return -EAFNOSUPPORT; + return inner_mode->afinfo->extract_output(x, skb); +} + EXPORT_SYMBOL_GPL(xfrm_output); +EXPORT_SYMBOL_GPL(xfrm_inner_extract_output); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 7ba65e82941..58f1f9347b5 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -388,6 +388,8 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) kfree(x->coaddr); if (x->inner_mode) xfrm_put_mode(x->inner_mode); + if (x->inner_mode_iaf) + xfrm_put_mode(x->inner_mode_iaf); if (x->outer_mode) xfrm_put_mode(x->outer_mode); if (x->type) { @@ -523,6 +525,8 @@ struct xfrm_state *xfrm_state_alloc(void) x->lft.hard_packet_limit = XFRM_INF; x->replay_maxage = 0; x->replay_maxdiff = 0; + x->inner_mode = NULL; + x->inner_mode_iaf = NULL; spin_lock_init(&x->lock); } return x; @@ -796,7 +800,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, selector. */ if (x->km.state == XFRM_STATE_VALID) { - if (!xfrm_selector_match(&x->sel, fl, x->sel.family) || + if ((x->sel.family && !xfrm_selector_match(&x->sel, fl, x->sel.family)) || !security_xfrm_state_pol_flow_match(x, pol, fl)) continue; if (!best || @@ -1944,6 +1948,7 @@ int xfrm_state_mtu(struct xfrm_state *x, int mtu) int xfrm_init_state(struct xfrm_state *x) { struct xfrm_state_afinfo *afinfo; + struct xfrm_mode *inner_mode; int family = x->props.family; int err; @@ -1962,13 +1967,48 @@ int xfrm_init_state(struct xfrm_state *x) goto error; err = -EPROTONOSUPPORT; - x->inner_mode = xfrm_get_mode(x->props.mode, x->sel.family); - if (x->inner_mode == NULL) - goto error; - if (!(x->inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) && - family != x->sel.family) - goto error; + if (x->sel.family != AF_UNSPEC) { + inner_mode = xfrm_get_mode(x->props.mode, x->sel.family); + if (inner_mode == NULL) + goto error; + + if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) && + family != x->sel.family) { + xfrm_put_mode(inner_mode); + goto error; + } + + x->inner_mode = inner_mode; + } else { + struct xfrm_mode *inner_mode_iaf; + + inner_mode = xfrm_get_mode(x->props.mode, AF_INET); + if (inner_mode == NULL) + goto error; + + if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL)) { + xfrm_put_mode(inner_mode); + goto error; + } + + inner_mode_iaf = xfrm_get_mode(x->props.mode, AF_INET6); + if (inner_mode_iaf == NULL) + goto error; + + if (!(inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL)) { + xfrm_put_mode(inner_mode_iaf); + goto error; + } + + if (x->props.family == AF_INET) { + x->inner_mode = inner_mode; + x->inner_mode_iaf = inner_mode_iaf; + } else { + x->inner_mode = inner_mode_iaf; + x->inner_mode_iaf = inner_mode; + } + } x->type = xfrm_get_type(x->id.proto, family); if (x->type == NULL) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index f971ca5645f..5d96f2728dc 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -288,12 +288,9 @@ static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info * memcpy(&x->props.saddr, &p->saddr, sizeof(x->props.saddr)); x->props.flags = p->flags; - /* - * Set inner address family if the KM left it as zero. - * See comment in validate_tmpl. - */ - if (!x->sel.family) + if (x->props.mode == XFRM_MODE_TRANSPORT) x->sel.family = p->family; + } /* |