diff options
author | David Woodhouse <dwmw2@infradead.org> | 2007-10-13 14:43:54 +0100 |
---|---|---|
committer | David Woodhouse <dwmw2@infradead.org> | 2007-10-13 14:43:54 +0100 |
commit | b160292cc216a50fd0cd386b0bda2cd48352c73b (patch) | |
tree | ef07cf98f91353ee4c9ec1e1ca7a2a5d9d4b538a /net | |
parent | b37bde147890c8fea8369a5a4e230dabdea4ebfb (diff) | |
parent | bbf25010f1a6b761914430f5fca081ec8c7accd1 (diff) |
Merge Linux 2.6.23
Diffstat (limited to 'net')
74 files changed, 1028 insertions, 621 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 1583c5ef963..2a546919d6f 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -562,8 +562,6 @@ static int register_vlan_device(struct net_device *real_dev, if (err < 0) goto out_free_newdev; - /* Account for reference in struct vlan_dev_info */ - dev_hold(real_dev); #ifdef VLAN_DEBUG printk(VLAN_DBG "Allocated new device successfully, returning.\n"); #endif diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 4bab322c9f8..328759c32d6 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -116,12 +116,22 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type* ptype, struct net_device *orig_dev) { unsigned char *rawp = NULL; - struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data); + struct vlan_hdr *vhdr; unsigned short vid; struct net_device_stats *stats; unsigned short vlan_TCI; __be16 proto; + if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + return -1; + + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) { + kfree_skb(skb); + return -1; + } + + vhdr = (struct vlan_hdr *)(skb->data); + /* vlan_TCI = ntohs(get_unaligned(&vhdr->h_vlan_TCI)); */ vlan_TCI = ntohs(vhdr->h_vlan_TCI); diff --git a/net/9p/conv.c b/net/9p/conv.c index f2a041cb508..d979d958ea1 100644 --- a/net/9p/conv.c +++ b/net/9p/conv.c @@ -796,6 +796,7 @@ struct p9_fcall *p9_create_twrite_u(u32 fid, u64 offset, u32 count, if (err) { kfree(fc); fc = ERR_PTR(err); + goto error; } if (buf_check_overflow(bufp)) { diff --git a/net/9p/mux.c b/net/9p/mux.c index acb038810f3..5d70558c4c6 100644 --- a/net/9p/mux.c +++ b/net/9p/mux.c @@ -288,9 +288,10 @@ struct p9_conn *p9_conn_create(struct p9_transport *trans, int msize, m->extended = extended; m->trans = trans; m->tagpool = p9_idpool_create(); - if (!m->tagpool) { + if (IS_ERR(m->tagpool)) { + mtmp = ERR_PTR(-ENOMEM); kfree(m); - return ERR_PTR(PTR_ERR(m->tagpool)); + return mtmp; } m->err = 0; @@ -308,8 +309,10 @@ struct p9_conn *p9_conn_create(struct p9_transport *trans, int msize, memset(&m->poll_waddr, 0, sizeof(m->poll_waddr)); m->poll_task = NULL; n = p9_mux_poll_start(m); - if (n) + if (n) { + kfree(m); return ERR_PTR(n); + } n = trans->poll(trans, &m->pt); if (n & POLLIN) { diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 63caa414945..18e3afc964d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -183,6 +183,7 @@ static void hci_init_req(struct hci_dev *hdev, unsigned long opt) { struct sk_buff *skb; __le16 param; + __u8 flt_type; BT_DBG("%s %ld", hdev->name, opt); @@ -233,11 +234,8 @@ static void hci_init_req(struct hci_dev *hdev, unsigned long opt) /* Optional initialization */ /* Clear Event Filters */ - { - struct hci_cp_set_event_flt cp; - cp.flt_type = HCI_FLT_CLEAR_ALL; - hci_send_cmd(hdev, OGF_HOST_CTL, OCF_SET_EVENT_FLT, sizeof(cp), &cp); - } + flt_type = HCI_FLT_CLEAR_ALL; + hci_send_cmd(hdev, OGF_HOST_CTL, OCF_SET_EVENT_FLT, 1, &flt_type); /* Page timeout ~20 secs */ param = cpu_to_le16(0x8000); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 1dae3dfc66a..5ccea5fbd23 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -37,6 +37,7 @@ #include <linux/skbuff.h> #include <linux/workqueue.h> #include <linux/interrupt.h> +#include <linux/compat.h> #include <linux/socket.h> #include <linux/ioctl.h> #include <net/sock.h> @@ -70,15 +71,15 @@ static struct hci_sec_filter hci_sec_filter = { { { 0x0 }, /* OGF_LINK_CTL */ - { 0xbe000006, 0x00000001, 0x000000, 0x00 }, + { 0xbe000006, 0x00000001, 0x00000000, 0x00 }, /* OGF_LINK_POLICY */ - { 0x00005200, 0x00000000, 0x000000, 0x00 }, + { 0x00005200, 0x00000000, 0x00000000, 0x00 }, /* OGF_HOST_CTL */ - { 0xaab00200, 0x2b402aaa, 0x020154, 0x00 }, + { 0xaab00200, 0x2b402aaa, 0x05220154, 0x00 }, /* OGF_INFO_PARAM */ - { 0x000002be, 0x00000000, 0x000000, 0x00 }, + { 0x000002be, 0x00000000, 0x00000000, 0x00 }, /* OGF_STATUS_PARAM */ - { 0x000000ea, 0x00000000, 0x000000, 0x00 } + { 0x000000ea, 0x00000000, 0x00000000, 0x00 } } }; @@ -342,9 +343,24 @@ static inline void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, struct sk_ if (mask & HCI_CMSG_TSTAMP) { struct timeval tv; + void *data; + int len; skb_get_timestamp(skb, &tv); - put_cmsg(msg, SOL_HCI, HCI_CMSG_TSTAMP, sizeof(tv), &tv); + + data = &tv; + len = sizeof(tv); +#ifdef CONFIG_COMPAT + if (msg->msg_flags & MSG_CMSG_COMPAT) { + struct compat_timeval ctv; + ctv.tv_sec = tv.tv_sec; + ctv.tv_usec = tv.tv_usec; + data = &ctv; + len = sizeof(ctv); + } +#endif + + put_cmsg(msg, SOL_HCI, HCI_CMSG_TSTAMP, len, data); } } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 0eded176ce9..99292e8e1d0 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -41,11 +41,11 @@ int br_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb_pull(skb, ETH_HLEN); if (dest[0] & 1) - br_flood_deliver(br, skb, 0); + br_flood_deliver(br, skb); else if ((dst = __br_fdb_get(br, dest)) != NULL) br_deliver(dst->dst, skb); else - br_flood_deliver(br, skb, 0); + br_flood_deliver(br, skb); return 0; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 69b70977f00..eb57502bb26 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -384,6 +384,11 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, if (hold_time(br) == 0) return; + /* ignore packets unless we are using this port */ + if (!(source->state == BR_STATE_LEARNING || + source->state == BR_STATE_FORWARDING)) + return; + fdb = fdb_find(head, addr); if (likely(fdb)) { /* attempt to update an entry for a local interface */ diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index ada7f495445..bdd7c35c3c7 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -100,24 +100,13 @@ void br_forward(const struct net_bridge_port *to, struct sk_buff *skb) } /* called under bridge lock */ -static void br_flood(struct net_bridge *br, struct sk_buff *skb, int clone, +static void br_flood(struct net_bridge *br, struct sk_buff *skb, void (*__packet_hook)(const struct net_bridge_port *p, struct sk_buff *skb)) { struct net_bridge_port *p; struct net_bridge_port *prev; - if (clone) { - struct sk_buff *skb2; - - if ((skb2 = skb_clone(skb, GFP_ATOMIC)) == NULL) { - br->statistics.tx_dropped++; - return; - } - - skb = skb2; - } - prev = NULL; list_for_each_entry_rcu(p, &br->port_list, list) { @@ -148,13 +137,13 @@ static void br_flood(struct net_bridge *br, struct sk_buff *skb, int clone, /* called with rcu_read_lock */ -void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, int clone) +void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb) { - br_flood(br, skb, clone, __br_deliver); + br_flood(br, skb, __br_deliver); } /* called under bridge lock */ -void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, int clone) +void br_flood_forward(struct net_bridge *br, struct sk_buff *skb) { - br_flood(br, skb, clone, __br_forward); + br_flood(br, skb, __br_forward); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 749f0e8f541..9272f12f664 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -33,17 +33,17 @@ */ static int port_cost(struct net_device *dev) { - if (dev->ethtool_ops->get_settings) { - struct ethtool_cmd ecmd = { ETHTOOL_GSET }; - int err = dev->ethtool_ops->get_settings(dev, &ecmd); - if (!err) { + if (dev->ethtool_ops && dev->ethtool_ops->get_settings) { + struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET, }; + + if (!dev->ethtool_ops->get_settings(dev, &ecmd)) { switch(ecmd.speed) { - case SPEED_100: - return 19; - case SPEED_1000: - return 4; case SPEED_10000: return 2; + case SPEED_1000: + return 4; + case SPEED_100: + return 19; case SPEED_10: return 100; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 5c18595b761..3a8a015c92e 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -43,7 +43,7 @@ int br_handle_frame_finish(struct sk_buff *skb) struct net_bridge_port *p = rcu_dereference(skb->dev->br_port); struct net_bridge *br; struct net_bridge_fdb_entry *dst; - int passedup = 0; + struct sk_buff *skb2; if (!p || p->state == BR_STATE_DISABLED) goto drop; @@ -55,39 +55,35 @@ int br_handle_frame_finish(struct sk_buff *skb) if (p->state == BR_STATE_LEARNING) goto drop; - if (br->dev->flags & IFF_PROMISC) { - struct sk_buff *skb2; + /* The packet skb2 goes to the local host (NULL to skip). */ + skb2 = NULL; - skb2 = skb_clone(skb, GFP_ATOMIC); - if (skb2 != NULL) { - passedup = 1; - br_pass_frame_up(br, skb2); - } - } + if (br->dev->flags & IFF_PROMISC) + skb2 = skb; + + dst = NULL; if (is_multicast_ether_addr(dest)) { br->statistics.multicast++; - br_flood_forward(br, skb, !passedup); - if (!passedup) - br_pass_frame_up(br, skb); - goto out; + skb2 = skb; + } else if ((dst = __br_fdb_get(br, dest)) && dst->is_local) { + skb2 = skb; + /* Do not forward the packet since it's local. */ + skb = NULL; } - dst = __br_fdb_get(br, dest); - if (dst != NULL && dst->is_local) { - if (!passedup) - br_pass_frame_up(br, skb); - else - kfree_skb(skb); - goto out; - } + if (skb2 == skb) + skb2 = skb_clone(skb, GFP_ATOMIC); - if (dst != NULL) { - br_forward(dst->dst, skb); - goto out; - } + if (skb2) + br_pass_frame_up(br, skb2); - br_flood_forward(br, skb, 0); + if (skb) { + if (dst) + br_forward(dst->dst, skb); + else + br_flood_forward(br, skb); + } out: return 0; @@ -101,9 +97,8 @@ static int br_handle_local_finish(struct sk_buff *skb) { struct net_bridge_port *p = rcu_dereference(skb->dev->br_port); - if (p && p->state != BR_STATE_DISABLED) + if (p) br_fdb_update(p->br, p, eth_hdr(skb)->h_source); - return 0; /* process further */ } diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index fa779874b9d..fc13130035e 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -183,7 +183,7 @@ int nf_bridge_copy_header(struct sk_buff *skb) int err; int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb); - err = skb_cow(skb, header_size); + err = skb_cow_head(skb, header_size); if (err) return err; @@ -509,8 +509,14 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, int (*okfn)(struct sk_buff *)) { struct iphdr *iph; - __u32 len; struct sk_buff *skb = *pskb; + __u32 len = nf_bridge_encap_header_len(skb); + + if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + return NF_STOLEN; + + if (unlikely(!pskb_may_pull(skb, len))) + goto out; if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) { @@ -518,8 +524,6 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, if (!brnf_call_ip6tables) return NF_ACCEPT; #endif - if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL) - goto out; nf_bridge_pull_encap_header_rcsum(skb); return br_nf_pre_routing_ipv6(hook, skb, in, out, okfn); } @@ -532,8 +536,6 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, !IS_PPPOE_IP(skb)) return NF_ACCEPT; - if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL) - goto out; nf_bridge_pull_encap_header_rcsum(skb); if (!pskb_may_pull(skb, sizeof(struct iphdr))) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 21bf3a9a03f..e6dc6f52990 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -170,12 +170,8 @@ extern int br_dev_queue_push_xmit(struct sk_buff *skb); extern void br_forward(const struct net_bridge_port *to, struct sk_buff *skb); extern int br_forward_finish(struct sk_buff *skb); -extern void br_flood_deliver(struct net_bridge *br, - struct sk_buff *skb, - int clone); -extern void br_flood_forward(struct net_bridge *br, - struct sk_buff *skb, - int clone); +extern void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb); +extern void br_flood_forward(struct net_bridge *br, struct sk_buff *skb); /* br_if.c */ extern void br_port_carrier_check(struct net_bridge_port *p); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 4169a2a89a3..6018d0e5193 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1513,6 +1513,7 @@ static struct nf_sockopt_ops ebt_sockopts = .get_optmin = EBT_BASE_CTL, .get_optmax = EBT_SO_GET_MAX + 1, .get = do_ebt_get_ctl, + .owner = THIS_MODULE, }; static int __init ebtables_init(void) diff --git a/net/core/datagram.c b/net/core/datagram.c index cb056f47612..029b93e246b 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -450,6 +450,9 @@ int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, __wsum csum; int chunk = skb->len - hlen; + if (!chunk) + return 0; + /* Skip filled elements. * Pretty silly, look at memcpy_toiovec, though 8) */ diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c index 99aece1aecc..20330c57261 100644 --- a/net/core/dev_mcast.c +++ b/net/core/dev_mcast.c @@ -116,11 +116,13 @@ int dev_mc_add(struct net_device *dev, void *addr, int alen, int glbl) */ int dev_mc_sync(struct net_device *to, struct net_device *from) { - struct dev_addr_list *da; + struct dev_addr_list *da, *next; int err = 0; netif_tx_lock_bh(to); - for (da = from->mc_list; da != NULL; da = da->next) { + da = from->mc_list; + while (da != NULL) { + next = da->next; if (!da->da_synced) { err = __dev_addr_add(&to->mc_list, &to->mc_count, da->da_addr, da->da_addrlen, 0); @@ -134,6 +136,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from) __dev_addr_delete(&from->mc_list, &from->mc_count, da->da_addr, da->da_addrlen, 0); } + da = next; } if (!err) __dev_set_rx_mode(to); @@ -156,12 +159,14 @@ EXPORT_SYMBOL(dev_mc_sync); */ void dev_mc_unsync(struct net_device *to, struct net_device *from) { - struct dev_addr_list *da; + struct dev_addr_list *da, *next; netif_tx_lock_bh(from); netif_tx_lock_bh(to); - for (da = from->mc_list; da != NULL; da = da->next) { + da = from->mc_list; + while (da != NULL) { + next = da->next; if (!da->da_synced) continue; __dev_addr_delete(&to->mc_list, &to->mc_count, @@ -169,6 +174,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) 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); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index ca2a1533138..f7de8f24d8d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -33,6 +33,7 @@ #include <linux/rtnetlink.h> #include <linux/random.h> #include <linux/string.h> +#include <linux/log2.h> #define NEIGH_DEBUG 1 @@ -311,7 +312,7 @@ static void neigh_hash_grow(struct neigh_table *tbl, unsigned long new_entries) NEIGH_CACHE_STAT_INC(tbl, hash_grows); - BUG_ON(new_entries & (new_entries - 1)); + BUG_ON(!is_power_of_2(new_entries)); new_hash = neigh_hash_alloc(new_entries); if (!new_hash) return; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 7bae576ac11..803d0c8826a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -111,6 +111,9 @@ * * 802.1Q/Q-in-Q support by Francesco Fondelli (FF) <francesco.fondelli@gmail.com> * + * Fixed src_mac command to set source mac of packet to value specified in + * command by Adit Ranadive <adit.262@gmail.com> + * */ #include <linux/sys.h> #include <linux/types.h> @@ -380,7 +383,6 @@ struct pktgen_thread { /* Field for thread to receive "posted" events terminate, stop ifs etc. */ u32 control; - int pid; int cpu; wait_queue_head_t queue; @@ -1452,8 +1454,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "src_mac")) { char *v = valstr; + unsigned char old_smac[ETH_ALEN]; unsigned char *m = pkt_dev->src_mac; + memcpy(old_smac, pkt_dev->src_mac, ETH_ALEN); + len = strn_len(&user_buffer[i], sizeof(valstr) - 1); if (len < 0) { return len; @@ -1482,6 +1487,10 @@ static ssize_t pktgen_if_write(struct file *file, } } + /* Set up Src MAC */ + if (compare_ether_addr(old_smac, pkt_dev->src_mac)) + memcpy(&(pkt_dev->hh[6]), pkt_dev->src_mac, ETH_ALEN); + sprintf(pg_result, "OK: srcmac"); return count; } @@ -3331,8 +3340,9 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) } if ((netif_queue_stopped(odev) || - netif_subqueue_stopped(odev, pkt_dev->skb->queue_mapping)) || - need_resched()) { + (pkt_dev->skb && + netif_subqueue_stopped(odev, pkt_dev->skb->queue_mapping))) || + need_resched()) { idle_start = getCurUs(); if (!netif_running(odev)) { @@ -3462,8 +3472,6 @@ static int pktgen_thread_worker(void *arg) init_waitqueue_head(&t->queue); - t->pid = current->pid; - pr_debug("pktgen: starting pktgen/%d: pid=%d\n", cpu, current->pid); max_before_softirq = t->max_before_softirq; diff --git a/net/core/sock.c b/net/core/sock.c index cfed7d42c48..190de61cd64 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -362,6 +362,61 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) } EXPORT_SYMBOL(sk_dst_check); +static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen) +{ + int ret = -ENOPROTOOPT; +#ifdef CONFIG_NETDEVICES + char devname[IFNAMSIZ]; + int index; + + /* Sorry... */ + ret = -EPERM; + if (!capable(CAP_NET_RAW)) + goto out; + + ret = -EINVAL; + if (optlen < 0) + goto out; + + /* Bind this socket to a particular device like "eth0", + * as specified in the passed interface name. If the + * name is "" or the option length is zero the socket + * is not bound. + */ + if (optlen > IFNAMSIZ - 1) + optlen = IFNAMSIZ - 1; + memset(devname, 0, sizeof(devname)); + + ret = -EFAULT; + if (copy_from_user(devname, optval, optlen)) + goto out; + + if (devname[0] == '\0') { + index = 0; + } else { + struct net_device *dev = dev_get_by_name(devname); + + ret = -ENODEV; + if (!dev) + goto out; + + index = dev->ifindex; + dev_put(dev); + } + + lock_sock(sk); + sk->sk_bound_dev_if = index; + sk_dst_reset(sk); + release_sock(sk); + + ret = 0; + +out: +#endif + + return ret; +} + /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. @@ -390,6 +445,9 @@ int sock_setsockopt(struct socket *sock, int level, int optname, } #endif + if (optname == SO_BINDTODEVICE) + return sock_bindtodevice(sk, optval, optlen); + if (optlen < sizeof(int)) return -EINVAL; @@ -578,54 +636,6 @@ set_rcvbuf: ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen); break; -#ifdef CONFIG_NETDEVICES - case SO_BINDTODEVICE: - { - char devname[IFNAMSIZ]; - - /* Sorry... */ - if (!capable(CAP_NET_RAW)) { - ret = -EPERM; - break; - } - - /* Bind this socket to a particular device like "eth0", - * as specified in the passed interface name. If the - * name is "" or the option length is zero the socket - * is not bound. - */ - - if (!valbool) { - sk->sk_bound_dev_if = 0; - } else { - if (optlen > IFNAMSIZ - 1) - optlen = IFNAMSIZ - 1; - memset(devname, 0, sizeof(devname)); - if (copy_from_user(devname, optval, optlen)) { - ret = -EFAULT; - break; - } - - /* Remove any cached route for this socket. */ - sk_dst_reset(sk); - - if (devname[0] == '\0') { - sk->sk_bound_dev_if = 0; - } else { - struct net_device *dev = dev_get_by_name(devname); - if (!dev) { - ret = -ENODEV; - break; - } - sk->sk_bound_dev_if = dev->ifindex; - dev_put(dev); - } - } - break; - } -#endif - - case SO_ATTACH_FILTER: ret = -EINVAL; if (optlen == sizeof(struct sock_fprog)) { diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index fa6604fcf0e..8def68209ed 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -814,7 +814,7 @@ static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) for (ifa = dn_db->ifa_list, dn_idx = 0; ifa; ifa = ifa->ifa_next, dn_idx++) { if (dn_idx < skip_naddr) - goto cont; + continue; if (dn_nl_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWADDR, diff --git a/net/ieee80211/ieee80211_rx.c b/net/ieee80211/ieee80211_rx.c index f2de2e48b02..6284c99b456 100644 --- a/net/ieee80211/ieee80211_rx.c +++ b/net/ieee80211/ieee80211_rx.c @@ -366,6 +366,12 @@ int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb, frag = WLAN_GET_SEQ_FRAG(sc); hdrlen = ieee80211_get_hdrlen(fc); + if (skb->len < hdrlen) { + printk(KERN_INFO "%s: invalid SKB length %d\n", + dev->name, skb->len); + goto rx_dropped; + } + /* Put this code here so that we avoid duplicating it in all * Rx paths. - Jean II */ #ifdef CONFIG_WIRELESS_EXT diff --git a/net/ieee80211/softmac/ieee80211softmac_assoc.c b/net/ieee80211/softmac/ieee80211softmac_assoc.c index afb6c6698b2..e475f2e1be1 100644 --- a/net/ieee80211/softmac/ieee80211softmac_assoc.c +++ b/net/ieee80211/softmac/ieee80211softmac_assoc.c @@ -273,8 +273,6 @@ ieee80211softmac_assoc_work(struct work_struct *work) ieee80211softmac_notify(mac->dev, IEEE80211SOFTMAC_EVENT_SCAN_FINISHED, ieee80211softmac_assoc_notify_scan, NULL); if (ieee80211softmac_start_scan(mac)) { dprintk(KERN_INFO PFX "Associate: failed to initiate scan. Is device up?\n"); - mac->associnfo.associating = 0; - mac->associnfo.associated = 0; } goto out; } else { diff --git a/net/ieee80211/softmac/ieee80211softmac_wx.c b/net/ieee80211/softmac/ieee80211softmac_wx.c index d054e9224b3..5742dc803b7 100644 --- a/net/ieee80211/softmac/ieee80211softmac_wx.c +++ b/net/ieee80211/softmac/ieee80211softmac_wx.c @@ -70,44 +70,30 @@ ieee80211softmac_wx_set_essid(struct net_device *net_dev, char *extra) { struct ieee80211softmac_device *sm = ieee80211_priv(net_dev); - struct ieee80211softmac_network *n; struct ieee80211softmac_auth_queue_item *authptr; int length = 0; check_assoc_again: mutex_lock(&sm->associnfo.mutex); - /* Check if we're already associating to this or another network - * If it's another network, cancel and start over with our new network - * If it's our network, ignore the change, we're already doing it! - */ if((sm->associnfo.associating || sm->associnfo.associated) && (data->essid.flags && data->essid.length)) { - /* Get the associating network */ - n = ieee80211softmac_get_network_by_bssid(sm, sm->associnfo.bssid); - if(n && n->essid.len == data->essid.length && - !memcmp(n->essid.data, extra, n->essid.len)) { - dprintk(KERN_INFO PFX "Already associating or associated to "MAC_FMT"\n", - MAC_ARG(sm->associnfo.bssid)); - goto out; - } else { - dprintk(KERN_INFO PFX "Canceling existing associate request!\n"); - /* Cancel assoc work */ - cancel_delayed_work(&sm->associnfo.work); - /* We don't have to do this, but it's a little cleaner */ - list_for_each_entry(authptr, &sm->auth_queue, list) - cancel_delayed_work(&authptr->work); - sm->associnfo.bssvalid = 0; - sm->associnfo.bssfixed = 0; - sm->associnfo.associating = 0; - sm->associnfo.associated = 0; - /* We must unlock to avoid deadlocks with the assoc workqueue - * on the associnfo.mutex */ - mutex_unlock(&sm->associnfo.mutex); - flush_scheduled_work(); - /* Avoid race! Check assoc status again. Maybe someone started an - * association while we flushed. */ - goto check_assoc_again; - } + dprintk(KERN_INFO PFX "Canceling existing associate request!\n"); + /* Cancel assoc work */ + cancel_delayed_work(&sm->associnfo.work); + /* We don't have to do this, but it's a little cleaner */ + list_for_each_entry(authptr, &sm->auth_queue, list) + cancel_delayed_work(&authptr->work); + sm->associnfo.bssvalid = 0; + sm->associnfo.bssfixed = 0; + sm->associnfo.associating = 0; + sm->associnfo.associated = 0; + /* We must unlock to avoid deadlocks with the assoc workqueue + * on the associnfo.mutex */ + mutex_unlock(&sm->associnfo.mutex); + flush_scheduled_work(); + /* Avoid race! Check assoc status again. Maybe someone started an + * association while we flushed. */ + goto check_assoc_again; } sm->associnfo.static_essid = 0; @@ -128,7 +114,7 @@ check_assoc_again: sm->associnfo.associating = 1; /* queue lower level code to do work (if necessary) */ schedule_delayed_work(&sm->associnfo.work, 0); -out: + mutex_unlock(&sm->associnfo.mutex); return 0; @@ -153,13 +139,13 @@ ieee80211softmac_wx_get_essid(struct net_device *net_dev, data->essid.length = sm->associnfo.req_essid.len; data->essid.flags = 1; /* active */ memcpy(extra, sm->associnfo.req_essid.data, sm->associnfo.req_essid.len); - } - + dprintk(KERN_INFO PFX "Getting essid from req_essid\n"); + } else if (sm->associnfo.associated || sm->associnfo.associating) { /* If we're associating/associated, return that */ - if (sm->associnfo.associated || sm->associnfo.associating) { data->essid.length = sm->associnfo.associate_essid.len; data->essid.flags = 1; /* active */ memcpy(extra, sm->associnfo.associate_essid.data, sm->associnfo.associate_essid.len); + dprintk(KERN_INFO PFX "Getting essid from associate_essid\n"); } mutex_unlock(&sm->associnfo.mutex); diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 7a23e59c374..39f6211f149 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -46,7 +46,7 @@ static int ip_clear_mutable_options(struct iphdr *iph, __be32 *daddr) memcpy(daddr, optptr+optlen-4, 4); /* Fall through */ default: - memset(optptr+2, 0, optlen-2); + memset(optptr, 0, optlen); } l -= optlen; optptr += optlen; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 5b77bdaa57d..5dbe5803b7d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1193,7 +1193,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) for (ifa = in_dev->ifa_list, ip_idx = 0; ifa; ifa = ifa->ifa_next, ip_idx++) { if (ip_idx < s_ip_idx) - goto cont; + continue; if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWADDR, NLM_F_MULTI) <= 0) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index dbeacd8b0f9..def007ec1d6 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -836,12 +836,16 @@ static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return inet_diag_get_exact(skb, nlh); } +static DEFINE_MUTEX(inet_diag_mutex); + static void inet_diag_rcv(struct sock *sk, int len) { unsigned int qlen = 0; do { + mutex_lock(&inet_diag_mutex); netlink_run_queue(sk, &qlen, &inet_diag_rcv_msg); + mutex_unlock(&inet_diag_mutex); } while (qlen); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 4d544573f48..6b420aedcdc 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -625,6 +625,10 @@ static int do_ip_setsockopt(struct sock *sk, int level, { struct ip_mreqn mreq; + err = -EPROTO; + if (inet_sk(sk)->is_icsk) + break; + if (optlen < sizeof(struct ip_mreq)) goto e_inval; err = -EFAULT; diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c index 902fd578aa3..f656d41d8d4 100644 --- a/net/ipv4/ipvs/ip_vs_ctl.c +++ b/net/ipv4/ipvs/ip_vs_ctl.c @@ -2339,6 +2339,7 @@ static struct nf_sockopt_ops ip_vs_sockopts = { .get_optmin = IP_VS_BASE_CTL, .get_optmax = IP_VS_SO_GET_MAX+1, .get = do_ip_vs_get_ctl, + .owner = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index d1149aba935..29114a9ccd1 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1161,6 +1161,7 @@ static struct nf_sockopt_ops arpt_sockopts = { .get_optmin = ARPT_BASE_CTL, .get_optmax = ARPT_SO_GET_MAX+1, .get = do_arpt_get_ctl, + .owner = THIS_MODULE, }; static int __init arp_tables_init(void) diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index e1b402c6b85..6486894f450 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -2296,6 +2296,7 @@ static struct nf_sockopt_ops ipt_sockopts = { #ifdef CONFIG_COMPAT .compat_get = compat_do_ipt_get_ctl, #endif + .owner = THIS_MODULE, }; static struct xt_match icmp_matchstruct __read_mostly = { diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index d9b5177989c..f813e02aab3 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -87,14 +87,10 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, if (iph == NULL) return -NF_DROP; - /* Never happen */ - if (iph->frag_off & htons(IP_OFFSET)) { - if (net_ratelimit()) { - printk(KERN_ERR "ipv4_get_l4proto: Frag of proto %u\n", - iph->protocol); - } + /* Conntrack defragments packets, we might still see fragments + * inside ICMP packets though. */ + if (iph->frag_off & htons(IP_OFFSET)) return -NF_DROP; - } *dataoff = nhoff + (iph->ihl << 2); *protonum = iph->protocol; @@ -403,6 +399,7 @@ static struct nf_sockopt_ops so_getorigdst = { .get_optmin = SO_ORIGINAL_DST, .get_optmax = SO_ORIGINAL_DST+1, .get = &getorigdst, + .owner = THIS_MODULE, }; struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f030435e0eb..f893e90061e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -555,6 +555,16 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) tcp_grow_window(sk, skb); } +static u32 tcp_rto_min(struct sock *sk) +{ + struct dst_entry *dst = __sk_dst_get(sk); + u32 rto_min = TCP_RTO_MIN; + + if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) + rto_min = dst->metrics[RTAX_RTO_MIN-1]; + return rto_min; +} + /* Called to compute a smoothed rtt estimate. The data fed to this * routine either comes from timestamps, or from segments that were * known _not_ to have been retransmitted [see Karn/Partridge @@ -616,13 +626,13 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) if (tp->mdev_max < tp->rttvar) tp->rttvar -= (tp->rttvar-tp->mdev_max)>>2; tp->rtt_seq = tp->snd_nxt; - tp->mdev_max = TCP_RTO_MIN; + tp->mdev_max = tcp_rto_min(sk); } } else { /* no previous measure. */ tp->srtt = m<<3; /* take the measured time to be rtt */ tp->mdev = m<<1; /* make sure rto = 3*rtt */ - tp->mdev_max = tp->rttvar = max(tp->mdev, TCP_RTO_MIN); + tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); tp->rtt_seq = tp->snd_nxt; } } @@ -755,7 +765,15 @@ void tcp_update_metrics(struct sock *sk) } } -/* Numbers are taken from RFC2414. */ +/* Numbers are taken from RFC3390. + * + * John Heffner states: + * + * The RFC specifies a window of no more than 4380 bytes + * unless 2*MSS > 4380. Reading the pseudocode in the RFC + * is a bit misleading because they use a clamp at 4380 bytes + * rather than use a multiplier in the relevant range. + */ __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst) { __u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0); @@ -2402,6 +2420,9 @@ static int tcp_tso_acked(struct sock *sk, struct sk_buff *skb, __u32 dval = min(tp->fackets_out, packets_acked); tp->fackets_out -= dval; } + /* hint's skb might be NULL but we don't need to care */ + tp->fastpath_cnt_hint -= min_t(u32, packets_acked, + tp->fastpath_cnt_hint); tp->packets_out -= packets_acked; BUG_ON(tcp_skb_pcount(skb) == 0); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9c94627c8c7..e089a978e12 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -833,8 +833,7 @@ static struct tcp_md5sig_key * return NULL; for (i = 0; i < tp->md5sig_info->entries4; i++) { if (tp->md5sig_info->keys4[i].addr == addr) - return (struct tcp_md5sig_key *) - &tp->md5sig_info->keys4[i]; + return &tp->md5sig_info->keys4[i].base; } return NULL; } @@ -865,9 +864,9 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, key = (struct tcp4_md5sig_key *)tcp_v4_md5_do_lookup(sk, addr); if (key) { /* Pre-existing entry - just update that one. */ - kfree(key->key); - key->key = newkey; - key->keylen = newkeylen; + kfree(key->base.key); + key->base.key = newkey; + key->base.keylen = newkeylen; } else { struct tcp_md5sig_info *md5sig; @@ -906,9 +905,9 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, md5sig->alloced4++; } md5sig->entries4++; - md5sig->keys4[md5sig->entries4 - 1].addr = addr; - md5sig->keys4[md5sig->entries4 - 1].key = newkey; - md5sig->keys4[md5sig->entries4 - 1].keylen = newkeylen; + md5sig->keys4[md5sig->entries4 - 1].addr = addr; + md5sig->keys4[md5sig->entries4 - 1].base.key = newkey; + md5sig->keys4[md5sig->entries4 - 1].base.keylen = newkeylen; } return 0; } @@ -930,7 +929,7 @@ int tcp_v4_md5_do_del(struct sock *sk, __be32 addr) for (i = 0; i < tp->md5sig_info->entries4; i++) { if (tp->md5sig_info->keys4[i].addr == addr) { /* Free the key */ - kfree(tp->md5sig_info->keys4[i].key); + kfree(tp->md5sig_info->keys4[i].base.key); tp->md5sig_info->entries4--; if (tp->md5sig_info->entries4 == 0) { @@ -964,7 +963,7 @@ static void tcp_v4_clear_md5_list(struct sock *sk) if (tp->md5sig_info->entries4) { int i; for (i = 0; i < tp->md5sig_info->entries4; i++) - kfree(tp->md5sig_info->keys4[i].key); + kfree(tp->md5sig_info->keys4[i].base.key); tp->md5sig_info->entries4 = 0; tcp_free_md5sig_pool(); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 28355350fb6..69d4bd10f9c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -505,6 +505,8 @@ send: out: up->len = 0; up->pending = 0; + if (!err) + UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, up->pcflag); return err; } @@ -693,10 +695,8 @@ out: ip_rt_put(rt); if (free) kfree(ipc.opt); - if (!err) { - UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite); + if (!err) return len; - } /* * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting * ENOBUFS might not be good (it's not tunable per se), but otherwise diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 91ef3be5aba..45b4c82148a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1021,7 +1021,7 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev, hiscore.rule++; } if (ipv6_saddr_preferred(score.addr_type) || - (((ifa_result->flags & + (((ifa->flags & (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC)) == 0))) { score.attrs |= IPV6_SADDR_SCORE_PREFERRED; if (!(hiscore.attrs & IPV6_SADDR_SCORE_PREFERRED)) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5dead399fe6..26de3c0ea31 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1427,8 +1427,9 @@ void ip6_flush_pending_frames(struct sock *sk) struct sk_buff *skb; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) { - IP6_INC_STATS(ip6_dst_idev(skb->dst), - IPSTATS_MIB_OUTDISCARDS); + if (skb->dst) + IP6_INC_STATS(ip6_dst_idev(skb->dst), + IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 761a910f4f9..6b038aa72e8 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -554,6 +554,10 @@ done: { struct ipv6_mreq mreq; + retv = -EPROTO; + if (inet_sk(sk)->is_icsk) + break; + retv = -EFAULT; if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq))) break; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0358e6066a4..5b596659177 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -736,7 +736,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) * so fail our DAD process */ addrconf_dad_failure(ifp); - goto out; + return; } else { /* * This is not a dad solicitation. @@ -1268,9 +1268,10 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) if (ipv6_addr_equal(dest, target)) { on_link = 1; - } else if (!(ipv6_addr_type(target) & IPV6_ADDR_LINKLOCAL)) { + } else if (ipv6_addr_type(target) != + (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: target address is not link-local.\n"); + "ICMPv6 Redirect: target address is not link-local unicast.\n"); return; } @@ -1344,9 +1345,9 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, } if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) && - !(ipv6_addr_type(target) & IPV6_ADDR_LINKLOCAL)) { + ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { ND_PRINTK2(KERN_WARNING - "ICMPv6 Redirect: target address is not link-local.\n"); + "ICMPv6 Redirect: target address is not link-local unicast.\n"); return; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index aeda617246b..cd9df02bb85 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1462,6 +1462,7 @@ static struct nf_sockopt_ops ip6t_sockopts = { .get_optmin = IP6T_BASE_CTL, .get_optmax = IP6T_SO_GET_MAX+1, .get = do_ip6t_get_ctl, + .owner = THIS_MODULE, }; static struct xt_match icmp6_matchstruct __read_mostly = { diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e27383d855d..77167afa345 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -882,11 +882,10 @@ back_from_confirm: ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) err = rawv6_push_pending_frames(sk, &fl, rp); + release_sock(sk); } done: dst_release(dst); - if (!inet->hdrincl) - release_sock(sk); out: fl6_sock_release(flowlabel); return err<0?err:len; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0f7defb482e..3e06799b37a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -539,7 +539,7 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, for (i = 0; i < tp->md5sig_info->entries6; i++) { if (ipv6_addr_cmp(&tp->md5sig_info->keys6[i].addr, addr) == 0) - return (struct tcp_md5sig_key *)&tp->md5sig_info->keys6[i]; + return &tp->md5sig_info->keys6[i].base; } return NULL; } @@ -567,9 +567,9 @@ static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer, key = (struct tcp6_md5sig_key*) tcp_v6_md5_do_lookup(sk, peer); if (key) { /* modify existing entry - just update that one */ - kfree(key->key); - key->key = newkey; - key->keylen = newkeylen; + kfree(key->base.key); + key->base.key = newkey; + key->base.keylen = newkeylen; } else { /* reallocate new list if current one is full. */ if (!tp->md5sig_info) { @@ -603,8 +603,8 @@ static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer, ipv6_addr_copy(&tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr, peer); - tp->md5sig_info->keys6[tp->md5sig_info->entries6].key = newkey; - tp->md5sig_info->keys6[tp->md5sig_info->entries6].keylen = newkeylen; + tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.key = newkey; + tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.keylen = newkeylen; tp->md5sig_info->entries6++; } @@ -626,7 +626,7 @@ static int tcp_v6_md5_do_del(struct sock *sk, struct in6_addr *peer) for (i = 0; i < tp->md5sig_info->entries6; i++) { if (ipv6_addr_cmp(&tp->md5sig_info->keys6[i].addr, peer) == 0) { /* Free the key */ - kfree(tp->md5sig_info->keys6[i].key); + kfree(tp->md5sig_info->keys6[i].base.key); tp->md5sig_info->entries6--; if (tp->md5sig_info->entries6 == 0) { @@ -657,7 +657,7 @@ static void tcp_v6_clear_md5_list (struct sock *sk) if (tp->md5sig_info->entries6) { for (i = 0; i < tp->md5sig_info->entries6; i++) - kfree(tp->md5sig_info->keys6[i].key); + kfree(tp->md5sig_info->keys6[i].base.key); tp->md5sig_info->entries6 = 0; tcp_free_md5sig_pool(); } @@ -668,7 +668,7 @@ static void tcp_v6_clear_md5_list (struct sock *sk) if (tp->md5sig_info->entries4) { for (i = 0; i < tp->md5sig_info->entries4; i++) - kfree(tp->md5sig_info->keys4[i].key); + kfree(tp->md5sig_info->keys4[i].base.key); tp->md5sig_info->entries4 = 0; tcp_free_md5sig_pool(); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4210951edb6..c347f3e30e2 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -555,6 +555,8 @@ static int udp_v6_push_pending_frames(struct sock *sk) out: up->len = 0; up->pending = 0; + if (!err) + UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, up->pcflag); return err; } @@ -823,10 +825,8 @@ do_append_data: release_sock(sk); out: fl6_sock_release(flowlabel); - if (!err) { - UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite); + if (!err) return len; - } /* * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting * ENOBUFS might not be good (it's not tunable per se), but otherwise diff --git a/net/mac80211/ieee80211.c b/net/mac80211/ieee80211.c index 7286c389a4d..ff2172ffd86 100644 --- a/net/mac80211/ieee80211.c +++ b/net/mac80211/ieee80211.c @@ -5259,7 +5259,7 @@ static void __exit ieee80211_exit(void) } -module_init(ieee80211_init); +subsys_initcall(ieee80211_init); module_exit(ieee80211_exit); MODULE_DESCRIPTION("IEEE 802.11 subsystem"); diff --git a/net/mac80211/rc80211_simple.c b/net/mac80211/rc80211_simple.c index f6780d63b34..17b9f46bbf2 100644 --- a/net/mac80211/rc80211_simple.c +++ b/net/mac80211/rc80211_simple.c @@ -431,7 +431,7 @@ static void __exit rate_control_simple_exit(void) } -module_init(rate_control_simple_init); +subsys_initcall(rate_control_simple_init); module_exit(rate_control_simple_exit); MODULE_DESCRIPTION("Simple rate control algorithm for ieee80211"); diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 89ce8152969..7ab82b376e1 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -424,7 +424,7 @@ static int wme_qdiscop_init(struct Qdisc *qd, struct rtattr *opt) skb_queue_head_init(&q->requeued[i]); q->queues[i] = qdisc_create_dflt(qd->dev, &pfifo_qdisc_ops, qd->handle); - if (q->queues[i] == 0) { + if (!q->queues[i]) { q->queues[i] = &noop_qdisc; printk(KERN_ERR "%s child qdisc %i creation failed", dev->name, i); } diff --git a/net/netfilter/nf_sockopt.c b/net/netfilter/nf_sockopt.c index 8b8ece75031..e32761ce260 100644 --- a/net/netfilter/nf_sockopt.c +++ b/net/netfilter/nf_sockopt.c @@ -55,18 +55,7 @@ EXPORT_SYMBOL(nf_register_sockopt); void nf_unregister_sockopt(struct nf_sockopt_ops *reg) { - /* No point being interruptible: we're probably in cleanup_module() */ - restart: mutex_lock(&nf_sockopt_mutex); - if (reg->use != 0) { - /* To be woken by nf_sockopt call... */ - /* FIXME: Stuart Young's name appears gratuitously. */ - set_current_state(TASK_UNINTERRUPTIBLE); - reg->cleanup_task = current; - mutex_unlock(&nf_sockopt_mutex); - schedule(); - goto restart; - } list_del(®->list); mutex_unlock(&nf_sockopt_mutex); } @@ -86,10 +75,11 @@ static int nf_sockopt(struct sock *sk, int pf, int val, 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) { - ops->use++; mutex_unlock(&nf_sockopt_mutex); ret = ops->get(sk, val, opt, len); goto out; @@ -97,23 +87,20 @@ static int nf_sockopt(struct sock *sk, int pf, int val, } else { if (val >= ops->set_optmin && val < ops->set_optmax) { - ops->use++; mutex_unlock(&nf_sockopt_mutex); ret = ops->set(sk, val, opt, *len); goto out; } } + module_put(ops->owner); } } + out_nosup: mutex_unlock(&nf_sockopt_mutex); return -ENOPROTOOPT; out: - mutex_lock(&nf_sockopt_mutex); - ops->use--; - if (ops->cleanup_task) - wake_up_process(ops->cleanup_task); - mutex_unlock(&nf_sockopt_mutex); + module_put(ops->owner); return ret; } @@ -144,10 +131,12 @@ static int compat_nf_sockopt(struct sock *sk, int pf, int val, 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) { - ops->use++; mutex_unlock(&nf_sockopt_mutex); if (ops->compat_get) ret = ops->compat_get(sk, @@ -160,7 +149,6 @@ static int compat_nf_sockopt(struct sock *sk, int pf, int val, } else { if (val >= ops->set_optmin && val < ops->set_optmax) { - ops->use++; mutex_unlock(&nf_sockopt_mutex); if (ops->compat_set) ret = ops->compat_set(sk, @@ -171,17 +159,15 @@ static int compat_nf_sockopt(struct sock *sk, int pf, int val, goto out; } } + module_put(ops->owner); } } + out_nosup: mutex_unlock(&nf_sockopt_mutex); return -ENOPROTOOPT; out: - mutex_lock(&nf_sockopt_mutex); - ops->use--; - if (ops->cleanup_task) - wake_up_process(ops->cleanup_task); - mutex_unlock(&nf_sockopt_mutex); + module_put(ops->owner); return ret; } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index e185a5b5591..2351533a850 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -58,7 +58,6 @@ struct nfulnl_instance { unsigned int qlen; /* number of nlmsgs in skb */ struct sk_buff *skb; /* pre-allocatd skb */ - struct nlmsghdr *lastnlh; /* netlink header of last msg in skb */ struct timer_list timer; int peer_pid; /* PID of the peer process */ @@ -345,10 +344,12 @@ static struct sk_buff *nfulnl_alloc_skb(unsigned int inst_size, static int __nfulnl_send(struct nfulnl_instance *inst) { - int status; + int status = -1; if (inst->qlen > 1) - inst->lastnlh->nlmsg_type = NLMSG_DONE; + NLMSG_PUT(inst->skb, 0, 0, + NLMSG_DONE, + sizeof(struct nfgenmsg)); status = nfnetlink_unicast(inst->skb, inst->peer_pid, MSG_DONTWAIT); if (status < 0) { @@ -358,8 +359,8 @@ __nfulnl_send(struct nfulnl_instance *inst) inst->qlen = 0; inst->skb = NULL; - inst->lastnlh = NULL; +nlmsg_failure: return status; } @@ -538,7 +539,6 @@ __build_packet_message(struct nfulnl_instance *inst, } nlh->nlmsg_len = inst->skb->tail - old_tail; - inst->lastnlh = nlh; return 0; nlmsg_failure: @@ -644,7 +644,8 @@ nfulnl_log_packet(unsigned int pf, } if (inst->qlen >= qthreshold || - (inst->skb && size > skb_tailroom(inst->skb))) { + (inst->skb && size > + skb_tailroom(inst->skb) - sizeof(struct nfgenmsg))) { /* either the queue len is too high or we don't have * enough room in the skb left. flush to userspace. */ UDEBUG("flushing old skb\n"); diff --git a/net/netfilter/xt_tcpudp.c b/net/netfilter/xt_tcpudp.c index ab7d845224f..223f9bded67 100644 --- a/net/netfilter/xt_tcpudp.c +++ b/net/netfilter/xt_tcpudp.c @@ -188,7 +188,7 @@ udp_checkentry(const char *tablename, void *matchinfo, unsigned int hook_mask) { - const struct xt_tcp *udpinfo = matchinfo; + const struct xt_udp *udpinfo = matchinfo; /* Must specify no unknown invflags */ return !(udpinfo->invflags & ~XT_UDP_INV_MASK); diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index cd01642f049..114df6eec8c 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -79,7 +79,7 @@ static void rose_loopback_timer(unsigned long param) skb_reset_transport_header(skb); - sk = rose_find_socket(lci_o, &rose_loopback_neigh); + sk = rose_find_socket(lci_o, rose_loopback_neigh); if (sk) { if (rose_process_rx_frame(sk, skb) == 0) kfree_skb(skb); @@ -88,7 +88,7 @@ static void rose_loopback_timer(unsigned long param) if (frametype == ROSE_CALL_REQUEST) { if ((dev = rose_dev_get(dest)) != NULL) { - if (rose_rx_call_request(skb, dev, &rose_loopback_neigh, lci_o) == 0) + if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0) kfree_skb(skb); } else { kfree_skb(skb); diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index bbcbad1da0d..96f61a71b25 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -45,7 +45,7 @@ static DEFINE_SPINLOCK(rose_neigh_list_lock); static struct rose_route *rose_route_list; static DEFINE_SPINLOCK(rose_route_list_lock); -struct rose_neigh rose_loopback_neigh; +struct rose_neigh *rose_loopback_neigh; /* * Add a new route to a node, and in the process add the node and the @@ -362,7 +362,12 @@ out: */ void rose_add_loopback_neigh(void) { - struct rose_neigh *sn = &rose_loopback_neigh; + struct rose_neigh *sn; + + rose_loopback_neigh = kmalloc(sizeof(struct rose_neigh), GFP_KERNEL); + if (!rose_loopback_neigh) + return; + sn = rose_loopback_neigh; sn->callsign = null_ax25_address; sn->digipeat = NULL; @@ -417,13 +422,13 @@ int rose_add_loopback_node(rose_address *address) rose_node->mask = 10; rose_node->count = 1; rose_node->loopback = 1; - rose_node->neighbour[0] = &rose_loopback_neigh; + rose_node->neighbour[0] = rose_loopback_neigh; /* Insert at the head of list. Address is always mask=10 */ rose_node->next = rose_node_list; rose_node_list = rose_node; - rose_loopback_neigh.count++; + rose_loopback_neigh->count++; out: spin_unlock_bh(&rose_node_list_lock); @@ -454,7 +459,7 @@ void rose_del_loopback_node(rose_address *address) rose_remove_node(rose_node); - rose_loopback_neigh.count--; + rose_loopback_neigh->count--; out: spin_unlock_bh(&rose_node_list_lock); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index feef366cad5..72cdb0fade2 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -68,7 +68,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, int err = 0, index = -1,i = 0, s_i = 0, n_i = 0; struct rtattr *r ; - read_lock(hinfo->lock); + read_lock_bh(hinfo->lock); s_i = cb->args[0]; @@ -96,7 +96,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, } } done: - read_unlock(hinfo->lock); + read_unlock_bh(hinfo->lock); if (n_i) cb->args[0] += n_i; return n_i; @@ -156,13 +156,13 @@ struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo) { struct tcf_common *p; - read_lock(hinfo->lock); + read_lock_bh(hinfo->lock); for (p = hinfo->htab[tcf_hash(index, hinfo->hmask)]; p; p = p->tcfc_next) { if (p->tcfc_index == index) break; } - read_unlock(hinfo->lock); + read_unlock_bh(hinfo->lock); return p; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 6085be57845..17f6f27e28a 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -56,7 +56,7 @@ static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *c int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; struct rtattr *r; - read_lock(&police_lock); + read_lock_bh(&police_lock); s_i = cb->args[0]; @@ -85,7 +85,7 @@ static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *c } } done: - read_unlock(&police_lock); + read_unlock_bh(&police_lock); if (n_i) cb->args[0] += n_i; return n_i; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 8dbe36912ec..d4d5d2f271d 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -502,7 +502,7 @@ static int u32_set_parms(struct tcf_proto *tp, unsigned long base, #ifdef CONFIG_NET_CLS_IND if (tb[TCA_U32_INDEV-1]) { - int err = tcf_change_indev(tp, n->indev, tb[TCA_U32_INDEV-1]); + err = tcf_change_indev(tp, n->indev, tb[TCA_U32_INDEV-1]); if (err < 0) goto errout; } diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index e38c2839b25..cbef3bbfc20 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -380,7 +380,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); int len = skb->len; - int ret; + int uninitialized_var(ret); struct cbq_class *cl = cbq_classify(skb, sch, &ret); #ifdef CONFIG_NET_CLS_ACT diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 4a49db65772..abd82fc3ec6 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -44,7 +44,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) if (TC_H_MAJ(skb->priority) != sch->handle) { err = tc_classify(skb, q->filter_list, &res); #ifdef CONFIG_NET_CLS_ACT - switch (tc_classify(skb, q->filter_list, &res)) { + switch (err) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: *qerr = NET_XMIT_SUCCESS; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 95795730985..b542c875e15 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/ipv6.h> #include <linux/skbuff.h> +#include <linux/jhash.h> #include <net/ip.h> #include <net/netlink.h> #include <net/pkt_sched.h> @@ -95,7 +96,7 @@ struct sfq_sched_data /* Variables */ struct timer_list perturb_timer; - int perturbation; + u32 perturbation; sfq_index tail; /* Index of current slot in round */ sfq_index max_depth; /* Maximal depth */ @@ -109,12 +110,7 @@ struct sfq_sched_data static __inline__ unsigned sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1) { - int pert = q->perturbation; - - /* Have we any rotation primitives? If not, WHY? */ - h ^= (h1<<pert) ^ (h1>>(0x1F - pert)); - h ^= h>>10; - return h & 0x3FF; + return jhash_2words(h, h1, q->perturbation) & (SFQ_HASH_DIVISOR - 1); } static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) @@ -256,6 +252,13 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc* sch) q->ht[hash] = x = q->dep[SFQ_DEPTH].next; q->hash[x] = hash; } + /* If selected queue has length q->limit, this means that + * all another queues are empty and that we do simple tail drop, + * i.e. drop _this_ packet. + */ + if (q->qs[x].qlen >= q->limit) + return qdisc_drop(skb, sch); + sch->qstats.backlog += skb->len; __skb_queue_tail(&q->qs[x], skb); sfq_inc(q, x); @@ -270,7 +273,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc* sch) q->tail = x; } } - if (++sch->q.qlen < q->limit-1) { + if (++sch->q.qlen <= q->limit) { sch->bstats.bytes += skb->len; sch->bstats.packets++; return 0; @@ -294,6 +297,19 @@ sfq_requeue(struct sk_buff *skb, struct Qdisc* sch) } sch->qstats.backlog += skb->len; __skb_queue_head(&q->qs[x], skb); + /* If selected queue has length q->limit+1, this means that + * all another queues are empty and we do simple tail drop. + * This packet is still requeued at head of queue, tail packet + * is dropped. + */ + if (q->qs[x].qlen > q->limit) { + skb = q->qs[x].prev; + __skb_unlink(skb, &q->qs[x]); + sch->qstats.drops++; + sch->qstats.backlog -= skb->len; + kfree_skb(skb); + return NET_XMIT_CN; + } sfq_inc(q, x); if (q->qs[x].qlen == 1) { /* The flow is new */ if (q->tail == SFQ_DEPTH) { /* It is the first flow */ @@ -306,7 +322,7 @@ sfq_requeue(struct sk_buff *skb, struct Qdisc* sch) q->tail = x; } } - if (++sch->q.qlen < q->limit - 1) { + if (++sch->q.qlen <= q->limit) { sch->qstats.requeues++; return 0; } @@ -370,12 +386,10 @@ static void sfq_perturbation(unsigned long arg) struct Qdisc *sch = (struct Qdisc*)arg; struct sfq_sched_data *q = qdisc_priv(sch); - q->perturbation = net_random()&0x1F; + get_random_bytes(&q->perturbation, 4); - if (q->perturb_period) { - q->perturb_timer.expires = jiffies + q->perturb_period; - add_timer(&q->perturb_timer); - } + if (q->perturb_period) + mod_timer(&q->perturb_timer, jiffies + q->perturb_period); } static int sfq_change(struct Qdisc *sch, struct rtattr *opt) @@ -391,17 +405,17 @@ static int sfq_change(struct Qdisc *sch, struct rtattr *opt) q->quantum = ctl->quantum ? : psched_mtu(sch->dev); q->perturb_period = ctl->perturb_period*HZ; if (ctl->limit) - q->limit = min_t(u32, ctl->limit, SFQ_DEPTH); + q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 1); qlen = sch->q.qlen; - while (sch->q.qlen >= q->limit-1) + while (sch->q.qlen > q->limit) sfq_drop(sch); qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); del_timer(&q->perturb_timer); if (q->perturb_period) { - q->perturb_timer.expires = jiffies + q->perturb_period; - add_timer(&q->perturb_timer); + mod_timer(&q->perturb_timer, jiffies + q->perturb_period); + get_random_bytes(&q->perturbation, 4); } sch_tree_unlock(sch); return 0; @@ -423,12 +437,13 @@ static int sfq_init(struct Qdisc *sch, struct rtattr *opt) q->dep[i+SFQ_DEPTH].next = i+SFQ_DEPTH; q->dep[i+SFQ_DEPTH].prev = i+SFQ_DEPTH; } - q->limit = SFQ_DEPTH; + q->limit = SFQ_DEPTH - 1; q->max_depth = 0; q->tail = SFQ_DEPTH; if (opt == NULL) { q->quantum = psched_mtu(sch->dev); q->perturb_period = 0; + get_random_bytes(&q->perturbation, 4); } else { int err = sfq_change(sch, opt); if (err) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 498edb0cd4e..9bad8ba0fed 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -99,7 +99,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a /* Initialize the bind addr area. */ sctp_bind_addr_init(&asoc->base.bind_addr, ep->base.bind_addr.port); - rwlock_init(&asoc->base.addr_lock); asoc->state = SCTP_STATE_CLOSED; @@ -727,7 +726,12 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, break; case SCTP_TRANSPORT_DOWN: - transport->state = SCTP_INACTIVE; + /* if the transort was never confirmed, do not transition it + * to inactive state. + */ + if (transport->state != SCTP_UNCONFIRMED) + transport->state = SCTP_INACTIVE; + spc_state = SCTP_ADDR_UNREACHABLE; break; @@ -932,8 +936,6 @@ struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc, { struct sctp_transport *transport; - sctp_read_lock(&asoc->base.addr_lock); - if ((htons(asoc->base.bind_addr.port) == laddr->v4.sin_port) && (htons(asoc->peer.port) == paddr->v4.sin_port)) { transport = sctp_assoc_lookup_paddr(asoc, paddr); @@ -947,7 +949,6 @@ struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc, transport = NULL; out: - sctp_read_unlock(&asoc->base.addr_lock); return transport; } @@ -1371,19 +1372,13 @@ int sctp_assoc_set_bind_addr_from_cookie(struct sctp_association *asoc, int sctp_assoc_lookup_laddr(struct sctp_association *asoc, const union sctp_addr *laddr) { - int found; + int found = 0; - sctp_read_lock(&asoc->base.addr_lock); if ((asoc->base.bind_addr.port == ntohs(laddr->v4.sin_port)) && sctp_bind_addr_match(&asoc->base.bind_addr, laddr, - sctp_sk(asoc->base.sk))) { + sctp_sk(asoc->base.sk))) found = 1; - goto out; - } - found = 0; -out: - sctp_read_unlock(&asoc->base.addr_lock); return found; } diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index fdb287a9e2e..dfffa94fb9f 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -163,9 +163,15 @@ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new, addr->a.v4.sin_port = htons(bp->port); addr->use_as_src = use_as_src; + addr->valid = 1; INIT_LIST_HEAD(&addr->list); - list_add_tail(&addr->list, &bp->address_list); + INIT_RCU_HEAD(&addr->rcu); + + /* We always hold a socket lock when calling this function, + * and that acts as a writer synchronizing lock. + */ + list_add_tail_rcu(&addr->list, &bp->address_list); SCTP_DBG_OBJCNT_INC(addr); return 0; @@ -174,23 +180,35 @@ 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) +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))) { - struct list_head *pos, *temp; - struct sctp_sockaddr_entry *addr; + struct sctp_sockaddr_entry *addr, *temp; - list_for_each_safe(pos, temp, &bp->address_list) { - addr = list_entry(pos, struct sctp_sockaddr_entry, list); + /* We hold the socket lock when calling this function, + * and that acts as a writer synchronizing lock. + */ + list_for_each_entry_safe(addr, temp, &bp->address_list, list) { if (sctp_cmp_addr_exact(&addr->a, del_addr)) { /* Found the exact match. */ - list_del(pos); - kfree(addr); - SCTP_DBG_OBJCNT_DEC(addr); - - return 0; + addr->valid = 0; + list_del_rcu(&addr->list); + break; } } + /* 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); + SCTP_DBG_OBJCNT_DEC(addr); + } + return -EINVAL; } @@ -300,15 +318,20 @@ int sctp_bind_addr_match(struct sctp_bind_addr *bp, struct sctp_sock *opt) { struct sctp_sockaddr_entry *laddr; - struct list_head *pos; - - list_for_each(pos, &bp->address_list) { - laddr = list_entry(pos, struct sctp_sockaddr_entry, list); - if (opt->pf->cmp_addr(&laddr->a, addr, opt)) - return 1; + int match = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(laddr, &bp->address_list, list) { + if (!laddr->valid) + continue; + if (opt->pf->cmp_addr(&laddr->a, addr, opt)) { + match = 1; + break; + } } + rcu_read_unlock(); - return 0; + return match; } /* Find the first address in the bind address list that is not present in @@ -323,18 +346,19 @@ union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr *bp, union sctp_addr *addr; void *addr_buf; struct sctp_af *af; - struct list_head *pos; int i; - list_for_each(pos, &bp->address_list) { - laddr = list_entry(pos, struct sctp_sockaddr_entry, list); - + /* This is only called sctp_send_asconf_del_ip() and we hold + * the socket lock in that code patch, so that address list + * can't change. + */ + list_for_each_entry(laddr, &bp->address_list, list) { addr_buf = (union sctp_addr *)addrs; for (i = 0; i < addrcnt; i++) { addr = (union sctp_addr *)addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); if (!af) - return NULL; + break; if (opt->pf->cmp_addr(&laddr->a, addr, opt)) break; diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 1404a9e2e78..8f485a0d14b 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -92,7 +92,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, /* Initialize the bind addr area */ sctp_bind_addr_init(&ep->base.bind_addr, 0); - rwlock_init(&ep->base.addr_lock); /* Remember who we are attached to. */ ep->base.sk = sk; @@ -225,21 +224,14 @@ void sctp_endpoint_put(struct sctp_endpoint *ep) struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep, const union sctp_addr *laddr) { - struct sctp_endpoint *retval; + struct sctp_endpoint *retval = NULL; - sctp_read_lock(&ep->base.addr_lock); if (htons(ep->base.bind_addr.port) == laddr->v4.sin_port) { if (sctp_bind_addr_match(&ep->base.bind_addr, laddr, - sctp_sk(ep->base.sk))) { + sctp_sk(ep->base.sk))) retval = ep; - goto out; - } } - retval = NULL; - -out: - sctp_read_unlock(&ep->base.addr_lock); return retval; } @@ -261,9 +253,7 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( list_for_each(pos, &ep->asocs) { asoc = list_entry(pos, struct sctp_association, asocs); if (rport == asoc->peer.port) { - sctp_read_lock(&asoc->base.addr_lock); *transport = sctp_assoc_lookup_paddr(asoc, paddr); - sctp_read_unlock(&asoc->base.addr_lock); if (*transport) return asoc; @@ -295,20 +285,17 @@ struct sctp_association *sctp_endpoint_lookup_assoc( int sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep, const union sctp_addr *paddr) { - struct list_head *pos; struct sctp_sockaddr_entry *addr; struct sctp_bind_addr *bp; - sctp_read_lock(&ep->base.addr_lock); bp = &ep->base.bind_addr; - list_for_each(pos, &bp->address_list) { - addr = list_entry(pos, struct sctp_sockaddr_entry, list); - if (sctp_has_association(&addr->a, paddr)) { - sctp_read_unlock(&ep->base.addr_lock); + /* This function is called with the socket lock held, + * so the address_list can not change. + */ + list_for_each_entry(addr, &bp->address_list, list) { + if (sctp_has_association(&addr->a, paddr)) return 1; - } } - sctp_read_unlock(&ep->base.addr_lock); return 0; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 47e56017f4c..f9a0c9276e3 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -622,6 +622,14 @@ static int sctp_rcv_ootb(struct sk_buff *skb) if (SCTP_CID_SHUTDOWN_COMPLETE == ch->type) goto discard; + /* RFC 4460, 2.11.2 + * This will discard packets with INIT chunk bundled as + * subsequent chunks in the packet. When INIT is first, + * the normal INIT processing will discard the chunk. + */ + if (SCTP_CID_INIT == ch->type && (void *)ch != skb->data) + goto discard; + /* RFC 8.4, 7) If the packet contains a "Stale cookie" ERROR * or a COOKIE ACK the SCTP Packet should be silently * discarded. diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 88aa2240754..e4ea7fdf36e 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -130,6 +130,14 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) /* Force chunk->skb->data to chunk->chunk_end. */ skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data); + + /* Verify that we have at least chunk headers + * worth of buffer left. + */ + if (skb_headlen(chunk->skb) < sizeof(sctp_chunkhdr_t)) { + sctp_chunk_free(chunk); + chunk = queue->in_progress = NULL; + } } } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index f8aa23dda1c..670fd2740b8 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -77,13 +77,18 @@ #include <asm/uaccess.h> -/* Event handler for inet6 address addition/deletion events. */ +/* Event handler for inet6 address addition/deletion events. + * The sctp_local_addr_list needs to be protocted by a spin lock since + * multiple notifiers (say IPv4 and IPv6) may be running at the same + * time and thus corrupt the list. + * The reader side is protected with RCU. + */ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, void *ptr) { struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; - struct sctp_sockaddr_entry *addr; - struct list_head *pos, *temp; + struct sctp_sockaddr_entry *addr = NULL; + struct sctp_sockaddr_entry *temp; switch (ev) { case NETDEV_UP: @@ -94,19 +99,26 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, memcpy(&addr->a.v6.sin6_addr, &ifa->addr, sizeof(struct in6_addr)); addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex; - list_add_tail(&addr->list, &sctp_local_addr_list); + addr->valid = 1; + spin_lock_bh(&sctp_local_addr_lock); + list_add_tail_rcu(&addr->list, &sctp_local_addr_list); + spin_unlock_bh(&sctp_local_addr_lock); } break; case NETDEV_DOWN: - list_for_each_safe(pos, temp, &sctp_local_addr_list) { - addr = list_entry(pos, struct sctp_sockaddr_entry, list); - if (ipv6_addr_equal(&addr->a.v6.sin6_addr, &ifa->addr)) { - list_del(pos); - kfree(addr); + spin_lock_bh(&sctp_local_addr_lock); + list_for_each_entry_safe(addr, temp, + &sctp_local_addr_list, list) { + if (ipv6_addr_equal(&addr->a.v6.sin6_addr, + &ifa->addr)) { + addr->valid = 0; + list_del_rcu(&addr->list); break; } } - + spin_unlock_bh(&sctp_local_addr_lock); + if (addr && !addr->valid) + call_rcu(&addr->rcu, sctp_local_addr_free); break; } @@ -290,9 +302,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc, union sctp_addr *saddr) { struct sctp_bind_addr *bp; - rwlock_t *addr_lock; struct sctp_sockaddr_entry *laddr; - struct list_head *pos; sctp_scope_t scope; union sctp_addr *baddr = NULL; __u8 matchlen = 0; @@ -312,14 +322,14 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc, scope = sctp_scope(daddr); bp = &asoc->base.bind_addr; - addr_lock = &asoc->base.addr_lock; /* Go through the bind address list and find the best source address * that matches the scope of the destination address. */ - sctp_read_lock(addr_lock); - list_for_each(pos, &bp->address_list) { - laddr = list_entry(pos, struct sctp_sockaddr_entry, list); + rcu_read_lock(); + list_for_each_entry_rcu(laddr, &bp->address_list, list) { + if (!laddr->valid) + continue; if ((laddr->use_as_src) && (laddr->a.sa.sa_family == AF_INET6) && (scope <= sctp_scope(&laddr->a))) { @@ -341,7 +351,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc, __FUNCTION__, asoc, NIP6(daddr->v6.sin6_addr)); } - sctp_read_unlock(addr_lock); + rcu_read_unlock(); } /* Make a copy of all potential local addresses. */ @@ -367,7 +377,9 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, addr->a.v6.sin6_port = 0; addr->a.v6.sin6_addr = ifp->addr; addr->a.v6.sin6_scope_id = dev->ifindex; + addr->valid = 1; INIT_LIST_HEAD(&addr->list); + INIT_RCU_HEAD(&addr->rcu); list_add_tail(&addr->list, addrlist); } } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 992f361084b..28f4fe77cee 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -421,6 +421,13 @@ void sctp_retransmit_mark(struct sctp_outq *q, */ if ((fast_retransmit && (chunk->fast_retransmit > 0)) || (!fast_retransmit && !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. + */ + if ((jiffies - chunk->sent_at) < transport->rto) + continue; + /* RFC 2960 6.2.1 Processing a Received SACK * * C) Any time a DATA chunk is marked for diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index e98579b788b..3d036cdfae4 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -153,6 +153,9 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist, addr->a.v4.sin_family = AF_INET; addr->a.v4.sin_port = 0; addr->a.v4.sin_addr.s_addr = ifa->ifa_local; + addr->valid = 1; + INIT_LIST_HEAD(&addr->list); + INIT_RCU_HEAD(&addr->rcu); list_add_tail(&addr->list, addrlist); } } @@ -192,16 +195,24 @@ static void sctp_free_local_addr_list(void) } } +void sctp_local_addr_free(struct rcu_head *head) +{ + struct sctp_sockaddr_entry *e = container_of(head, + struct sctp_sockaddr_entry, rcu); + kfree(e); +} + /* Copy the local addresses which are valid for 'scope' into 'bp'. */ int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope, gfp_t gfp, int copy_flags) { struct sctp_sockaddr_entry *addr; int error = 0; - struct list_head *pos, *temp; - list_for_each_safe(pos, temp, &sctp_local_addr_list) { - addr = list_entry(pos, struct sctp_sockaddr_entry, list); + rcu_read_lock(); + list_for_each_entry_rcu(addr, &sctp_local_addr_list, list) { + if (!addr->valid) + continue; if (sctp_in_scope(&addr->a, scope)) { /* Now that the address is in scope, check to see if * the address type is really supported by the local @@ -213,7 +224,7 @@ int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope, (copy_flags & SCTP_ADDR6_ALLOWED) && (copy_flags & SCTP_ADDR6_PEERSUPP)))) { error = sctp_add_bind_addr(bp, &addr->a, 1, - GFP_ATOMIC); + GFP_ATOMIC); if (error) goto end_copy; } @@ -221,6 +232,7 @@ int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope, } end_copy: + rcu_read_unlock(); return error; } @@ -416,9 +428,7 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, struct rtable *rt; struct flowi fl; struct sctp_bind_addr *bp; - rwlock_t *addr_lock; struct sctp_sockaddr_entry *laddr; - struct list_head *pos; struct dst_entry *dst = NULL; union sctp_addr dst_saddr; @@ -447,23 +457,20 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, goto out; bp = &asoc->base.bind_addr; - addr_lock = &asoc->base.addr_lock; if (dst) { /* Walk through the bind address list and look for a bind * address that matches the source address of the returned dst. */ - sctp_read_lock(addr_lock); - list_for_each(pos, &bp->address_list) { - laddr = list_entry(pos, struct sctp_sockaddr_entry, - list); - if (!laddr->use_as_src) + rcu_read_lock(); + list_for_each_entry_rcu(laddr, &bp->address_list, list) { + if (!laddr->valid || !laddr->use_as_src) continue; sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port)); if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a)) goto out_unlock; } - sctp_read_unlock(addr_lock); + rcu_read_unlock(); /* None of the bound addresses match the source address of the * dst. So release it. @@ -475,10 +482,10 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, /* Walk through the bind address list and try to get a dst that * matches a bind address as the source address. */ - sctp_read_lock(addr_lock); - list_for_each(pos, &bp->address_list) { - laddr = list_entry(pos, struct sctp_sockaddr_entry, list); - + rcu_read_lock(); + list_for_each_entry_rcu(laddr, &bp->address_list, list) { + if (!laddr->valid) + continue; if ((laddr->use_as_src) && (AF_INET == laddr->a.sa.sa_family)) { fl.fl4_src = laddr->a.v4.sin_addr.s_addr; @@ -490,7 +497,7 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, } out_unlock: - sctp_read_unlock(addr_lock); + rcu_read_unlock(); out: if (dst) SCTP_DEBUG_PRINTK("rt_dst:%u.%u.%u.%u, rt_src:%u.%u.%u.%u\n", @@ -600,13 +607,18 @@ static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) seq_printf(seq, "%d.%d.%d.%d ", NIPQUAD(addr->v4.sin_addr)); } -/* Event handler for inet address addition/deletion events. */ +/* Event handler for inet address addition/deletion events. + * The sctp_local_addr_list needs to be protocted by a spin lock since + * multiple notifiers (say IPv4 and IPv6) may be running at the same + * time and thus corrupt the list. + * The reader side is protected with RCU. + */ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, void *ptr) { struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; - struct sctp_sockaddr_entry *addr; - struct list_head *pos, *temp; + struct sctp_sockaddr_entry *addr = NULL; + struct sctp_sockaddr_entry *temp; switch (ev) { case NETDEV_UP: @@ -615,19 +627,25 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, addr->a.v4.sin_family = AF_INET; addr->a.v4.sin_port = 0; addr->a.v4.sin_addr.s_addr = ifa->ifa_local; - list_add_tail(&addr->list, &sctp_local_addr_list); + addr->valid = 1; + spin_lock_bh(&sctp_local_addr_lock); + list_add_tail_rcu(&addr->list, &sctp_local_addr_list); + spin_unlock_bh(&sctp_local_addr_lock); } break; case NETDEV_DOWN: - list_for_each_safe(pos, temp, &sctp_local_addr_list) { - addr = list_entry(pos, struct sctp_sockaddr_entry, list); + spin_lock_bh(&sctp_local_addr_lock); + list_for_each_entry_safe(addr, temp, + &sctp_local_addr_list, list) { if (addr->a.v4.sin_addr.s_addr == ifa->ifa_local) { - list_del(pos); - kfree(addr); + addr->valid = 0; + list_del_rcu(&addr->list); break; } } - + spin_unlock_bh(&sctp_local_addr_lock); + if (addr && !addr->valid) + call_rcu(&addr->rcu, sctp_local_addr_free); break; } @@ -1160,6 +1178,7 @@ SCTP_STATIC __init int sctp_init(void) /* 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. */ @@ -1227,6 +1246,9 @@ SCTP_STATIC __exit void sctp_exit(void) 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(); @@ -1240,9 +1262,6 @@ SCTP_STATIC __exit void sctp_exit(void) inet_unregister_protosw(&sctp_stream_protosw); inet_unregister_protosw(&sctp_seqpacket_protosw); - /* Unregister notifier for inet address additions/deletions. */ - unregister_inetaddr_notifier(&sctp_inetaddr_notifier); - sctp_sysctl_unregister(); list_del(&sctp_ipv4_specific.list); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 51c4d7fef1d..23ae37ec871 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -110,7 +110,7 @@ static const struct sctp_paramhdr prsctp_param = { * abort chunk. */ void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, - const void *payload, size_t paylen) + size_t paylen) { sctp_errhdr_t err; __u16 len; @@ -120,7 +120,6 @@ void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, len = sizeof(sctp_errhdr_t) + paylen; err.length = htons(len); chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(sctp_errhdr_t), &err); - sctp_addto_chunk(chunk, paylen, payload); } /* 3.3.2 Initiation (INIT) (1) @@ -780,8 +779,8 @@ struct sctp_chunk *sctp_make_abort_no_data( /* Put the tsn back into network byte order. */ payload = htonl(tsn); - sctp_init_cause(retval, SCTP_ERROR_NO_DATA, (const void *)&payload, - sizeof(payload)); + sctp_init_cause(retval, SCTP_ERROR_NO_DATA, sizeof(payload)); + sctp_addto_chunk(retval, sizeof(payload), (const void *)&payload); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * @@ -823,7 +822,8 @@ struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *asoc, goto err_copy; } - sctp_init_cause(retval, SCTP_ERROR_USER_ABORT, payload, paylen); + sctp_init_cause(retval, SCTP_ERROR_USER_ABORT, paylen); + sctp_addto_chunk(retval, paylen, payload); if (paylen) kfree(payload); @@ -850,15 +850,17 @@ struct sctp_chunk *sctp_make_abort_violation( struct sctp_paramhdr phdr; retval = sctp_make_abort(asoc, chunk, sizeof(sctp_errhdr_t) + paylen - + sizeof(sctp_chunkhdr_t)); + + sizeof(sctp_paramhdr_t)); if (!retval) goto end; - sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, payload, paylen); + sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, paylen + + sizeof(sctp_paramhdr_t)); phdr.type = htons(chunk->chunk_hdr->type); phdr.length = chunk->chunk_hdr->length; - sctp_addto_chunk(retval, sizeof(sctp_paramhdr_t), &phdr); + sctp_addto_chunk(retval, paylen, payload); + sctp_addto_param(retval, sizeof(sctp_paramhdr_t), &phdr); end: return retval; @@ -955,7 +957,8 @@ struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, if (!retval) goto nodata; - sctp_init_cause(retval, cause_code, payload, paylen); + sctp_init_cause(retval, cause_code, paylen); + sctp_addto_chunk(retval, paylen, payload); nodata: return retval; @@ -1128,7 +1131,7 @@ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data) void *target; void *padding; int chunklen = ntohs(chunk->chunk_hdr->length); - int padlen = chunklen % 4; + int padlen = WORD_ROUND(chunklen) - chunklen; padding = skb_put(chunk->skb, padlen); target = skb_put(chunk->skb, len); @@ -1143,6 +1146,25 @@ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data) return target; } +/* Append bytes to the end of a parameter. Will panic if chunk is not big + * enough. + */ +void *sctp_addto_param(struct sctp_chunk *chunk, int len, const void *data) +{ + void *target; + int chunklen = ntohs(chunk->chunk_hdr->length); + + target = skb_put(chunk->skb, len); + + memcpy(target, data, len); + + /* Adjust the chunk length field. */ + chunk->chunk_hdr->length = htons(chunklen + len); + chunk->chunk_end = skb_tail_pointer(chunk->skb); + + return target; +} + /* Append bytes from user space to the end of a chunk. Will panic if * chunk is not big enough. * Returns a kernel err value. @@ -1174,25 +1196,36 @@ out: */ void sctp_chunk_assign_ssn(struct sctp_chunk *chunk) { + struct sctp_datamsg *msg; + struct sctp_chunk *lchunk; + struct sctp_stream *stream; __u16 ssn; __u16 sid; if (chunk->has_ssn) return; - /* This is the last possible instant to assign a SSN. */ - if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) { - ssn = 0; - } else { - sid = ntohs(chunk->subh.data_hdr->stream); - if (chunk->chunk_hdr->flags & SCTP_DATA_LAST_FRAG) - ssn = sctp_ssn_next(&chunk->asoc->ssnmap->out, sid); - else - ssn = sctp_ssn_peek(&chunk->asoc->ssnmap->out, sid); - } + /* All fragments will be on the same stream */ + sid = ntohs(chunk->subh.data_hdr->stream); + stream = &chunk->asoc->ssnmap->out; + + /* Now assign the sequence number to the entire message. + * All fragments must have the same stream sequence number. + */ + msg = chunk->msg; + list_for_each_entry(lchunk, &msg->chunks, frag_list) { + if (lchunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) { + ssn = 0; + } else { + if (lchunk->chunk_hdr->flags & SCTP_DATA_LAST_FRAG) + ssn = sctp_ssn_next(stream, sid); + else + ssn = sctp_ssn_peek(stream, sid); + } - chunk->subh.data_hdr->ssn = htons(ssn); - chunk->has_ssn = 1; + lchunk->subh.data_hdr->ssn = htons(ssn); + lchunk->has_ssn = 1; + } } /* Helper function to assign a TSN if needed. This assumes that both @@ -1466,7 +1499,8 @@ no_hmac: __be32 n = htonl(usecs); sctp_init_cause(*errp, SCTP_ERROR_STALE_COOKIE, - &n, sizeof(n)); + sizeof(n)); + sctp_addto_chunk(*errp, sizeof(n), &n); *error = -SCTP_IERROR_STALE_COOKIE; } else *error = -SCTP_IERROR_NOMEM; @@ -1497,7 +1531,7 @@ no_hmac: /* Also, add the destination address. */ if (list_empty(&retval->base.bind_addr.address_list)) { sctp_add_bind_addr(&retval->base.bind_addr, &chunk->dest, 1, - GFP_ATOMIC); + GFP_ATOMIC); } retval->next_tsn = retval->c.initial_tsn; @@ -1556,7 +1590,8 @@ static int sctp_process_missing_param(const struct sctp_association *asoc, report.num_missing = htonl(1); report.type = paramtype; sctp_init_cause(*errp, SCTP_ERROR_MISS_PARAM, - &report, sizeof(report)); + sizeof(report)); + sctp_addto_chunk(*errp, sizeof(report), &report); } /* Stop processing this chunk. */ @@ -1574,7 +1609,7 @@ static int sctp_process_inv_mandatory(const struct sctp_association *asoc, *errp = sctp_make_op_error_space(asoc, chunk, 0); if (*errp) - sctp_init_cause(*errp, SCTP_ERROR_INV_PARAM, NULL, 0); + sctp_init_cause(*errp, SCTP_ERROR_INV_PARAM, 0); /* Stop processing this chunk. */ return 0; @@ -1595,9 +1630,10 @@ static int sctp_process_inv_paramlength(const struct sctp_association *asoc, *errp = sctp_make_op_error_space(asoc, chunk, payload_len); if (*errp) { - sctp_init_cause(*errp, SCTP_ERROR_PROTO_VIOLATION, error, - sizeof(error)); - sctp_addto_chunk(*errp, sizeof(sctp_paramhdr_t), param); + sctp_init_cause(*errp, SCTP_ERROR_PROTO_VIOLATION, + sizeof(error) + sizeof(sctp_paramhdr_t)); + sctp_addto_chunk(*errp, sizeof(error), error); + sctp_addto_param(*errp, sizeof(sctp_paramhdr_t), param); } return 0; @@ -1618,9 +1654,10 @@ static int sctp_process_hn_param(const struct sctp_association *asoc, if (!*errp) *errp = sctp_make_op_error_space(asoc, chunk, len); - if (*errp) - sctp_init_cause(*errp, SCTP_ERROR_DNS_FAILED, - param.v, len); + if (*errp) { + sctp_init_cause(*errp, SCTP_ERROR_DNS_FAILED, len); + sctp_addto_chunk(*errp, len, param.v); + } /* Stop processing this chunk. */ return 0; @@ -1672,10 +1709,13 @@ static int sctp_process_unk_param(const struct sctp_association *asoc, *errp = sctp_make_op_error_space(asoc, chunk, ntohs(chunk->chunk_hdr->length)); - if (*errp) + if (*errp) { sctp_init_cause(*errp, SCTP_ERROR_UNKNOWN_PARAM, - param.v, WORD_ROUND(ntohs(param.p->length))); + sctp_addto_chunk(*errp, + WORD_ROUND(ntohs(param.p->length)), + param.v); + } break; case SCTP_PARAM_ACTION_SKIP: @@ -1690,8 +1730,10 @@ static int sctp_process_unk_param(const struct sctp_association *asoc, if (*errp) { sctp_init_cause(*errp, SCTP_ERROR_UNKNOWN_PARAM, - param.v, WORD_ROUND(ntohs(param.p->length))); + sctp_addto_chunk(*errp, + WORD_ROUND(ntohs(param.p->length)), + param.v); } else { /* If there is no memory for generating the ERROR * report as specified, an ABORT will be triggered @@ -1791,7 +1833,7 @@ 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 - sizeof(sctp_paramhdr_t)) { + if (param.v != (void*)chunk->chunk_end) { sctp_process_inv_paramlength(asoc, param.p, chunk, errp); return 0; } @@ -2457,6 +2499,52 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, return SCTP_ERROR_NO_ERROR; } +/* Verify the ASCONF packet before we process it. */ +int sctp_verify_asconf(const struct sctp_association *asoc, + struct sctp_paramhdr *param_hdr, void *chunk_end, + struct sctp_paramhdr **errp) { + sctp_addip_param_t *asconf_param; + union sctp_params param; + int length, plen; + + param.v = (sctp_paramhdr_t *) param_hdr; + while (param.v <= chunk_end - sizeof(sctp_paramhdr_t)) { + length = ntohs(param.p->length); + *errp = param.p; + + if (param.v > chunk_end - length || + length < sizeof(sctp_paramhdr_t)) + return 0; + + switch (param.p->type) { + case SCTP_PARAM_ADD_IP: + case SCTP_PARAM_DEL_IP: + case SCTP_PARAM_SET_PRIMARY: + asconf_param = (sctp_addip_param_t *)param.v; + plen = ntohs(asconf_param->param_hdr.length); + if (plen < sizeof(sctp_addip_param_t) + + sizeof(sctp_paramhdr_t)) + return 0; + break; + case SCTP_PARAM_SUCCESS_REPORT: + case SCTP_PARAM_ADAPTATION_LAYER_IND: + if (length != sizeof(sctp_addip_param_t)) + return 0; + + break; + default: + break; + } + + param.v += WORD_ROUND(length); + } + + if (param.v != chunk_end) + return 0; + + return 1; +} + /* Process an incoming ASCONF chunk with the next expected serial no. and * return an ASCONF_ACK chunk to be sent in response. */ @@ -2571,22 +2659,16 @@ static int sctp_asconf_param_success(struct sctp_association *asoc, switch (asconf_param->param_hdr.type) { case SCTP_PARAM_ADD_IP: - sctp_local_bh_disable(); - sctp_write_lock(&asoc->base.addr_lock); - list_for_each(pos, &bp->address_list) { - saddr = list_entry(pos, struct sctp_sockaddr_entry, list); + /* This is always done in BH context with a socket lock + * held, so the list can not change. + */ + list_for_each_entry(saddr, &bp->address_list, list) { if (sctp_cmp_addr_exact(&saddr->a, &addr)) saddr->use_as_src = 1; } - sctp_write_unlock(&asoc->base.addr_lock); - sctp_local_bh_enable(); break; case SCTP_PARAM_DEL_IP: - sctp_local_bh_disable(); - sctp_write_lock(&asoc->base.addr_lock); - retval = sctp_del_bind_addr(bp, &addr); - sctp_write_unlock(&asoc->base.addr_lock); - sctp_local_bh_enable(); + retval = sctp_del_bind_addr(bp, &addr, call_rcu_bh); list_for_each(pos, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index d9fad4f6ffc..8d789008349 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1013,8 +1013,9 @@ static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, break; case SCTP_DISPOSITION_VIOLATION: - printk(KERN_ERR "sctp protocol violation state %d " - "chunkid %d\n", state, subtype.chunk); + if (net_ratelimit()) + printk(KERN_ERR "sctp protocol violation state %d " + "chunkid %d\n", state, subtype.chunk); break; case SCTP_DISPOSITION_NOT_IMPL: @@ -1130,6 +1131,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, /* Move the Cumulattive TSN Ack ahead. */ sctp_tsnmap_skip(&asoc->peer.tsn_map, cmd->obj.u32); + /* purge the fragmentation queue */ + sctp_ulpq_reasm_flushtsn(&asoc->ulpq, cmd->obj.u32); + /* Abort any in progress partial delivery. */ sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC); break; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 71cad56dd73..a583d67cab6 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -90,6 +90,11 @@ static sctp_disposition_t sctp_sf_shut_8_4_5(const struct sctp_endpoint *ep, const sctp_subtype_t type, void *arg, sctp_cmd_seq_t *commands); +static sctp_disposition_t sctp_sf_tabort_8_4_8(const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const sctp_subtype_t type, + void *arg, + sctp_cmd_seq_t *commands); static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk); static sctp_disposition_t sctp_stop_t1_and_abort(sctp_cmd_seq_t *commands, @@ -98,6 +103,7 @@ static sctp_disposition_t sctp_stop_t1_and_abort(sctp_cmd_seq_t *commands, struct sctp_transport *transport); static sctp_disposition_t sctp_sf_abort_violation( + const struct sctp_endpoint *ep, const struct sctp_association *asoc, void *arg, sctp_cmd_seq_t *commands, @@ -111,6 +117,13 @@ static sctp_disposition_t sctp_sf_violation_chunklen( void *arg, sctp_cmd_seq_t *commands); +static sctp_disposition_t sctp_sf_violation_paramlen( + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const sctp_subtype_t type, + void *arg, + sctp_cmd_seq_t *commands); + static sctp_disposition_t sctp_sf_violation_ctsn( const struct sctp_endpoint *ep, const struct sctp_association *asoc, @@ -118,6 +131,13 @@ static sctp_disposition_t sctp_sf_violation_ctsn( void *arg, sctp_cmd_seq_t *commands); +static sctp_disposition_t sctp_sf_violation_chunk( + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const sctp_subtype_t type, + void *arg, + sctp_cmd_seq_t *commands); + /* Small helper function that checks if the chunk length * is of the appropriate length. The 'required_length' argument * is set to be the size of a specific chunk we are testing. @@ -181,16 +201,21 @@ sctp_disposition_t sctp_sf_do_4_C(const struct sctp_endpoint *ep, struct sctp_chunk *chunk = arg; struct sctp_ulpevent *ev; + if (!sctp_vtag_verify_either(chunk, asoc)) + return sctp_sf_pdiscard(ep, asoc, type, arg, commands); + /* RFC 2960 6.10 Bundling * * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. */ if (!chunk->singleton) - return SCTP_DISPOSITION_VIOLATION; + return sctp_sf_violation_chunk(ep, asoc, type, arg, commands); - if (!sctp_vtag_verify_either(chunk, asoc)) - return sctp_sf_pdiscard(ep, asoc, type, arg, commands); + /* Make sure that the SHUTDOWN_COMPLETE chunk has a valid length. */ + if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + return sctp_sf_violation_chunklen(ep, asoc, type, arg, + commands); /* RFC 2960 10.2 SCTP-to-ULP * @@ -264,7 +289,6 @@ sctp_disposition_t sctp_sf_do_5_1B_init(const struct sctp_endpoint *ep, struct sctp_chunk *err_chunk; struct sctp_packet *packet; sctp_unrecognized_param_t *unk_param; - struct sock *sk; int len; /* 6.10 Bundling @@ -285,16 +309,6 @@ sctp_disposition_t sctp_sf_do_5_1B_init(const struct sctp_endpoint *ep, if (ep == sctp_sk((sctp_get_ctl_sock()))->ep) return sctp_sf_tabort_8_4_8(ep, asoc, type, arg, commands); - sk = ep->base.sk; - /* If the endpoint is not listening or if the number of associations - * on the TCP-style socket exceed the max backlog, respond with an - * ABORT. - */ - if (!sctp_sstate(sk, LISTENING) || - (sctp_style(sk, TCP) && - sk_acceptq_is_full(sk))) - return sctp_sf_tabort_8_4_8(ep, asoc, type, arg, commands); - /* 3.1 A packet containing an INIT chunk MUST have a zero Verification * Tag. */ @@ -461,17 +475,17 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(const struct sctp_endpoint *ep, if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(ep, asoc, type, arg, commands); - /* Make sure that the INIT-ACK chunk has a valid length */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_initack_chunk_t))) - return sctp_sf_violation_chunklen(ep, asoc, type, arg, - commands); /* 6.10 Bundling * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. */ if (!chunk->singleton) - return SCTP_DISPOSITION_VIOLATION; + return sctp_sf_violation_chunk(ep, asoc, type, arg, commands); + /* Make sure that the INIT-ACK chunk has a valid length */ + if (!sctp_chunk_length_valid(chunk, sizeof(sctp_initack_chunk_t))) + return sctp_sf_violation_chunklen(ep, asoc, type, arg, + commands); /* Grab the INIT header. */ chunk->subh.init_hdr = (sctp_inithdr_t *) chunk->skb->data; @@ -590,12 +604,13 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep, struct sctp_ulpevent *ev, *ai_ev = NULL; int error = 0; struct sctp_chunk *err_chk_p; + struct sock *sk; /* If the packet is an OOTB packet which is temporarily on the * control endpoint, respond with an ABORT. */ if (ep == sctp_sk((sctp_get_ctl_sock()))->ep) - return sctp_sf_ootb(ep, asoc, type, arg, commands); + return sctp_sf_tabort_8_4_8(ep, asoc, type, arg, commands); /* Make sure that the COOKIE_ECHO chunk has a valid length. * In this case, we check that we have enough for at least a @@ -605,6 +620,15 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep, if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) return sctp_sf_pdiscard(ep, asoc, type, arg, commands); + /* If the endpoint is not listening or if the number of associations + * on the TCP-style socket exceed the max backlog, respond with an + * ABORT. + */ + sk = ep->base.sk; + if (!sctp_sstate(sk, LISTENING) || + (sctp_style(sk, TCP) && sk_acceptq_is_full(sk))) + return sctp_sf_tabort_8_4_8(ep, asoc, type, arg, commands); + /* "Decode" the chunk. We have no optional parameters so we * are in good shape. */ @@ -1032,19 +1056,21 @@ sctp_disposition_t sctp_sf_backbeat_8_3(const struct sctp_endpoint *ep, /* This should never happen, but lets log it if so. */ if (unlikely(!link)) { if (from_addr.sa.sa_family == AF_INET6) { - printk(KERN_WARNING - "%s association %p could not find address " - NIP6_FMT "\n", - __FUNCTION__, - asoc, - NIP6(from_addr.v6.sin6_addr)); + if (net_ratelimit()) + printk(KERN_WARNING + "%s association %p could not find address " + NIP6_FMT "\n", + __FUNCTION__, + asoc, + NIP6(from_addr.v6.sin6_addr)); } else { - printk(KERN_WARNING - "%s association %p could not find address " - NIPQUAD_FMT "\n", - __FUNCTION__, - asoc, - NIPQUAD(from_addr.v4.sin_addr.s_addr)); + if (net_ratelimit()) + printk(KERN_WARNING + "%s association %p could not find address " + NIPQUAD_FMT "\n", + __FUNCTION__, + asoc, + NIPQUAD(from_addr.v4.sin_addr.s_addr)); } return SCTP_DISPOSITION_DISCARD; } @@ -2495,6 +2521,11 @@ sctp_disposition_t sctp_sf_do_9_2_reshutack(const struct sctp_endpoint *ep, struct sctp_chunk *chunk = (struct sctp_chunk *) arg; struct sctp_chunk *reply; + /* Make sure that the chunk has a valid length */ + if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + return sctp_sf_violation_chunklen(ep, asoc, type, arg, + commands); + /* Since we are not going to really process this INIT, there * is no point in verifying chunk boundries. Just generate * the SHUTDOWN ACK. @@ -2928,7 +2959,7 @@ sctp_disposition_t sctp_sf_eat_sack_6_2(const struct sctp_endpoint *ep, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_tabort_8_4_8(const struct sctp_endpoint *ep, +static sctp_disposition_t sctp_sf_tabort_8_4_8(const struct sctp_endpoint *ep, const struct sctp_association *asoc, const sctp_subtype_t type, void *arg, @@ -2964,6 +2995,7 @@ sctp_disposition_t sctp_sf_tabort_8_4_8(const struct sctp_endpoint *ep, SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS); + sctp_sf_pdiscard(ep, asoc, type, arg, commands); return SCTP_DISPOSITION_CONSUME; } @@ -3124,14 +3156,14 @@ sctp_disposition_t sctp_sf_ootb(const struct sctp_endpoint *ep, ch = (sctp_chunkhdr_t *) chunk->chunk_hdr; do { - /* Break out if chunk length is less then minimal. */ + /* Report violation if the chunk is less then minimal */ if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) - break; - - ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); - if (ch_end > skb_tail_pointer(skb)) - break; + return sctp_sf_violation_chunklen(ep, asoc, type, arg, + commands); + /* Now that we know we at least have a chunk header, + * do things that are type appropriate. + */ if (SCTP_CID_SHUTDOWN_ACK == ch->type) ootb_shut_ack = 1; @@ -3143,15 +3175,19 @@ sctp_disposition_t sctp_sf_ootb(const struct sctp_endpoint *ep, if (SCTP_CID_ABORT == ch->type) return sctp_sf_pdiscard(ep, asoc, type, arg, commands); + /* Report violation if chunk len overflows */ + ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); + if (ch_end > skb_tail_pointer(skb)) + return sctp_sf_violation_chunklen(ep, asoc, type, arg, + commands); + ch = (sctp_chunkhdr_t *) ch_end; } while (ch_end < skb_tail_pointer(skb)); if (ootb_shut_ack) - sctp_sf_shut_8_4_5(ep, asoc, type, arg, commands); + return sctp_sf_shut_8_4_5(ep, asoc, type, arg, commands); else - sctp_sf_tabort_8_4_8(ep, asoc, type, arg, commands); - - return sctp_sf_pdiscard(ep, asoc, type, arg, commands); + return sctp_sf_tabort_8_4_8(ep, asoc, type, arg, commands); } /* @@ -3217,7 +3253,11 @@ static sctp_disposition_t sctp_sf_shut_8_4_5(const struct sctp_endpoint *ep, if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) return sctp_sf_pdiscard(ep, asoc, type, arg, commands); - return SCTP_DISPOSITION_CONSUME; + /* We need to discard the rest of the packet to prevent + * potential bomming attacks from additional bundled chunks. + * This is documented in SCTP Threats ID. + */ + return sctp_sf_pdiscard(ep, asoc, type, arg, commands); } return SCTP_DISPOSITION_NOMEM; @@ -3240,6 +3280,13 @@ sctp_disposition_t sctp_sf_do_8_5_1_E_sa(const struct sctp_endpoint *ep, void *arg, sctp_cmd_seq_t *commands) { + struct sctp_chunk *chunk = arg; + + /* Make sure that the SHUTDOWN_ACK chunk has a valid length. */ + if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + return sctp_sf_violation_chunklen(ep, asoc, type, arg, + commands); + /* Although we do have an association in this case, it corresponds * to a restarted association. So the packet is treated as an OOTB * packet and the state function that handles OOTB SHUTDOWN_ACK is @@ -3256,8 +3303,11 @@ sctp_disposition_t sctp_sf_do_asconf(const struct sctp_endpoint *ep, { struct sctp_chunk *chunk = arg; struct sctp_chunk *asconf_ack = NULL; + struct sctp_paramhdr *err_param = NULL; sctp_addiphdr_t *hdr; + union sctp_addr_param *addr_param; __u32 serial; + int length; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, @@ -3273,6 +3323,20 @@ sctp_disposition_t sctp_sf_do_asconf(const struct sctp_endpoint *ep, hdr = (sctp_addiphdr_t *)chunk->skb->data; serial = ntohl(hdr->serial); + addr_param = (union sctp_addr_param *)hdr->params; + length = ntohs(addr_param->p.length); + if (length < sizeof(sctp_paramhdr_t)) + return sctp_sf_violation_paramlen(ep, asoc, type, + (void *)addr_param, commands); + + /* Verify the ASCONF chunk before processing it. */ + if (!sctp_verify_asconf(asoc, + (sctp_paramhdr_t *)((void *)addr_param + length), + (void *)chunk->chunk_end, + &err_param)) + return sctp_sf_violation_paramlen(ep, asoc, type, + (void *)&err_param, commands); + /* ADDIP 4.2 C1) Compare the value of the serial number to the value * the endpoint stored in a new association variable * 'Peer-Serial-Number'. @@ -3327,6 +3391,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(const struct sctp_endpoint *ep, struct sctp_chunk *asconf_ack = arg; struct sctp_chunk *last_asconf = asoc->addip_last_asconf; struct sctp_chunk *abort; + struct sctp_paramhdr *err_param = NULL; sctp_addiphdr_t *addip_hdr; __u32 sent_serial, rcvd_serial; @@ -3344,6 +3409,14 @@ sctp_disposition_t sctp_sf_do_asconf_ack(const struct sctp_endpoint *ep, addip_hdr = (sctp_addiphdr_t *)asconf_ack->skb->data; rcvd_serial = ntohl(addip_hdr->serial); + /* Verify the ASCONF-ACK chunk before processing it. */ + if (!sctp_verify_asconf(asoc, + (sctp_paramhdr_t *)addip_hdr->params, + (void *)asconf_ack->chunk_end, + &err_param)) + return sctp_sf_violation_paramlen(ep, asoc, type, + (void *)&err_param, commands); + if (last_asconf) { addip_hdr = (sctp_addiphdr_t *)last_asconf->subh.addip_hdr; sent_serial = ntohl(addip_hdr->serial); @@ -3362,7 +3435,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(const struct sctp_endpoint *ep, abort = sctp_make_abort(asoc, asconf_ack, sizeof(sctp_errhdr_t)); if (abort) { - sctp_init_cause(abort, SCTP_ERROR_ASCONF_ACK, NULL, 0); + sctp_init_cause(abort, SCTP_ERROR_ASCONF_ACK, 0); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); } @@ -3392,7 +3465,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(const struct sctp_endpoint *ep, abort = sctp_make_abort(asoc, asconf_ack, sizeof(sctp_errhdr_t)); if (abort) { - sctp_init_cause(abort, SCTP_ERROR_RSRC_LOW, NULL, 0); + sctp_init_cause(abort, SCTP_ERROR_RSRC_LOW, 0); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); } @@ -3654,6 +3727,16 @@ sctp_disposition_t sctp_sf_discard_chunk(const struct sctp_endpoint *ep, void *arg, sctp_cmd_seq_t *commands) { + struct sctp_chunk *chunk = arg; + + /* Make sure that the chunk has a valid length. + * Since we don't know the chunk type, we use a general + * chunkhdr structure to make a comparison. + */ + if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + return sctp_sf_violation_chunklen(ep, asoc, type, arg, + commands); + SCTP_DEBUG_PRINTK("Chunk %d is discarded\n", type.chunk); return SCTP_DISPOSITION_DISCARD; } @@ -3709,6 +3792,13 @@ sctp_disposition_t sctp_sf_violation(const struct sctp_endpoint *ep, void *arg, sctp_cmd_seq_t *commands) { + struct sctp_chunk *chunk = arg; + + /* Make sure that the chunk has a valid length. */ + if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + return sctp_sf_violation_chunklen(ep, asoc, type, arg, + commands); + return SCTP_DISPOSITION_VIOLATION; } @@ -3716,12 +3806,14 @@ sctp_disposition_t sctp_sf_violation(const struct sctp_endpoint *ep, * Common function to handle a protocol violation. */ static sctp_disposition_t sctp_sf_abort_violation( + const struct sctp_endpoint *ep, const struct sctp_association *asoc, void *arg, sctp_cmd_seq_t *commands, const __u8 *payload, const size_t paylen) { + struct sctp_packet *packet = NULL; struct sctp_chunk *chunk = arg; struct sctp_chunk *abort = NULL; @@ -3730,30 +3822,51 @@ static sctp_disposition_t sctp_sf_abort_violation( if (!abort) goto nomem; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); - SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS); + if (asoc) { + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); + SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS); - if (asoc->state <= SCTP_STATE_COOKIE_ECHOED) { - sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, - SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); - sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, - SCTP_ERROR(ECONNREFUSED)); - sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED, - SCTP_PERR(SCTP_ERROR_PROTO_VIOLATION)); + if (asoc->state <= SCTP_STATE_COOKIE_ECHOED) { + sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, + SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); + sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, + SCTP_ERROR(ECONNREFUSED)); + sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED, + SCTP_PERR(SCTP_ERROR_PROTO_VIOLATION)); + } else { + sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, + SCTP_ERROR(ECONNABORTED)); + sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, + SCTP_PERR(SCTP_ERROR_PROTO_VIOLATION)); + SCTP_DEC_STATS(SCTP_MIB_CURRESTAB); + } } else { - sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, - SCTP_ERROR(ECONNABORTED)); - sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, - SCTP_PERR(SCTP_ERROR_PROTO_VIOLATION)); - SCTP_DEC_STATS(SCTP_MIB_CURRESTAB); + packet = sctp_ootb_pkt_new(asoc, chunk); + + if (!packet) + goto nomem_pkt; + + if (sctp_test_T_bit(abort)) + packet->vtag = ntohl(chunk->sctp_hdr->vtag); + + abort->skb->sk = ep->base.sk; + + sctp_packet_append_chunk(packet, abort); + + sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, + SCTP_PACKET(packet)); + + SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS); } - sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL()); + sctp_sf_pdiscard(ep, asoc, SCTP_ST_CHUNK(0), arg, commands); SCTP_INC_STATS(SCTP_MIB_ABORTEDS); return SCTP_DISPOSITION_ABORT; +nomem_pkt: + sctp_chunk_free(abort); nomem: return SCTP_DISPOSITION_NOMEM; } @@ -3786,7 +3899,24 @@ static sctp_disposition_t sctp_sf_violation_chunklen( { char err_str[]="The following chunk had invalid length:"; - return sctp_sf_abort_violation(asoc, arg, commands, err_str, + return sctp_sf_abort_violation(ep, asoc, arg, commands, err_str, + sizeof(err_str)); +} + +/* + * Handle a protocol violation when the parameter length is invalid. + * "Invalid" length is identified as smaller then the minimal length a + * given parameter can be. + */ +static sctp_disposition_t sctp_sf_violation_paramlen( + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const sctp_subtype_t type, + void *arg, + sctp_cmd_seq_t *commands) { + char err_str[] = "The following parameter had invalid length:"; + + return sctp_sf_abort_violation(ep, asoc, arg, commands, err_str, sizeof(err_str)); } @@ -3805,10 +3935,31 @@ static sctp_disposition_t sctp_sf_violation_ctsn( { char err_str[]="The cumulative tsn ack beyond the max tsn currently sent:"; - return sctp_sf_abort_violation(asoc, arg, commands, err_str, + return sctp_sf_abort_violation(ep, asoc, arg, commands, err_str, sizeof(err_str)); } +/* Handle protocol violation of an invalid chunk bundling. For example, + * when we have an association and we recieve bundled INIT-ACK, or + * SHUDOWN-COMPLETE, our peer is clearly violationg the "MUST NOT bundle" + * statement from the specs. Additinally, there might be an attacker + * on the path and we may not want to continue this communication. + */ +static sctp_disposition_t sctp_sf_violation_chunk( + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const sctp_subtype_t type, + void *arg, + sctp_cmd_seq_t *commands) +{ + char err_str[]="The following chunk violates protocol:"; + + if (!asoc) + return sctp_sf_violation(ep, asoc, type, arg, commands); + + return sctp_sf_abort_violation(ep, asoc, arg, commands, err_str, + sizeof(err_str)); +} /*************************************************************************** * These are the state functions for handling primitive (Section 10) events. ***************************************************************************/ @@ -5175,7 +5326,22 @@ static struct sctp_packet *sctp_ootb_pkt_new(const struct sctp_association *asoc * association exists, otherwise, use the peer's vtag. */ if (asoc) { - vtag = asoc->peer.i.init_tag; + /* Special case the INIT-ACK as there is no peer's vtag + * yet. + */ + switch(chunk->chunk_hdr->type) { + case SCTP_CID_INIT_ACK: + { + sctp_initack_chunk_t *initack; + + initack = (sctp_initack_chunk_t *)chunk->chunk_hdr; + vtag = ntohl(initack->init_hdr.init_tag); + break; + } + default: + vtag = asoc->peer.i.init_tag; + break; + } } else { /* Special case the INIT and stale COOKIE_ECHO as there is no * vtag yet. diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 70a91ece3c4..ddb0ba3974b 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -110,7 +110,7 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, /* SCTP_STATE_EMPTY */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ - TYPE_SCTP_FUNC(sctp_sf_tabort_8_4_8), \ + TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ @@ -173,7 +173,7 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, /* SCTP_STATE_EMPTY */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ - TYPE_SCTP_FUNC(sctp_sf_tabort_8_4_8), \ + TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ @@ -194,7 +194,7 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, /* SCTP_STATE_EMPTY */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ - TYPE_SCTP_FUNC(sctp_sf_tabort_8_4_8), \ + TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ @@ -216,7 +216,7 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, /* SCTP_STATE_EMPTY */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ - TYPE_SCTP_FUNC(sctp_sf_tabort_8_4_8), \ + TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_violation), \ /* SCTP_STATE_COOKIE_ECHOED */ \ @@ -258,7 +258,7 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, /* SCTP_STATE_EMPTY */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ - TYPE_SCTP_FUNC(sctp_sf_tabort_8_4_8), \ + TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ @@ -300,7 +300,7 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type, /* SCTP_STATE_EMPTY */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ - TYPE_SCTP_FUNC(sctp_sf_tabort_8_4_8), \ + TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ @@ -499,7 +499,7 @@ static const sctp_sm_table_entry_t addip_chunk_event_table[SCTP_NUM_ADDIP_CHUNK_ /* SCTP_STATE_EMPTY */ \ TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_CLOSED */ \ - TYPE_SCTP_FUNC(sctp_sf_tabort_8_4_8), \ + TYPE_SCTP_FUNC(sctp_sf_ootb), \ /* SCTP_STATE_COOKIE_WAIT */ \ TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \ /* SCTP_STATE_COOKIE_ECHOED */ \ @@ -528,7 +528,7 @@ chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_EMPTY */ TYPE_SCTP_FUNC(sctp_sf_ootb), /* SCTP_STATE_CLOSED */ - TYPE_SCTP_FUNC(sctp_sf_tabort_8_4_8), + TYPE_SCTP_FUNC(sctp_sf_ootb), /* SCTP_STATE_COOKIE_WAIT */ TYPE_SCTP_FUNC(sctp_sf_unk_chunk), /* SCTP_STATE_COOKIE_ECHOED */ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 01c6364245b..772fbfb4bfd 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -353,6 +353,7 @@ SCTP_STATIC int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) * The function sctp_get_port_local() does duplicate address * detection. */ + addr->v4.sin_port = htons(snum); if ((ret = sctp_get_port_local(sk, addr))) { if (ret == (long) sk) { /* This endpoint has a conflicting address. */ @@ -366,14 +367,10 @@ SCTP_STATIC int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) if (!bp->port) bp->port = inet_sk(sk)->num; - /* Add the address to the bind address list. */ - sctp_local_bh_disable(); - sctp_write_lock(&ep->base.addr_lock); - - /* Use GFP_ATOMIC since BHs are disabled. */ + /* Add the address to the bind address list. + * Use GFP_ATOMIC since BHs will be disabled. + */ ret = sctp_add_bind_addr(bp, addr, 1, GFP_ATOMIC); - sctp_write_unlock(&ep->base.addr_lock); - sctp_local_bh_enable(); /* Copy back into socket for getsockname() use. */ if (!ret) { @@ -543,15 +540,12 @@ static int sctp_send_asconf_add_ip(struct sock *sk, if (i < addrcnt) continue; - /* Use the first address in bind addr list of association as - * Address Parameter of ASCONF CHUNK. + /* Use the first valid address in bind addr list of + * association as Address Parameter of ASCONF CHUNK. */ - sctp_read_lock(&asoc->base.addr_lock); bp = &asoc->base.bind_addr; p = bp->address_list.next; laddr = list_entry(p, struct sctp_sockaddr_entry, list); - sctp_read_unlock(&asoc->base.addr_lock); - chunk = sctp_make_asconf_update_ip(asoc, &laddr->a, addrs, addrcnt, SCTP_PARAM_ADD_IP); if (!chunk) { @@ -566,8 +560,6 @@ static int sctp_send_asconf_add_ip(struct sock *sk, /* Add the new addresses to the bind address list with * use_as_src set to 0. */ - sctp_local_bh_disable(); - sctp_write_lock(&asoc->base.addr_lock); addr_buf = addrs; for (i = 0; i < addrcnt; i++) { addr = (union sctp_addr *)addr_buf; @@ -577,8 +569,6 @@ static int sctp_send_asconf_add_ip(struct sock *sk, GFP_ATOMIC); addr_buf += af->sockaddr_len; } - sctp_write_unlock(&asoc->base.addr_lock); - sctp_local_bh_enable(); } out: @@ -650,13 +640,7 @@ 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 */ - sctp_local_bh_disable(); - sctp_write_lock(&ep->base.addr_lock); - - retval = sctp_del_bind_addr(bp, sa_addr); - - sctp_write_unlock(&ep->base.addr_lock); - sctp_local_bh_enable(); + retval = sctp_del_bind_addr(bp, sa_addr, call_rcu); addr_buf += af->sockaddr_len; err_bindx_rem: @@ -747,14 +731,16 @@ static int sctp_send_asconf_del_ip(struct sock *sk, * make sure that we do not delete all the addresses in the * association. */ - sctp_read_lock(&asoc->base.addr_lock); bp = &asoc->base.bind_addr; laddr = sctp_find_unmatch_addr(bp, (union sctp_addr *)addrs, addrcnt, sp); - sctp_read_unlock(&asoc->base.addr_lock); if (!laddr) continue; + /* We do not need RCU protection throughout this loop + * because this is done under a socket lock from the + * setsockopt call. + */ chunk = sctp_make_asconf_update_ip(asoc, laddr, addrs, addrcnt, SCTP_PARAM_DEL_IP); if (!chunk) { @@ -765,23 +751,16 @@ static int sctp_send_asconf_del_ip(struct sock *sk, /* Reset use_as_src flag for the addresses in the bind address * list that are to be deleted. */ - sctp_local_bh_disable(); - sctp_write_lock(&asoc->base.addr_lock); addr_buf = addrs; for (i = 0; i < addrcnt; i++) { laddr = (union sctp_addr *)addr_buf; af = sctp_get_af_specific(laddr->v4.sin_family); - list_for_each(pos1, &bp->address_list) { - saddr = list_entry(pos1, - struct sctp_sockaddr_entry, - list); + list_for_each_entry(saddr, &bp->address_list, list) { if (sctp_cmp_addr_exact(&saddr->a, laddr)) saddr->use_as_src = 0; } addr_buf += af->sockaddr_len; } - sctp_write_unlock(&asoc->base.addr_lock); - sctp_local_bh_enable(); /* Update the route and saddr entries for all the transports * as some of the addresses in the bind address list are @@ -4058,9 +4037,7 @@ static int sctp_getsockopt_local_addrs_num_old(struct sock *sk, int len, sctp_assoc_t id; struct sctp_bind_addr *bp; struct sctp_association *asoc; - struct list_head *pos, *temp; struct sctp_sockaddr_entry *addr; - rwlock_t *addr_lock; int cnt = 0; if (len < sizeof(sctp_assoc_t)) @@ -4077,17 +4054,13 @@ static int sctp_getsockopt_local_addrs_num_old(struct sock *sk, int len, */ if (0 == id) { bp = &sctp_sk(sk)->ep->base.bind_addr; - addr_lock = &sctp_sk(sk)->ep->base.addr_lock; } else { asoc = sctp_id2assoc(sk, id); if (!asoc) return -EINVAL; bp = &asoc->base.bind_addr; - addr_lock = &asoc->base.addr_lock; } - sctp_read_lock(addr_lock); - /* If the endpoint is bound to 0.0.0.0 or ::0, count the valid * addresses from the global local address list. */ @@ -4095,27 +4068,33 @@ static int sctp_getsockopt_local_addrs_num_old(struct sock *sk, int len, addr = list_entry(bp->address_list.next, struct sctp_sockaddr_entry, list); if (sctp_is_any(&addr->a)) { - list_for_each_safe(pos, temp, &sctp_local_addr_list) { - addr = list_entry(pos, - struct sctp_sockaddr_entry, - list); + rcu_read_lock(); + list_for_each_entry_rcu(addr, + &sctp_local_addr_list, list) { + if (!addr->valid) + continue; + if ((PF_INET == sk->sk_family) && (AF_INET6 == addr->a.sa.sa_family)) continue; + cnt++; } + rcu_read_unlock(); } else { cnt = 1; } goto done; } - list_for_each(pos, &bp->address_list) { + /* Protection on the bound address list is not needed, + * since in the socket option context we hold the socket lock, + * so there is no way that the bound address list can change. + */ + list_for_each_entry(addr, &bp->address_list, list) { cnt ++; } - done: - sctp_read_unlock(addr_lock); return cnt; } @@ -4126,14 +4105,16 @@ static int sctp_copy_laddrs_old(struct sock *sk, __u16 port, int max_addrs, void *to, int *bytes_copied) { - struct list_head *pos, *next; struct sctp_sockaddr_entry *addr; union sctp_addr temp; int cnt = 0; int addrlen; - list_for_each_safe(pos, next, &sctp_local_addr_list) { - addr = list_entry(pos, struct sctp_sockaddr_entry, list); + rcu_read_lock(); + list_for_each_entry_rcu(addr, &sctp_local_addr_list, list) { + if (!addr->valid) + continue; + if ((PF_INET == sk->sk_family) && (AF_INET6 == addr->a.sa.sa_family)) continue; @@ -4148,6 +4129,7 @@ static int sctp_copy_laddrs_old(struct sock *sk, __u16 port, cnt ++; if (cnt >= max_addrs) break; } + rcu_read_unlock(); return cnt; } @@ -4155,14 +4137,16 @@ static int sctp_copy_laddrs_old(struct sock *sk, __u16 port, static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, size_t space_left, int *bytes_copied) { - struct list_head *pos, *next; struct sctp_sockaddr_entry *addr; union sctp_addr temp; int cnt = 0; int addrlen; - list_for_each_safe(pos, next, &sctp_local_addr_list) { - addr = list_entry(pos, struct sctp_sockaddr_entry, list); + rcu_read_lock(); + list_for_each_entry_rcu(addr, &sctp_local_addr_list, list) { + if (!addr->valid) + continue; + if ((PF_INET == sk->sk_family) && (AF_INET6 == addr->a.sa.sa_family)) continue; @@ -4170,8 +4154,10 @@ static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk), &temp); addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; - if (space_left < addrlen) - return -ENOMEM; + if (space_left < addrlen) { + cnt = -ENOMEM; + break; + } memcpy(to, &temp, addrlen); to += addrlen; @@ -4179,6 +4165,7 @@ static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, space_left -= addrlen; *bytes_copied += addrlen; } + rcu_read_unlock(); return cnt; } @@ -4191,7 +4178,6 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, { struct sctp_bind_addr *bp; struct sctp_association *asoc; - struct list_head *pos; int cnt = 0; struct sctp_getaddrs_old getaddrs; struct sctp_sockaddr_entry *addr; @@ -4199,7 +4185,6 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, union sctp_addr temp; struct sctp_sock *sp = sctp_sk(sk); int addrlen; - rwlock_t *addr_lock; int err = 0; void *addrs; void *buf; @@ -4221,13 +4206,11 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, */ if (0 == getaddrs.assoc_id) { bp = &sctp_sk(sk)->ep->base.bind_addr; - addr_lock = &sctp_sk(sk)->ep->base.addr_lock; } else { asoc = sctp_id2assoc(sk, getaddrs.assoc_id); if (!asoc) return -EINVAL; bp = &asoc->base.bind_addr; - addr_lock = &asoc->base.addr_lock; } to = getaddrs.addrs; @@ -4241,8 +4224,6 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, if (!addrs) return -ENOMEM; - sctp_read_lock(addr_lock); - /* If the endpoint is bound to 0.0.0.0 or ::0, get the valid * addresses from the global local address list. */ @@ -4258,8 +4239,11 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, } buf = addrs; - list_for_each(pos, &bp->address_list) { - addr = list_entry(pos, struct sctp_sockaddr_entry, list); + /* Protection on the bound address list is not needed since + * in the socket option context we hold a socket lock and + * thus the bound address list can't change. + */ + list_for_each_entry(addr, &bp->address_list, list) { memcpy(&temp, &addr->a, sizeof(temp)); sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp); addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; @@ -4271,8 +4255,6 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, } copy_getaddrs: - sctp_read_unlock(addr_lock); - /* copy the entire address list into the user provided space */ if (copy_to_user(to, addrs, bytes_copied)) { err = -EFAULT; @@ -4294,7 +4276,6 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len, { struct sctp_bind_addr *bp; struct sctp_association *asoc; - struct list_head *pos; int cnt = 0; struct sctp_getaddrs getaddrs; struct sctp_sockaddr_entry *addr; @@ -4302,7 +4283,6 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len, union sctp_addr temp; struct sctp_sock *sp = sctp_sk(sk); int addrlen; - rwlock_t *addr_lock; int err = 0; size_t space_left; int bytes_copied = 0; @@ -4323,13 +4303,11 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len, */ if (0 == getaddrs.assoc_id) { bp = &sctp_sk(sk)->ep->base.bind_addr; - addr_lock = &sctp_sk(sk)->ep->base.addr_lock; } else { asoc = sctp_id2assoc(sk, getaddrs.assoc_id); if (!asoc) return -EINVAL; bp = &asoc->base.bind_addr; - addr_lock = &asoc->base.addr_lock; } to = optval + offsetof(struct sctp_getaddrs,addrs); @@ -4339,8 +4317,6 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len, if (!addrs) return -ENOMEM; - sctp_read_lock(addr_lock); - /* If the endpoint is bound to 0.0.0.0 or ::0, get the valid * addresses from the global local address list. */ @@ -4352,21 +4328,24 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len, space_left, &bytes_copied); if (cnt < 0) { err = cnt; - goto error_lock; + goto out; } goto copy_getaddrs; } } buf = addrs; - list_for_each(pos, &bp->address_list) { - addr = list_entry(pos, struct sctp_sockaddr_entry, list); + /* Protection on the bound address list is not needed since + * in the socket option context we hold a socket lock and + * thus the bound address list can't change. + */ + list_for_each_entry(addr, &bp->address_list, list) { memcpy(&temp, &addr->a, sizeof(temp)); sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp); addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; if (space_left < addrlen) { err = -ENOMEM; /*fixme: right error?*/ - goto error_lock; + goto out; } memcpy(buf, &temp, addrlen); buf += addrlen; @@ -4376,8 +4355,6 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len, } copy_getaddrs: - sctp_read_unlock(addr_lock); - if (copy_to_user(to, addrs, bytes_copied)) { err = -EFAULT; goto out; @@ -4388,12 +4365,6 @@ copy_getaddrs: } if (put_user(bytes_copied, optlen)) err = -EFAULT; - - goto out; - -error_lock: - sctp_read_unlock(addr_lock); - out: kfree(addrs); return err; @@ -5202,6 +5173,7 @@ SCTP_STATIC int sctp_seqpacket_listen(struct sock *sk, int backlog) sctp_unhash_endpoint(ep); sk->sk_state = SCTP_SS_CLOSED; + return 0; } /* Return if we are already listening. */ @@ -5249,6 +5221,7 @@ SCTP_STATIC int sctp_stream_listen(struct sock *sk, int backlog) sctp_unhash_endpoint(ep); sk->sk_state = SCTP_SS_CLOSED; + return 0; } if (sctp_sstate(sk, LISTENING)) diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 34eb977a204..fa0ba2a5564 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -659,6 +659,46 @@ done: return retval; } +/* + * Flush out stale fragments from the reassembly queue when processing + * a Forward TSN. + * + * RFC 3758, Section 3.6 + * + * After receiving and processing a FORWARD TSN, the data receiver MUST + * take cautions in updating its re-assembly queue. The receiver MUST + * remove any partially reassembled message, which is still missing one + * or more TSNs earlier than or equal to the new cumulative TSN point. + * In the event that the receiver has invoked the partial delivery API, + * a notification SHOULD also be generated to inform the upper layer API + * that the message being partially delivered will NOT be completed. + */ +void sctp_ulpq_reasm_flushtsn(struct sctp_ulpq *ulpq, __u32 fwd_tsn) +{ + struct sk_buff *pos, *tmp; + struct sctp_ulpevent *event; + __u32 tsn; + + if (skb_queue_empty(&ulpq->reasm)) + return; + + skb_queue_walk_safe(&ulpq->reasm, pos, tmp) { + event = sctp_skb2event(pos); + tsn = event->tsn; + + /* Since the entire message must be abandoned by the + * sender (item A3 in Section 3.5, RFC 3758), we can + * free all fragments on the list that are less then + * or equal to ctsn_point + */ + if (TSN_lte(tsn, fwd_tsn)) { + __skb_unlink(pos, &ulpq->reasm); + sctp_ulpevent_free(event); + } else + break; + } +} + /* Helper function to gather skbs that have possibly become * ordered by an an incoming chunk. */ @@ -794,7 +834,7 @@ static struct sctp_ulpevent *sctp_ulpq_order(struct sctp_ulpq *ulpq, /* Helper function to gather skbs that have possibly become * ordered by forward tsn skipping their dependencies. */ -static inline void sctp_ulpq_reap_ordered(struct sctp_ulpq *ulpq) +static inline void sctp_ulpq_reap_ordered(struct sctp_ulpq *ulpq, __u16 sid) { struct sk_buff *pos, *tmp; struct sctp_ulpevent *cevent; @@ -813,31 +853,40 @@ static inline void sctp_ulpq_reap_ordered(struct sctp_ulpq *ulpq) csid = cevent->stream; cssn = cevent->ssn; - if (cssn != sctp_ssn_peek(in, csid)) + /* Have we gone too far? */ + if (csid > sid) break; - /* Found it, so mark in the ssnmap. */ - sctp_ssn_next(in, csid); + /* Have we not gone far enough? */ + if (csid < sid) + continue; + + /* see if this ssn has been marked by skipping */ + if (!SSN_lt(cssn, sctp_ssn_peek(in, csid))) + break; __skb_unlink(pos, &ulpq->lobby); - if (!event) { + if (!event) /* Create a temporary list to collect chunks on. */ event = sctp_skb2event(pos); - __skb_queue_tail(&temp, sctp_event2skb(event)); - } else { - /* Attach all gathered skbs to the event. */ - __skb_queue_tail(&temp, pos); - } + + /* Attach all gathered skbs to the event. */ + __skb_queue_tail(&temp, pos); } /* Send event to the ULP. 'event' is the sctp_ulpevent for * very first SKB on the 'temp' list. */ - if (event) + if (event) { + /* see if we have more ordered that we can deliver */ + sctp_ulpq_retrieve_ordered(ulpq, event); sctp_ulpq_tail_event(ulpq, event); + } } -/* Skip over an SSN. */ +/* Skip over an SSN. This is used during the processing of + * Forwared TSN chunk to skip over the abandoned ordered data + */ void sctp_ulpq_skip(struct sctp_ulpq *ulpq, __u16 sid, __u16 ssn) { struct sctp_stream *in; @@ -855,7 +904,7 @@ void sctp_ulpq_skip(struct sctp_ulpq *ulpq, __u16 sid, __u16 ssn) /* Go find any other chunks that were waiting for * ordering and deliver them if needed. */ - sctp_ulpq_reap_ordered(ulpq); + sctp_ulpq_reap_ordered(ulpq, sid); return; } diff --git a/net/socket.c b/net/socket.c index 7d44453dfae..b09eb9036a1 100644 --- a/net/socket.c +++ b/net/socket.c @@ -777,9 +777,6 @@ static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, if (pos != 0) return -ESPIPE; - if (iocb->ki_left == 0) /* Match SYS5 behaviour */ - return 0; - x = alloc_sock_iocb(iocb, &siocb); if (!x) return -ENOMEM; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 12ff5da8160..036ab520df2 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1110,7 +1110,8 @@ svc_tcp_accept(struct svc_sock *svsk) serv->sv_name); printk(KERN_NOTICE "%s: last TCP connect from %s\n", - serv->sv_name, buf); + serv->sv_name, __svc_print_addr(sin, + buf, sizeof(buf))); } /* * Always select the oldest socket. It's not fair, @@ -1592,7 +1593,7 @@ svc_age_temp_sockets(unsigned long closure) if (!test_and_set_bit(SK_OLD, &svsk->sk_flags)) continue; - if (atomic_read(&svsk->sk_inuse) || test_bit(SK_BUSY, &svsk->sk_flags)) + if (atomic_read(&svsk->sk_inuse) > 1 || test_bit(SK_BUSY, &svsk->sk_flags)) continue; atomic_inc(&svsk->sk_inuse); list_move(le, &to_be_aged); diff --git a/net/wireless/core.c b/net/wireless/core.c index 7eabd55417a..9771451eae2 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -213,7 +213,7 @@ out_fail_notifier: out_fail_sysfs: return err; } -module_init(cfg80211_init); +subsys_initcall(cfg80211_init); static void cfg80211_exit(void) { diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 88aaacd9f82..2d5d2255a27 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -52,12 +52,14 @@ static void wiphy_dev_release(struct device *dev) cfg80211_dev_free(rdev); } +#ifdef CONFIG_HOTPLUG static int wiphy_uevent(struct device *dev, char **envp, int num_envp, char *buf, int size) { /* TODO, we probably need stuff here */ return 0; } +#endif struct class ieee80211_class = { .name = "ieee80211", |