diff options
Diffstat (limited to 'net')
98 files changed, 819 insertions, 477 deletions
diff --git a/net/802/p8023.c b/net/802/p8023.c index d23e906456e..53cf0570928 100644 --- a/net/802/p8023.c +++ b/net/802/p8023.c @@ -59,3 +59,5 @@ void destroy_8023_client(struct datalink_proto *dl) EXPORT_SYMBOL(destroy_8023_client); EXPORT_SYMBOL(make_8023_client); + +MODULE_LICENSE("GPL"); diff --git a/net/802/psnap.c b/net/802/psnap.c index 4d638944d93..34e42968b47 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -59,8 +59,10 @@ static int snap_rcv(struct sk_buff *skb, struct net_device *dev, proto = find_snap_client(skb->h.raw); if (proto) { /* Pass the frame on. */ + u8 *hdr = skb->data; skb->h.raw += 5; skb_pull(skb, 5); + skb_postpull_rcsum(skb, hdr, 5); rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev); } else { skb->sk = NULL; diff --git a/net/Kconfig b/net/Kconfig index bc603d9aea5..5126f58d9c4 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -27,6 +27,13 @@ if NET menu "Networking options" +config NETDEBUG + bool "Network packet debugging" + help + You can say Y here if you want to get additional messages useful in + debugging bad packets, but can overwhelm logs under denial of service + attacks. + source "net/packet/Kconfig" source "net/unix/Kconfig" source "net/xfrm/Kconfig" diff --git a/net/atm/signaling.c b/net/atm/signaling.c index e7211a7f382..93ad59a28ef 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -56,7 +56,8 @@ static void sigd_put_skb(struct sk_buff *skb) remove_wait_queue(&sigd_sleep,&wait); #else if (!sigd) { - printk(KERN_WARNING "atmsvc: no signaling demon\n"); + if (net_ratelimit()) + printk(KERN_WARNING "atmsvc: no signaling demon\n"); kfree_skb(skb); return; } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index bdb6458c6bd..97bdec73d17 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -143,13 +143,15 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) static int hci_sock_release(struct socket *sock) { struct sock *sk = sock->sk; - struct hci_dev *hdev = hci_pi(sk)->hdev; + struct hci_dev *hdev; BT_DBG("sock %p sk %p", sock, sk); if (!sk) return 0; + hdev = hci_pi(sk)->hdev; + bt_sock_unlink(&hci_sk_list, sk); if (hdev) { @@ -311,14 +313,18 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, int *add { struct sockaddr_hci *haddr = (struct sockaddr_hci *) addr; struct sock *sk = sock->sk; + struct hci_dev *hdev = hci_pi(sk)->hdev; BT_DBG("sock %p sk %p", sock, sk); + if (!hdev) + return -EBADFD; + lock_sock(sk); *addr_len = sizeof(*haddr); haddr->hci_family = AF_BLUETOOTH; - haddr->hci_dev = hci_pi(sk)->hdev->id; + haddr->hci_dev = hdev->id; release_sock(sk); return 0; diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 0d89d643413..5b4253c61f6 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -46,13 +46,15 @@ #include <net/bluetooth/l2cap.h> #include <net/bluetooth/rfcomm.h> -#define VERSION "1.6" - #ifndef CONFIG_BT_RFCOMM_DEBUG #undef BT_DBG #define BT_DBG(D...) #endif +#define VERSION "1.7" + +static unsigned int l2cap_mtu = RFCOMM_MAX_L2CAP_MTU; + static struct task_struct *rfcomm_thread; static DECLARE_MUTEX(rfcomm_sem); @@ -623,7 +625,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst /* Set L2CAP options */ sk = sock->sk; lock_sock(sk); - l2cap_pi(sk)->imtu = RFCOMM_MAX_L2CAP_MTU; + l2cap_pi(sk)->imtu = l2cap_mtu; release_sock(sk); s = rfcomm_session_add(sock, BT_BOUND); @@ -1868,7 +1870,7 @@ static int rfcomm_add_listener(bdaddr_t *ba) /* Set L2CAP options */ sk = sock->sk; lock_sock(sk); - l2cap_pi(sk)->imtu = RFCOMM_MAX_L2CAP_MTU; + l2cap_pi(sk)->imtu = l2cap_mtu; release_sock(sk); /* Start listening on the socket */ @@ -2070,6 +2072,9 @@ static void __exit rfcomm_exit(void) module_init(rfcomm_init); module_exit(rfcomm_exit); +module_param(l2cap_mtu, uint, 0644); +MODULE_PARM_DESC(l2cap_mtu, "Default MTU for the L2CAP connection"); + MODULE_AUTHOR("Maxim Krasnyansky <maxk@qualcomm.com>, Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth RFCOMM ver " VERSION); MODULE_VERSION(VERSION); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index ba442883e87..7fa3a5a9971 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -79,9 +79,14 @@ static int port_cost(struct net_device *dev) */ static void port_carrier_check(void *arg) { - struct net_bridge_port *p = arg; + struct net_device *dev = arg; + struct net_bridge_port *p; rtnl_lock(); + p = dev->br_port; + if (!p) + goto done; + if (netif_carrier_ok(p->dev)) { u32 cost = port_cost(p->dev); @@ -97,9 +102,24 @@ static void port_carrier_check(void *arg) br_stp_disable_port(p); spin_unlock_bh(&p->br->lock); } +done: rtnl_unlock(); } +static void release_nbp(struct kobject *kobj) +{ + struct net_bridge_port *p + = container_of(kobj, struct net_bridge_port, kobj); + kfree(p); +} + +static struct kobj_type brport_ktype = { +#ifdef CONFIG_SYSFS + .sysfs_ops = &brport_sysfs_ops, +#endif + .release = release_nbp, +}; + static void destroy_nbp(struct net_bridge_port *p) { struct net_device *dev = p->dev; @@ -108,7 +128,7 @@ static void destroy_nbp(struct net_bridge_port *p) p->dev = NULL; dev_put(dev); - br_sysfs_freeif(p); + kobject_put(&p->kobj); } static void destroy_nbp_rcu(struct rcu_head *head) @@ -118,17 +138,25 @@ static void destroy_nbp_rcu(struct rcu_head *head) destroy_nbp(p); } -/* called with RTNL */ +/* Delete port(interface) from bridge is done in two steps. + * via RCU. First step, marks device as down. That deletes + * all the timers and stops new packets from flowing through. + * + * Final cleanup doesn't occur until after all CPU's finished + * processing packets. + * + * Protected from multiple admin operations by RTNL mutex + */ static void del_nbp(struct net_bridge_port *p) { struct net_bridge *br = p->br; struct net_device *dev = p->dev; - dev->br_port = NULL; + sysfs_remove_link(&br->ifobj, dev->name); + dev_set_promiscuity(dev, -1); cancel_delayed_work(&p->carrier_check); - flush_scheduled_work(); spin_lock_bh(&br->lock); br_stp_disable_port(p); @@ -138,10 +166,10 @@ static void del_nbp(struct net_bridge_port *p) list_del_rcu(&p->list); - del_timer_sync(&p->message_age_timer); - del_timer_sync(&p->forward_delay_timer); - del_timer_sync(&p->hold_timer); - + rcu_assign_pointer(dev->br_port, NULL); + + kobject_del(&p->kobj); + call_rcu(&p->rcu, destroy_nbp_rcu); } @@ -151,7 +179,6 @@ static void del_br(struct net_bridge *br) struct net_bridge_port *p, *n; list_for_each_entry_safe(p, n, &br->port_list, list) { - br_sysfs_removeif(p); del_nbp(p); } @@ -245,13 +272,17 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, p->dev = dev; p->path_cost = port_cost(dev); p->priority = 0x8000 >> BR_PORT_BITS; - dev->br_port = p; p->port_no = index; br_init_port(p); p->state = BR_STATE_DISABLED; - INIT_WORK(&p->carrier_check, port_carrier_check, p); + INIT_WORK(&p->carrier_check, port_carrier_check, dev); kobject_init(&p->kobj); + kobject_set_name(&p->kobj, SYSFS_BRIDGE_PORT_ATTR); + p->kobj.ktype = &brport_ktype; + p->kobj.parent = &(dev->class_dev.kobj); + p->kobj.kset = NULL; + return p; } @@ -379,30 +410,43 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (dev->br_port != NULL) return -EBUSY; - if (IS_ERR(p = new_nbp(br, dev))) + p = new_nbp(br, dev); + if (IS_ERR(p)) return PTR_ERR(p); - if ((err = br_fdb_insert(br, p, dev->dev_addr))) - destroy_nbp(p); - - else if ((err = br_sysfs_addif(p))) - del_nbp(p); - else { - dev_set_promiscuity(dev, 1); + err = kobject_add(&p->kobj); + if (err) + goto err0; - list_add_rcu(&p->list, &br->port_list); + err = br_fdb_insert(br, p, dev->dev_addr); + if (err) + goto err1; - spin_lock_bh(&br->lock); - br_stp_recalculate_bridge_id(br); - br_features_recompute(br); - if ((br->dev->flags & IFF_UP) - && (dev->flags & IFF_UP) && netif_carrier_ok(dev)) - br_stp_enable_port(p); - spin_unlock_bh(&br->lock); + err = br_sysfs_addif(p); + if (err) + goto err2; - dev_set_mtu(br->dev, br_min_mtu(br)); - } + rcu_assign_pointer(dev->br_port, p); + dev_set_promiscuity(dev, 1); + + list_add_rcu(&p->list, &br->port_list); + + spin_lock_bh(&br->lock); + br_stp_recalculate_bridge_id(br); + br_features_recompute(br); + schedule_delayed_work(&p->carrier_check, BR_PORT_DEBOUNCE); + spin_unlock_bh(&br->lock); + dev_set_mtu(br->dev, br_min_mtu(br)); + kobject_uevent(&p->kobj, KOBJ_ADD); + + return 0; +err2: + br_fdb_delete_by_port(br, p); +err1: + kobject_del(&p->kobj); +err0: + kobject_put(&p->kobj); return err; } @@ -414,7 +458,6 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) if (!p || p->br != br) return -EINVAL; - br_sysfs_removeif(p); del_nbp(p); spin_lock_bh(&br->lock); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index e3a73cead6b..4eef8375531 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -45,18 +45,20 @@ static void br_pass_frame_up(struct net_bridge *br, struct sk_buff *skb) int br_handle_frame_finish(struct sk_buff *skb) { const unsigned char *dest = eth_hdr(skb)->h_dest; - struct net_bridge_port *p = skb->dev->br_port; - struct net_bridge *br = p->br; + struct net_bridge_port *p = rcu_dereference(skb->dev->br_port); + struct net_bridge *br; struct net_bridge_fdb_entry *dst; int passedup = 0; + if (!p || p->state == BR_STATE_DISABLED) + goto drop; + /* insert into forwarding database after filtering to avoid spoofing */ - br_fdb_update(p->br, p, eth_hdr(skb)->h_source); + br = p->br; + br_fdb_update(br, p, eth_hdr(skb)->h_source); - if (p->state == BR_STATE_LEARNING) { - kfree_skb(skb); - goto out; - } + if (p->state == BR_STATE_LEARNING) + goto drop; if (br->dev->flags & IFF_PROMISC) { struct sk_buff *skb2; @@ -93,6 +95,9 @@ int br_handle_frame_finish(struct sk_buff *skb) out: return 0; +drop: + kfree_skb(skb); + goto out; } /* diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 7cac3fb9f80..e060aad8624 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -51,9 +51,6 @@ #define store_orig_dstaddr(skb) (skb_origaddr(skb) = (skb)->nh.iph->daddr) #define dnat_took_place(skb) (skb_origaddr(skb) != (skb)->nh.iph->daddr) -#define has_bridge_parent(device) ((device)->br_port != NULL) -#define bridge_parent(device) ((device)->br_port->br->dev) - #ifdef CONFIG_SYSCTL static struct ctl_table_header *brnf_sysctl_header; static int brnf_call_iptables = 1; @@ -93,11 +90,18 @@ static struct rtable __fake_rtable = { .dev = &__fake_net_device, .path = &__fake_rtable.u.dst, .metrics = {[RTAX_MTU - 1] = 1500}, + .flags = DST_NOXFRM, } }, .rt_flags = 0, }; +static inline struct net_device *bridge_parent(const struct net_device *dev) +{ + struct net_bridge_port *port = rcu_dereference(dev->br_port); + + return port ? port->br->dev : NULL; +} /* PF_BRIDGE/PRE_ROUTING *********************************************/ /* Undo the changes made for ip6tables PREROUTING and continue the @@ -189,11 +193,15 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) skb->nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; skb->dev = bridge_parent(skb->dev); - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { - skb_pull(skb, VLAN_HLEN); - skb->nh.raw += VLAN_HLEN; + if (!skb->dev) + kfree_skb(skb); + else { + if (skb->protocol == __constant_htons(ETH_P_8021Q)) { + skb_pull(skb, VLAN_HLEN); + skb->nh.raw += VLAN_HLEN; + } + skb->dst->output(skb); } - skb->dst->output(skb); return 0; } @@ -270,7 +278,7 @@ bridged_dnat: } /* Some common code for IPv4/IPv6 */ -static void setup_pre_routing(struct sk_buff *skb) +static struct net_device *setup_pre_routing(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = skb->nf_bridge; @@ -282,6 +290,8 @@ static void setup_pre_routing(struct sk_buff *skb) nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING; nf_bridge->physindev = skb->dev; skb->dev = bridge_parent(skb->dev); + + return skb->dev; } /* We only check the length. A bridge shouldn't do any hop-by-hop stuff anyway */ @@ -376,7 +386,8 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook, nf_bridge_put(skb->nf_bridge); if ((nf_bridge = nf_bridge_alloc(skb)) == NULL) return NF_DROP; - setup_pre_routing(skb); + if (!setup_pre_routing(skb)) + return NF_DROP; NF_HOOK(PF_INET6, NF_IP6_PRE_ROUTING, skb, skb->dev, NULL, br_nf_pre_routing_finish_ipv6); @@ -465,7 +476,8 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, nf_bridge_put(skb->nf_bridge); if ((nf_bridge = nf_bridge_alloc(skb)) == NULL) return NF_DROP; - setup_pre_routing(skb); + if (!setup_pre_routing(skb)) + return NF_DROP; store_orig_dstaddr(skb); NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, skb->dev, NULL, @@ -539,11 +551,16 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff **pskb, struct sk_buff *skb = *pskb; struct nf_bridge_info *nf_bridge; struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); + struct net_device *parent; int pf; if (!skb->nf_bridge) return NF_ACCEPT; + parent = bridge_parent(out); + if (!parent) + return NF_DROP; + if (skb->protocol == __constant_htons(ETH_P_IP) || IS_VLAN_IP) pf = PF_INET; else @@ -564,8 +581,8 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff **pskb, nf_bridge->mask |= BRNF_BRIDGED; nf_bridge->physoutdev = skb->dev; - NF_HOOK(pf, NF_IP_FORWARD, skb, bridge_parent(in), - bridge_parent(out), br_nf_forward_finish); + NF_HOOK(pf, NF_IP_FORWARD, skb, bridge_parent(in), parent, + br_nf_forward_finish); return NF_STOLEN; } @@ -688,6 +705,8 @@ static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb, goto out; } realoutdev = bridge_parent(skb->dev); + if (!realoutdev) + return NF_DROP; #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) /* iptables should match -o br0.x */ @@ -701,9 +720,11 @@ static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb, /* IP forwarded traffic has a physindev, locally * generated traffic hasn't. */ if (realindev != NULL) { - if (!(nf_bridge->mask & BRNF_DONT_TAKE_PARENT) && - has_bridge_parent(realindev)) - realindev = bridge_parent(realindev); + if (!(nf_bridge->mask & BRNF_DONT_TAKE_PARENT) ) { + struct net_device *parent = bridge_parent(realindev); + if (parent) + realindev = parent; + } NF_HOOK_THRESH(pf, NF_IP_FORWARD, skb, realindev, realoutdev, br_nf_local_out_finish, @@ -743,6 +764,9 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, if (!nf_bridge) return NF_ACCEPT; + if (!realoutdev) + return NF_DROP; + if (skb->protocol == __constant_htons(ETH_P_IP) || IS_VLAN_IP) pf = PF_INET; else @@ -782,8 +806,8 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, print_error: if (skb->dev != NULL) { printk("[%s]", skb->dev->name); - if (has_bridge_parent(skb->dev)) - printk("[%s]", bridge_parent(skb->dev)->name); + if (realoutdev) + printk("[%s]", realoutdev->name); } printk(" head:%p, raw:%p, data:%p\n", skb->head, skb->mac.raw, skb->data); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index c5bd631ffcd..8f10e09f251 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -232,9 +232,8 @@ extern void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ +extern struct sysfs_ops brport_sysfs_ops; extern int br_sysfs_addif(struct net_bridge_port *p); -extern void br_sysfs_removeif(struct net_bridge_port *p); -extern void br_sysfs_freeif(struct net_bridge_port *p); /* br_sysfs_br.c */ extern int br_sysfs_addbr(struct net_device *dev); @@ -243,8 +242,6 @@ extern void br_sysfs_delbr(struct net_device *dev); #else #define br_sysfs_addif(p) (0) -#define br_sysfs_removeif(p) do { } while(0) -#define br_sysfs_freeif(p) kfree(p) #define br_sysfs_addbr(dev) (0) #define br_sysfs_delbr(dev) do { } while(0) #endif /* CONFIG_SYSFS */ diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index d071f1c9ad0..296f6a487c5 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -133,29 +133,35 @@ void br_send_tcn_bpdu(struct net_bridge_port *p) static const unsigned char header[6] = {0x42, 0x42, 0x03, 0x00, 0x00, 0x00}; -/* NO locks */ +/* NO locks, but rcu_read_lock (preempt_disabled) */ int br_stp_handle_bpdu(struct sk_buff *skb) { - struct net_bridge_port *p = skb->dev->br_port; - struct net_bridge *br = p->br; + struct net_bridge_port *p = rcu_dereference(skb->dev->br_port); + struct net_bridge *br; unsigned char *buf; + if (!p) + goto err; + + br = p->br; + spin_lock(&br->lock); + + if (p->state == BR_STATE_DISABLED || !(br->dev->flags & IFF_UP)) + goto out; + /* insert into forwarding database after filtering to avoid spoofing */ - br_fdb_update(p->br, p, eth_hdr(skb)->h_source); + br_fdb_update(br, p, eth_hdr(skb)->h_source); + + if (!br->stp_enabled) + goto out; /* need at least the 802 and STP headers */ if (!pskb_may_pull(skb, sizeof(header)+1) || memcmp(skb->data, header, sizeof(header))) - goto err; + goto out; buf = skb_pull(skb, sizeof(header)); - spin_lock_bh(&br->lock); - if (p->state == BR_STATE_DISABLED - || !(br->dev->flags & IFF_UP) - || !br->stp_enabled) - goto out; - if (buf[0] == BPDU_TYPE_CONFIG) { struct br_config_bpdu bpdu; @@ -201,7 +207,7 @@ int br_stp_handle_bpdu(struct sk_buff *skb) br_received_tcn_bpdu(p); } out: - spin_unlock_bh(&br->lock); + spin_unlock(&br->lock); err: kfree_skb(skb); return 0; diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index cc047f7fb6e..35cf3a07408 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -67,7 +67,7 @@ void br_stp_disable_bridge(struct net_bridge *br) { struct net_bridge_port *p; - spin_lock(&br->lock); + spin_lock_bh(&br->lock); list_for_each_entry(p, &br->port_list, list) { if (p->state != BR_STATE_DISABLED) br_stp_disable_port(p); @@ -76,7 +76,7 @@ void br_stp_disable_bridge(struct net_bridge *br) br->topology_change = 0; br->topology_change_detected = 0; - spin_unlock(&br->lock); + spin_unlock_bh(&br->lock); del_timer_sync(&br->hello_timer); del_timer_sync(&br->topology_change_timer); diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 0ac0355d16d..c51c9e42aeb 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -195,23 +195,11 @@ static ssize_t brport_store(struct kobject * kobj, return ret; } -/* called from kobject_put when port ref count goes to zero. */ -static void brport_release(struct kobject *kobj) -{ - kfree(container_of(kobj, struct net_bridge_port, kobj)); -} - -static struct sysfs_ops brport_sysfs_ops = { +struct sysfs_ops brport_sysfs_ops = { .show = brport_show, .store = brport_store, }; -static struct kobj_type brport_ktype = { - .sysfs_ops = &brport_sysfs_ops, - .release = brport_release, -}; - - /* * Add sysfs entries to ethernet device added to a bridge. * Creates a brport subdirectory with bridge attributes. @@ -223,17 +211,6 @@ int br_sysfs_addif(struct net_bridge_port *p) struct brport_attribute **a; int err; - ASSERT_RTNL(); - - kobject_set_name(&p->kobj, SYSFS_BRIDGE_PORT_ATTR); - p->kobj.ktype = &brport_ktype; - p->kobj.parent = &(p->dev->class_dev.kobj); - p->kobj.kset = NULL; - - err = kobject_add(&p->kobj); - if(err) - goto out1; - err = sysfs_create_link(&p->kobj, &br->dev->class_dev.kobj, SYSFS_BRIDGE_PORT_LINK); if (err) @@ -245,28 +222,7 @@ int br_sysfs_addif(struct net_bridge_port *p) goto out2; } - err = sysfs_create_link(&br->ifobj, &p->kobj, p->dev->name); - if (err) - goto out2; - - kobject_uevent(&p->kobj, KOBJ_ADD); - return 0; - out2: - kobject_del(&p->kobj); - out1: + err= sysfs_create_link(&br->ifobj, &p->kobj, p->dev->name); +out2: return err; } - -void br_sysfs_removeif(struct net_bridge_port *p) -{ - pr_debug("br_sysfs_removeif\n"); - sysfs_remove_link(&p->br->ifobj, p->dev->name); - kobject_uevent(&p->kobj, KOBJ_REMOVE); - kobject_del(&p->kobj); -} - -void br_sysfs_freeif(struct net_bridge_port *p) -{ - pr_debug("br_sysfs_freeif\n"); - kobject_put(&p->kobj); -} diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index ce617b3dbbb..802baf755ef 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -46,7 +46,7 @@ #define PRINTR(format, args...) do { if (net_ratelimit()) \ printk(format , ## args); } while (0) -static unsigned int nlbufsiz = 4096; +static unsigned int nlbufsiz = NLMSG_GOODSIZE; module_param(nlbufsiz, uint, 0600); MODULE_PARM_DESC(nlbufsiz, "netlink buffer size (number of bytes) " "(defaults to 4096)"); @@ -98,12 +98,14 @@ static void ulog_timer(unsigned long data) static struct sk_buff *ulog_alloc_skb(unsigned int size) { struct sk_buff *skb; + unsigned int n; - skb = alloc_skb(nlbufsiz, GFP_ATOMIC); + n = max(size, nlbufsiz); + skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { PRINTR(KERN_ERR "ebt_ulog: can't alloc whole buffer " - "of size %ub!\n", nlbufsiz); - if (size < nlbufsiz) { + "of size %ub!\n", n); + if (n > size) { /* try to allocate only as much as we need for * current packet */ skb = alloc_skb(size, GFP_ATOMIC); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 00729b3604f..cbd4020cc84 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -934,6 +934,13 @@ static int do_replace(void __user *user, unsigned int len) BUGPRINT("Entries_size never zero\n"); return -EINVAL; } + /* overflow check */ + if (tmp.nentries >= ((INT_MAX - sizeof(struct ebt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) / sizeof(struct ebt_counter)) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) + return -ENOMEM; + countersize = COUNTER_OFFSET(tmp.nentries) * (highest_possible_processor_id()+1); newinfo = (struct ebt_table_info *) diff --git a/net/core/datagram.c b/net/core/datagram.c index f8d322e1ea9..b8ce6bf8118 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -247,49 +247,74 @@ EXPORT_SYMBOL(skb_kill_datagram); int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, struct iovec *to, int len) { - int i, err, fraglen, end = 0; - struct sk_buff *next = skb_shinfo(skb)->frag_list; + int start = skb_headlen(skb); + int i, copy = start - offset; - if (!len) - return 0; + /* Copy header. */ + if (copy > 0) { + if (copy > len) + copy = len; + if (memcpy_toiovec(to, skb->data + offset, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + } -next_skb: - fraglen = skb_headlen(skb); - i = -1; + /* Copy paged appendix. Hmm... why does this look so complicated? */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; - while (1) { - int start = end; + BUG_TRAP(start <= offset + len); - if ((end += fraglen) > offset) { - int copy = end - offset, o = offset - start; + end = start + skb_shinfo(skb)->frags[i].size; + if ((copy = end - offset) > 0) { + int err; + u8 *vaddr; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = frag->page; if (copy > len) copy = len; - if (i == -1) - err = memcpy_toiovec(to, skb->data + o, copy); - else { - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; - void *p = kmap(page) + frag->page_offset + o; - err = memcpy_toiovec(to, p, copy); - kunmap(page); - } + vaddr = kmap(page); + err = memcpy_toiovec(to, vaddr + frag->page_offset + + offset - start, copy); + kunmap(page); if (err) goto fault; if (!(len -= copy)) return 0; offset += copy; } - if (++i >= skb_shinfo(skb)->nr_frags) - break; - fraglen = skb_shinfo(skb)->frags[i].size; + start = end; } - if (next) { - skb = next; - BUG_ON(skb_shinfo(skb)->frag_list); - next = skb->next; - goto next_skb; + + if (skb_shinfo(skb)->frag_list) { + struct sk_buff *list = skb_shinfo(skb)->frag_list; + + for (; list; list = list->next) { + int end; + + BUG_TRAP(start <= offset + len); + + end = start + list->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_iovec(list, + offset - start, + to, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + } + start = end; + } } + if (!len) + return 0; + fault: return -EFAULT; } diff --git a/net/core/dev.c b/net/core/dev.c index fd070a098f2..2afb0de9532 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2543,13 +2543,14 @@ int dev_ioctl(unsigned int cmd, void __user *arg) case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: - case SIOCBONDSLAVEINFOQUERY: - case SIOCBONDINFOQUERY: case SIOCBONDCHANGEACTIVE: case SIOCBRADDIF: case SIOCBRDELIF: if (!capable(CAP_NET_ADMIN)) return -EPERM; + /* fall through */ + case SIOCBONDSLAVEINFOQUERY: + case SIOCBONDINFOQUERY: dev_load(ifr.ifr_name); rtnl_lock(); ret = dev_ifsioc(&ifr, cmd); @@ -3236,7 +3237,7 @@ static int __init net_dev_init(void) * Initialise the packet receive queues. */ - for (i = 0; i < NR_CPUS; i++) { + for_each_cpu(i) { struct softnet_data *queue; queue = &per_cpu(softnet_data, i); diff --git a/net/core/filter.c b/net/core/filter.c index 9540946a48f..93fbd01d225 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -64,7 +64,7 @@ static inline void *load_pointer(struct sk_buff *skb, int k, } /** - * sk_run_filter - run a filter on a socket + * sk_run_filter - run a filter on a socket * @skb: buffer to run the filter on * @filter: filter to apply * @flen: length of filter @@ -78,8 +78,8 @@ unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int { struct sock_filter *fentry; /* We walk down these */ void *ptr; - u32 A = 0; /* Accumulator */ - u32 X = 0; /* Index Register */ + u32 A = 0; /* Accumulator */ + u32 X = 0; /* Index Register */ u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */ u32 tmp; int k; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8700379685e..eca2976abb2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -455,7 +455,7 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) if (!skb) return; - if (rtnetlink_fill_ifinfo(skb, dev, type, current->pid, 0, change, 0) < 0) { + if (rtnetlink_fill_ifinfo(skb, dev, type, 0, 0, change, 0) < 0) { kfree_skb(skb); return; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d0732e9c856..2144952d1c6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -135,13 +135,15 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here) struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int fclone) { + kmem_cache_t *cache; struct skb_shared_info *shinfo; struct sk_buff *skb; u8 *data; + cache = fclone ? skbuff_fclone_cache : skbuff_head_cache; + /* Get the HEAD */ - skb = kmem_cache_alloc(fclone ? skbuff_fclone_cache : skbuff_head_cache, - gfp_mask & ~__GFP_DMA); + skb = kmem_cache_alloc(cache, gfp_mask & ~__GFP_DMA); if (!skb) goto out; @@ -180,7 +182,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, out: return skb; nodata: - kmem_cache_free(skbuff_head_cache, skb); + kmem_cache_free(cache, skb); skb = NULL; goto out; } @@ -409,6 +411,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) C(pkt_type); C(ip_summed); C(priority); +#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) + C(ipvs_property); +#endif C(protocol); n->destructor = NULL; #ifdef CONFIG_NETFILTER @@ -420,13 +425,6 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) C(nfct_reasm); nf_conntrack_get_reasm(skb->nfct_reasm); #endif -#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) - C(ipvs_property); -#endif -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - C(nfct_reasm); - nf_conntrack_get_reasm(skb->nfct_reasm); -#endif #ifdef CONFIG_BRIDGE_NETFILTER C(nf_bridge); nf_bridge_get(skb->nf_bridge); diff --git a/net/core/utils.c b/net/core/utils.c index ac1d1fcf867..fdc4f38bc46 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -121,7 +121,7 @@ void __init net_random_init(void) { int i; - for (i = 0; i < NR_CPUS; i++) { + for_each_cpu(i) { struct nrnd_state *state = &per_cpu(net_rand_state,i); __net_srandom(state, i+jiffies); } @@ -133,7 +133,7 @@ static int net_random_reseed(void) unsigned long seed[NR_CPUS]; get_random_bytes(seed, sizeof(seed)); - for (i = 0; i < NR_CPUS; i++) { + for_each_cpu(i) { struct nrnd_state *state = &per_cpu(net_rand_state,i); __net_srandom(state, seed[i]); } diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index d2b5933b451..add3cae65e2 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -15,7 +15,6 @@ #include <linux/config.h> #include <linux/module.h> -#include <asm/bug.h> #include <asm/div64.h> #include "tfrc.h" diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 00f98322667..dc0487b5bac 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -119,7 +119,8 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err != 0) goto failure; - err = ip_route_newports(&rt, inet->sport, inet->dport, sk); + err = ip_route_newports(&rt, IPPROTO_DCCP, inet->sport, inet->dport, + sk); if (err != 0) goto failure; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index df074259f9c..80c4d048869 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -468,6 +468,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, done: if (opt && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); + dst_release(dst); return err; } diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 9890fd97e53..c971f14712e 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -95,6 +95,12 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, saddr = dev->dev_addr; memcpy(eth->h_source,saddr,dev->addr_len); + if(daddr) + { + memcpy(eth->h_dest,daddr,dev->addr_len); + return ETH_HLEN; + } + /* * Anyway, the loopback-device should never use this function... */ @@ -105,12 +111,6 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, return ETH_HLEN; } - if(daddr) - { - memcpy(eth->h_dest,daddr,dev->addr_len); - return ETH_HLEN; - } - return -ETH_HLEN; } diff --git a/net/ieee80211/ieee80211_rx.c b/net/ieee80211/ieee80211_rx.c index 7a121802faa..960aa78cdb9 100644 --- a/net/ieee80211/ieee80211_rx.c +++ b/net/ieee80211/ieee80211_rx.c @@ -350,6 +350,7 @@ int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb, u8 src[ETH_ALEN]; struct ieee80211_crypt_data *crypt = NULL; int keyidx = 0; + int can_be_decrypted = 0; hdr = (struct ieee80211_hdr_4addr *)skb->data; stats = &ieee->stats; @@ -410,12 +411,23 @@ int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb, return 1; } - if (is_multicast_ether_addr(hdr->addr1) - ? ieee->host_mc_decrypt : ieee->host_decrypt) { + can_be_decrypted = (is_multicast_ether_addr(hdr->addr1) || + is_broadcast_ether_addr(hdr->addr2)) ? + ieee->host_mc_decrypt : ieee->host_decrypt; + + if (can_be_decrypted) { int idx = 0; - if (skb->len >= hdrlen + 3) + if (skb->len >= hdrlen + 3) { + /* Top two-bits of byte 3 are the key index */ idx = skb->data[hdrlen + 3] >> 6; + } + + /* ieee->crypt[] is WEP_KEY (4) in length. Given that idx + * is only allowed 2-bits of storage, no value of idx can + * be provided via above code that would result in idx + * being out of range */ crypt = ieee->crypt[idx]; + #ifdef NOT_YET sta = NULL; @@ -553,7 +565,7 @@ int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb, /* skb: hdr + (possibly fragmented, possibly encrypted) payload */ - if (ieee->host_decrypt && (fc & IEEE80211_FCTL_PROTECTED) && + if ((fc & IEEE80211_FCTL_PROTECTED) && can_be_decrypted && (keyidx = ieee80211_rx_frame_decrypt(ieee, skb, crypt)) < 0) goto rx_dropped; @@ -617,7 +629,7 @@ int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb, /* skb: hdr + (possible reassembled) full MSDU payload; possibly still * encrypted/authenticated */ - if (ieee->host_decrypt && (fc & IEEE80211_FCTL_PROTECTED) && + if ((fc & IEEE80211_FCTL_PROTECTED) && can_be_decrypted && ieee80211_rx_frame_decrypt_msdu(ieee, skb, keyidx, crypt)) goto rx_dropped; @@ -1439,7 +1451,7 @@ void ieee80211_rx_mgt(struct ieee80211_device *ieee, break; case IEEE80211_STYPE_PROBE_REQ: - IEEE80211_DEBUG_MGMT("recieved auth (%d)\n", + IEEE80211_DEBUG_MGMT("received auth (%d)\n", WLAN_FC_GET_STYPE(le16_to_cpu (header->frame_ctl))); @@ -1473,7 +1485,7 @@ void ieee80211_rx_mgt(struct ieee80211_device *ieee, break; case IEEE80211_STYPE_AUTH: - IEEE80211_DEBUG_MGMT("recieved auth (%d)\n", + IEEE80211_DEBUG_MGMT("received auth (%d)\n", WLAN_FC_GET_STYPE(le16_to_cpu (header->frame_ctl))); diff --git a/net/ieee80211/ieee80211_wx.c b/net/ieee80211/ieee80211_wx.c index 23e1630f50b..f87c6b89f84 100644 --- a/net/ieee80211/ieee80211_wx.c +++ b/net/ieee80211/ieee80211_wx.c @@ -232,15 +232,18 @@ static char *ipw2100_translate_scan(struct ieee80211_device *ieee, return start; } +#define SCAN_ITEM_SIZE 128 + int ieee80211_wx_get_scan(struct ieee80211_device *ieee, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct ieee80211_network *network; unsigned long flags; + int err = 0; char *ev = extra; - char *stop = ev + IW_SCAN_MAX_DATA; + char *stop = ev + wrqu->data.length; int i = 0; IEEE80211_DEBUG_WX("Getting scan\n"); @@ -249,6 +252,11 @@ int ieee80211_wx_get_scan(struct ieee80211_device *ieee, list_for_each_entry(network, &ieee->network_list, list) { i++; + if (stop - ev < SCAN_ITEM_SIZE) { + err = -E2BIG; + break; + } + if (ieee->scan_age == 0 || time_after(network->last_scanned + ieee->scan_age, jiffies)) ev = ipw2100_translate_scan(ieee, ev, stop, network); @@ -270,7 +278,7 @@ int ieee80211_wx_get_scan(struct ieee80211_device *ieee, IEEE80211_DEBUG_WX("exit: %d networks returned.\n", i); - return 0; + return err; } int ieee80211_wx_set_encode(struct ieee80211_device *ieee, diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 95b9d81ac48..3ffa60dadc0 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1135,7 +1135,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr* ifa) if (!skb) netlink_set_err(rtnl, 0, RTNLGRP_IPV4_IFADDR, ENOBUFS); - else if (inet_fill_ifaddr(skb, ifa, current->pid, 0, event, 0) < 0) { + else if (inet_fill_ifaddr(skb, ifa, 0, 0, event, 0) < 0) { kfree_skb(skb); netlink_set_err(rtnl, 0, RTNLGRP_IPV4_IFADDR, EINVAL); } else { diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index ef4724de735..0f4145babb1 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1045,7 +1045,7 @@ fib_convert_rtentry(int cmd, struct nlmsghdr *nl, struct rtmsg *rtm, } nl->nlmsg_flags = NLM_F_REQUEST; - nl->nlmsg_pid = current->pid; + nl->nlmsg_pid = 0; nl->nlmsg_seq = 0; nl->nlmsg_len = NLMSG_LENGTH(sizeof(*rtm)); if (cmd == SIOCDELRT) { diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 105039eb762..e7bbff4340b 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -192,7 +192,7 @@ int sysctl_icmp_echo_ignore_all; int sysctl_icmp_echo_ignore_broadcasts = 1; /* Control parameter - ignore bogus broadcast responses? */ -int sysctl_icmp_ignore_bogus_error_responses; +int sysctl_icmp_ignore_bogus_error_responses = 1; /* * Configurable global rate limit. @@ -385,7 +385,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) u32 daddr; if (ip_options_echo(&icmp_param->replyopts, skb)) - goto out; + return; if (icmp_xmit_lock()) return; @@ -416,7 +416,6 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) ip_rt_put(rt); out_unlock: icmp_xmit_unlock(); -out:; } @@ -525,7 +524,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info) iph->tos; if (ip_options_echo(&icmp_param.replyopts, skb_in)) - goto ende; + goto out_unlock; /* diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d8ce7133cd8..64ce52bf048 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -970,7 +970,7 @@ int igmp_rcv(struct sk_buff *skb) case IGMP_MTRACE_RESP: break; default: - NETDEBUG(KERN_DEBUG "New IGMP type=%d, why we do not know about it?\n", ih->type); + break; } drop: @@ -1578,7 +1578,7 @@ static int sf_setstate(struct ip_mc_list *pmc) new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { - struct ip_sf_list *prev = 0; + struct ip_sf_list *prev = NULL; for (dpsf=pmc->tomb; dpsf; dpsf=dpsf->sf_next) { if (dpsf->sf_inaddr == psf->sf_inaddr) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index abe23923e4e..9981dcd68f1 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -830,7 +830,8 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb->h.raw = skb->nh.raw; skb->nh.raw = skb_push(skb, gre_hlen); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE|IPSKB_XFRM_TRANSFORMED); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | + IPSKB_REROUTED); dst_release(skb->dst); skb->dst = &rt->u.dst; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 3324fbfe528..57d290d89ec 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -207,8 +207,10 @@ static inline int ip_finish_output(struct sk_buff *skb) { #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ - if (skb->dst->xfrm != NULL) - return xfrm4_output_finish(skb); + if (skb->dst->xfrm != NULL) { + IPCB(skb)->flags |= IPSKB_REROUTED; + return dst_output(skb); + } #endif if (skb->len > dst_mtu(skb->dst) && !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size)) @@ -271,8 +273,9 @@ int ip_mc_output(struct sk_buff *skb) newskb->dev, ip_dev_loopback_xmit); } - return NF_HOOK(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dev, - ip_finish_output); + return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dev, + ip_finish_output, + !(IPCB(skb)->flags & IPSKB_REROUTED)); } int ip_output(struct sk_buff *skb) @@ -284,8 +287,9 @@ int ip_output(struct sk_buff *skb) skb->dev = dev; skb->protocol = htons(ETH_P_IP); - return NF_HOOK(PF_INET, NF_IP_POST_ROUTING, skb, NULL, dev, - ip_finish_output); + return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, dev, + ip_finish_output, + !(IPCB(skb)->flags & IPSKB_REROUTED)); } int ip_queue_xmit(struct sk_buff *skb, int ipfragok) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index e5cbe72c6b8..03d13742a4b 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -622,7 +622,8 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb->h.raw = skb->nh.raw; skb->nh.raw = skb_push(skb, sizeof(struct iphdr)); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE|IPSKB_XFRM_TRANSFORMED); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | + IPSKB_REROUTED); dst_release(skb->dst); skb->dst = &rt->u.dst; diff --git a/net/ipv4/multipath_wrandom.c b/net/ipv4/multipath_wrandom.c index d34a9fa608e..342d0b9098f 100644 --- a/net/ipv4/multipath_wrandom.c +++ b/net/ipv4/multipath_wrandom.c @@ -228,7 +228,7 @@ static void wrandom_set_nhinfo(__u32 network, struct multipath_dest *d, *target_dest = NULL; /* store the weight information for a certain route */ - spin_lock(&state[state_idx].lock); + spin_lock_bh(&state[state_idx].lock); /* find state entry for gateway or add one if necessary */ list_for_each_entry_rcu(r, &state[state_idx].head, list) { @@ -276,7 +276,7 @@ static void wrandom_set_nhinfo(__u32 network, * we are finished */ - spin_unlock(&state[state_idx].lock); + spin_unlock_bh(&state[state_idx].lock); } static void __multipath_free(struct rcu_head *head) @@ -302,7 +302,7 @@ static void wrandom_flush(void) for (i = 0; i < MULTIPATH_STATE_SIZE; ++i) { struct multipath_route *r; - spin_lock(&state[i].lock); + spin_lock_bh(&state[i].lock); list_for_each_entry_rcu(r, &state[i].head, list) { struct multipath_dest *d; list_for_each_entry_rcu(d, &r->dests, list) { @@ -315,7 +315,7 @@ static void wrandom_flush(void) __multipath_free); } - spin_unlock(&state[i].lock); + spin_unlock_bh(&state[i].lock); } } diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 52a3d7c5790..ed42cdc57cd 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -78,6 +78,47 @@ int ip_route_me_harder(struct sk_buff **pskb) } EXPORT_SYMBOL(ip_route_me_harder); +#ifdef CONFIG_XFRM +int ip_xfrm_me_harder(struct sk_buff **pskb) +{ + struct flowi fl; + unsigned int hh_len; + struct dst_entry *dst; + + if (IPCB(*pskb)->flags & IPSKB_XFRM_TRANSFORMED) + return 0; + if (xfrm_decode_session(*pskb, &fl, AF_INET) < 0) + return -1; + + dst = (*pskb)->dst; + if (dst->xfrm) + dst = ((struct xfrm_dst *)dst)->route; + dst_hold(dst); + + if (xfrm_lookup(&dst, &fl, (*pskb)->sk, 0) < 0) + return -1; + + dst_release((*pskb)->dst); + (*pskb)->dst = dst; + + /* Change in oif may mean change in hh_len. */ + hh_len = (*pskb)->dst->dev->hard_header_len; + if (skb_headroom(*pskb) < hh_len) { + struct sk_buff *nskb; + + nskb = skb_realloc_headroom(*pskb, hh_len); + if (!nskb) + return -1; + if ((*pskb)->sk) + skb_set_owner_w(nskb, (*pskb)->sk); + kfree_skb(*pskb); + *pskb = nskb; + } + return 0; +} +EXPORT_SYMBOL(ip_xfrm_me_harder); +#endif + void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *); EXPORT_SYMBOL(ip_nat_decode_session); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index afe3d8f8177..dd1048be8a0 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -807,6 +807,13 @@ static int do_replace(void __user *user, unsigned int len) if (len != sizeof(tmp) + tmp.size) return -ENOPROTOOPT; + /* overflow check */ + if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c index c9ebbe0d2d9..e0b5926c76f 100644 --- a/net/ipv4/netfilter/ip_conntrack_netlink.c +++ b/net/ipv4/netfilter/ip_conntrack_netlink.c @@ -1216,7 +1216,7 @@ static int ctnetlink_expect_event(struct notifier_block *this, b = skb->tail; - type |= NFNL_SUBSYS_CTNETLINK << 8; + type |= NFNL_SUBSYS_CTNETLINK_EXP << 8; nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg)); nfmsg = NLMSG_DATA(nlh); @@ -1567,6 +1567,7 @@ static struct nfnetlink_subsystem ctnl_exp_subsys = { }; MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); static int __init ctnetlink_init(void) { diff --git a/net/ipv4/netfilter/ip_conntrack_tftp.c b/net/ipv4/netfilter/ip_conntrack_tftp.c index d3c5a371f99..4ba4463cec2 100644 --- a/net/ipv4/netfilter/ip_conntrack_tftp.c +++ b/net/ipv4/netfilter/ip_conntrack_tftp.c @@ -71,6 +71,7 @@ static int tftp_help(struct sk_buff **pskb, exp->tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; exp->mask.src.ip = 0xffffffff; + exp->mask.src.u.udp.port = 0; exp->mask.dst.ip = 0xffffffff; exp->mask.dst.u.udp.port = 0xffff; exp->mask.dst.protonum = 0xff; diff --git a/net/ipv4/netfilter/ip_nat_core.c b/net/ipv4/netfilter/ip_nat_core.c index c1a61462507..1741d555ad0 100644 --- a/net/ipv4/netfilter/ip_nat_core.c +++ b/net/ipv4/netfilter/ip_nat_core.c @@ -434,6 +434,7 @@ int ip_nat_icmp_reply_translation(struct sk_buff **pskb, } *inside; struct ip_conntrack_tuple inner, target; int hdrlen = (*pskb)->nh.iph->ihl * 4; + unsigned long statusbit; if (!skb_make_writable(pskb, hdrlen + sizeof(*inside))) return 0; @@ -495,17 +496,16 @@ int ip_nat_icmp_reply_translation(struct sk_buff **pskb, /* Change outer to look the reply to an incoming packet * (proto 0 means don't invert per-proto part). */ + if (manip == IP_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; - /* Obviously, we need to NAT destination IP, but source IP - should be NAT'ed only if it is from a NAT'd host. + /* Invert if this is reply dir. */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; - Explanation: some people use NAT for anonymizing. Also, - CERT recommends dropping all packets from private IP - addresses (although ICMP errors from internal links with - such addresses are not too uncommon, as Alan Cox points - out) */ - if (manip != IP_NAT_MANIP_SRC - || ((*pskb)->nh.iph->saddr == ct->tuplehash[dir].tuple.src.ip)) { + if (ct->status & statusbit) { invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); if (!manip_pkt(0, pskb, 0, &target, manip)) return 0; diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index ad438fb185b..ab1f88fa21e 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -200,20 +200,14 @@ ip_nat_in(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct ip_conntrack *ct; - enum ip_conntrack_info ctinfo; unsigned int ret; + u_int32_t daddr = (*pskb)->nh.iph->daddr; ret = ip_nat_fn(hooknum, pskb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN - && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) { - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - - if (ct->tuplehash[dir].tuple.src.ip != - ct->tuplehash[!dir].tuple.dst.ip) { - dst_release((*pskb)->dst); - (*pskb)->dst = NULL; - } + && daddr != (*pskb)->nh.iph->daddr) { + dst_release((*pskb)->dst); + (*pskb)->dst = NULL; } return ret; } @@ -235,19 +229,19 @@ ip_nat_out(unsigned int hooknum, return NF_ACCEPT; ret = ip_nat_fn(hooknum, pskb, in, out, okfn); +#ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.src.ip != ct->tuplehash[!dir].tuple.dst.ip -#ifdef CONFIG_XFRM || ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all -#endif ) - return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP; + return ip_xfrm_me_harder(pskb) == 0 ? ret : NF_DROP; } +#endif return ret; } @@ -276,7 +270,7 @@ ip_nat_local_fn(unsigned int hooknum, ct->tuplehash[!dir].tuple.src.ip #ifdef CONFIG_XFRM || ct->tuplehash[dir].tuple.dst.u.all != - ct->tuplehash[dir].tuple.src.u.all + ct->tuplehash[!dir].tuple.src.u.all #endif ) return ip_route_me_harder(pskb) == 0 ? ret : NF_DROP; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2371b2062c2..16f47c675fe 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -921,6 +921,13 @@ do_replace(void __user *user, unsigned int len) if (len != sizeof(tmp) + tmp.size) return -ENOPROTOOPT; + /* overflow check */ + if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 641dbc47765..180a9ea57b6 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -35,6 +35,10 @@ * each nlgroup you are using, so the total kernel memory usage increases * by that factor. * + * Actually you should use nlbufsiz a bit smaller than PAGE_SIZE, since + * nlbufsiz is used with alloc_skb, which adds another + * sizeof(struct skb_shared_info). Use NLMSG_GOODSIZE instead. + * * flushtimeout: * Specify, after how many hundredths of a second the queue should be * flushed even if it is not full yet. @@ -76,7 +80,7 @@ MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NFLOG); #define PRINTR(format, args...) do { if (net_ratelimit()) printk(format , ## args); } while (0) -static unsigned int nlbufsiz = 4096; +static unsigned int nlbufsiz = NLMSG_GOODSIZE; module_param(nlbufsiz, uint, 0400); MODULE_PARM_DESC(nlbufsiz, "netlink buffer size"); @@ -143,22 +147,26 @@ static void ulog_timer(unsigned long data) static struct sk_buff *ulog_alloc_skb(unsigned int size) { struct sk_buff *skb; + unsigned int n; /* alloc skb which should be big enough for a whole * multipart message. WARNING: has to be <= 131000 * due to slab allocator restrictions */ - skb = alloc_skb(nlbufsiz, GFP_ATOMIC); + n = max(size, nlbufsiz); + skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { - PRINTR("ipt_ULOG: can't alloc whole buffer %ub!\n", - nlbufsiz); + PRINTR("ipt_ULOG: can't alloc whole buffer %ub!\n", n); - /* try to allocate only as much as we need for - * current packet */ + if (n > size) { + /* try to allocate only as much as we need for + * current packet */ - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - PRINTR("ipt_ULOG: can't even allocate %ub\n", size); + skb = alloc_skb(size, GFP_ATOMIC); + if (!skb) + PRINTR("ipt_ULOG: can't even allocate %ub\n", + size); + } } return skb; diff --git a/net/ipv4/netfilter/ipt_policy.c b/net/ipv4/netfilter/ipt_policy.c index 18ca8258a1c..5a7a265280f 100644 --- a/net/ipv4/netfilter/ipt_policy.c +++ b/net/ipv4/netfilter/ipt_policy.c @@ -26,10 +26,13 @@ MODULE_LICENSE("GPL"); static inline int match_xfrm_state(struct xfrm_state *x, const struct ipt_policy_elem *e) { -#define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) +#define MATCH_ADDR(x,y,z) (!e->match.x || \ + ((e->x.a4.s_addr == (e->y.a4.s_addr & (z))) \ + ^ e->invert.x)) +#define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) - return MATCH(saddr, x->props.saddr.a4 & e->smask) && - MATCH(daddr, x->id.daddr.a4 & e->dmask) && + return MATCH_ADDR(saddr, smask, x->props.saddr.a4) && + MATCH_ADDR(daddr, dmask, x->id.daddr.a4) && MATCH(proto, x->id.proto) && MATCH(mode, x->props.mode) && MATCH(spi, x->id.spi) && @@ -89,7 +92,7 @@ match_policy_out(const struct sk_buff *skb, const struct ipt_policy_info *info) return 0; } - return strict ? 1 : 0; + return strict ? i == info->len : 0; } static int match(const struct sk_buff *skb, diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 167619f638c..6c8624a5493 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -529,15 +529,10 @@ static int init_or_cleanup(int init) goto cleanup_localinops; } #endif - - /* For use by REJECT target */ - ip_ct_attach = __nf_conntrack_attach; - return ret; cleanup: synchronize_net(); - ip_ct_attach = NULL; #ifdef CONFIG_SYSCTL unregister_sysctl_table(nf_ct_ipv4_sysctl_header); cleanup_localinops: diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 39d49dc333a..1b167c4bb3b 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -49,7 +49,7 @@ static int fold_prot_inuse(struct proto *proto) int res = 0; int cpu; - for (cpu = 0; cpu < NR_CPUS; cpu++) + for_each_cpu(cpu) res += proto->stats[cpu].inuse; return res; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d82c242ea70..fca5fe0cf94 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -835,7 +835,7 @@ static int rt_garbage_collect(void) int r; rthp = rt_remove_balanced_route( - &rt_hash_table[i].chain, + &rt_hash_table[k].chain, rth, &r); goal -= r; diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 3284cfb993e..128de4d7c0b 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -230,7 +230,6 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 rtt, if (tp->snd_cwnd < tp->snd_cwnd_clamp) tp->snd_cwnd++; tp->snd_cwnd_cnt = 0; - ca->ccount++; } } } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a97ed5416c2..e9a54ae7d69 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -456,7 +456,8 @@ void tcp_rcv_space_adjust(struct sock *sk) tp->rcvq_space.space = space; - if (sysctl_tcp_moderate_rcvbuf) { + if (sysctl_tcp_moderate_rcvbuf && + !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { int new_clamp = space; /* Receive space grows, normalize in order to diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6ea353907af..233bdf25996 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -236,7 +236,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err) goto failure; - err = ip_route_newports(&rt, inet->sport, inet->dport, sk); + err = ip_route_newports(&rt, IPPROTO_TCP, inet->sport, inet->dport, sk); if (err) goto failure; @@ -1845,7 +1845,6 @@ void __init tcp_v4_init(struct net_proto_family *ops) } EXPORT_SYMBOL(ipv4_specific); -EXPORT_SYMBOL(inet_bind_bucket_create); EXPORT_SYMBOL(tcp_hashinfo); EXPORT_SYMBOL(tcp_prot); EXPORT_SYMBOL(tcp_unhash); diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index d4df0ddd424..32ad229b4fe 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -152,10 +152,16 @@ error_nolock: goto out_exit; } -int xfrm4_output_finish(struct sk_buff *skb) +static int xfrm4_output_finish(struct sk_buff *skb) { int err; +#ifdef CONFIG_NETFILTER + if (!skb->dst->xfrm) { + IPCB(skb)->flags |= IPSKB_REROUTED; + return dst_output(skb); + } +#endif while (likely((err = xfrm4_output_one(skb)) == 0)) { nf_reset(skb); @@ -178,6 +184,7 @@ int xfrm4_output_finish(struct sk_buff *skb) int xfrm4_output(struct sk_buff *skb) { - return NF_HOOK(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dst->dev, - xfrm4_output_finish); + return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dst->dev, + xfrm4_output_finish, + !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 42196ba3b0b..f285bbf296e 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -8,7 +8,6 @@ * */ -#include <asm/bug.h> #include <linux/compiler.h> #include <linux/config.h> #include <linux/inetdevice.h> @@ -36,6 +35,7 @@ __xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy) if (xdst->u.rt.fl.oif == fl->oif && /*XXX*/ xdst->u.rt.fl.fl4_dst == fl->fl4_dst && xdst->u.rt.fl.fl4_src == fl->fl4_src && + xdst->u.rt.fl.fl4_tos == fl->fl4_tos && xfrm_bundle_ok(xdst, fl, AF_INET)) { dst_clone(dst); break; @@ -62,7 +62,8 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int .nl_u = { .ip4_u = { .saddr = local, - .daddr = remote + .daddr = remote, + .tos = fl->fl4_tos } } }; @@ -231,6 +232,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl) fl->proto = iph->protocol; fl->fl4_dst = iph->daddr; fl->fl4_src = iph->saddr; + fl->fl4_tos = iph->tos; } static inline int xfrm4_garbage_collect(void) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d328d598614..b7d8822c1be 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2165,6 +2165,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, dev->name); break; } + + if (idev) + idev->if_flags |= IF_READY; } else { if (!netif_carrier_ok(dev)) { /* device is still not ready. */ @@ -3321,9 +3324,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) switch (event) { case RTM_NEWADDR: - dst_hold(&ifp->rt->u.dst); - if (ip6_ins_rt(ifp->rt, NULL, NULL, NULL)) - dst_release(&ifp->rt->u.dst); + ip6_ins_rt(ifp->rt, NULL, NULL, NULL); if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); break; @@ -3334,8 +3335,6 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) dst_hold(&ifp->rt->u.dst); if (ip6_del_rt(ifp->rt, NULL, NULL, NULL)) dst_free(&ifp->rt->u.dst); - else - dst_release(&ifp->rt->u.dst); break; } } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 064ffab82a9..6c9711ac1c0 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -369,12 +369,6 @@ int inet6_destroy_sock(struct sock *sk) struct sk_buff *skb; struct ipv6_txoptions *opt; - /* - * Release destination entry - */ - - sk_dst_reset(sk); - /* Release rx options */ if ((skb = xchg(&np->pktoptions, NULL)) != NULL) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index fcf883183ce..21eb725e885 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -42,6 +42,7 @@ #include <linux/net.h> #include <linux/skbuff.h> #include <linux/init.h> +#include <linux/netfilter.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> @@ -255,6 +256,7 @@ out: struct icmpv6_msg { struct sk_buff *skb; int offset; + uint8_t type; }; static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) @@ -266,6 +268,8 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset, to, len, csum); skb->csum = csum_block_add(skb->csum, csum, odd); + if (!(msg->type & ICMPV6_INFOMSG_MASK)) + nf_ct_attach(skb, org_skb); return 0; } @@ -403,6 +407,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, msg.skb = skb; msg.offset = skb->nh.raw - skb->data; + msg.type = type; len = skb->len - msg.offset; len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) -sizeof(struct icmp6hdr)); @@ -500,6 +505,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) msg.skb = skb; msg.offset = 0; + msg.type = ICMPV6_ECHO_REPLY; err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl, diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 92ead3cf956..faea8a120ee 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -458,7 +458,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, mtu = IPV6_MIN_MTU; t->dev->mtu = mtu; - if ((len = sizeof (*ipv6h) + ipv6h->payload_len) > mtu) { + if ((len = sizeof (*ipv6h) + ntohs(ipv6h->payload_len)) > mtu) { rel_type = ICMPV6_PKT_TOOBIG; rel_code = 0; rel_info = mtu; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 6c05c7978be..807c021d64a 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1252,8 +1252,7 @@ int igmp6_event_query(struct sk_buff *skb) } } else { for (ma = idev->mc_list; ma; ma=ma->next) { - if (group_type != IPV6_ADDR_ANY && - !ipv6_addr_equal(group, &ma->mca_addr)) + if (!ipv6_addr_equal(group, &ma->mca_addr)) continue; spin_lock_bh(&ma->mca_lock); if (ma->mca_flags & MAF_TIMER_RUNNING) { @@ -1268,11 +1267,10 @@ int igmp6_event_query(struct sk_buff *skb) ma->mca_flags &= ~MAF_GSQUERY; } if (!(ma->mca_flags & MAF_GSQUERY) || - mld_marksources(ma, ntohs(mlh2->nsrcs), mlh2->srcs)) + mld_marksources(ma, ntohs(mlh2->nsrcs), mlh2->srcs)) igmp6_group_queried(ma, max_delay); spin_unlock_bh(&ma->mca_lock); - if (group_type != IPV6_ADDR_ANY) - break; + break; } } read_unlock_bh(&idev->lock); @@ -1351,7 +1349,7 @@ static int is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) - return 0; + return type == MLD2_MODE_IS_INCLUDE; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } @@ -1966,7 +1964,7 @@ static void sf_markstate(struct ifmcaddr6 *pmc) static int sf_setstate(struct ifmcaddr6 *pmc) { - struct ip6_sf_list *psf; + struct ip6_sf_list *psf, *dpsf; int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; int qrv = pmc->idev->mc_qrv; int new_in, rv; @@ -1978,8 +1976,48 @@ static int sf_setstate(struct ifmcaddr6 *pmc) !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; - if (new_in != psf->sf_oldin) { - psf->sf_crcount = qrv; + if (new_in) { + if (!psf->sf_oldin) { + struct ip6_sf_list *prev = NULL; + + for (dpsf=pmc->mca_tomb; dpsf; + dpsf=dpsf->sf_next) { + if (ipv6_addr_equal(&dpsf->sf_addr, + &psf->sf_addr)) + break; + prev = dpsf; + } + if (dpsf) { + if (prev) + prev->sf_next = dpsf->sf_next; + else + pmc->mca_tomb = dpsf->sf_next; + kfree(dpsf); + } + psf->sf_crcount = qrv; + rv++; + } + } else if (psf->sf_oldin) { + psf->sf_crcount = 0; + /* + * add or update "delete" records if an active filter + * is now inactive + */ + for (dpsf=pmc->mca_tomb; dpsf; dpsf=dpsf->sf_next) + if (ipv6_addr_equal(&dpsf->sf_addr, + &psf->sf_addr)) + break; + if (!dpsf) { + dpsf = (struct ip6_sf_list *) + kmalloc(sizeof(*dpsf), GFP_ATOMIC); + if (!dpsf) + continue; + *dpsf = *psf; + /* pmc->mca_lock held by callers */ + dpsf->sf_next = pmc->mca_tomb; + pmc->mca_tomb = dpsf; + } + dpsf->sf_crcount = qrv; rv++; } } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 847068fd336..74ff56c322f 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -978,6 +978,13 @@ do_replace(void __user *user, unsigned int len) if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; + /* overflow check */ + if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index c745717b4ce..0e6d1d4bbd5 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -160,6 +160,8 @@ static void send_reset(struct sk_buff *oldskb) csum_partial((char *)tcph, sizeof(struct tcphdr), 0)); + nf_ct_attach(nskb, oldskb); + NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, nskb, NULL, nskb->dst->dev, dst_output); } diff --git a/net/ipv6/netfilter/ip6t_policy.c b/net/ipv6/netfilter/ip6t_policy.c index afe1cc4c18a..3d39ec92404 100644 --- a/net/ipv6/netfilter/ip6t_policy.c +++ b/net/ipv6/netfilter/ip6t_policy.c @@ -26,8 +26,9 @@ MODULE_LICENSE("GPL"); static inline int match_xfrm_state(struct xfrm_state *x, const struct ip6t_policy_elem *e) { -#define MATCH_ADDR(x,y,z) (!e->match.x || \ - ((ip6_masked_addrcmp((z), &e->x, &e->y)) == 0) ^ e->invert.x) +#define MATCH_ADDR(x,y,z) (!e->match.x || \ + ((!ip6_masked_addrcmp(&e->x.a6, &e->y.a6, z)) \ + ^ e->invert.x)) #define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) return MATCH_ADDR(saddr, smask, (struct in6_addr *)&x->props.saddr.a6) && @@ -91,7 +92,7 @@ match_policy_out(const struct sk_buff *skb, const struct ip6t_policy_info *info) return 0; } - return strict ? 1 : 0; + return strict ? i == info->len : 0; } static int match(const struct sk_buff *skb, diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 50a13e75d70..4238b1ed886 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -38,7 +38,7 @@ static int fold_prot_inuse(struct proto *proto) int res = 0; int cpu; - for (cpu=0; cpu<NR_CPUS; cpu++) + for_each_cpu(cpu) res += proto->stats[cpu].inuse; return res; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 66f1d12ea57..ae20a0ec9bd 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -35,7 +35,6 @@ #include <linux/skbuff.h> #include <asm/uaccess.h> #include <asm/ioctls.h> -#include <asm/bug.h> #include <net/ip.h> #include <net/sock.h> @@ -804,10 +803,7 @@ back_from_confirm: err = rawv6_push_pending_frames(sk, &fl, rp); } done: - ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ? - &np->daddr : NULL); - + dst_release(dst); release_sock(sk); out: fl6_sock_release(flowlabel); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 66d04004afd..ca9cf685375 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -515,6 +515,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, done: if (opt && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); + dst_release(dst); return err; } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 69bd957380e..91cce8b2d7a 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -11,7 +11,6 @@ * */ -#include <asm/bug.h> #include <linux/compiler.h> #include <linux/config.h> #include <linux/netdevice.h> diff --git a/net/irda/irda_device.c b/net/irda/irda_device.c index 890bac0d4a5..e3debbdb67f 100644 --- a/net/irda/irda_device.c +++ b/net/irda/irda_device.c @@ -343,12 +343,12 @@ static void irda_task_timer_expired(void *data) static void irda_device_setup(struct net_device *dev) { dev->hard_header_len = 0; - dev->addr_len = 0; + dev->addr_len = LAP_ALEN; dev->type = ARPHRD_IRDA; dev->tx_queue_len = 8; /* Window size + 1 s-frame */ - memset(dev->broadcast, 0xff, 4); + memset(dev->broadcast, 0xff, LAP_ALEN); dev->mtu = 2048; dev->flags = IFF_NOARP; diff --git a/net/irda/irnet/irnet_irda.c b/net/irda/irnet/irnet_irda.c index 07ec326c71f..f65c7a83bc5 100644 --- a/net/irda/irnet/irnet_irda.c +++ b/net/irda/irnet/irnet_irda.c @@ -696,7 +696,7 @@ irnet_daddr_to_dname(irnet_socket * self) { /* Yes !!! Get it.. */ strlcpy(self->rname, discoveries[i].info, sizeof(self->rname)); - self->rname[NICKNAME_MAX_LEN + 1] = '\0'; + self->rname[sizeof(self->rname) - 1] = '\0'; DEBUG(IRDA_SERV_INFO, "Device 0x%08x is in fact ``%s''.\n", self->daddr, self->rname); kfree(discoveries); diff --git a/net/key/af_key.c b/net/key/af_key.c index 43f1ce74187..b2d4d1dd211 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1423,7 +1423,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, if (err < 0) { x->km.state = XFRM_STATE_DEAD; - xfrm_state_put(x); + __xfrm_state_put(x); goto out; } @@ -1620,6 +1620,7 @@ static int key_notify_sa_flush(struct km_event *c) return -ENOBUFS; hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_satype = pfkey_proto2satype(c->data.proto); + hdr->sadb_msg_type = SADB_FLUSH; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->pid; hdr->sadb_msg_version = PF_KEY_V2; @@ -2385,6 +2386,7 @@ static int key_notify_policy_flush(struct km_event *c) if (!skb_out) return -ENOBUFS; hdr = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg)); + hdr->sadb_msg_type = SADB_X_SPDFLUSH; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->pid; hdr->sadb_msg_version = PF_KEY_V2; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 99c0a0fa4a9..a8e5544da93 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -102,8 +102,6 @@ config NF_CT_NETLINK help This option enables support for a netlink-based userspace interface -endmenu - config NETFILTER_XTABLES tristate "Netfilter Xtables support (required for ip_tables)" help @@ -128,7 +126,7 @@ config NETFILTER_XT_TARGET_CONNMARK tristate '"CONNMARK" target support' depends on NETFILTER_XTABLES depends on IP_NF_MANGLE || IP6_NF_MANGLE - depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK_IPV4) + depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK) help This option adds a `CONNMARK' target, which allows one to manipulate the connection mark value. Similar to the MARK target, but @@ -189,7 +187,7 @@ config NETFILTER_XT_MATCH_COMMENT config NETFILTER_XT_MATCH_CONNBYTES tristate '"connbytes" per-connection counter match support' depends on NETFILTER_XTABLES - depends on (IP_NF_CONNTRACK && IP_NF_CT_ACCT) || NF_CT_ACCT + depends on (IP_NF_CONNTRACK && IP_NF_CT_ACCT) || (NF_CT_ACCT && NF_CONNTRACK) help This option adds a `connbytes' match, which allows you to match the number of bytes and/or packets for each direction within a connection. @@ -200,7 +198,7 @@ config NETFILTER_XT_MATCH_CONNBYTES config NETFILTER_XT_MATCH_CONNMARK tristate '"connmark" connection mark match support' depends on NETFILTER_XTABLES - depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || NF_CONNTRACK_MARK + depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK) help This option adds a `connmark' match, which allows you to match the connection mark value previously set for the session by `CONNMARK'. @@ -361,3 +359,5 @@ config NETFILTER_XT_MATCH_TCPMSS To compile it as a module, choose M here. If unsure, say N. +endmenu + diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 62bb509f05d..d622ddf08bb 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -188,7 +188,7 @@ extern struct nf_conntrack_protocol nf_conntrack_generic_protocol; struct nf_conntrack_protocol * __nf_ct_proto_find(u_int16_t l3proto, u_int8_t protocol) { - if (unlikely(nf_ct_protos[l3proto] == NULL)) + if (unlikely(l3proto >= AF_MAX || nf_ct_protos[l3proto] == NULL)) return &nf_conntrack_generic_protocol; return nf_ct_protos[l3proto][protocol]; @@ -1556,6 +1556,8 @@ void nf_conntrack_cleanup(void) { int i; + ip_ct_attach = NULL; + /* This makes sure all current packets have passed through netfilter framework. Roll on, two-stage module delete... */ @@ -1715,6 +1717,9 @@ int __init nf_conntrack_init(void) nf_ct_l3protos[i] = &nf_conntrack_generic_l3proto; write_unlock_bh(&nf_conntrack_lock); + /* For use by REJECT target */ + ip_ct_attach = __nf_conntrack_attach; + /* Set up fake conntrack: - to never be deleted, not in any hashes */ atomic_set(&nf_conntrack_untracked.ct_general.use, 1); diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index ab0c920f0d3..6f210f39976 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -657,8 +657,6 @@ static int __init init(void) /* FIXME should be configurable whether IPv4 and IPv6 FTP connections are tracked or not - YK */ for (i = 0; i < ports_c; i++) { - memset(&ftp[i], 0, sizeof(struct nf_conntrack_helper)); - ftp[i][0].tuple.src.l3num = PF_INET; ftp[i][1].tuple.src.l3num = PF_INET6; for (j = 0; j < 2; j++) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 73ab16bc7d4..9ff3463037e 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1232,7 +1232,7 @@ static int ctnetlink_expect_event(struct notifier_block *this, b = skb->tail; - type |= NFNL_SUBSYS_CTNETLINK << 8; + type |= NFNL_SUBSYS_CTNETLINK_EXP << 8; nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg)); nfmsg = NLMSG_DATA(nlh); @@ -1589,6 +1589,7 @@ static struct nfnetlink_subsystem ctnl_exp_subsys = { }; MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); static int __init ctnetlink_init(void) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index df99138c3b3..6492ed66fb3 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -864,7 +864,9 @@ static int csum6(const struct sk_buff *skb, unsigned int dataoff) { return csum_ipv6_magic(&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr, skb->len - dataoff, IPPROTO_TCP, - skb->ip_summed == CHECKSUM_HW ? skb->csum + skb->ip_summed == CHECKSUM_HW + ? csum_sub(skb->csum, + skb_checksum(skb, 0, dataoff, 0)) : skb_checksum(skb, dataoff, skb->len - dataoff, 0)); } diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 4264dd079a1..831d206344e 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -161,7 +161,9 @@ static int csum6(const struct sk_buff *skb, unsigned int dataoff) { return csum_ipv6_magic(&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr, skb->len - dataoff, IPPROTO_UDP, - skb->ip_summed == CHECKSUM_HW ? skb->csum + skb->ip_summed == CHECKSUM_HW + ? csum_sub(skb->csum, + skb_checksum(skb, 0, dataoff, 0)) : skb_checksum(skb, dataoff, skb->len - dataoff, 0)); } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index e10512e229b..3b3c781b40c 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -37,7 +37,7 @@ #include "../bridge/br_private.h" #endif -#define NFULNL_NLBUFSIZ_DEFAULT 4096 +#define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ @@ -314,24 +314,28 @@ static struct sk_buff *nfulnl_alloc_skb(unsigned int inst_size, unsigned int pkt_size) { struct sk_buff *skb; + unsigned int n; UDEBUG("entered (%u, %u)\n", inst_size, pkt_size); /* alloc skb which should be big enough for a whole multipart * message. WARNING: has to be <= 128k due to slab restrictions */ - skb = alloc_skb(inst_size, GFP_ATOMIC); + n = max(inst_size, pkt_size); + skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { PRINTR("nfnetlink_log: can't alloc whole buffer (%u bytes)\n", inst_size); - /* try to allocate only as much as we need for current - * packet */ + if (n > pkt_size) { + /* try to allocate only as much as we need for current + * packet */ - skb = alloc_skb(pkt_size, GFP_ATOMIC); - if (!skb) - PRINTR("nfnetlink_log: can't even alloc %u bytes\n", - pkt_size); + skb = alloc_skb(pkt_size, GFP_ATOMIC); + if (!skb) + PRINTR("nfnetlink_log: can't even alloc %u " + "bytes\n", pkt_size); + } } return skb; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 18ed9c5d209..cac38b2e147 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -825,7 +825,8 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, } if (nfqa[NFQA_MARK-1]) - skb->nfmark = ntohl(*(u_int32_t *)NFA_DATA(nfqa[NFQA_MARK-1])); + entry->skb->nfmark = ntohl(*(u_int32_t *) + NFA_DATA(nfqa[NFQA_MARK-1])); issue_verdict(entry, verdict); instance_put(queue); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 2101b45d2ec..6b9772d9587 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -702,7 +702,8 @@ struct sock *netlink_getsockbyfilp(struct file *filp) * 0: continue * 1: repeat lookup - reference dropped while waiting for socket memory. */ -int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, long timeo) +int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, + long timeo, struct sock *ssk) { struct netlink_sock *nlk; @@ -712,7 +713,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, long t test_bit(0, &nlk->state)) { DECLARE_WAITQUEUE(wait, current); if (!timeo) { - if (!nlk->pid) + if (!ssk || nlk_sk(ssk)->pid == 0) netlink_overrun(sk); sock_put(sk); kfree_skb(skb); @@ -797,7 +798,7 @@ retry: kfree_skb(skb); return PTR_ERR(sk); } - err = netlink_attachskb(sk, skb, nonblock, timeo); + err = netlink_attachskb(sk, skb, nonblock, timeo, ssk); if (err == 1) goto retry; if (err) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 4ae1538c54a..43e72419c86 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -238,7 +238,7 @@ int genl_register_family(struct genl_family *family) sizeof(struct nlattr *), GFP_KERNEL); if (family->attrbuf == NULL) { err = -ENOMEM; - goto errout; + goto errout_locked; } } else family->attrbuf = NULL; @@ -288,7 +288,7 @@ int genl_unregister_family(struct genl_family *family) return -ENOENT; } -static inline int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, +static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp) { struct genl_ops *ops; @@ -375,7 +375,7 @@ static void genl_rcv(struct sock *sk, int len) do { if (genl_trylock()) return; - netlink_run_queue(sk, &qlen, &genl_rcv_msg); + netlink_run_queue(sk, &qlen, genl_rcv_msg); genl_unlock(); } while (qlen && genl_sock && genl_sock->sk_receive_queue.qlen); } @@ -549,10 +549,8 @@ static int __init genl_init(void) netlink_set_nonroot(NETLINK_GENERIC, NL_NONROOT_RECV); genl_sock = netlink_kernel_create(NETLINK_GENERIC, GENL_MAX_ID, genl_rcv, THIS_MODULE); - if (genl_sock == NULL) { + if (genl_sock == NULL) panic("GENL: Cannot initialize generic netlink\n"); - return -ENOMEM; - } return 0; @@ -560,7 +558,6 @@ errout_register: genl_unregister_family(&genl_ctrl); errout: panic("GENL: Cannot register controller: %d\n", err); - return err; } subsys_initcall(genl_init); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ee93abc71cb..9db7dbdb16e 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -365,7 +365,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, */ err = -EMSGSIZE; - if(len>dev->mtu+dev->hard_header_len) + if (len > dev->mtu + dev->hard_header_len) goto out_unlock; err = -ENOBUFS; @@ -935,7 +935,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int add * Check legality */ - if(addr_len!=sizeof(struct sockaddr)) + if (addr_len != sizeof(struct sockaddr)) return -EINVAL; strlcpy(name,uaddr->sa_data,sizeof(name)); @@ -1092,7 +1092,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, * retries. */ - if(skb==NULL) + if (skb == NULL) goto out; /* @@ -1392,8 +1392,8 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, if (level != SOL_PACKET) return -ENOPROTOOPT; - if (get_user(len,optlen)) - return -EFAULT; + if (get_user(len, optlen)) + return -EFAULT; if (len < 0) return -EINVAL; @@ -1419,9 +1419,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, return -ENOPROTOOPT; } - if (put_user(len, optlen)) - return -EFAULT; - return 0; + if (put_user(len, optlen)) + return -EFAULT; + return 0; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 4aa6fc60357..cb78b50868e 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -257,20 +257,26 @@ int sctp_rcv(struct sk_buff *skb) */ sctp_bh_lock_sock(sk); + /* It is possible that the association could have moved to a different + * socket if it is peeled off. If so, update the sk. + */ + if (sk != rcvr->sk) { + sctp_bh_lock_sock(rcvr->sk); + sctp_bh_unlock_sock(sk); + sk = rcvr->sk; + } + if (sock_owned_by_user(sk)) sk_add_backlog(sk, skb); else sctp_backlog_rcv(sk, skb); - /* Release the sock and any reference counts we took in the - * lookup calls. + /* Release the sock and the sock ref we took in the lookup calls. + * The asoc/ep ref will be released in sctp_backlog_rcv. */ sctp_bh_unlock_sock(sk); - if (asoc) - sctp_association_put(asoc); - else - sctp_endpoint_put(ep); sock_put(sk); + return ret; discard_it: @@ -296,12 +302,50 @@ discard_release: int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) { struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; - struct sctp_inq *inqueue = &chunk->rcvr->inqueue; - - sctp_inq_push(inqueue, chunk); + struct sctp_inq *inqueue = NULL; + struct sctp_ep_common *rcvr = NULL; + + rcvr = chunk->rcvr; + + BUG_TRAP(rcvr->sk == sk); + + if (rcvr->dead) { + sctp_chunk_free(chunk); + } else { + inqueue = &chunk->rcvr->inqueue; + sctp_inq_push(inqueue, chunk); + } + + /* Release the asoc/ep ref we took in the lookup calls in sctp_rcv. */ + if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type) + sctp_association_put(sctp_assoc(rcvr)); + else + sctp_endpoint_put(sctp_ep(rcvr)); + return 0; } +void sctp_backlog_migrate(struct sctp_association *assoc, + struct sock *oldsk, struct sock *newsk) +{ + struct sk_buff *skb; + struct sctp_chunk *chunk; + + skb = oldsk->sk_backlog.head; + oldsk->sk_backlog.head = oldsk->sk_backlog.tail = NULL; + while (skb != NULL) { + struct sk_buff *next = skb->next; + + chunk = SCTP_INPUT_CB(skb)->chunk; + skb->next = NULL; + if (&assoc->base == chunk->rcvr) + sk_add_backlog(newsk, skb); + else + sk_add_backlog(oldsk, skb); + skb = next; + } +} + /* Handle icmp frag needed error. */ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, struct sctp_transport *t, __u32 pmtu) @@ -544,10 +588,16 @@ int sctp_rcv_ootb(struct sk_buff *skb) sctp_errhdr_t *err; ch = (sctp_chunkhdr_t *) skb->data; - ch_end = ((__u8 *) ch) + WORD_ROUND(ntohs(ch->length)); /* Scan through all the chunks in the packet. */ - while (ch_end > (__u8 *)ch && ch_end < skb->tail) { + do { + /* Break out if chunk length 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) + break; /* RFC 8.4, 2) If the OOTB packet contains an ABORT chunk, the * receiver MUST silently discard the OOTB packet and take no @@ -578,8 +628,7 @@ int sctp_rcv_ootb(struct sk_buff *skb) } ch = (sctp_chunkhdr_t *) ch_end; - ch_end = ((__u8 *) ch) + WORD_ROUND(ntohs(ch->length)); - } + } while (ch_end < skb->tail); return 0; diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 2d33922c044..297b8951463 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -73,8 +73,10 @@ void sctp_inq_free(struct sctp_inq *queue) /* If there is a packet which is currently being worked on, * free it as well. */ - if (queue->in_progress) + if (queue->in_progress) { sctp_chunk_free(queue->in_progress); + queue->in_progress = NULL; + } if (queue->malloced) { /* Dump the master memory segment. */ diff --git a/net/sctp/output.c b/net/sctp/output.c index a40991ef72c..437cba7260a 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -608,7 +608,7 @@ static sctp_xmit_t sctp_packet_append_data(struct sctp_packet *packet, * When a Fast Retransmit is being performed the sender SHOULD * ignore the value of cwnd and SHOULD NOT delay retransmission. */ - if (!chunk->fast_retransmit) + if (chunk->fast_retransmit <= 0) if (transport->flight_size >= transport->cwnd) { retval = SCTP_XMIT_RWND_FULL; goto finish; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index efb72faba20..f148f9576dd 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -406,7 +406,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, * chunks that are not yet acked should be added to the * retransmit queue. */ - if ((fast_retransmit && chunk->fast_retransmit) || + if ((fast_retransmit && (chunk->fast_retransmit > 0)) || (!fast_retransmit && !chunk->tsn_gap_acked)) { /* RFC 2960 6.2.1 Processing a Received SACK * @@ -603,7 +603,8 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, /* Mark the chunk as ineligible for fast retransmit * after it is retransmitted. */ - chunk->fast_retransmit = 0; + if (chunk->fast_retransmit > 0) + chunk->fast_retransmit = -1; *start_timer = 1; q->empty = 0; @@ -621,7 +622,8 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, list_for_each(lchunk1, lqueue) { chunk1 = list_entry(lchunk1, struct sctp_chunk, transmitted_list); - chunk1->fast_retransmit = 0; + if (chunk1->fast_retransmit > 0) + chunk1->fast_retransmit = -1; } } } @@ -1562,11 +1564,11 @@ static void sctp_mark_missing(struct sctp_outq *q, /* * M4) If any DATA chunk is found to have a * 'TSN.Missing.Report' - * value larger than or equal to 4, mark that chunk for + * value larger than or equal to 3, mark that chunk for * retransmission and start the fast retransmit procedure. */ - if (chunk->tsn_missing_report >= 4) { + if (chunk->tsn_missing_report >= 3) { chunk->fast_retransmit = 1; do_fast_retransmit = 1; } diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 6e4dc28874d..d47a52c303a 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -176,7 +176,7 @@ static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_associa static void * sctp_eps_seq_start(struct seq_file *seq, loff_t *pos) { - if (*pos > sctp_ep_hashsize) + if (*pos >= sctp_ep_hashsize) return NULL; if (*pos < 0) @@ -185,8 +185,6 @@ static void * sctp_eps_seq_start(struct seq_file *seq, loff_t *pos) if (*pos == 0) seq_printf(seq, " ENDPT SOCK STY SST HBKT LPORT UID INODE LADDRS\n"); - ++*pos; - return (void *)pos; } @@ -198,11 +196,9 @@ static void sctp_eps_seq_stop(struct seq_file *seq, void *v) static void * sctp_eps_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - if (*pos > sctp_ep_hashsize) + if (++*pos >= sctp_ep_hashsize) return NULL; - ++*pos; - return pos; } @@ -214,19 +210,19 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_endpoint *ep; struct sock *sk; - int hash = *(int *)v; + int hash = *(loff_t *)v; - if (hash > sctp_ep_hashsize) + if (hash >= sctp_ep_hashsize) return -ENOMEM; - head = &sctp_ep_hashtable[hash-1]; + head = &sctp_ep_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); for (epb = head->chain; epb; epb = epb->next) { ep = sctp_ep(epb); sk = epb->sk; seq_printf(seq, "%8p %8p %-3d %-3d %-4d %-5d %5d %5lu ", ep, sk, - sctp_sk(sk)->type, sk->sk_state, hash-1, + sctp_sk(sk)->type, sk->sk_state, hash, epb->bind_addr.port, sock_i_uid(sk), sock_i_ino(sk)); @@ -283,7 +279,7 @@ void sctp_eps_proc_exit(void) static void * sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) { - if (*pos > sctp_assoc_hashsize) + if (*pos >= sctp_assoc_hashsize) return NULL; if (*pos < 0) @@ -293,8 +289,6 @@ static void * sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) seq_printf(seq, " ASSOC SOCK STY SST ST HBKT ASSOC-ID TX_QUEUE RX_QUEUE UID INODE LPORT " "RPORT LADDRS <-> RADDRS\n"); - ++*pos; - return (void *)pos; } @@ -306,11 +300,9 @@ static void sctp_assocs_seq_stop(struct seq_file *seq, void *v) static void * sctp_assocs_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - if (*pos > sctp_assoc_hashsize) + if (++*pos >= sctp_assoc_hashsize) return NULL; - ++*pos; - return pos; } @@ -321,12 +313,12 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_association *assoc; struct sock *sk; - int hash = *(int *)v; + int hash = *(loff_t *)v; - if (hash > sctp_assoc_hashsize) + if (hash >= sctp_assoc_hashsize) return -ENOMEM; - head = &sctp_assoc_hashtable[hash-1]; + head = &sctp_assoc_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); for (epb = head->chain; epb; epb = epb->next) { @@ -335,7 +327,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%8p %8p %-3d %-3d %-2d %-4d %4d %8d %8d %7d %5lu %-5d %5d ", assoc, sk, sctp_sk(sk)->type, sk->sk_state, - assoc->state, hash-1, assoc->assoc_id, + assoc->state, hash, assoc->assoc_id, (sk->sk_rcvbuf - assoc->rwnd), assoc->sndbuf_used, sock_i_uid(sk), sock_i_ino(sk), diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 556c495c692..5e0de3c0eea 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1275,7 +1275,12 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep, unsigned int keylen; char *key; - headersize = sizeof(sctp_paramhdr_t) + SCTP_SECRET_SIZE; + /* Header size is static data prior to the actual cookie, including + * any padding. + */ + headersize = sizeof(sctp_paramhdr_t) + + (sizeof(struct sctp_signed_cookie) - + sizeof(struct sctp_cookie)); bodysize = sizeof(struct sctp_cookie) + ntohs(init_chunk->chunk_hdr->length) + addrs_len; @@ -1354,7 +1359,7 @@ struct sctp_association *sctp_unpack_cookie( struct sctp_signed_cookie *cookie; struct sctp_cookie *bear_cookie; int headersize, bodysize, fixed_size; - __u8 digest[SCTP_SIGNATURE_SIZE]; + __u8 *digest = ep->digest; struct scatterlist sg; unsigned int keylen, len; char *key; @@ -1362,7 +1367,12 @@ struct sctp_association *sctp_unpack_cookie( struct sk_buff *skb = chunk->skb; struct timeval tv; - headersize = sizeof(sctp_chunkhdr_t) + SCTP_SECRET_SIZE; + /* Header size is static data prior to the actual cookie, including + * any padding. + */ + headersize = sizeof(sctp_chunkhdr_t) + + (sizeof(struct sctp_signed_cookie) - + sizeof(struct sctp_cookie)); bodysize = ntohs(chunk->chunk_hdr->length) - headersize; fixed_size = headersize + sizeof(struct sctp_cookie); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index b8b38aba92b..8d1dc24bab4 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1300,7 +1300,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, "T1 INIT Timeout adjustment" " init_err_counter: %d" " cycle: %d" - " timeout: %d\n", + " timeout: %ld\n", asoc->init_err_counter, asoc->init_cycle, asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT]); @@ -1328,7 +1328,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, SCTP_DEBUG_PRINTK( "T1 COOKIE Timeout adjustment" " init_err_counter: %d" - " timeout: %d\n", + " timeout: %ld\n", asoc->init_err_counter, asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE]); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 477d7f80dba..2b9a832b29a 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -884,7 +884,7 @@ sctp_disposition_t sctp_sf_sendbeat_8_3(const struct sctp_endpoint *ep, { struct sctp_transport *transport = (struct sctp_transport *) arg; - if (asoc->overall_error_count > asoc->max_retrans) { + if (asoc->overall_error_count >= asoc->max_retrans) { /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, SCTP_U32(SCTP_ERROR_NO_ERROR)); @@ -2122,7 +2122,7 @@ static sctp_disposition_t sctp_sf_do_5_2_6_stale(const struct sctp_endpoint *ep, struct sctp_bind_addr *bp; int attempts = asoc->init_err_counter + 1; - if (attempts >= asoc->max_init_attempts) { + if (attempts > asoc->max_init_attempts) { sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED, SCTP_U32(SCTP_ERROR_STALE_COOKIE)); return SCTP_DISPOSITION_DELETE_TCB; @@ -3090,6 +3090,8 @@ sctp_disposition_t sctp_sf_ootb(const struct sctp_endpoint *ep, break; ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); + if (ch_end > skb->tail) + break; if (SCTP_CID_SHUTDOWN_ACK == ch->type) ootb_shut_ack = 1; @@ -4638,7 +4640,7 @@ sctp_disposition_t sctp_sf_t1_init_timer_expire(const struct sctp_endpoint *ep, SCTP_DEBUG_PRINTK("Timer T1 expired (INIT).\n"); - if (attempts < asoc->max_init_attempts) { + if (attempts <= asoc->max_init_attempts) { bp = (struct sctp_bind_addr *) &asoc->base.bind_addr; repl = sctp_make_init(asoc, bp, GFP_ATOMIC, 0); if (!repl) @@ -4695,7 +4697,7 @@ sctp_disposition_t sctp_sf_t1_cookie_timer_expire(const struct sctp_endpoint *ep SCTP_DEBUG_PRINTK("Timer T1 expired (COOKIE-ECHO).\n"); - if (attempts < asoc->max_init_attempts) { + if (attempts <= asoc->max_init_attempts) { repl = sctp_make_cookie_echo(asoc, NULL); if (!repl) return SCTP_DISPOSITION_NOMEM; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c98ee375ba5..0ea947eb681 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2995,7 +2995,7 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) sp->hbinterval = jiffies_to_msecs(sctp_hb_interval); sp->pathmaxrxt = sctp_max_retrans_path; sp->pathmtu = 0; // allow default discovery - sp->sackdelay = sctp_sack_timeout; + sp->sackdelay = jiffies_to_msecs(sctp_sack_timeout); sp->param_flags = SPP_HB_ENABLE | SPP_PMTUD_ENABLE | SPP_SACKDELAY_ENABLE; @@ -5426,7 +5426,7 @@ out: return err; do_error: - if (asoc->init_err_counter + 1 >= asoc->max_init_attempts) + if (asoc->init_err_counter + 1 > asoc->max_init_attempts) err = -ETIMEDOUT; else err = -ECONNREFUSED; @@ -5602,8 +5602,12 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, */ newsp->type = type; + spin_lock_bh(&oldsk->sk_lock.slock); + /* Migrate the backlog from oldsk to newsk. */ + sctp_backlog_migrate(assoc, oldsk, newsk); /* Migrate the association to the new socket. */ sctp_assoc_migrate(assoc, newsk); + spin_unlock_bh(&oldsk->sk_lock.slock); /* If the association on the newsk is already closed before accept() * is called, set RCV_SHUTDOWN flag. diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index fcd7096c953..dc6f3ff3235 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -159,12 +159,9 @@ static ctl_table sctp_table[] = { .ctl_name = NET_SCTP_PRESERVE_ENABLE, .procname = "cookie_preserve_enable", .data = &sctp_cookie_preserve_enable, - .maxlen = sizeof(long), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, - .strategy = &sctp_sysctl_jiffies_ms, - .extra1 = &rto_timer_min, - .extra2 = &rto_timer_max + .proc_handler = &proc_dointvec }, { .ctl_name = NET_SCTP_RTO_ALPHA, diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 68d73e2dd15..160f62ad1cc 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -350,7 +350,7 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) tp->rto_pending = 0; SCTP_DEBUG_PRINTK("%s: transport: %p, rtt: %d, srtt: %d " - "rttvar: %d, rto: %d\n", __FUNCTION__, + "rttvar: %d, rto: %ld\n", __FUNCTION__, tp, rtt, tp->srtt, tp->rttvar, tp->rto); } diff --git a/net/socket.c b/net/socket.c index b38a263853c..a00851f981d 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2078,7 +2078,7 @@ void socket_seq_show(struct seq_file *seq) int cpu; int counter = 0; - for (cpu = 0; cpu < NR_CPUS; cpu++) + for_each_cpu(cpu) counter += per_cpu(sockets_in_use, cpu); /* It can be negative, by the way. 8) */ diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 9ac1b8c26c0..8d6f1a176b1 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -184,7 +184,7 @@ rpcauth_gc_credcache(struct rpc_auth *auth, struct hlist_head *free) */ struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, - int taskflags) + int flags) { struct rpc_cred_cache *cache = auth->au_credcache; HLIST_HEAD(free); @@ -193,7 +193,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, *cred = NULL; int nr = 0; - if (!(taskflags & RPC_TASK_ROOTCREDS)) + if (!(flags & RPCAUTH_LOOKUP_ROOTCREDS)) nr = acred->uid & RPC_CREDCACHE_MASK; retry: spin_lock(&rpc_credcache_lock); @@ -202,7 +202,7 @@ retry: hlist_for_each_safe(pos, next, &cache->hashtable[nr]) { struct rpc_cred *entry; entry = hlist_entry(pos, struct rpc_cred, cr_hash); - if (entry->cr_ops->crmatch(acred, entry, taskflags)) { + if (entry->cr_ops->crmatch(acred, entry, flags)) { hlist_del(&entry->cr_hash); cred = entry; break; @@ -224,7 +224,7 @@ retry: rpcauth_destroy_credlist(&free); if (!cred) { - new = auth->au_ops->crcreate(auth, acred, taskflags); + new = auth->au_ops->crcreate(auth, acred, flags); if (!IS_ERR(new)) { #ifdef RPC_DEBUG new->cr_magic = RPCAUTH_CRED_MAGIC; @@ -232,13 +232,21 @@ retry: goto retry; } else cred = new; + } else if ((cred->cr_flags & RPCAUTH_CRED_NEW) + && cred->cr_ops->cr_init != NULL + && !(flags & RPCAUTH_LOOKUP_NEW)) { + int res = cred->cr_ops->cr_init(auth, cred); + if (res < 0) { + put_rpccred(cred); + cred = ERR_PTR(res); + } } return (struct rpc_cred *) cred; } struct rpc_cred * -rpcauth_lookupcred(struct rpc_auth *auth, int taskflags) +rpcauth_lookupcred(struct rpc_auth *auth, int flags) { struct auth_cred acred = { .uid = current->fsuid, @@ -250,7 +258,7 @@ rpcauth_lookupcred(struct rpc_auth *auth, int taskflags) dprintk("RPC: looking up %s cred\n", auth->au_ops->au_name); get_group_info(acred.group_info); - ret = auth->au_ops->lookup_cred(auth, &acred, taskflags); + ret = auth->au_ops->lookup_cred(auth, &acred, flags); put_group_info(acred.group_info); return ret; } @@ -265,11 +273,14 @@ rpcauth_bindcred(struct rpc_task *task) .group_info = current->group_info, }; struct rpc_cred *ret; + int flags = 0; dprintk("RPC: %4d looking up %s cred\n", task->tk_pid, task->tk_auth->au_ops->au_name); get_group_info(acred.group_info); - ret = auth->au_ops->lookup_cred(auth, &acred, task->tk_flags); + if (task->tk_flags & RPC_TASK_ROOTCREDS) + flags |= RPCAUTH_LOOKUP_ROOTCREDS; + ret = auth->au_ops->lookup_cred(auth, &acred, flags); if (!IS_ERR(ret)) task->tk_msg.rpc_cred = ret; else diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 8d782282ec1..bb46efd92e5 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -158,6 +158,7 @@ gss_cred_set_ctx(struct rpc_cred *cred, struct gss_cl_ctx *ctx) old = gss_cred->gc_ctx; gss_cred->gc_ctx = ctx; cred->cr_flags |= RPCAUTH_CRED_UPTODATE; + cred->cr_flags &= ~RPCAUTH_CRED_NEW; write_unlock(&gss_ctx_lock); if (old) gss_put_ctx(old); @@ -580,7 +581,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) } else { struct auth_cred acred = { .uid = uid }; spin_unlock(&gss_auth->lock); - cred = rpcauth_lookup_credcache(clnt->cl_auth, &acred, 0); + cred = rpcauth_lookup_credcache(clnt->cl_auth, &acred, RPCAUTH_LOOKUP_NEW); if (IS_ERR(cred)) { err = PTR_ERR(cred); goto err_put_ctx; @@ -758,13 +759,13 @@ gss_destroy_cred(struct rpc_cred *rc) * Lookup RPCSEC_GSS cred for the current process */ static struct rpc_cred * -gss_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int taskflags) +gss_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) { - return rpcauth_lookup_credcache(auth, acred, taskflags); + return rpcauth_lookup_credcache(auth, acred, flags); } static struct rpc_cred * -gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int taskflags) +gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) { struct gss_auth *gss_auth = container_of(auth, struct gss_auth, rpc_auth); struct gss_cred *cred = NULL; @@ -785,13 +786,8 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int taskflags) */ cred->gc_flags = 0; cred->gc_base.cr_ops = &gss_credops; + cred->gc_base.cr_flags = RPCAUTH_CRED_NEW; cred->gc_service = gss_auth->service; - do { - err = gss_create_upcall(gss_auth, cred); - } while (err == -EAGAIN); - if (err < 0) - goto out_err; - return &cred->gc_base; out_err: @@ -801,13 +797,34 @@ out_err: } static int -gss_match(struct auth_cred *acred, struct rpc_cred *rc, int taskflags) +gss_cred_init(struct rpc_auth *auth, struct rpc_cred *cred) +{ + struct gss_auth *gss_auth = container_of(auth, struct gss_auth, rpc_auth); + struct gss_cred *gss_cred = container_of(cred,struct gss_cred, gc_base); + int err; + + do { + err = gss_create_upcall(gss_auth, gss_cred); + } while (err == -EAGAIN); + return err; +} + +static int +gss_match(struct auth_cred *acred, struct rpc_cred *rc, int flags) { struct gss_cred *gss_cred = container_of(rc, struct gss_cred, gc_base); + /* + * If the searchflags have set RPCAUTH_LOOKUP_NEW, then + * we don't really care if the credential has expired or not, + * since the caller should be prepared to reinitialise it. + */ + if ((flags & RPCAUTH_LOOKUP_NEW) && (rc->cr_flags & RPCAUTH_CRED_NEW)) + goto out; /* Don't match with creds that have expired. */ if (gss_cred->gc_ctx && time_after(jiffies, gss_cred->gc_ctx->gc_expiry)) return 0; +out: return (rc->cr_uid == acred->uid); } @@ -1241,6 +1258,7 @@ static struct rpc_authops authgss_ops = { static struct rpc_credops gss_credops = { .cr_name = "AUTH_GSS", .crdestroy = gss_destroy_cred, + .cr_init = gss_cred_init, .crmatch = gss_match, .crmarshal = gss_marshal, .crrefresh = gss_refresh, diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index 1b3ed4fd198..df14b6bfbf1 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -75,7 +75,7 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) atomic_set(&cred->uc_count, 1); cred->uc_flags = RPCAUTH_CRED_UPTODATE; - if (flags & RPC_TASK_ROOTCREDS) { + if (flags & RPCAUTH_LOOKUP_ROOTCREDS) { cred->uc_uid = 0; cred->uc_gid = 0; cred->uc_gids[0] = NOGROUP; @@ -108,12 +108,12 @@ unx_destroy_cred(struct rpc_cred *cred) * request root creds (e.g. for NFS swapping). */ static int -unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int taskflags) +unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags) { struct unx_cred *cred = (struct unx_cred *) rcred; int i; - if (!(taskflags & RPC_TASK_ROOTCREDS)) { + if (!(flags & RPCAUTH_LOOKUP_ROOTCREDS)) { int groups; if (cred->uc_uid != acred->uid diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 9764c80ab0b..a5c0c7b6e15 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -38,44 +38,42 @@ static kmem_cache_t *rpc_inode_cachep __read_mostly; #define RPC_UPCALL_TIMEOUT (30*HZ) -static void -__rpc_purge_list(struct rpc_inode *rpci, struct list_head *head, int err) +static void rpc_purge_list(struct rpc_inode *rpci, struct list_head *head, + void (*destroy_msg)(struct rpc_pipe_msg *), int err) { struct rpc_pipe_msg *msg; - void (*destroy_msg)(struct rpc_pipe_msg *); - destroy_msg = rpci->ops->destroy_msg; - while (!list_empty(head)) { + if (list_empty(head)) + return; + do { msg = list_entry(head->next, struct rpc_pipe_msg, list); - list_del_init(&msg->list); + list_del(&msg->list); msg->errno = err; destroy_msg(msg); - } -} - -static void -__rpc_purge_upcall(struct inode *inode, int err) -{ - struct rpc_inode *rpci = RPC_I(inode); - - __rpc_purge_list(rpci, &rpci->pipe, err); - rpci->pipelen = 0; + } while (!list_empty(head)); wake_up(&rpci->waitq); } static void rpc_timeout_upcall_queue(void *data) { + LIST_HEAD(free_list); struct rpc_inode *rpci = (struct rpc_inode *)data; struct inode *inode = &rpci->vfs_inode; + void (*destroy_msg)(struct rpc_pipe_msg *); - mutex_lock(&inode->i_mutex); - if (rpci->ops == NULL) - goto out; - if (rpci->nreaders == 0 && !list_empty(&rpci->pipe)) - __rpc_purge_upcall(inode, -ETIMEDOUT); -out: - mutex_unlock(&inode->i_mutex); + spin_lock(&inode->i_lock); + if (rpci->ops == NULL) { + spin_unlock(&inode->i_lock); + return; + } + destroy_msg = rpci->ops->destroy_msg; + if (rpci->nreaders == 0) { + list_splice_init(&rpci->pipe, &free_list); + rpci->pipelen = 0; + } + spin_unlock(&inode->i_lock); + rpc_purge_list(rpci, &free_list, destroy_msg, -ETIMEDOUT); } int @@ -84,7 +82,7 @@ rpc_queue_upcall(struct inode *inode, struct rpc_pipe_msg *msg) struct rpc_inode *rpci = RPC_I(inode); int res = -EPIPE; - mutex_lock(&inode->i_mutex); + spin_lock(&inode->i_lock); if (rpci->ops == NULL) goto out; if (rpci->nreaders) { @@ -100,7 +98,7 @@ rpc_queue_upcall(struct inode *inode, struct rpc_pipe_msg *msg) res = 0; } out: - mutex_unlock(&inode->i_mutex); + spin_unlock(&inode->i_lock); wake_up(&rpci->waitq); return res; } @@ -115,21 +113,29 @@ static void rpc_close_pipes(struct inode *inode) { struct rpc_inode *rpci = RPC_I(inode); + struct rpc_pipe_ops *ops; mutex_lock(&inode->i_mutex); - if (rpci->ops != NULL) { + ops = rpci->ops; + if (ops != NULL) { + LIST_HEAD(free_list); + + spin_lock(&inode->i_lock); rpci->nreaders = 0; - __rpc_purge_list(rpci, &rpci->in_upcall, -EPIPE); - __rpc_purge_upcall(inode, -EPIPE); - rpci->nwriters = 0; - if (rpci->ops->release_pipe) - rpci->ops->release_pipe(inode); + list_splice_init(&rpci->in_upcall, &free_list); + list_splice_init(&rpci->pipe, &free_list); + rpci->pipelen = 0; rpci->ops = NULL; + spin_unlock(&inode->i_lock); + rpc_purge_list(rpci, &free_list, ops->destroy_msg, -EPIPE); + rpci->nwriters = 0; + if (ops->release_pipe) + ops->release_pipe(inode); + cancel_delayed_work(&rpci->queue_timeout); + flush_scheduled_work(); } rpc_inode_setowner(inode, NULL); mutex_unlock(&inode->i_mutex); - cancel_delayed_work(&rpci->queue_timeout); - flush_scheduled_work(); } static struct inode * @@ -177,16 +183,26 @@ rpc_pipe_release(struct inode *inode, struct file *filp) goto out; msg = (struct rpc_pipe_msg *)filp->private_data; if (msg != NULL) { + spin_lock(&inode->i_lock); msg->errno = -EAGAIN; - list_del_init(&msg->list); + list_del(&msg->list); + spin_unlock(&inode->i_lock); rpci->ops->destroy_msg(msg); } if (filp->f_mode & FMODE_WRITE) rpci->nwriters --; - if (filp->f_mode & FMODE_READ) + if (filp->f_mode & FMODE_READ) { rpci->nreaders --; - if (!rpci->nreaders) - __rpc_purge_upcall(inode, -EAGAIN); + if (rpci->nreaders == 0) { + LIST_HEAD(free_list); + spin_lock(&inode->i_lock); + list_splice_init(&rpci->pipe, &free_list); + rpci->pipelen = 0; + spin_unlock(&inode->i_lock); + rpc_purge_list(rpci, &free_list, + rpci->ops->destroy_msg, -EAGAIN); + } + } if (rpci->ops->release_pipe) rpci->ops->release_pipe(inode); out: @@ -209,6 +225,7 @@ rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset) } msg = filp->private_data; if (msg == NULL) { + spin_lock(&inode->i_lock); if (!list_empty(&rpci->pipe)) { msg = list_entry(rpci->pipe.next, struct rpc_pipe_msg, @@ -218,6 +235,7 @@ rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset) filp->private_data = msg; msg->copied = 0; } + spin_unlock(&inode->i_lock); if (msg == NULL) goto out_unlock; } @@ -225,7 +243,9 @@ rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset) res = rpci->ops->upcall(filp, msg, buf, len); if (res < 0 || msg->len == msg->copied) { filp->private_data = NULL; - list_del_init(&msg->list); + spin_lock(&inode->i_lock); + list_del(&msg->list); + spin_unlock(&inode->i_lock); rpci->ops->destroy_msg(msg); } out_unlock: @@ -610,7 +630,7 @@ rpc_lookup_negative(char *path, struct nameidata *nd) return ERR_PTR(error); dir = nd->dentry->d_inode; mutex_lock(&dir->i_mutex); - dentry = lookup_hash(nd); + dentry = lookup_one_len(nd->last.name, nd->dentry, nd->last.len); if (IS_ERR(dentry)) goto out_err; if (dentry->d_inode) { @@ -672,7 +692,7 @@ rpc_rmdir(char *path) return error; dir = nd.dentry->d_inode; mutex_lock(&dir->i_mutex); - dentry = lookup_hash(&nd); + dentry = lookup_one_len(nd.last.name, nd.dentry, nd.last.len); if (IS_ERR(dentry)) { error = PTR_ERR(dentry); goto out_release; @@ -733,7 +753,7 @@ rpc_unlink(char *path) return error; dir = nd.dentry->d_inode; mutex_lock(&dir->i_mutex); - dentry = lookup_hash(&nd); + dentry = lookup_one_len(nd.last.name, nd.dentry, nd.last.len); if (IS_ERR(dentry)) { error = PTR_ERR(dentry); goto out_release; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 7415406aa1a..802d4fe0f55 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -908,10 +908,10 @@ void rpc_release_task(struct rpc_task *task) /** * rpc_run_task - Allocate a new RPC task, then run rpc_execute against it - * @clnt - pointer to RPC client - * @flags - RPC flags - * @ops - RPC call ops - * @data - user call data + * @clnt: pointer to RPC client + * @flags: RPC flags + * @ops: RPC call ops + * @data: user call data */ struct rpc_task *rpc_run_task(struct rpc_clnt *clnt, int flags, const struct rpc_call_ops *ops, @@ -930,6 +930,7 @@ EXPORT_SYMBOL(rpc_run_task); /** * rpc_find_parent - find the parent of a child task. * @child: child task + * @parent: parent task * * Checks that the parent task is still sleeping on the * queue 'childq'. If so returns a pointer to the parent. diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 077bbf9fb9b..8206025d8e4 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -13,7 +13,6 @@ * */ -#include <asm/bug.h> #include <linux/config.h> #include <linux/slab.h> #include <linux/kmod.h> @@ -783,7 +782,7 @@ int xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl, int nx = 0; int err; u32 genid; - u16 family = dst_orig->ops->family; + u16 family; u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT); u32 sk_sid = security_sk_sid(sk, fl, dir); restart: @@ -797,13 +796,14 @@ restart: if ((dst_orig->flags & DST_NOXFRM) || !xfrm_policy_list[XFRM_POLICY_OUT]) return 0; - policy = flow_cache_lookup(fl, sk_sid, family, dir, - xfrm_policy_lookup); + policy = flow_cache_lookup(fl, sk_sid, dst_orig->ops->family, + dir, xfrm_policy_lookup); } if (!policy) return 0; + family = dst_orig->ops->family; policy->curlft.use_time = (unsigned long)xtime.tv_sec; switch (policy->action) { @@ -886,11 +886,11 @@ restart: * We can't enlist stable bundles either. */ write_unlock_bh(&policy->lock); - - xfrm_pol_put(policy); if (dst) dst_free(dst); - goto restart; + + err = -EHOSTUNREACH; + goto error; } dst->next = policy->bundles; policy->bundles = dst; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index e12d0be5f97..c656cbaf35e 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -220,14 +220,14 @@ static int __xfrm_state_delete(struct xfrm_state *x) x->km.state = XFRM_STATE_DEAD; spin_lock(&xfrm_state_lock); list_del(&x->bydst); - atomic_dec(&x->refcnt); + __xfrm_state_put(x); if (x->id.spi) { list_del(&x->byspi); - atomic_dec(&x->refcnt); + __xfrm_state_put(x); } spin_unlock(&xfrm_state_lock); if (del_timer(&x->timer)) - atomic_dec(&x->refcnt); + __xfrm_state_put(x); /* The number two in this test is the reference * mentioned in the comment below plus the reference @@ -243,7 +243,7 @@ static int __xfrm_state_delete(struct xfrm_state *x) * The xfrm_state_alloc call gives a reference, and that * is what we are dropping here. */ - atomic_dec(&x->refcnt); + __xfrm_state_put(x); err = 0; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ac87a09ba83..7de17559249 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -345,7 +345,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) if (err < 0) { x->km.state = XFRM_STATE_DEAD; - xfrm_state_put(x); + __xfrm_state_put(x); goto out; } |