diff options
Diffstat (limited to 'net')
103 files changed, 910 insertions, 492 deletions
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 078eb162d9bf..a30471e51740 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -153,10 +153,11 @@ struct p9_conn { unsigned long wsched; }; +static void p9_poll_workfn(struct work_struct *work); + static DEFINE_SPINLOCK(p9_poll_lock); static LIST_HEAD(p9_poll_pending_list); -static struct workqueue_struct *p9_mux_wq; -static struct task_struct *p9_poll_task; +static DECLARE_WORK(p9_poll_work, p9_poll_workfn); static void p9_mux_poll_stop(struct p9_conn *m) { @@ -384,7 +385,7 @@ static void p9_read_work(struct work_struct *work) if (n & POLLIN) { P9_DPRINTK(P9_DEBUG_TRANS, "sched read work %p\n", m); - queue_work(p9_mux_wq, &m->rq); + schedule_work(&m->rq); } else clear_bit(Rworksched, &m->wsched); } else @@ -497,7 +498,7 @@ static void p9_write_work(struct work_struct *work) if (n & POLLOUT) { P9_DPRINTK(P9_DEBUG_TRANS, "sched write work %p\n", m); - queue_work(p9_mux_wq, &m->wq); + schedule_work(&m->wq); } else clear_bit(Wworksched, &m->wsched); } else @@ -516,15 +517,14 @@ static int p9_pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) container_of(wait, struct p9_poll_wait, wait); struct p9_conn *m = pwait->conn; unsigned long flags; - DECLARE_WAITQUEUE(dummy_wait, p9_poll_task); spin_lock_irqsave(&p9_poll_lock, flags); if (list_empty(&m->poll_pending_link)) list_add_tail(&m->poll_pending_link, &p9_poll_pending_list); spin_unlock_irqrestore(&p9_poll_lock, flags); - /* perform the default wake up operation */ - return default_wake_function(&dummy_wait, mode, sync, key); + schedule_work(&p9_poll_work); + return 1; } /** @@ -629,7 +629,7 @@ static void p9_poll_mux(struct p9_conn *m) P9_DPRINTK(P9_DEBUG_TRANS, "mux %p can read\n", m); if (!test_and_set_bit(Rworksched, &m->wsched)) { P9_DPRINTK(P9_DEBUG_TRANS, "sched read work %p\n", m); - queue_work(p9_mux_wq, &m->rq); + schedule_work(&m->rq); } } @@ -639,7 +639,7 @@ static void p9_poll_mux(struct p9_conn *m) if ((m->wsize || !list_empty(&m->unsent_req_list)) && !test_and_set_bit(Wworksched, &m->wsched)) { P9_DPRINTK(P9_DEBUG_TRANS, "sched write work %p\n", m); - queue_work(p9_mux_wq, &m->wq); + schedule_work(&m->wq); } } } @@ -677,7 +677,7 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req) n = p9_fd_poll(m->client, NULL); if (n & POLLOUT && !test_and_set_bit(Wworksched, &m->wsched)) - queue_work(p9_mux_wq, &m->wq); + schedule_work(&m->wq); return 0; } @@ -1047,12 +1047,12 @@ static struct p9_trans_module p9_fd_trans = { * */ -static int p9_poll_proc(void *a) +static void p9_poll_workfn(struct work_struct *work) { unsigned long flags; P9_DPRINTK(P9_DEBUG_TRANS, "start %p\n", current); - repeat: + spin_lock_irqsave(&p9_poll_lock, flags); while (!list_empty(&p9_poll_pending_list)) { struct p9_conn *conn = list_first_entry(&p9_poll_pending_list, @@ -1067,35 +1067,11 @@ static int p9_poll_proc(void *a) } spin_unlock_irqrestore(&p9_poll_lock, flags); - set_current_state(TASK_INTERRUPTIBLE); - if (list_empty(&p9_poll_pending_list)) { - P9_DPRINTK(P9_DEBUG_TRANS, "sleeping...\n"); - schedule(); - } - __set_current_state(TASK_RUNNING); - - if (!kthread_should_stop()) - goto repeat; - P9_DPRINTK(P9_DEBUG_TRANS, "finish\n"); - return 0; } int p9_trans_fd_init(void) { - p9_mux_wq = create_workqueue("v9fs"); - if (!p9_mux_wq) { - printk(KERN_WARNING "v9fs: mux: creating workqueue failed\n"); - return -ENOMEM; - } - - p9_poll_task = kthread_run(p9_poll_proc, NULL, "v9fs-poll"); - if (IS_ERR(p9_poll_task)) { - destroy_workqueue(p9_mux_wq); - printk(KERN_WARNING "v9fs: mux: creating poll task failed\n"); - return PTR_ERR(p9_poll_task); - } - v9fs_register_trans(&p9_tcp_trans); v9fs_register_trans(&p9_unix_trans); v9fs_register_trans(&p9_fd_trans); @@ -1105,10 +1081,8 @@ int p9_trans_fd_init(void) void p9_trans_fd_exit(void) { - kthread_stop(p9_poll_task); + flush_work_sync(&p9_poll_work); v9fs_unregister_trans(&p9_tcp_trans); v9fs_unregister_trans(&p9_unix_trans); v9fs_unregister_trans(&p9_fd_trans); - - destroy_workqueue(p9_mux_wq); } diff --git a/net/Makefile b/net/Makefile index a3330ebe2c53..a51d9465e628 100644 --- a/net/Makefile +++ b/net/Makefile @@ -19,9 +19,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_XFRM) += xfrm/ obj-$(CONFIG_UNIX) += unix/ -ifneq ($(CONFIG_IPV6),) -obj-y += ipv6/ -endif +obj-$(CONFIG_NET) += ipv6/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index ee41fef04b21..d1a611322549 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -50,12 +50,12 @@ static struct sk_buff *frag_merge_packet(struct list_head *head, skb = tfp->skb; } + if (skb_linearize(skb) < 0 || skb_linearize(tmp_skb) < 0) + goto err; + skb_pull(tmp_skb, sizeof(struct unicast_frag_packet)); - if (pskb_expand_head(skb, 0, tmp_skb->len, GFP_ATOMIC) < 0) { - /* free buffered skb, skb will be freed later */ - kfree_skb(tfp->skb); - return NULL; - } + if (pskb_expand_head(skb, 0, tmp_skb->len, GFP_ATOMIC) < 0) + goto err; /* move free entry to end */ tfp->skb = NULL; @@ -70,6 +70,11 @@ static struct sk_buff *frag_merge_packet(struct list_head *head, unicast_packet->packet_type = BAT_UNICAST; return skb; + +err: + /* free buffered skb, skb will be freed later */ + kfree_skb(tfp->skb); + return NULL; } static void frag_create_entry(struct list_head *head, struct sk_buff *skb) diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index cd4c4231fa48..de1022cacaf7 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -64,6 +64,7 @@ static void free_info(struct kref *ref) spin_unlock_bh(&bat_priv->vis_list_lock); kfree_skb(info->skb_packet); + kfree(info); } /* Compare two vis packets, used by the hashing algorithm */ @@ -268,10 +269,10 @@ int vis_seq_print_text(struct seq_file *seq, void *offset) buff_pos += sprintf(buff + buff_pos, "%pM,", entry->addr); - for (i = 0; i < packet->entries; i++) + for (j = 0; j < packet->entries; j++) buff_pos += vis_data_read_entry( buff + buff_pos, - &entries[i], + &entries[j], entry->addr, entry->primary); @@ -444,7 +445,7 @@ static struct vis_info *add_packet(struct bat_priv *bat_priv, info); if (hash_added < 0) { /* did not work (for some reason) */ - kref_put(&old_info->refcount, free_info); + kref_put(&info->refcount, free_info); info = NULL; } @@ -815,7 +816,7 @@ static void send_vis_packets(struct work_struct *work) container_of(work, struct delayed_work, work); struct bat_priv *bat_priv = container_of(delayed_work, struct bat_priv, vis_work); - struct vis_info *info, *temp; + struct vis_info *info; spin_lock_bh(&bat_priv->vis_hash_lock); purge_vis_packets(bat_priv); @@ -825,8 +826,9 @@ static void send_vis_packets(struct work_struct *work) send_list_add(bat_priv, bat_priv->my_vis_info); } - list_for_each_entry_safe(info, temp, &bat_priv->vis_send_list, - send_list) { + while (!list_empty(&bat_priv->vis_send_list)) { + info = list_first_entry(&bat_priv->vis_send_list, + typeof(*info), send_list); kref_get(&info->refcount); spin_unlock_bh(&bat_priv->vis_hash_lock); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 6b90a4191734..99cd8d9d891b 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -379,14 +379,10 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 hci_conn_hold(acl); if (acl->state == BT_OPEN || acl->state == BT_CLOSED) { - acl->sec_level = sec_level; + acl->sec_level = BT_SECURITY_LOW; + acl->pending_sec_level = sec_level; acl->auth_type = auth_type; hci_acl_connect(acl); - } else { - if (acl->sec_level < sec_level) - acl->sec_level = sec_level; - if (acl->auth_type < auth_type) - acl->auth_type = auth_type; } if (type == ACL_LINK) @@ -442,11 +438,17 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) { BT_DBG("conn %p", conn); + if (conn->pending_sec_level > sec_level) + sec_level = conn->pending_sec_level; + if (sec_level > conn->sec_level) - conn->sec_level = sec_level; + conn->pending_sec_level = sec_level; else if (conn->link_mode & HCI_LM_AUTH) return 1; + /* Make sure we preserve an existing MITM requirement*/ + auth_type |= (conn->auth_type & 0x01); + conn->auth_type = auth_type; if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->pend)) { diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 8b602d881fd7..9c4541bc488a 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1011,6 +1011,10 @@ int hci_unregister_dev(struct hci_dev *hdev) destroy_workqueue(hdev->workqueue); + hci_dev_lock_bh(hdev); + hci_blacklist_clear(hdev); + hci_dev_unlock_bh(hdev); + __hci_dev_put(hdev); return 0; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 38100170d380..a290854fdaa6 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -692,13 +692,13 @@ static int hci_outgoing_auth_needed(struct hci_dev *hdev, if (conn->state != BT_CONFIG || !conn->out) return 0; - if (conn->sec_level == BT_SECURITY_SDP) + if (conn->pending_sec_level == BT_SECURITY_SDP) return 0; /* Only request authentication for SSP connections or non-SSP * devices with sec_level HIGH */ if (!(hdev->ssp_mode > 0 && conn->ssp_mode > 0) && - conn->sec_level != BT_SECURITY_HIGH) + conn->pending_sec_level != BT_SECURITY_HIGH) return 0; return 1; @@ -1095,9 +1095,10 @@ static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *s conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); if (conn) { - if (!ev->status) + if (!ev->status) { conn->link_mode |= HCI_LM_AUTH; - else + conn->sec_level = conn->pending_sec_level; + } else conn->sec_level = BT_SECURITY_LOW; clear_bit(HCI_CONN_AUTH_PEND, &conn->pend); diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index c791fcda7b2d..675614e38e14 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -305,33 +305,44 @@ static void l2cap_chan_del(struct sock *sk, int err) } } -/* Service level security */ -static inline int l2cap_check_security(struct sock *sk) +static inline u8 l2cap_get_auth_type(struct sock *sk) { - struct l2cap_conn *conn = l2cap_pi(sk)->conn; - __u8 auth_type; + if (sk->sk_type == SOCK_RAW) { + switch (l2cap_pi(sk)->sec_level) { + case BT_SECURITY_HIGH: + return HCI_AT_DEDICATED_BONDING_MITM; + case BT_SECURITY_MEDIUM: + return HCI_AT_DEDICATED_BONDING; + default: + return HCI_AT_NO_BONDING; + } + } else if (l2cap_pi(sk)->psm == cpu_to_le16(0x0001)) { + if (l2cap_pi(sk)->sec_level == BT_SECURITY_LOW) + l2cap_pi(sk)->sec_level = BT_SECURITY_SDP; - if (l2cap_pi(sk)->psm == cpu_to_le16(0x0001)) { if (l2cap_pi(sk)->sec_level == BT_SECURITY_HIGH) - auth_type = HCI_AT_NO_BONDING_MITM; + return HCI_AT_NO_BONDING_MITM; else - auth_type = HCI_AT_NO_BONDING; - - if (l2cap_pi(sk)->sec_level == BT_SECURITY_LOW) - l2cap_pi(sk)->sec_level = BT_SECURITY_SDP; + return HCI_AT_NO_BONDING; } else { switch (l2cap_pi(sk)->sec_level) { case BT_SECURITY_HIGH: - auth_type = HCI_AT_GENERAL_BONDING_MITM; - break; + return HCI_AT_GENERAL_BONDING_MITM; case BT_SECURITY_MEDIUM: - auth_type = HCI_AT_GENERAL_BONDING; - break; + return HCI_AT_GENERAL_BONDING; default: - auth_type = HCI_AT_NO_BONDING; - break; + return HCI_AT_NO_BONDING; } } +} + +/* Service level security */ +static inline int l2cap_check_security(struct sock *sk) +{ + struct l2cap_conn *conn = l2cap_pi(sk)->conn; + __u8 auth_type; + + auth_type = l2cap_get_auth_type(sk); return hci_conn_security(conn->hcon, l2cap_pi(sk)->sec_level, auth_type); @@ -848,6 +859,7 @@ static void __l2cap_sock_close(struct sock *sk, int reason) result = L2CAP_CR_SEC_BLOCK; else result = L2CAP_CR_BAD_PSM; + sk->sk_state = BT_DISCONN; rsp.scid = cpu_to_le16(l2cap_pi(sk)->dcid); rsp.dcid = cpu_to_le16(l2cap_pi(sk)->scid); @@ -1068,39 +1080,7 @@ static int l2cap_do_connect(struct sock *sk) err = -ENOMEM; - if (sk->sk_type == SOCK_RAW) { - switch (l2cap_pi(sk)->sec_level) { - case BT_SECURITY_HIGH: - auth_type = HCI_AT_DEDICATED_BONDING_MITM; - break; - case BT_SECURITY_MEDIUM: - auth_type = HCI_AT_DEDICATED_BONDING; - break; - default: - auth_type = HCI_AT_NO_BONDING; - break; - } - } else if (l2cap_pi(sk)->psm == cpu_to_le16(0x0001)) { - if (l2cap_pi(sk)->sec_level == BT_SECURITY_HIGH) - auth_type = HCI_AT_NO_BONDING_MITM; - else - auth_type = HCI_AT_NO_BONDING; - - if (l2cap_pi(sk)->sec_level == BT_SECURITY_LOW) - l2cap_pi(sk)->sec_level = BT_SECURITY_SDP; - } else { - switch (l2cap_pi(sk)->sec_level) { - case BT_SECURITY_HIGH: - auth_type = HCI_AT_GENERAL_BONDING_MITM; - break; - case BT_SECURITY_MEDIUM: - auth_type = HCI_AT_GENERAL_BONDING; - break; - default: - auth_type = HCI_AT_NO_BONDING; - break; - } - } + auth_type = l2cap_get_auth_type(sk); hcon = hci_connect(hdev, ACL_LINK, dst, l2cap_pi(sk)->sec_level, auth_type); @@ -1127,7 +1107,8 @@ static int l2cap_do_connect(struct sock *sk) if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM) { l2cap_sock_clear_timer(sk); - sk->sk_state = BT_CONNECTED; + if (l2cap_check_security(sk)) + sk->sk_state = BT_CONNECTED; } else l2cap_do_start(sk); } @@ -1893,8 +1874,8 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms if (pi->mode == L2CAP_MODE_STREAMING) { l2cap_streaming_send(sk); } else { - if (pi->conn_state & L2CAP_CONN_REMOTE_BUSY && - pi->conn_state && L2CAP_CONN_WAIT_F) { + if ((pi->conn_state & L2CAP_CONN_REMOTE_BUSY) && + (pi->conn_state & L2CAP_CONN_WAIT_F)) { err = len; break; } diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index ff8aaa736650..6b83776534fb 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1164,7 +1164,8 @@ static int rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci) * initiator rfcomm_process_rx already calls * rfcomm_session_put() */ if (s->sock->sk->sk_state != BT_CLOSED) - rfcomm_session_put(s); + if (list_empty(&s->dlcs)) + rfcomm_session_put(s); break; } } diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 2575c2db6404..d7b9af4703d0 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -727,7 +727,9 @@ static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp) break; } + tty_unlock(); schedule(); + tty_lock(); } set_current_state(TASK_RUNNING); remove_wait_queue(&dev->wait, &wait); diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig index 9190ae462cb4..6dee7bf648a9 100644 --- a/net/bridge/Kconfig +++ b/net/bridge/Kconfig @@ -6,6 +6,7 @@ config BRIDGE tristate "802.1d Ethernet Bridging" select LLC select STP + depends on IPV6 || IPV6=n ---help--- If you say Y here, then your Linux box will be able to act as an Ethernet bridge, which means that the different Ethernet segments it diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 2872393b2939..88485cc74dc3 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -328,12 +328,12 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, fdb = kmem_cache_alloc(br_fdb_cache, GFP_ATOMIC); if (fdb) { memcpy(fdb->addr.addr, addr, ETH_ALEN); - hlist_add_head_rcu(&fdb->hlist, head); - fdb->dst = source; fdb->is_local = is_local; fdb->is_static = is_local; fdb->ageing_timer = jiffies; + + hlist_add_head_rcu(&fdb->hlist, head); } return fdb; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 6f6d8e1b776f..88e4aa9cb1f9 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -80,7 +80,7 @@ int br_handle_frame_finish(struct sk_buff *skb) if (is_multicast_ether_addr(dest)) { mdst = br_mdb_get(br, skb); if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) { - if ((mdst && !hlist_unhashed(&mdst->mglist)) || + if ((mdst && mdst->mglist) || br_multicast_is_router(br)) skb2 = skb; br_multicast_forward(mdst, skb, skb2); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index f701a21acb34..030a002ff8ee 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -37,10 +37,9 @@ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static inline int ipv6_is_local_multicast(const struct in6_addr *addr) +static inline int ipv6_is_transient_multicast(const struct in6_addr *addr) { - if (ipv6_addr_is_multicast(addr) && - IPV6_ADDR_MC_SCOPE(addr) <= IPV6_ADDR_SCOPE_LINKLOCAL) + if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr)) return 1; return 0; } @@ -232,8 +231,7 @@ static void br_multicast_group_expired(unsigned long data) if (!netif_running(br->dev) || timer_pending(&mp->timer)) goto out; - if (!hlist_unhashed(&mp->mglist)) - hlist_del_init(&mp->mglist); + mp->mglist = false; if (mp->ports) goto out; @@ -276,7 +274,7 @@ static void br_multicast_del_pg(struct net_bridge *br, del_timer(&p->query_timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - if (!mp->ports && hlist_unhashed(&mp->mglist) && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); @@ -436,7 +434,6 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, eth = eth_hdr(skb); memcpy(eth->h_source, br->dev->dev_addr, 6); - ipv6_eth_mc_map(group, eth->h_dest); eth->h_proto = htons(ETH_P_IPV6); skb_put(skb, sizeof(*eth)); @@ -448,8 +445,10 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, ip6h->payload_len = htons(8 + sizeof(*mldq)); ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; - ipv6_addr_set(&ip6h->saddr, 0, 0, 0, 0); + ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, + &ip6h->saddr); ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1)); + ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); hopopt = (u8 *)(ip6h + 1); hopopt[0] = IPPROTO_ICMPV6; /* next hdr */ @@ -528,7 +527,7 @@ static void br_multicast_group_query_expired(unsigned long data) struct net_bridge *br = mp->br; spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || hlist_unhashed(&mp->mglist) || + if (!netif_running(br->dev) || !mp->mglist || mp->queries_sent >= br->multicast_last_member_count) goto out; @@ -719,7 +718,7 @@ static int br_multicast_add_group(struct net_bridge *br, goto err; if (!port) { - hlist_add_head(&mp->mglist, &br->mglist); + mp->mglist = true; mod_timer(&mp->timer, now + br->multicast_membership_interval); goto out; } @@ -781,11 +780,11 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, { struct br_ip br_group; - if (ipv6_is_local_multicast(group)) + if (!ipv6_is_transient_multicast(group)) return 0; ipv6_addr_copy(&br_group.u.ip6, group); - br_group.proto = htons(ETH_P_IP); + br_group.proto = htons(ETH_P_IPV6); return br_multicast_add_group(br, port, &br_group); } @@ -1014,18 +1013,19 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, nsrcs = skb_header_pointer(skb, len + offsetof(struct mld2_grec, - grec_mca), + grec_nsrcs), sizeof(_nsrcs), &_nsrcs); if (!nsrcs) return -EINVAL; if (!pskb_may_pull(skb, len + sizeof(*grec) + - sizeof(struct in6_addr) * (*nsrcs))) + sizeof(struct in6_addr) * ntohs(*nsrcs))) return -EINVAL; grec = (struct mld2_grec *)(skb->data + len); - len += sizeof(*grec) + sizeof(struct in6_addr) * (*nsrcs); + len += sizeof(*grec) + + sizeof(struct in6_addr) * ntohs(*nsrcs); /* We treat these as MLDv1 reports for now. */ switch (grec->grec_type) { @@ -1165,7 +1165,7 @@ static int br_ip4_multicast_query(struct net_bridge *br, max_delay *= br->multicast_last_member_count; - if (!hlist_unhashed(&mp->mglist) && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) @@ -1177,7 +1177,7 @@ static int br_ip4_multicast_query(struct net_bridge *br, if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0) - mod_timer(&mp->timer, now + max_delay); + mod_timer(&p->timer, now + max_delay); } out: @@ -1236,7 +1236,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, goto out; max_delay *= br->multicast_last_member_count; - if (!hlist_unhashed(&mp->mglist) && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) @@ -1248,7 +1248,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0) - mod_timer(&mp->timer, now + max_delay); + mod_timer(&p->timer, now + max_delay); } out: @@ -1283,7 +1283,7 @@ static void br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval; if (!port) { - if (!hlist_unhashed(&mp->mglist) && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { @@ -1341,7 +1341,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, { struct br_ip br_group; - if (ipv6_is_local_multicast(group)) + if (!ipv6_is_transient_multicast(group)) return; ipv6_addr_copy(&br_group.u.ip6, group); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 84aac7734bfc..4e1b620b6be6 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -84,13 +84,13 @@ struct net_bridge_port_group { struct net_bridge_mdb_entry { struct hlist_node hlist[2]; - struct hlist_node mglist; struct net_bridge *br; struct net_bridge_port_group __rcu *ports; struct rcu_head rcu; struct timer_list timer; struct timer_list query_timer; struct br_ip addr; + bool mglist; u32 queries_sent; }; @@ -238,7 +238,6 @@ struct net_bridge spinlock_t multicast_lock; struct net_bridge_mdb_htable __rcu *mdb; struct hlist_head router_list; - struct hlist_head mglist; struct timer_list multicast_router_timer; struct timer_list multicast_querier_timer; diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index fa9dab372b68..6008d6dc18a0 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -394,9 +394,7 @@ static void ipcaif_net_setup(struct net_device *dev) priv->conn_req.sockaddr.u.dgm.connection_id = -1; priv->flowenabled = false; - ASSERT_RTNL(); init_waitqueue_head(&priv->netmgmt_wq); - list_add(&priv->list_field, &chnl_net_list); } @@ -453,6 +451,8 @@ static int ipcaif_newlink(struct net *src_net, struct net_device *dev, ret = register_netdevice(dev); if (ret) pr_warn("device rtml registration failed\n"); + else + list_add(&caifdev->list_field, &chnl_net_list); return ret; } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index dff633d62e5b..05f357828a2f 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -252,8 +252,12 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) { struct kvec iov = {buf, len}; struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; + int r; - return kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags); + r = kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags); + if (r == -EAGAIN) + r = 0; + return r; } /* @@ -264,13 +268,17 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov, size_t kvlen, size_t len, int more) { struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; + int r; if (more) msg.msg_flags |= MSG_MORE; else msg.msg_flags |= MSG_EOR; /* superfluous, but what the hell */ - return kernel_sendmsg(sock, &msg, iov, kvlen, len); + r = kernel_sendmsg(sock, &msg, iov, kvlen, len); + if (r == -EAGAIN) + r = 0; + return r; } @@ -328,7 +336,6 @@ static void reset_connection(struct ceph_connection *con) ceph_msg_put(con->out_msg); con->out_msg = NULL; } - con->out_keepalive_pending = false; con->in_seq = 0; con->in_seq_acked = 0; } @@ -847,6 +854,8 @@ static int write_partial_msg_pages(struct ceph_connection *con) (msg->pages || msg->pagelist || msg->bio || in_trail)) kunmap(page); + if (ret == -EAGAIN) + ret = 0; if (ret <= 0) goto out; @@ -1238,8 +1247,6 @@ static int process_connect(struct ceph_connection *con) con->auth_retry); if (con->auth_retry == 2) { con->error_msg = "connect authorization failure"; - reset_connection(con); - set_bit(CLOSED, &con->state); return -1; } con->auth_retry = 1; @@ -1705,14 +1712,6 @@ more: /* open the socket first? */ if (con->sock == NULL) { - /* - * if we were STANDBY and are reconnecting _this_ - * connection, bump connect_seq now. Always bump - * global_seq. - */ - if (test_and_clear_bit(STANDBY, &con->state)) - con->connect_seq++; - prepare_write_banner(msgr, con); prepare_write_connect(msgr, con, 1); prepare_read_banner(con); @@ -1737,16 +1736,12 @@ more_kvec: if (con->out_skip) { ret = write_partial_skip(con); if (ret <= 0) - goto done; - if (ret < 0) { - dout("try_write write_partial_skip err %d\n", ret); - goto done; - } + goto out; } if (con->out_kvec_left) { ret = write_partial_kvec(con); if (ret <= 0) - goto done; + goto out; } /* msg pages? */ @@ -1761,11 +1756,11 @@ more_kvec: if (ret == 1) goto more_kvec; /* we need to send the footer, too! */ if (ret == 0) - goto done; + goto out; if (ret < 0) { dout("try_write write_partial_msg_pages err %d\n", ret); - goto done; + goto out; } } @@ -1789,10 +1784,9 @@ do_next: /* Nothing to do! */ clear_bit(WRITE_PENDING, &con->state); dout("try_write nothing else to write.\n"); -done: ret = 0; out: - dout("try_write done on %p\n", con); + dout("try_write done on %p ret %d\n", con, ret); return ret; } @@ -1821,19 +1815,17 @@ more: dout("try_read connecting\n"); ret = read_partial_banner(con); if (ret <= 0) - goto done; - if (process_banner(con) < 0) { - ret = -1; goto out; - } + ret = process_banner(con); + if (ret < 0) + goto out; } ret = read_partial_connect(con); if (ret <= 0) - goto done; - if (process_connect(con) < 0) { - ret = -1; goto out; - } + ret = process_connect(con); + if (ret < 0) + goto out; goto more; } @@ -1848,7 +1840,7 @@ more: dout("skipping %d / %d bytes\n", skip, -con->in_base_pos); ret = ceph_tcp_recvmsg(con->sock, buf, skip); if (ret <= 0) - goto done; + goto out; con->in_base_pos += ret; if (con->in_base_pos) goto more; @@ -1859,7 +1851,7 @@ more: */ ret = ceph_tcp_recvmsg(con->sock, &con->in_tag, 1); if (ret <= 0) - goto done; + goto out; dout("try_read got tag %d\n", (int)con->in_tag); switch (con->in_tag) { case CEPH_MSGR_TAG_MSG: @@ -1870,7 +1862,7 @@ more: break; case CEPH_MSGR_TAG_CLOSE: set_bit(CLOSED, &con->state); /* fixme */ - goto done; + goto out; default: goto bad_tag; } @@ -1882,13 +1874,12 @@ more: case -EBADMSG: con->error_msg = "bad crc"; ret = -EIO; - goto out; + break; case -EIO: con->error_msg = "io error"; - goto out; - default: - goto done; + break; } + goto out; } if (con->in_tag == CEPH_MSGR_TAG_READY) goto more; @@ -1898,15 +1889,13 @@ more: if (con->in_tag == CEPH_MSGR_TAG_ACK) { ret = read_partial_ack(con); if (ret <= 0) - goto done; + goto out; process_ack(con); goto more; } -done: - ret = 0; out: - dout("try_read done on %p\n", con); + dout("try_read done on %p ret %d\n", con, ret); return ret; bad_tag: @@ -1951,7 +1940,24 @@ static void con_work(struct work_struct *work) work.work); mutex_lock(&con->mutex); + if (test_and_clear_bit(BACKOFF, &con->state)) { + dout("con_work %p backing off\n", con); + if (queue_delayed_work(ceph_msgr_wq, &con->work, + round_jiffies_relative(con->delay))) { + dout("con_work %p backoff %lu\n", con, con->delay); + mutex_unlock(&con->mutex); + return; + } else { + con->ops->put(con); + dout("con_work %p FAILED to back off %lu\n", con, + con->delay); + } + } + if (test_bit(STANDBY, &con->state)) { + dout("con_work %p STANDBY\n", con); + goto done; + } if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */ dout("con_work CLOSED\n"); con_close_socket(con); @@ -2008,10 +2014,12 @@ static void ceph_fault(struct ceph_connection *con) /* Requeue anything that hasn't been acked */ list_splice_init(&con->out_sent, &con->out_queue); - /* If there are no messages in the queue, place the connection - * in a STANDBY state (i.e., don't try to reconnect just yet). */ - if (list_empty(&con->out_queue) && !con->out_keepalive_pending) { - dout("fault setting STANDBY\n"); + /* If there are no messages queued or keepalive pending, place + * the connection in a STANDBY state */ + if (list_empty(&con->out_queue) && + !test_bit(KEEPALIVE_PENDING, &con->state)) { + dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con); + clear_bit(WRITE_PENDING, &con->state); set_bit(STANDBY, &con->state); } else { /* retry after a delay. */ @@ -2019,11 +2027,24 @@ static void ceph_fault(struct ceph_connection *con) con->delay = BASE_DELAY_INTERVAL; else if (con->delay < MAX_DELAY_INTERVAL) con->delay *= 2; - dout("fault queueing %p delay %lu\n", con, con->delay); con->ops->get(con); if (queue_delayed_work(ceph_msgr_wq, &con->work, - round_jiffies_relative(con->delay)) == 0) + round_jiffies_relative(con->delay))) { + dout("fault queued %p delay %lu\n", con, con->delay); + } else { con->ops->put(con); + dout("fault failed to queue %p delay %lu, backoff\n", + con, con->delay); + /* + * In many cases we see a socket state change + * while con_work is running and end up + * queuing (non-delayed) work, such that we + * can't backoff with a delay. Set a flag so + * that when con_work restarts we schedule the + * delay then. + */ + set_bit(BACKOFF, &con->state); + } } out_unlock: @@ -2094,6 +2115,19 @@ void ceph_messenger_destroy(struct ceph_messenger *msgr) } EXPORT_SYMBOL(ceph_messenger_destroy); +static void clear_standby(struct ceph_connection *con) +{ + /* come back from STANDBY? */ + if (test_and_clear_bit(STANDBY, &con->state)) { + mutex_lock(&con->mutex); + dout("clear_standby %p and ++connect_seq\n", con); + con->connect_seq++; + WARN_ON(test_bit(WRITE_PENDING, &con->state)); + WARN_ON(test_bit(KEEPALIVE_PENDING, &con->state)); + mutex_unlock(&con->mutex); + } +} + /* * Queue up an outgoing message on the given connection. */ @@ -2126,6 +2160,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) /* if there wasn't anything waiting to send before, queue * new work */ + clear_standby(con); if (test_and_set_bit(WRITE_PENDING, &con->state) == 0) queue_con(con); } @@ -2191,6 +2226,8 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg) */ void ceph_con_keepalive(struct ceph_connection *con) { + dout("con_keepalive %p\n", con); + clear_standby(con); if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 && test_and_set_bit(WRITE_PENDING, &con->state) == 0) queue_con(con); diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index 1a040e64c69f..cd9c21df87d1 100644 --- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -16,22 +16,30 @@ struct page **ceph_get_direct_page_vector(const char __user *data, int num_pages, bool write_page) { struct page **pages; - int rc; + int got = 0; + int rc = 0; pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS); if (!pages) return ERR_PTR(-ENOMEM); down_read(¤t->mm->mmap_sem); - rc = get_user_pages(current, current->mm, (unsigned long)data, - num_pages, write_page, 0, pages, NULL); + while (got < num_pages) { + rc = get_user_pages(current, current->mm, + (unsigned long)data + ((unsigned long)got * PAGE_SIZE), + num_pages - got, write_page, 0, pages + got, NULL); + if (rc < 0) + break; + BUG_ON(rc == 0); + got += rc; + } up_read(¤t->mm->mmap_sem); - if (rc < num_pages) + if (rc < 0) goto fail; return pages; fail: - ceph_put_page_vector(pages, rc > 0 ? rc : 0, false); + ceph_put_page_vector(pages, got, false); return ERR_PTR(rc); } EXPORT_SYMBOL(ceph_get_direct_page_vector); diff --git a/net/core/dev.c b/net/core/dev.c index 7c6a46f80372..6561021d22d1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -749,7 +749,8 @@ EXPORT_SYMBOL(dev_get_by_index); * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device - * is not found or a pointer to the device. The caller must hold RCU + * is not found or a pointer to the device. + * The caller must hold RCU or RTNL. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * @@ -1113,13 +1114,21 @@ EXPORT_SYMBOL(netdev_bonding_change); void dev_load(struct net *net, const char *name) { struct net_device *dev; + int no_module; rcu_read_lock(); dev = dev_get_by_name_rcu(net, name); rcu_read_unlock(); - if (!dev && capable(CAP_NET_ADMIN)) - request_module("%s", name); + no_module = !dev; + if (no_module && capable(CAP_NET_ADMIN)) + no_module = request_module("netdev-%s", name); + if (no_module && capable(CAP_SYS_MODULE)) { + if (!request_module("%s", name)) + pr_err("Loading kernel module for a network device " +"with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s " +"instead\n", name); + } } EXPORT_SYMBOL(dev_load); @@ -1279,10 +1288,13 @@ static int __dev_close_many(struct list_head *head) static int __dev_close(struct net_device *dev) { + int retval; LIST_HEAD(single); list_add(&dev->unreg_list, &single); - return __dev_close_many(&single); + retval = __dev_close_many(&single); + list_del(&single); + return retval; } int dev_close_many(struct list_head *head) @@ -1324,7 +1336,7 @@ int dev_close(struct net_device *dev) list_add(&dev->unreg_list, &single); dev_close_many(&single); - + list_del(&single); return 0; } EXPORT_SYMBOL(dev_close); @@ -2562,7 +2574,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, map = rcu_dereference(rxqueue->rps_map); if (map) { - if (map->len == 1) { + if (map->len == 1 && + !rcu_dereference_raw(rxqueue->rps_flow_table)) { tcpu = map->cpus[0]; if (cpu_online(tcpu)) cpu = tcpu; @@ -3423,6 +3436,8 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) __skb_pull(skb, skb_headlen(skb)); skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb)); skb->vlan_tci = 0; + skb->dev = napi->dev; + skb->skb_iif = 0; napi->skb = skb; } @@ -5059,6 +5074,7 @@ static void rollback_registered(struct net_device *dev) list_add(&dev->unreg_list, &single); rollback_registered_many(&single); + list_del(&single); } unsigned long netdev_fix_features(unsigned long features, const char *name) @@ -5656,30 +5672,35 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); + dev->gso_max_size = GSO_MAX_SIZE; + + INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); + dev->ethtool_ntuple_list.count = 0; + INIT_LIST_HEAD(&dev->napi_list); + INIT_LIST_HEAD(&dev->unreg_list); + INIT_LIST_HEAD(&dev->link_watch_list); + dev->priv_flags = IFF_XMIT_DST_RELEASE; + setup(dev); + dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; if (netif_alloc_netdev_queues(dev)) - goto free_pcpu; + goto free_all; #ifdef CONFIG_RPS dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) - goto free_pcpu; + goto free_all; #endif - dev->gso_max_size = GSO_MAX_SIZE; - - INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); - dev->ethtool_ntuple_list.count = 0; - INIT_LIST_HEAD(&dev->napi_list); - INIT_LIST_HEAD(&dev->unreg_list); - INIT_LIST_HEAD(&dev->link_watch_list); - dev->priv_flags = IFF_XMIT_DST_RELEASE; - setup(dev); strcpy(dev->name, name); return dev; +free_all: + free_netdev(dev); + return NULL; + free_pcpu: free_percpu(dev->pcpu_refcnt); kfree(dev->_tx); @@ -6207,6 +6228,7 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) } } unregister_netdevice_many(&dev_kill_list); + list_del(&dev_kill_list); rtnl_unlock(); } diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 508f9c18992f..133fd22ea287 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -144,7 +144,7 @@ void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, list_for_each_entry(ha, &from_list->list, list) { type = addr_type ? addr_type : ha->type; - __hw_addr_del(to_list, ha->addr, addr_len, addr_type); + __hw_addr_del(to_list, ha->addr, addr_len, type); } } EXPORT_SYMBOL(__hw_addr_del_multiple); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 17741782a345..ff2302910b5e 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -817,7 +817,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (regs.len > reglen) regs.len = reglen; - regbuf = vmalloc(reglen); + regbuf = vzalloc(reglen); if (!regbuf) return -ENOMEM; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a9e7fc4c461f..b5bada92f637 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3321,7 +3321,7 @@ static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) pkt_dev->started_at); ktime_t idle = ns_to_ktime(pkt_dev->idle_acc); - p += sprintf(p, "OK: %llu(c%llu+d%llu) nsec, %llu (%dbyte,%dfrags)\n", + p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n", (unsigned long long)ktime_to_us(elapsed), (unsigned long long)ktime_to_us(ktime_sub(elapsed, idle)), (unsigned long long)ktime_to_us(idle), diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 750db57f3bb3..2d65c6bb24c1 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1121,8 +1121,7 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) return -EOPNOTSUPP; if (af_ops->validate_link_af) { - err = af_ops->validate_link_af(dev, - tb[IFLA_AF_SPEC]); + err = af_ops->validate_link_af(dev, af); if (err < 0) return err; } @@ -1672,6 +1671,9 @@ replay: snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind); dest_net = rtnl_link_get_net(net, tb); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + dev = rtnl_create_link(net, dest_net, ifname, ops, tb); if (IS_ERR(dev)) diff --git a/net/core/scm.c b/net/core/scm.c index bbe454450801..4c1ef026d695 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -95,7 +95,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) int fd = fdp[i]; struct file *file; - if (fd < 0 || !(file = fget(fd))) + if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; *fpp++ = file; fpl->count++; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d31bb36ae0dc..d883dcc78b6b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -210,6 +210,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); + kmemcheck_annotate_variable(shinfo->destructor_arg); if (fclone) { struct sk_buff *child = skb + 1; @@ -2744,8 +2745,12 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) merge: if (offset > headlen) { - skbinfo->frags[0].page_offset += offset - headlen; - skbinfo->frags[0].size -= offset - headlen; + unsigned int eat = offset - headlen; + + skbinfo->frags[0].page_offset += eat; + skbinfo->frags[0].size -= eat; + skb->data_len -= eat; + skb->len -= eat; offset = headlen; } diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index d900ab99814a..c44348adba3b 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -583,7 +583,7 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlattr **tb, u8 up, idtype; int ret = -EINVAL; - if (!tb[DCB_ATTR_APP] || !netdev->dcbnl_ops->getapp) + if (!tb[DCB_ATTR_APP]) goto out; ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP], @@ -604,7 +604,16 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlattr **tb, goto out; id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); - up = netdev->dcbnl_ops->getapp(netdev, idtype, id); + + if (netdev->dcbnl_ops->getapp) { + up = netdev->dcbnl_ops->getapp(netdev, idtype, id); + } else { + struct dcb_app app = { + .selector = idtype, + .protocol = id, + }; + up = dcb_getapp(netdev, &app); + } /* send this back */ dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); @@ -617,6 +626,9 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlattr **tb, dcb->cmd = DCB_CMD_GAPP; app_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_APP); + if (!app_nest) + goto out_cancel; + ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_IDTYPE, idtype); if (ret) goto out_cancel; @@ -1181,7 +1193,7 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb, goto err; } - if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setets) { + if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) { struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]); err = ops->ieee_setpfc(netdev, pfc); if (err) @@ -1604,6 +1616,10 @@ EXPORT_SYMBOL(dcb_getapp); u8 dcb_setapp(struct net_device *dev, struct dcb_app *new) { struct dcb_app_type *itr; + struct dcb_app_type event; + + memcpy(&event.name, dev->name, sizeof(event.name)); + memcpy(&event.app, new, sizeof(event.app)); spin_lock(&dcb_lock); /* Search for existing match and replace */ @@ -1635,7 +1651,7 @@ u8 dcb_setapp(struct net_device *dev, struct dcb_app *new) } out: spin_unlock(&dcb_lock); - call_dcbevent_notifiers(DCB_APP_EVENT, new); + call_dcbevent_notifiers(DCB_APP_EVENT, &event); return 0; } EXPORT_SYMBOL(dcb_setapp); diff --git a/net/dccp/input.c b/net/dccp/input.c index 8cde009e8b85..4222e7a654b0 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -614,6 +614,9 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* Caller (dccp_v4_do_rcv) will send Reset */ dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; return 1; + } else if (sk->sk_state == DCCP_CLOSED) { + dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; + return 1; } if (sk->sk_state != DCCP_REQUESTING && sk->sk_state != DCCP_RESPOND) { @@ -668,10 +671,6 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } switch (sk->sk_state) { - case DCCP_CLOSED: - dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; - return 1; - case DCCP_REQUESTING: queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len); if (queued >= 0) diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 739435a6af39..cfa7a5e1c5c9 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -67,8 +67,9 @@ dns_resolver_instantiate(struct key *key, const void *_data, size_t datalen) size_t result_len = 0; const char *data = _data, *end, *opt; - kenter("%%%d,%s,'%s',%zu", - key->serial, key->description, data, datalen); + kenter("%%%d,%s,'%*.*s',%zu", + key->serial, key->description, + (int)datalen, (int)datalen, data, datalen); if (datalen <= 1 || !data || data[datalen - 1] != '\0') return -EINVAL; @@ -217,6 +218,19 @@ static void dns_resolver_describe(const struct key *key, struct seq_file *m) seq_printf(m, ": %u", key->datalen); } +/* + * read the DNS data + * - the key's semaphore is read-locked + */ +static long dns_resolver_read(const struct key *key, + char __user *buffer, size_t buflen) +{ + if (key->type_data.x[0]) + return key->type_data.x[0]; + + return user_read(key, buffer, buflen); +} + struct key_type key_type_dns_resolver = { .name = "dns_resolver", .instantiate = dns_resolver_instantiate, @@ -224,7 +238,7 @@ struct key_type key_type_dns_resolver = { .revoke = user_revoke, .destroy = user_destroy, .describe = dns_resolver_describe, - .read = user_read, + .read = dns_resolver_read, }; static int __init init_dns_resolver(void) diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index 15dcc1a586b4..0c2826337919 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -265,13 +265,13 @@ static void ec_tx_done(struct sk_buff *skb, int result) static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { - struct sock *sk = sock->sk; struct sockaddr_ec *saddr=(struct sockaddr_ec *)msg->msg_name; struct net_device *dev; struct ec_addr addr; int err; unsigned char port, cb; #if defined(CONFIG_ECONET_AUNUDP) || defined(CONFIG_ECONET_NATIVE) + struct sock *sk = sock->sk; struct sk_buff *skb; struct ec_cb *eb; #endif @@ -488,10 +488,10 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, error_free_buf: vfree(userbuf); +error: #else err = -EPROTOTYPE; #endif - error: mutex_unlock(&econet_mutex); return err; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f2b61107df6c..45b89d7bda5a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -880,6 +880,19 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) } EXPORT_SYMBOL(inet_ioctl); +#ifdef CONFIG_COMPAT +int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + struct sock *sk = sock->sk; + int err = -ENOIOCTLCMD; + + if (sk->sk_prot->compat_ioctl) + err = sk->sk_prot->compat_ioctl(sk, cmd, arg); + + return err; +} +#endif + const struct proto_ops inet_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, @@ -903,6 +916,7 @@ const struct proto_ops inet_stream_ops = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, + .compat_ioctl = inet_compat_ioctl, #endif }; EXPORT_SYMBOL(inet_stream_ops); @@ -929,6 +943,7 @@ const struct proto_ops inet_dgram_ops = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, + .compat_ioctl = inet_compat_ioctl, #endif }; EXPORT_SYMBOL(inet_dgram_ops); @@ -959,6 +974,7 @@ static const struct proto_ops inet_sockraw_ops = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, + .compat_ioctl = inet_compat_ioctl, #endif }; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 04c8b69fd426..7927589813b5 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1017,14 +1017,13 @@ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) IPV4_DEVCONF_ALL(net, PROXY_ARP) = on; return 0; } - if (__in_dev_get_rcu(dev)) { - IN_DEV_CONF_SET(__in_dev_get_rcu(dev), PROXY_ARP, on); + if (__in_dev_get_rtnl(dev)) { + IN_DEV_CONF_SET(__in_dev_get_rtnl(dev), PROXY_ARP, on); return 0; } return -ENXIO; } -/* must be called with rcu_read_lock() */ static int arp_req_set_public(struct net *net, struct arpreq *r, struct net_device *dev) { @@ -1233,10 +1232,10 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!(r.arp_flags & ATF_NETMASK)) ((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr = htonl(0xFFFFFFFFUL); - rcu_read_lock(); + rtnl_lock(); if (r.arp_dev[0]) { err = -ENODEV; - dev = dev_get_by_name_rcu(net, r.arp_dev); + dev = __dev_get_by_name(net, r.arp_dev); if (dev == NULL) goto out; @@ -1263,7 +1262,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) break; } out: - rcu_read_unlock(); + rtnl_unlock(); if (cmd == SIOCGARP && !err && copy_to_user(arg, &r, sizeof(r))) err = -EFAULT; return err; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 748cb5b337bd..036652c8166d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -670,7 +670,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) ifap = &ifa->ifa_next) { if (!strcmp(ifr.ifr_name, ifa->ifa_label) && sin_orig.sin_addr.s_addr == - ifa->ifa_address) { + ifa->ifa_local) { break; /* found */ } } @@ -1030,6 +1030,21 @@ static inline bool inetdev_valid_mtu(unsigned mtu) return mtu >= 68; } +static void inetdev_send_gratuitous_arp(struct net_device *dev, + struct in_device *in_dev) + +{ + struct in_ifaddr *ifa = in_dev->ifa_list; + + if (!ifa) + return; + + arp_send(ARPOP_REQUEST, ETH_P_ARP, + ifa->ifa_local, dev, + ifa->ifa_local, NULL, + dev->dev_addr, NULL); +} + /* Called only under RTNL semaphore */ static int inetdev_event(struct notifier_block *this, unsigned long event, @@ -1082,18 +1097,13 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, } ip_mc_up(in_dev); /* fall through */ - case NETDEV_NOTIFY_PEERS: case NETDEV_CHANGEADDR: + if (!IN_DEV_ARP_NOTIFY(in_dev)) + break; + /* fall through */ + case NETDEV_NOTIFY_PEERS: /* Send gratuitous ARP to notify of link change */ - if (IN_DEV_ARP_NOTIFY(in_dev)) { - struct in_ifaddr *ifa = in_dev->ifa_list; - - if (ifa) - arp_send(ARPOP_REQUEST, ETH_P_ARP, - ifa->ifa_address, dev, - ifa->ifa_address, NULL, - dev->dev_addr, NULL); - } + inetdev_send_gratuitous_arp(dev, in_dev); break; case NETDEV_DOWN: ip_mc_down(in_dev); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index c5af909cf701..3c8dfa16614d 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -505,7 +505,9 @@ restart: } rcu_read_unlock(); + local_bh_disable(); inet_twsk_deschedule(tw, twdr); + local_bh_enable(); inet_twsk_put(tw); goto restart_rcu; } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d9bc85751c74..a96e65674ac3 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -475,7 +475,7 @@ static int cleanup_once(unsigned long ttl) struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) { struct inet_peer __rcu **stack[PEER_MAXDEPTH], ***stackptr; - struct inet_peer_base *base = family_to_base(AF_INET); + struct inet_peer_base *base = family_to_base(daddr->family); struct inet_peer *p; /* Look up for the address quickly, lockless. diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index eb68a0e34e49..d1d0e2c256fc 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -775,6 +775,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev .fl4_dst = dst, .fl4_src = tiph->saddr, .fl4_tos = RT_TOS(tos), + .proto = IPPROTO_GRE, .fl_gre_key = tunnel->parms.o_key }; if (ip_route_output_key(dev_net(dev), &rt, &fl)) { @@ -1764,4 +1765,4 @@ module_exit(ipgre_fini); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); -MODULE_ALIAS("gre0"); +MODULE_ALIAS_NETDEV("gre0"); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 988f52fba54a..a5f58e7cbb26 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -913,4 +913,4 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); MODULE_LICENSE("GPL"); -MODULE_ALIAS("tunl0"); +MODULE_ALIAS_NETDEV("tunl0"); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3f3a9afd73e0..8b65a12654e7 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -60,6 +60,7 @@ #include <linux/notifier.h> #include <linux/if_arp.h> #include <linux/netfilter_ipv4.h> +#include <linux/compat.h> #include <net/ipip.h> #include <net/checksum.h> #include <net/netlink.h> @@ -1434,6 +1435,81 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) } } +#ifdef CONFIG_COMPAT +struct compat_sioc_sg_req { + struct in_addr src; + struct in_addr grp; + compat_ulong_t pktcnt; + compat_ulong_t bytecnt; + compat_ulong_t wrong_if; +}; + +struct compat_sioc_vif_req { + vifi_t vifi; /* Which iface */ + compat_ulong_t icount; + compat_ulong_t ocount; + compat_ulong_t ibytes; + compat_ulong_t obytes; +}; + +int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) +{ + struct compat_sioc_sg_req sr; + struct compat_sioc_vif_req vr; + struct vif_device *vif; + struct mfc_cache *c; + struct net *net = sock_net(sk); + struct mr_table *mrt; + + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); + if (mrt == NULL) + return -ENOENT; + + switch (cmd) { + case SIOCGETVIFCNT: + if (copy_from_user(&vr, arg, sizeof(vr))) + return -EFAULT; + if (vr.vifi >= mrt->maxvif) + return -EINVAL; + read_lock(&mrt_lock); + vif = &mrt->vif_table[vr.vifi]; + if (VIF_EXISTS(mrt, vr.vifi)) { + vr.icount = vif->pkt_in; + vr.ocount = vif->pkt_out; + vr.ibytes = vif->bytes_in; + vr.obytes = vif->bytes_out; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &vr, sizeof(vr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + case SIOCGETSGCNT: + if (copy_from_user(&sr, arg, sizeof(sr))) + return -EFAULT; + + rcu_read_lock(); + c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); + if (c) { + sr.pktcnt = c->mfc_un.res.pkt; + sr.bytecnt = c->mfc_un.res.bytes; + sr.wrong_if = c->mfc_un.res.wrong_if; + rcu_read_unlock(); + + if (copy_to_user(arg, &sr, sizeof(sr))) + return -EFAULT; + return 0; + } + rcu_read_unlock(); + return -EADDRNOTAVAIL; + default: + return -ENOIOCTLCMD; + } +} +#endif + static int ipmr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index b8ddcc480ed9..a5e52a9f0a12 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -60,12 +60,12 @@ static int checkentry(const struct xt_tgchk_param *par) if (mangle->flags & ~ARPT_MANGLE_MASK || !(mangle->flags & ARPT_MANGLE_MASK)) - return false; + return -EINVAL; if (mangle->target != NF_DROP && mangle->target != NF_ACCEPT && mangle->target != XT_CONTINUE) - return false; - return true; + return -EINVAL; + return 0; } static struct xt_target arpt_mangle_reg __read_mostly = { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a3d5ab786e81..6390ba299b3d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -76,6 +76,7 @@ #include <linux/seq_file.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> +#include <linux/compat.h> static struct raw_hashinfo raw_v4_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock), @@ -838,6 +839,23 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg) } } +#ifdef CONFIG_COMPAT +static int compat_raw_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case SIOCOUTQ: + case SIOCINQ: + return -ENOIOCTLCMD; + default: +#ifdef CONFIG_IP_MROUTE + return ipmr_compat_ioctl(sk, cmd, compat_ptr(arg)); +#else + return -ENOIOCTLCMD; +#endif + } +} +#endif + struct proto raw_prot = { .name = "RAW", .owner = THIS_MODULE, @@ -860,6 +878,7 @@ struct proto raw_prot = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_raw_setsockopt, .compat_getsockopt = compat_raw_getsockopt, + .compat_ioctl = compat_raw_ioctl, #endif }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 351dc4e85242..6ed6603c2f6d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2707,6 +2707,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo return NULL; } +static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst) +{ + return 0; +} + static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } @@ -2716,6 +2721,8 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, .check = ipv4_blackhole_dst_check, + .default_mtu = ipv4_blackhole_default_mtu, + .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2549b29b062d..65f6c0406245 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1222,7 +1222,7 @@ static int tcp_check_dsack(struct sock *sk, struct sk_buff *ack_skb, } /* D-SACK for already forgotten data... Do dumb counting. */ - if (dup_sack && + if (dup_sack && tp->undo_marker && tp->undo_retrans && !after(end_seq_0, prior_snd_una) && after(end_seq_0, tp->undo_marker)) tp->undo_retrans--; @@ -1299,7 +1299,8 @@ static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { - if (after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker)) + if (tp->undo_marker && tp->undo_retrans && + after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker)) tp->undo_retrans--; if (sacked & TCPCB_SACKED_ACKED) state->reord = min(fack_count, state->reord); @@ -4399,7 +4400,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (!skb_copy_datagram_iovec(skb, 0, tp->ucopy.iov, chunk)) { tp->ucopy.len -= chunk; tp->copied_seq += chunk; - eaten = (chunk == skb->len && !th->fin); + eaten = (chunk == skb->len); tcp_rcv_space_adjust(sk); } local_bh_disable(); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 856f68466d49..02f583b3744a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1994,7 +1994,6 @@ static void *listening_get_next(struct seq_file *seq, void *cur) } req = req->dl_next; } - st->offset = 0; if (++st->sbucket >= icsk->icsk_accept_queue.listen_opt->nr_table_entries) break; get_req: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 406f320336e6..dfa5beb0c1c8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2162,7 +2162,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (!tp->retrans_stamp) tp->retrans_stamp = TCP_SKB_CB(skb)->when; - tp->undo_retrans++; + tp->undo_retrans += tcp_skb_pcount(skb); /* snd_nxt is stored to detect loss of retransmitted segment, * see tcp_input.c tcp_sacktag_write_queue(). diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 24a1cf110d80..fd6782e3a038 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2661,14 +2661,12 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa; - LIST_HEAD(keep_list); - int state; + int state, i; ASSERT_RTNL(); - /* Flush routes if device is being removed or it is not loopback */ - if (how || !(dev->flags & IFF_LOOPBACK)) - rt6_ifdown(net, dev); + rt6_ifdown(net, dev); + neigh_ifdown(&nd_tbl, dev); idev = __in6_dev_get(dev); if (idev == NULL) @@ -2689,6 +2687,23 @@ static int addrconf_ifdown(struct net_device *dev, int how) } + /* Step 2: clear hash table */ + for (i = 0; i < IN6_ADDR_HSIZE; i++) { + struct hlist_head *h = &inet6_addr_lst[i]; + struct hlist_node *n; + + spin_lock_bh(&addrconf_hash_lock); + restart: + hlist_for_each_entry_rcu(ifa, n, h, addr_lst) { + if (ifa->idev == idev) { + hlist_del_init_rcu(&ifa->addr_lst); + addrconf_del_timer(ifa); + goto restart; + } + } + spin_unlock_bh(&addrconf_hash_lock); + } + write_lock_bh(&idev->lock); /* Step 2: clear flags for stateless addrconf */ @@ -2722,52 +2737,23 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct inet6_ifaddr, if_list); addrconf_del_timer(ifa); - /* If just doing link down, and address is permanent - and not link-local, then retain it. */ - if (!how && - (ifa->flags&IFA_F_PERMANENT) && - !(ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)) { - list_move_tail(&ifa->if_list, &keep_list); - - /* If not doing DAD on this address, just keep it. */ - if ((dev->flags&(IFF_NOARP|IFF_LOOPBACK)) || - idev->cnf.accept_dad <= 0 || - (ifa->flags & IFA_F_NODAD)) - continue; + list_del(&ifa->if_list); - /* If it was tentative already, no need to notify */ - if (ifa->flags & IFA_F_TENTATIVE) - continue; + write_unlock_bh(&idev->lock); - /* Flag it for later restoration when link comes up */ - ifa->flags |= IFA_F_TENTATIVE; - ifa->state = INET6_IFADDR_STATE_DAD; - } else { - list_del(&ifa->if_list); - - /* clear hash table */ - spin_lock_bh(&addrconf_hash_lock); - hlist_del_init_rcu(&ifa->addr_lst); - spin_unlock_bh(&addrconf_hash_lock); - - write_unlock_bh(&idev->lock); - spin_lock_bh(&ifa->state_lock); - state = ifa->state; - ifa->state = INET6_IFADDR_STATE_DEAD; - spin_unlock_bh(&ifa->state_lock); - - if (state != INET6_IFADDR_STATE_DEAD) { - __ipv6_ifa_notify(RTM_DELADDR, ifa); - atomic_notifier_call_chain(&inet6addr_chain, - NETDEV_DOWN, ifa); - } + spin_lock_bh(&ifa->state_lock); + state = ifa->state; + ifa->state = INET6_IFADDR_STATE_DEAD; + spin_unlock_bh(&ifa->state_lock); - in6_ifa_put(ifa); - write_lock_bh(&idev->lock); + if (state != INET6_IFADDR_STATE_DEAD) { + __ipv6_ifa_notify(RTM_DELADDR, ifa); + atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa); } - } + in6_ifa_put(ifa); - list_splice(&keep_list, &idev->addr_list); + write_lock_bh(&idev->lock); + } write_unlock_bh(&idev->lock); @@ -4156,8 +4142,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) addrconf_leave_solict(ifp->idev, &ifp->addr); dst_hold(&ifp->rt->dst); - if (ifp->state == INET6_IFADDR_STATE_DEAD && - ip6_del_rt(ifp->rt)) + if (ip6_del_rt(ifp->rt)) dst_free(&ifp->rt->dst); break; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 4f4483e697bd..e528a42a52be 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -57,6 +57,7 @@ MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_NETDEV("ip6tnl0"); #ifdef IP6_TNL_DEBUG #define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __func__) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 9fab274019c0..0e1d53bcf1e0 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -34,6 +34,7 @@ #include <linux/seq_file.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/compat.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> @@ -1804,6 +1805,80 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) } } +#ifdef CONFIG_COMPAT +struct compat_sioc_sg_req6 { + struct sockaddr_in6 src; + struct sockaddr_in6 grp; + compat_ulong_t pktcnt; + compat_ulong_t bytecnt; + compat_ulong_t wrong_if; +}; + +struct compat_sioc_mif_req6 { + mifi_t mifi; + compat_ulong_t icount; + compat_ulong_t ocount; + compat_ulong_t ibytes; + compat_ulong_t obytes; +}; + +int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) +{ + struct compat_sioc_sg_req6 sr; + struct compat_sioc_mif_req6 vr; + struct mif_device *vif; + struct mfc6_cache *c; + struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; + + switch (cmd) { + case SIOCGETMIFCNT_IN6: + if (copy_from_user(&vr, arg, sizeof(vr))) + return -EFAULT; + if (vr.mifi >= mrt->maxvif) + return -EINVAL; + read_lock(&mrt_lock); + vif = &mrt->vif6_table[vr.mifi]; + if (MIF_EXISTS(mrt, vr.mifi)) { + vr.icount = vif->pkt_in; + vr.ocount = vif->pkt_out; + vr.ibytes = vif->bytes_in; + vr.obytes = vif->bytes_out; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &vr, sizeof(vr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + case SIOCGETSGCNT_IN6: + if (copy_from_user(&sr, arg, sizeof(sr))) + return -EFAULT; + + read_lock(&mrt_lock); + c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); + if (c) { + sr.pktcnt = c->mfc_un.res.pkt; + sr.bytecnt = c->mfc_un.res.bytes; + sr.wrong_if = c->mfc_un.res.wrong_if; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &sr, sizeof(sr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + default: + return -ENOIOCTLCMD; + } +} +#endif static inline int ip6mr_forward2_finish(struct sk_buff *skb) { diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 09c88891a753..de338037a736 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -410,7 +410,7 @@ fallback: if (p != NULL) { sb_add(m, "%02x", *p++); for (i = 1; i < len; i++) - sb_add(m, ":%02x", p[i]); + sb_add(m, ":%02x", *p++); } sb_add(m, " "); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 86c39526ba5e..c5b0915d106b 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -31,6 +31,7 @@ #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/skbuff.h> +#include <linux/compat.h> #include <asm/uaccess.h> #include <asm/ioctls.h> @@ -1157,6 +1158,23 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) } } +#ifdef CONFIG_COMPAT +static int compat_rawv6_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case SIOCOUTQ: + case SIOCINQ: + return -ENOIOCTLCMD; + default: +#ifdef CONFIG_IPV6_MROUTE + return ip6mr_compat_ioctl(sk, cmd, compat_ptr(arg)); +#else + return -ENOIOCTLCMD; +#endif + } +} +#endif + static void rawv6_close(struct sock *sk, long timeout) { if (inet_sk(sk)->inet_num == IPPROTO_RAW) @@ -1215,6 +1233,7 @@ struct proto rawv6_prot = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_rawv6_setsockopt, .compat_getsockopt = compat_rawv6_getsockopt, + .compat_ioctl = compat_rawv6_ioctl, #endif }; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 373bd0416f69..e7db7014e89f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -72,8 +72,6 @@ #define RT6_TRACE(x...) do { ; } while (0) #endif -#define CLONE_OFFLINK_ROUTE 0 - static struct rt6_info * ip6_rt_copy(struct rt6_info *ort); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); @@ -115,6 +113,11 @@ static struct dst_ops ip6_dst_ops_template = { .local_out = __ip6_local_out, }; +static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst) +{ + return 0; +} + static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } @@ -124,6 +127,8 @@ static struct dst_ops ip6_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .destroy = ip6_dst_destroy, .check = ip6_dst_check, + .default_mtu = ip6_blackhole_default_mtu, + .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, }; @@ -196,7 +201,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) in6_dev_put(idev); } if (peer) { - BUG_ON(!(rt->rt6i_flags & RTF_CACHE)); rt->rt6i_peer = NULL; inet_putpeer(peer); } @@ -206,9 +210,6 @@ void rt6_bind_peer(struct rt6_info *rt, int create) { struct inet_peer *peer; - if (WARN_ON(!(rt->rt6i_flags & RTF_CACHE))) - return; - peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create); if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL) inet_putpeer(peer); @@ -738,13 +739,10 @@ restart: if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src); - else { -#if CLONE_OFFLINK_ROUTE + else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl->fl6_dst); -#else + else goto out2; -#endif - } dst_release(&rt->dst); rt = nrt ? : net->ipv6.ip6_null_entry; @@ -2561,14 +2559,16 @@ static int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; - int delay = net->ipv6.sysctl.flush_delay; - if (write) { - proc_dointvec(ctl, write, buffer, lenp, ppos); - fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); - return 0; - } else + struct net *net; + int delay; + if (!write) return -EINVAL; + + net = (struct net *)ctl->extra1; + delay = net->ipv6.sysctl.flush_delay; + proc_dointvec(ctl, write, buffer, lenp, ppos); + fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); + return 0; } ctl_table ipv6_route_table_template[] = { @@ -2655,6 +2655,7 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) if (table) { table[0].data = &net->ipv6.sysctl.flush_delay; + table[0].extra1 = net; table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; table[2].data = &net->ipv6.sysctl.ip6_rt_max_size; table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 8ce38f10a547..d2c16e10f650 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1290,4 +1290,4 @@ static int __init sit_init(void) module_init(sit_init); module_exit(sit_cleanup); MODULE_LICENSE("GPL"); -MODULE_ALIAS("sit0"); +MODULE_ALIAS_NETDEV("sit0"); diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index fa1d8f4e0051..7cb65ef79f9c 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -15,6 +15,8 @@ #include <net/addrconf.h> #include <net/inet_frag.h> +static struct ctl_table empty[1]; + static ctl_table ipv6_table_template[] = { { .procname = "route", @@ -35,6 +37,12 @@ static ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "neigh", + .maxlen = 0, + .mode = 0555, + .child = empty, + }, { } }; @@ -152,7 +160,6 @@ static struct ctl_table_header *ip6_base; int ipv6_static_sysctl_register(void) { - static struct ctl_table empty[1]; ip6_base = register_sysctl_paths(net_ipv6_ctl_path, empty); if (ip6_base == NULL) return -ENOMEM; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 7e74023ea6e4..da87428681cc 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -98,6 +98,10 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, if (!xdst->u.rt6.rt6i_idev) return -ENODEV; + xdst->u.rt6.rt6i_peer = rt->rt6i_peer; + if (rt->rt6i_peer) + atomic_inc(&rt->rt6i_peer->refcnt); + /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | @@ -216,6 +220,8 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); + if (likely(xdst->u.rt6.rt6i_peer)) + inet_putpeer(xdst->u.rt6.rt6i_peer); xfrm_dst_destroy(xdst); } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 4bc8a9250cfd..9cd73b11506e 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1822,6 +1822,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, *cookie ^= 2; IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_TX_OFFCHAN; local->hw_roc_skb = skb; + local->hw_roc_skb_for_status = skb; mutex_unlock(&local->mtx); return 0; @@ -1875,6 +1876,7 @@ static int ieee80211_mgmt_tx_cancel_wait(struct wiphy *wiphy, if (ret == 0) { kfree_skb(local->hw_roc_skb); local->hw_roc_skb = NULL; + local->hw_roc_skb_for_status = NULL; } mutex_unlock(&local->mtx); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index c47d7c0e48a4..533fd32f49ff 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -953,7 +953,7 @@ struct ieee80211_local { struct ieee80211_channel *hw_roc_channel; struct net_device *hw_roc_dev; - struct sk_buff *hw_roc_skb; + struct sk_buff *hw_roc_skb, *hw_roc_skb_for_status; struct work_struct hw_roc_start, hw_roc_done; enum nl80211_channel_type hw_roc_channel_type; unsigned int hw_roc_duration; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 8acba456744e..7a10a8d1b2d0 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1229,6 +1229,7 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) } mutex_unlock(&local->iflist_mtx); unregister_netdevice_many(&unreg_list); + list_del(&unreg_list); } static u32 ieee80211_idle_off(struct ieee80211_local *local, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 45fbb9e33746..c9ceb4d57ab0 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1033,6 +1033,12 @@ void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, if (is_multicast_ether_addr(hdr->addr1)) return; + /* + * In case we receive frames after disassociation. + */ + if (!sdata->u.mgd.associated) + return; + ieee80211_sta_reset_conn_monitor(sdata); } diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 38a797217a91..071ac95c4aa0 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -323,6 +323,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) { struct ieee80211_work *wk; + u64 cookie = (unsigned long)skb; rcu_read_lock(); list_for_each_entry_rcu(wk, &local->work_list, list) { @@ -334,8 +335,12 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) break; } rcu_read_unlock(); + if (local->hw_roc_skb_for_status == skb) { + cookie = local->hw_roc_cookie ^ 2; + local->hw_roc_skb_for_status = NULL; + } cfg80211_mgmt_tx_status( - skb->dev, (unsigned long) skb, skb->data, skb->len, + skb->dev, cookie, skb->data, skb->len, !!(info->flags & IEEE80211_TX_STAT_ACK), GFP_ATOMIC); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 5950e3abead9..b0beaa58246b 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1547,7 +1547,7 @@ static int ieee80211_skb_resize(struct ieee80211_local *local, skb_orphan(skb); } - if (skb_header_cloned(skb)) + if (skb_cloned(skb)) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else if (head_need || tail_need) I802_DEBUG_INC(local->tx_expand_skb_head); @@ -2230,6 +2230,9 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, sdata = vif_to_sdata(vif); + if (!ieee80211_sdata_running(sdata)) + goto out; + if (tim_offset) *tim_offset = 0; if (tim_length) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index cf68700abffa..d036597aabbe 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1210,7 +1210,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: changed |= BSS_CHANGED_ASSOC; + mutex_lock(&sdata->u.mgd.mtx); ieee80211_bss_info_change_notify(sdata, changed); + mutex_unlock(&sdata->u.mgd.mtx); break; case NL80211_IFTYPE_ADHOC: changed |= BSS_CHANGED_IBSS; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 32fcbe290c04..4aa614b8a96a 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -133,6 +133,7 @@ unsigned int nf_iterate(struct list_head *head, /* Optimization: we don't need to hold module reference here, since function can't sleep. --RR */ +repeat: verdict = elem->hook(hook, skb, indev, outdev, okfn); if (verdict != NF_ACCEPT) { #ifdef CONFIG_NETFILTER_DEBUG @@ -145,7 +146,7 @@ unsigned int nf_iterate(struct list_head *head, #endif if (verdict != NF_REPEAT) return verdict; - *i = (*i)->prev; + goto repeat; } } return NF_ACCEPT; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 22f7ad5101ab..ba98e1308f3c 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -808,9 +808,9 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, dest->u_threshold = udest->u_threshold; dest->l_threshold = udest->l_threshold; - spin_lock(&dest->dst_lock); + spin_lock_bh(&dest->dst_lock); ip_vs_dst_reset(dest); - spin_unlock(&dest->dst_lock); + spin_unlock_bh(&dest->dst_lock); if (add) ip_vs_new_estimator(&dest->stats); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e61511929c66..84f4fcc5884b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -942,8 +942,15 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_REPLY, ct); out: - if (tmpl) - nf_ct_put(tmpl); + if (tmpl) { + /* Special case: we have to repeat this hook, assign the + * template again to this packet. We assume that this packet + * has no conntrack assigned. This is used by nf_ct_tcp. */ + if (ret == NF_REPEAT) + skb->nfct = (struct nf_conntrack *)tmpl; + else + nf_ct_put(tmpl); + } return ret; } diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 5702de35e2bb..63a1b915a7e4 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -63,6 +63,9 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct) * this does not harm and it happens very rarely. */ unsigned long missed = e->missed; + if (!((events | missed) & e->ctmask)) + goto out_unlock; + ret = notify->fcn(events | missed, &item); if (unlikely(ret < 0 || missed)) { spin_lock_bh(&ct->lock); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 93297aaceb2b..eead9db6f899 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -667,6 +667,7 @@ restart: if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, IPCTNL_MSG_CT_NEW, ct) < 0) { + nf_conntrack_get(&ct->ct_general); cb->args[1] = (unsigned long)ct; goto out; } diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index b07393eab88e..91816998ed86 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -85,6 +85,8 @@ EXPORT_SYMBOL(nf_log_unregister); int nf_log_bind_pf(u_int8_t pf, const struct nf_logger *logger) { + if (pf >= ARRAY_SIZE(nf_loggers)) + return -EINVAL; mutex_lock(&nf_log_mutex); if (__find_logger(pf, logger->name) == NULL) { mutex_unlock(&nf_log_mutex); @@ -98,6 +100,8 @@ EXPORT_SYMBOL(nf_log_bind_pf); void nf_log_unbind_pf(u_int8_t pf) { + if (pf >= ARRAY_SIZE(nf_loggers)) + return; mutex_lock(&nf_log_mutex); rcu_assign_pointer(nf_loggers[pf], NULL); mutex_unlock(&nf_log_mutex); diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c index 4d87befb04c0..474d621cbc2e 100644 --- a/net/netfilter/nf_tproxy_core.c +++ b/net/netfilter/nf_tproxy_core.c @@ -28,26 +28,23 @@ nf_tproxy_destructor(struct sk_buff *skb) skb->destructor = NULL; if (sk) - nf_tproxy_put_sock(sk); + sock_put(sk); } /* consumes sk */ -int +void nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) { - bool transparent = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_transparent : - inet_sk(sk)->transparent; - - if (transparent) { - skb_orphan(skb); - skb->sk = sk; - skb->destructor = nf_tproxy_destructor; - return 1; - } else - nf_tproxy_put_sock(sk); - - return 0; + /* assigning tw sockets complicates things; most + * skb->sk->X checks would have to test sk->sk_state first */ + if (sk->sk_state == TCP_TIME_WAIT) { + inet_twsk_put(inet_twsk(sk)); + return; + } + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = nf_tproxy_destructor; } EXPORT_SYMBOL_GPL(nf_tproxy_assign_sock); diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 640678f47a2a..dcfd57eb9d02 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -33,6 +33,20 @@ #include <net/netfilter/nf_tproxy_core.h> #include <linux/netfilter/xt_TPROXY.h> +static bool tproxy_sk_is_transparent(struct sock *sk) +{ + if (sk->sk_state != TCP_TIME_WAIT) { + if (inet_sk(sk)->transparent) + return true; + sock_put(sk); + } else { + if (inet_twsk(sk)->tw_transparent) + return true; + inet_twsk_put(inet_twsk(sk)); + } + return false; +} + static inline __be32 tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) { @@ -141,7 +155,7 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, skb->dev, NFT_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ - if (sk && nf_tproxy_assign_sock(skb, sk)) { + if (sk && tproxy_sk_is_transparent(sk)) { /* This should be in a separate target, but we don't do multiple targets on the same rule yet */ skb->mark = (skb->mark & ~mark_mask) ^ mark_value; @@ -149,6 +163,8 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, pr_debug("redirecting: proto %hhu %pI4:%hu -> %pI4:%hu, mark: %x\n", iph->protocol, &iph->daddr, ntohs(hp->dest), &laddr, ntohs(lport), skb->mark); + + nf_tproxy_assign_sock(skb, sk); return NF_ACCEPT; } @@ -306,7 +322,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) par->in, NFT_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ - if (sk && nf_tproxy_assign_sock(skb, sk)) { + if (sk && tproxy_sk_is_transparent(sk)) { /* This should be in a separate target, but we don't do multiple targets on the same rule yet */ skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value; @@ -314,6 +330,8 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) pr_debug("redirecting: proto %hhu %pI6:%hu -> %pI6:%hu, mark: %x\n", tproto, &iph->saddr, ntohs(hp->source), laddr, ntohs(lport), skb->mark); + + nf_tproxy_assign_sock(skb, sk); return NF_ACCEPT; } diff --git a/net/netfilter/xt_iprange.c b/net/netfilter/xt_iprange.c index 88f7c3511c72..73c33a42f87f 100644 --- a/net/netfilter/xt_iprange.c +++ b/net/netfilter/xt_iprange.c @@ -53,15 +53,13 @@ iprange_mt4(const struct sk_buff *skb, struct xt_action_param *par) } static inline int -iprange_ipv6_sub(const struct in6_addr *a, const struct in6_addr *b) +iprange_ipv6_lt(const struct in6_addr *a, const struct in6_addr *b) { unsigned int i; - int r; for (i = 0; i < 4; ++i) { - r = ntohl(a->s6_addr32[i]) - ntohl(b->s6_addr32[i]); - if (r != 0) - return r; + if (a->s6_addr32[i] != b->s6_addr32[i]) + return ntohl(a->s6_addr32[i]) < ntohl(b->s6_addr32[i]); } return 0; @@ -75,15 +73,15 @@ iprange_mt6(const struct sk_buff *skb, struct xt_action_param *par) bool m; if (info->flags & IPRANGE_SRC) { - m = iprange_ipv6_sub(&iph->saddr, &info->src_min.in6) < 0; - m |= iprange_ipv6_sub(&iph->saddr, &info->src_max.in6) > 0; + m = iprange_ipv6_lt(&iph->saddr, &info->src_min.in6); + m |= iprange_ipv6_lt(&info->src_max.in6, &iph->saddr); m ^= !!(info->flags & IPRANGE_SRC_INV); if (m) return false; } if (info->flags & IPRANGE_DST) { - m = iprange_ipv6_sub(&iph->daddr, &info->dst_min.in6) < 0; - m |= iprange_ipv6_sub(&iph->daddr, &info->dst_max.in6) > 0; + m = iprange_ipv6_lt(&iph->daddr, &info->dst_min.in6); + m |= iprange_ipv6_lt(&info->dst_max.in6, &iph->daddr); m ^= !!(info->flags & IPRANGE_DST_INV); if (m) return false; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 00d6ae838303..9cc46356b577 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -35,6 +35,15 @@ #include <net/netfilter/nf_conntrack.h> #endif +static void +xt_socket_put_sk(struct sock *sk) +{ + if (sk->sk_state == TCP_TIME_WAIT) + inet_twsk_put(inet_twsk(sk)); + else + sock_put(sk); +} + static int extract_icmp4_fields(const struct sk_buff *skb, u8 *protocol, @@ -164,7 +173,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); - nf_tproxy_put_sock(sk); + xt_socket_put_sk(sk); if (wildcard || !transparent) sk = NULL; @@ -298,7 +307,7 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); - nf_tproxy_put_sock(sk); + xt_socket_put_sk(sk); if (wildcard || !transparent) sk = NULL; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 478181d53c55..1f924595bdef 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1407,7 +1407,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, int noblock = flags&MSG_DONTWAIT; size_t copied; struct sk_buff *skb, *data_skb; - int err; + int err, ret; if (flags&MSG_OOB) return -EOPNOTSUPP; @@ -1470,8 +1470,13 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, skb_free_datagram(sk, skb); - if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) - netlink_dump(sk); + if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { + ret = netlink_dump(sk); + if (ret) { + sk->sk_err = ret; + sk->sk_error_report(sk); + } + } scm_recv(sock, msg, siocb->scm, flags); out: @@ -1736,6 +1741,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, struct netlink_callback *cb; struct sock *sk; struct netlink_sock *nlk; + int ret; cb = kzalloc(sizeof(*cb), GFP_KERNEL); if (cb == NULL) @@ -1764,9 +1770,13 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, nlk->cb = cb; mutex_unlock(nlk->cb_mutex); - netlink_dump(sk); + ret = netlink_dump(sk); + sock_put(sk); + if (ret) + return ret; + /* We successfully started a dump, by returning -EINTR we * signal not to send ACK even if it was requested. */ diff --git a/net/rds/ib.c b/net/rds/ib.c index 4123967d4d65..cce19f95c624 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -364,7 +364,6 @@ void rds_ib_exit(void) rds_ib_sysctl_exit(); rds_ib_recv_exit(); rds_trans_unregister(&rds_ib_transport); - rds_ib_fmr_exit(); } struct rds_transport rds_ib_transport = { @@ -400,13 +399,9 @@ int rds_ib_init(void) INIT_LIST_HEAD(&rds_ib_devices); - ret = rds_ib_fmr_init(); - if (ret) - goto out; - ret = ib_register_client(&rds_ib_client); if (ret) - goto out_fmr_exit; + goto out; ret = rds_ib_sysctl_init(); if (ret) @@ -430,8 +425,6 @@ out_sysctl: rds_ib_sysctl_exit(); out_ibreg: rds_ib_unregister_client(); -out_fmr_exit: - rds_ib_fmr_exit(); out: return ret; } diff --git a/net/rds/ib.h b/net/rds/ib.h index e34ad032b66d..4297d92788dc 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -307,8 +307,6 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, void rds_ib_sync_mr(void *trans_private, int dir); void rds_ib_free_mr(void *trans_private, int invalidate); void rds_ib_flush_mrs(void); -int rds_ib_fmr_init(void); -void rds_ib_fmr_exit(void); /* ib_recv.c */ int rds_ib_recv_init(void); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 18a833c450c8..819c35a0d9cb 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -38,8 +38,6 @@ #include "ib.h" #include "xlist.h" -static struct workqueue_struct *rds_ib_fmr_wq; - static DEFINE_PER_CPU(unsigned long, clean_list_grace); #define CLEAN_LIST_BUSY_BIT 0 @@ -307,7 +305,7 @@ static struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev) int err = 0, iter = 0; if (atomic_read(&pool->dirty_count) >= pool->max_items / 10) - queue_delayed_work(rds_ib_fmr_wq, &pool->flush_worker, 10); + schedule_delayed_work(&pool->flush_worker, 10); while (1) { ibmr = rds_ib_reuse_fmr(pool); @@ -696,24 +694,6 @@ out_nolock: return ret; } -int rds_ib_fmr_init(void) -{ - rds_ib_fmr_wq = create_workqueue("rds_fmr_flushd"); - if (!rds_ib_fmr_wq) - return -ENOMEM; - return 0; -} - -/* - * By the time this is called all the IB devices should have been torn down and - * had their pools freed. As each pool is freed its work struct is waited on, - * so the pool flushing work queue should be idle by the time we get here. - */ -void rds_ib_fmr_exit(void) -{ - destroy_workqueue(rds_ib_fmr_wq); -} - static void rds_ib_mr_pool_flush_worker(struct work_struct *work) { struct rds_ib_mr_pool *pool = container_of(work, struct rds_ib_mr_pool, flush_worker.work); @@ -741,7 +721,7 @@ void rds_ib_free_mr(void *trans_private, int invalidate) /* If we've pinned too many pages, request a flush */ if (atomic_read(&pool->free_pinned) >= pool->max_free_pinned || atomic_read(&pool->dirty_count) >= pool->max_items / 10) - queue_delayed_work(rds_ib_fmr_wq, &pool->flush_worker, 10); + schedule_delayed_work(&pool->flush_worker, 10); if (invalidate) { if (likely(!in_interrupt())) { @@ -749,8 +729,7 @@ void rds_ib_free_mr(void *trans_private, int invalidate) } else { /* We get here if the user created a MR marked * as use_once and invalidate at the same time. */ - queue_delayed_work(rds_ib_fmr_wq, - &pool->flush_worker, 10); + schedule_delayed_work(&pool->flush_worker, 10); } } diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 71f373c421bc..c47a511f203d 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -551,7 +551,10 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, if (conn->c_loopback && rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) { rds_cong_map_updated(conn->c_fcong, ~(u64) 0); - return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES; + scat = &rm->data.op_sg[sg]; + ret = sizeof(struct rds_header) + RDS_CONG_MAP_BYTES; + ret = min_t(int, ret, scat->length - conn->c_xmit_data_off); + return ret; } /* FIXME we may overallocate here */ diff --git a/net/rds/loop.c b/net/rds/loop.c index aeec1d483b17..bca6761a3ca2 100644 --- a/net/rds/loop.c +++ b/net/rds/loop.c @@ -61,10 +61,15 @@ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm, unsigned int hdr_off, unsigned int sg, unsigned int off) { + struct scatterlist *sgp = &rm->data.op_sg[sg]; + int ret = sizeof(struct rds_header) + + be32_to_cpu(rm->m_inc.i_hdr.h_len); + /* Do not send cong updates to loopback */ if (rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) { rds_cong_map_updated(conn->c_fcong, ~(u64) 0); - return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES; + ret = min_t(int, ret, sgp->length - conn->c_xmit_data_off); + goto out; } BUG_ON(hdr_off || sg || off); @@ -80,8 +85,8 @@ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm, NULL); rds_inc_put(&rm->m_inc); - - return sizeof(struct rds_header) + be32_to_cpu(rm->m_inc.i_hdr.h_len); +out: + return ret; } /* diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c index 89315009bab1..1a2b0633fece 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/ar-input.c @@ -423,6 +423,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) goto protocol_error; } + case RXRPC_PACKET_TYPE_ACKALL: case RXRPC_PACKET_TYPE_ACK: /* ACK processing is done in process context */ read_lock_bh(&call->state_lock); diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index 5ee16f0353fe..d763793d39de 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -89,11 +89,11 @@ static int rxrpc_instantiate_xdr_rxkad(struct key *key, const __be32 *xdr, return ret; plen -= sizeof(*token); - token = kmalloc(sizeof(*token), GFP_KERNEL); + token = kzalloc(sizeof(*token), GFP_KERNEL); if (!token) return -ENOMEM; - token->kad = kmalloc(plen, GFP_KERNEL); + token->kad = kzalloc(plen, GFP_KERNEL); if (!token->kad) { kfree(token); return -ENOMEM; @@ -731,10 +731,10 @@ static int rxrpc_instantiate(struct key *key, const void *data, size_t datalen) goto error; ret = -ENOMEM; - token = kmalloc(sizeof(*token), GFP_KERNEL); + token = kzalloc(sizeof(*token), GFP_KERNEL); if (!token) goto error; - token->kad = kmalloc(plen, GFP_KERNEL); + token->kad = kzalloc(plen, GFP_KERNEL); if (!token->kad) goto error_free; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index c80d1c210c5d..5f63ec58942c 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -390,7 +390,6 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = qdisc_enqueue(skb, cl->q); if (ret == NET_XMIT_SUCCESS) { sch->q.qlen++; - qdisc_bstats_update(sch, skb); cbq_mark_toplevel(q, cl); if (!cl->next_alive) cbq_activate_class(cl); @@ -649,7 +648,6 @@ static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child) ret = qdisc_enqueue(skb, cl->q); if (ret == NET_XMIT_SUCCESS) { sch->q.qlen++; - qdisc_bstats_update(sch, skb); if (!cl->next_alive) cbq_activate_class(cl); return 0; @@ -971,6 +969,7 @@ cbq_dequeue(struct Qdisc *sch) skb = cbq_dequeue_1(sch); if (skb) { + qdisc_bstats_update(sch, skb); sch->q.qlen--; sch->flags &= ~TCQ_F_THROTTLED; return skb; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index de55e642eafc..6b7fe4a84f13 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -376,7 +376,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch) } bstats_update(&cl->bstats, skb); - qdisc_bstats_update(sch, skb); sch->q.qlen++; return err; @@ -403,6 +402,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch) skb = qdisc_dequeue_peeked(cl->qdisc); if (cl->qdisc->q.qlen == 0) list_del(&cl->alist); + qdisc_bstats_update(sch, skb); sch->q.qlen--; return skb; } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 60f4bdd4408e..0f7bf3fdfea5 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -260,7 +260,6 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) return err; } - qdisc_bstats_update(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; @@ -283,6 +282,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) if (skb == NULL) return NULL; + qdisc_bstats_update(sch, skb); sch->q.qlen--; index = skb->tc_index & (p->indices - 1); diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index aa4d6337e43c..d468b479aa93 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -46,17 +46,14 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc* sch) { - struct sk_buff *skb_head; struct fifo_sched_data *q = qdisc_priv(sch); if (likely(skb_queue_len(&sch->q) < q->limit)) return qdisc_enqueue_tail(skb, sch); /* queue full, remove one skb to fulfill the limit */ - skb_head = qdisc_dequeue_head(sch); + __qdisc_queue_drop_head(sch, &sch->q); sch->qstats.drops++; - kfree_skb(skb_head); - qdisc_enqueue_tail(skb, sch); return NET_XMIT_CN; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 34dc598440a2..1bc698039ae2 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -839,6 +839,7 @@ void dev_deactivate(struct net_device *dev) list_add(&dev->unreg_list, &single); dev_deactivate_many(&single); + list_del(&single); } static void dev_init_scheduler_queue(struct net_device *dev, diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 2e45791d4f6c..14a799de1c35 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1600,7 +1600,6 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch) set_active(cl, qdisc_pkt_len(skb)); bstats_update(&cl->bstats, skb); - qdisc_bstats_update(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; @@ -1666,6 +1665,7 @@ hfsc_dequeue(struct Qdisc *sch) } sch->flags &= ~TCQ_F_THROTTLED; + qdisc_bstats_update(sch, skb); sch->q.qlen--; return skb; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 984c1b0c6836..fc12fe6f5597 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -574,7 +574,6 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) } sch->q.qlen++; - qdisc_bstats_update(sch, skb); return NET_XMIT_SUCCESS; } @@ -842,7 +841,7 @@ next: static struct sk_buff *htb_dequeue(struct Qdisc *sch) { - struct sk_buff *skb = NULL; + struct sk_buff *skb; struct htb_sched *q = qdisc_priv(sch); int level; psched_time_t next_event; @@ -851,6 +850,8 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch) /* try to dequeue direct packets as high prio (!) to minimize cpu work */ skb = __skb_dequeue(&q->direct_queue); if (skb != NULL) { +ok: + qdisc_bstats_update(sch, skb); sch->flags &= ~TCQ_F_THROTTLED; sch->q.qlen--; return skb; @@ -884,11 +885,8 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch) int prio = ffz(m); m |= 1 << prio; skb = htb_dequeue_tree(q, prio, level); - if (likely(skb != NULL)) { - sch->q.qlen--; - sch->flags &= ~TCQ_F_THROTTLED; - goto fin; - } + if (likely(skb != NULL)) + goto ok; } } sch->qstats.overlimits++; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 21f13da24763..436a2e75b322 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -83,7 +83,6 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = qdisc_enqueue(skb, qdisc); if (ret == NET_XMIT_SUCCESS) { - qdisc_bstats_update(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; } @@ -112,6 +111,7 @@ static struct sk_buff *multiq_dequeue(struct Qdisc *sch) qdisc = q->queues[q->curband]; skb = qdisc->dequeue(qdisc); if (skb) { + qdisc_bstats_update(sch, skb); sch->q.qlen--; return skb; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 1c4bce863479..6a3006b38dc5 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -240,7 +240,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (likely(ret == NET_XMIT_SUCCESS)) { sch->q.qlen++; - qdisc_bstats_update(sch, skb); } else if (net_xmit_drop_count(ret)) { sch->qstats.drops++; } @@ -289,6 +288,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) skb->tstamp.tv64 = 0; #endif pr_debug("netem_dequeue: return skb=%p\n", skb); + qdisc_bstats_update(sch, skb); sch->q.qlen--; return skb; } @@ -476,7 +476,6 @@ static int tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) __skb_queue_after(list, skb, nskb); sch->qstats.backlog += qdisc_pkt_len(nskb); - qdisc_bstats_update(sch, nskb); return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 966158d49dd1..fbd710d619bf 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -84,7 +84,6 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = qdisc_enqueue(skb, qdisc); if (ret == NET_XMIT_SUCCESS) { - qdisc_bstats_update(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; } @@ -116,6 +115,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc* sch) struct Qdisc *qdisc = q->queues[prio]; struct sk_buff *skb = qdisc->dequeue(qdisc); if (skb) { + qdisc_bstats_update(sch, skb); sch->q.qlen--; return skb; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index a6009c5a2c97..9f98dbd32d4c 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -94,7 +94,6 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) ret = qdisc_enqueue(skb, child); if (likely(ret == NET_XMIT_SUCCESS)) { - qdisc_bstats_update(sch, skb); sch->q.qlen++; } else if (net_xmit_drop_count(ret)) { q->stats.pdrop++; @@ -114,11 +113,13 @@ static struct sk_buff * red_dequeue(struct Qdisc* sch) struct Qdisc *child = q->qdisc; skb = child->dequeue(child); - if (skb) + if (skb) { + qdisc_bstats_update(sch, skb); sch->q.qlen--; - else if (!red_is_idling(&q->parms)) - red_start_of_idle_period(&q->parms); - + } else { + if (!red_is_idling(&q->parms)) + red_start_of_idle_period(&q->parms); + } return skb; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 239ec53a634d..edea8cefec6c 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -402,10 +402,8 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) q->tail = slot; slot->allot = q->scaled_quantum; } - if (++sch->q.qlen <= q->limit) { - qdisc_bstats_update(sch, skb); + if (++sch->q.qlen <= q->limit) return NET_XMIT_SUCCESS; - } sfq_drop(sch); return NET_XMIT_CN; @@ -445,6 +443,7 @@ next_slot: } skb = slot_dequeue_head(slot); sfq_dec(q, a); + qdisc_bstats_update(sch, skb); sch->q.qlen--; sch->qstats.backlog -= qdisc_pkt_len(skb); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 77565e721811..e93165820c3f 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -134,7 +134,6 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) } sch->q.qlen++; - qdisc_bstats_update(sch, skb); return NET_XMIT_SUCCESS; } @@ -187,6 +186,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc* sch) q->ptokens = ptoks; sch->q.qlen--; sch->flags &= ~TCQ_F_THROTTLED; + qdisc_bstats_update(sch, skb); return skb; } diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 84ce48eadff4..d84e7329660f 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -87,7 +87,6 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc* sch) if (q->q.qlen < dev->tx_queue_len) { __skb_queue_tail(&q->q, skb); - qdisc_bstats_update(sch, skb); return NET_XMIT_SUCCESS; } @@ -111,6 +110,8 @@ teql_dequeue(struct Qdisc* sch) dat->m->slaves = sch; netif_wake_queue(m); } + } else { + qdisc_bstats_update(sch, skb); } sch->q.qlen = dat->q.qlen + dat_queue->qdisc->q.qlen; return skb; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 2cc46f0962ca..b23428f3c0dd 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2029,11 +2029,11 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc, *errp = sctp_make_op_error_fixed(asoc, chunk); if (*errp) { - sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM, - WORD_ROUND(ntohs(param.p->length))); - sctp_addto_chunk_fixed(*errp, - WORD_ROUND(ntohs(param.p->length)), - param.v); + if (!sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM, + WORD_ROUND(ntohs(param.p->length)))) + sctp_addto_chunk_fixed(*errp, + WORD_ROUND(ntohs(param.p->length)), + param.v); } else { /* If there is no memory for generating the ERROR * report as specified, an ABORT will be triggered diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 243fc09b164e..3fc8624fcd17 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -252,23 +252,37 @@ static void rpc_set_active(struct rpc_task *task) /* * Mark an RPC call as having completed by clearing the 'active' bit + * and then waking up all tasks that were sleeping. */ -static void rpc_mark_complete_task(struct rpc_task *task) +static int rpc_complete_task(struct rpc_task *task) { - smp_mb__before_clear_bit(); + void *m = &task->tk_runstate; + wait_queue_head_t *wq = bit_waitqueue(m, RPC_TASK_ACTIVE); + struct wait_bit_key k = __WAIT_BIT_KEY_INITIALIZER(m, RPC_TASK_ACTIVE); + unsigned long flags; + int ret; + + spin_lock_irqsave(&wq->lock, flags); clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate); - smp_mb__after_clear_bit(); - wake_up_bit(&task->tk_runstate, RPC_TASK_ACTIVE); + ret = atomic_dec_and_test(&task->tk_count); + if (waitqueue_active(wq)) + __wake_up_locked_key(wq, TASK_NORMAL, &k); + spin_unlock_irqrestore(&wq->lock, flags); + return ret; } /* * Allow callers to wait for completion of an RPC call + * + * Note the use of out_of_line_wait_on_bit() rather than wait_on_bit() + * to enforce taking of the wq->lock and hence avoid races with + * rpc_complete_task(). */ int __rpc_wait_for_completion_task(struct rpc_task *task, int (*action)(void *)) { if (action == NULL) action = rpc_wait_bit_killable; - return wait_on_bit(&task->tk_runstate, RPC_TASK_ACTIVE, + return out_of_line_wait_on_bit(&task->tk_runstate, RPC_TASK_ACTIVE, action, TASK_KILLABLE); } EXPORT_SYMBOL_GPL(__rpc_wait_for_completion_task); @@ -857,34 +871,67 @@ static void rpc_async_release(struct work_struct *work) rpc_free_task(container_of(work, struct rpc_task, u.tk_work)); } -void rpc_put_task(struct rpc_task *task) +static void rpc_release_resources_task(struct rpc_task *task) { - if (!atomic_dec_and_test(&task->tk_count)) - return; - /* Release resources */ if (task->tk_rqstp) xprt_release(task); if (task->tk_msg.rpc_cred) put_rpccred(task->tk_msg.rpc_cred); rpc_task_release_client(task); - if (task->tk_workqueue != NULL) { +} + +static void rpc_final_put_task(struct rpc_task *task, + struct workqueue_struct *q) +{ + if (q != NULL) { INIT_WORK(&task->u.tk_work, rpc_async_release); - queue_work(task->tk_workqueue, &task->u.tk_work); + queue_work(q, &task->u.tk_work); } else rpc_free_task(task); } + +static void rpc_do_put_task(struct rpc_task *task, struct workqueue_struct *q) +{ + if (atomic_dec_and_test(&task->tk_count)) { + rpc_release_resources_task(task); + rpc_final_put_task(task, q); + } +} + +void rpc_put_task(struct rpc_task *task) +{ + rpc_do_put_task(task, NULL); +} EXPORT_SYMBOL_GPL(rpc_put_task); +void rpc_put_task_async(struct rpc_task *task) +{ + rpc_do_put_task(task, task->tk_workqueue); +} +EXPORT_SYMBOL_GPL(rpc_put_task_async); + static void rpc_release_task(struct rpc_task *task) { dprintk("RPC: %5u release task\n", task->tk_pid); BUG_ON (RPC_IS_QUEUED(task)); - /* Wake up anyone who is waiting for task completion */ - rpc_mark_complete_task(task); + rpc_release_resources_task(task); - rpc_put_task(task); + /* + * Note: at this point we have been removed from rpc_clnt->cl_tasks, + * so it should be safe to use task->tk_count as a test for whether + * or not any other processes still hold references to our rpc_task. + */ + if (atomic_read(&task->tk_count) != 1 + !RPC_IS_ASYNC(task)) { + /* Wake up anyone who may be waiting for task completion */ + if (!rpc_complete_task(task)) + return; + } else { + if (!atomic_dec_and_test(&task->tk_count)) + return; + } + rpc_final_put_task(task, task->tk_workqueue); } int rpciod_up(void) @@ -908,7 +955,7 @@ static int rpciod_start(void) * Create the rpciod thread and wait for it to start. */ dprintk("RPC: creating workqueue rpciod\n"); - wq = alloc_workqueue("rpciod", WQ_RESCUER, 0); + wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM, 0); rpciod_workqueue = wq; return rpciod_workqueue != NULL; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 7bd3bbba4710..d802e941d365 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1609,9 +1609,7 @@ static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv, */ static void svc_bc_sock_free(struct svc_xprt *xprt) { - if (xprt) { - kfree(xprt->xpt_bc_sid); + if (xprt) kfree(container_of(xprt, struct svc_sock, sk_xprt)); - } } #endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 9df1eadc912a..1a10dcd999ea 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -1335,6 +1335,7 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, p, 0, length, DMA_FROM_DEVICE); if (ib_dma_mapping_error(xprt->sc_cm_id->device, ctxt->sge[0].addr)) { put_page(p); + svc_rdma_put_context(ctxt, 1); return; } atomic_inc(&xprt->sc_dma_used); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c431f5a57960..be96d429b475 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1631,7 +1631,8 @@ static struct socket *xs_create_sock(struct rpc_xprt *xprt, } xs_reclassify_socket(family, sock); - if (xs_bind(transport, sock)) { + err = xs_bind(transport, sock); + if (err) { sock_release(sock); goto out; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index dd419d286204..ba5b8c208498 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -850,7 +850,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) * Get the parent directory, calculate the hash for last * component. */ - err = path_lookup(sunaddr->sun_path, LOOKUP_PARENT, &nd); + err = kern_path_parent(sunaddr->sun_path, &nd); if (err) goto out_mknod_parent; @@ -1724,7 +1724,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, msg->msg_namelen = 0; - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) { + err = sock_intr_errno(sock_rcvtimeo(sk, noblock)); + goto out; + } skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) { @@ -1864,7 +1868,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, memset(&tmp_scm, 0, sizeof(tmp_scm)); } - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) { + err = sock_intr_errno(timeo); + goto out; + } do { int chunk; @@ -1895,11 +1903,12 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, timeo = unix_stream_data_wait(sk, timeo); - if (signal_pending(current)) { + if (signal_pending(current) + || mutex_lock_interruptible(&u->readlock)) { err = sock_intr_errno(timeo); goto out; } - mutex_lock(&u->readlock); + continue; unlock: unix_state_unlock(sk); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index f89f83bf828e..b6f4b994eb35 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -104,7 +104,7 @@ struct sock *unix_get_socket(struct file *filp) /* * Socket ? */ - if (S_ISSOCK(inode->i_mode)) { + if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { struct socket *sock = SOCKET_I(inode); struct sock *s = sock->sk; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 3e5dbd4e4cd5..d112f038edf0 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -802,11 +802,11 @@ int cfg80211_wext_siwfreq(struct net_device *dev, return freq; if (freq == 0) return -EINVAL; - wdev_lock(wdev); mutex_lock(&rdev->devlist_mtx); + wdev_lock(wdev); err = cfg80211_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT); - mutex_unlock(&rdev->devlist_mtx); wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); return err; default: return -EOPNOTSUPP; diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index 55187c8f6420..406207515b5e 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -27,9 +27,19 @@ #include <net/sock.h> #include <net/x25.h> -/* - * Parse a set of facilities into the facilities structures. Unrecognised - * facilities are written to the debug log file. +/** + * x25_parse_facilities - Parse facilities from skb into the facilities structs + * + * @skb: sk_buff to parse + * @facilities: Regular facilites, updated as facilities are found + * @dte_facs: ITU DTE facilities, updated as DTE facilities are found + * @vc_fac_mask: mask is updated with all facilities found + * + * Return codes: + * -1 - Parsing error, caller should drop call and clean up + * 0 - Parse OK, this skb has no facilities + * >0 - Parse OK, returns the length of the facilities header + * */ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, struct x25_dte_facilities *dte_facs, unsigned long *vc_fac_mask) @@ -62,7 +72,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, switch (*p & X25_FAC_CLASS_MASK) { case X25_FAC_CLASS_A: if (len < 2) - return 0; + return -1; switch (*p) { case X25_FAC_REVERSE: if((p[1] & 0x81) == 0x81) { @@ -107,7 +117,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, break; case X25_FAC_CLASS_B: if (len < 3) - return 0; + return -1; switch (*p) { case X25_FAC_PACKET_SIZE: facilities->pacsize_in = p[1]; @@ -130,7 +140,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, break; case X25_FAC_CLASS_C: if (len < 4) - return 0; + return -1; printk(KERN_DEBUG "X.25: unknown facility %02X, " "values %02X, %02X, %02X\n", p[0], p[1], p[2], p[3]); @@ -139,18 +149,18 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, break; case X25_FAC_CLASS_D: if (len < p[1] + 2) - return 0; + return -1; switch (*p) { case X25_FAC_CALLING_AE: if (p[1] > X25_MAX_DTE_FACIL_LEN || p[1] <= 1) - return 0; + return -1; dte_facs->calling_len = p[2]; memcpy(dte_facs->calling_ae, &p[3], p[1] - 1); *vc_fac_mask |= X25_MASK_CALLING_AE; break; case X25_FAC_CALLED_AE: if (p[1] > X25_MAX_DTE_FACIL_LEN || p[1] <= 1) - return 0; + return -1; dte_facs->called_len = p[2]; memcpy(dte_facs->called_ae, &p[3], p[1] - 1); *vc_fac_mask |= X25_MASK_CALLED_AE; diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index f729f022be69..15de65f04719 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -91,10 +91,10 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp { struct x25_address source_addr, dest_addr; int len; + struct x25_sock *x25 = x25_sk(sk); switch (frametype) { case X25_CALL_ACCEPTED: { - struct x25_sock *x25 = x25_sk(sk); x25_stop_timer(sk); x25->condition = 0x00; @@ -113,14 +113,16 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp &dest_addr); if (len > 0) skb_pull(skb, len); + else if (len < 0) + goto out_clear; len = x25_parse_facilities(skb, &x25->facilities, &x25->dte_facilities, &x25->vc_facil_mask); if (len > 0) skb_pull(skb, len); - else - return -1; + else if (len < 0) + goto out_clear; /* * Copy any Call User Data. */ @@ -144,6 +146,12 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp } return 0; + +out_clear: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; } /* diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 4cbc942f762a..21306928d47f 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -396,9 +396,12 @@ void __exit x25_link_free(void) write_lock_bh(&x25_neigh_list_lock); list_for_each_safe(entry, tmp, &x25_neigh_list) { + struct net_device *dev; + nb = list_entry(entry, struct x25_neigh, node); + dev = nb->dev; __x25_remove_neigh(nb); - dev_put(nb->dev); + dev_put(dev); } write_unlock_bh(&x25_neigh_list_lock); } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 8b3ef404c794..6459588befc3 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1340,10 +1340,13 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) default: BUG(); } - xdst = dst_alloc(dst_ops) ?: ERR_PTR(-ENOBUFS); + xdst = dst_alloc(dst_ops); xfrm_policy_put_afinfo(afinfo); - xdst->flo.ops = &xfrm_bundle_fc_ops; + if (likely(xdst)) + xdst->flo.ops = &xfrm_bundle_fc_ops; + else + xdst = ERR_PTR(-ENOBUFS); return xdst; } |