diff options
Diffstat (limited to 'net')
41 files changed, 414 insertions, 200 deletions
diff --git a/net/atm/clip.c b/net/atm/clip.c index c12c2582457c..127fe70a1baa 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -46,8 +46,8 @@ static struct net_device *clip_devs; static struct atm_vcc *atmarpd; -static struct neigh_table clip_tbl; static struct timer_list idle_timer; +static const struct neigh_ops clip_neigh_ops; static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip) { @@ -123,6 +123,8 @@ static int neigh_check_cb(struct neighbour *n) struct atmarp_entry *entry = neighbour_priv(n); struct clip_vcc *cv; + if (n->ops != &clip_neigh_ops) + return 0; for (cv = entry->vccs; cv; cv = cv->next) { unsigned long exp = cv->last_use + cv->idle_timeout; @@ -154,10 +156,10 @@ static int neigh_check_cb(struct neighbour *n) static void idle_timer_check(unsigned long dummy) { - write_lock(&clip_tbl.lock); - __neigh_for_each_release(&clip_tbl, neigh_check_cb); + write_lock(&arp_tbl.lock); + __neigh_for_each_release(&arp_tbl, neigh_check_cb); mod_timer(&idle_timer, jiffies + CLIP_CHECK_INTERVAL * HZ); - write_unlock(&clip_tbl.lock); + write_unlock(&arp_tbl.lock); } static int clip_arp_rcv(struct sk_buff *skb) diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index ef92864ac625..72eb187a5f60 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -71,19 +71,16 @@ static const char *const bt_slock_key_strings[BT_MAX_PROTO] = { "slock-AF_BLUETOOTH-BTPROTO_AVDTP", }; -static inline void bt_sock_reclassify_lock(struct socket *sock, int proto) +void bt_sock_reclassify_lock(struct sock *sk, int proto) { - struct sock *sk = sock->sk; - - if (!sk) - return; - + BUG_ON(!sk); BUG_ON(sock_owned_by_user(sk)); sock_lock_init_class_and_name(sk, bt_slock_key_strings[proto], &bt_slock_key[proto], bt_key_strings[proto], &bt_lock_key[proto]); } +EXPORT_SYMBOL(bt_sock_reclassify_lock); int bt_sock_register(int proto, const struct net_proto_family *ops) { @@ -145,7 +142,8 @@ static int bt_sock_create(struct net *net, struct socket *sock, int proto, if (bt_proto[proto] && try_module_get(bt_proto[proto]->owner)) { err = bt_proto[proto]->create(net, sock, proto, kern); - bt_sock_reclassify_lock(sock, proto); + if (!err) + bt_sock_reclassify_lock(sock->sk, proto); module_put(bt_proto[proto]->owner); } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3db432473ad5..07bc69ed9498 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -635,6 +635,10 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->pend)) { struct hci_cp_auth_requested cp; + + /* encrypt must be pending if auth is also pending */ + set_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend); + cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 9de93714213a..5aeb62491198 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -640,7 +640,8 @@ static int hci_dev_do_close(struct hci_dev *hdev) /* Reset device */ skb_queue_purge(&hdev->cmd_q); atomic_set(&hdev->cmd_cnt, 1); - if (!test_bit(HCI_RAW, &hdev->flags)) { + if (!test_bit(HCI_RAW, &hdev->flags) && + test_bit(HCI_QUIRK_NO_RESET, &hdev->quirks)) { set_bit(HCI_INIT, &hdev->flags); __hci_request(hdev, hci_reset_req, 0, msecs_to_jiffies(250)); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index faf0b11ac1d3..32d338c30e65 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1018,10 +1018,10 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) hci_chan_del(conn->hchan); if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) - __cancel_delayed_work(&conn->info_timer); + cancel_delayed_work_sync(&conn->info_timer); if (test_and_clear_bit(HCI_CONN_LE_SMP_PEND, &hcon->pend)) { - __cancel_delayed_work(&conn->security_timer); + cancel_delayed_work_sync(&conn->security_timer); smp_chan_destroy(conn); } @@ -1120,7 +1120,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, bdaddr return c1; } -inline int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, bdaddr_t *dst) +int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, bdaddr_t *dst) { struct sock *sk = chan->sk; bdaddr_t *src = &bt_sk(sk)->src; @@ -2574,7 +2574,7 @@ static inline int l2cap_command_rej(struct l2cap_conn *conn, struct l2cap_cmd_hd if ((conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) && cmd->ident == conn->info_ident) { - __cancel_delayed_work(&conn->info_timer); + cancel_delayed_work(&conn->info_timer); conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE; conn->info_ident = 0; @@ -2970,7 +2970,8 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr default: sk->sk_err = ECONNRESET; - __set_chan_timer(chan, L2CAP_DISC_REJ_TIMEOUT); + __set_chan_timer(chan, + msecs_to_jiffies(L2CAP_DISC_REJ_TIMEOUT)); l2cap_send_disconn_req(conn, chan, ECONNRESET); goto done; } @@ -3120,7 +3121,7 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, struct l2cap_cm conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_DONE) return 0; - __cancel_delayed_work(&conn->info_timer); + cancel_delayed_work(&conn->info_timer); if (result != L2CAP_IR_SUCCESS) { conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE; @@ -4478,7 +4479,8 @@ static inline void l2cap_check_encryption(struct l2cap_chan *chan, u8 encrypt) if (encrypt == 0x00) { if (chan->sec_level == BT_SECURITY_MEDIUM) { __clear_chan_timer(chan); - __set_chan_timer(chan, L2CAP_ENC_TIMEOUT); + __set_chan_timer(chan, + msecs_to_jiffies(L2CAP_ENC_TIMEOUT)); } else if (chan->sec_level == BT_SECURITY_HIGH) l2cap_chan_close(chan, ECONNREFUSED); } else { @@ -4499,7 +4501,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) if (hcon->type == LE_LINK) { smp_distribute_keys(conn, 0); - __cancel_delayed_work(&conn->security_timer); + cancel_delayed_work(&conn->security_timer); } rcu_read_lock(); @@ -4546,7 +4548,8 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) L2CAP_CONN_REQ, sizeof(req), &req); } else { __clear_chan_timer(chan); - __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); + __set_chan_timer(chan, + msecs_to_jiffies(L2CAP_DISC_TIMEOUT)); } } else if (chan->state == BT_CONNECT2) { struct l2cap_conn_rsp rsp; @@ -4566,7 +4569,8 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) } } else { l2cap_state_change(chan, BT_DISCONN); - __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); + __set_chan_timer(chan, + msecs_to_jiffies(L2CAP_DISC_TIMEOUT)); res = L2CAP_CR_SEC_BLOCK; stat = L2CAP_CS_NO_INFO; } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index c61d967012b2..401d9428ae4c 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -849,6 +849,8 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(void *data) if (!sk) return NULL; + bt_sock_reclassify_lock(sk, BTPROTO_L2CAP); + l2cap_sock_init(sk, parent); return l2cap_pi(sk)->chan; @@ -1002,7 +1004,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int p INIT_LIST_HEAD(&bt_sk(sk)->accept_q); sk->sk_destruct = l2cap_sock_destruct; - sk->sk_sndtimeo = L2CAP_CONN_TIMEOUT; + sk->sk_sndtimeo = msecs_to_jiffies(L2CAP_CONN_TIMEOUT); sock_reset_flag(sk, SOCK_ZAPPED); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 501649bf5596..8a602388f1e7 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1164,12 +1164,18 @@ static int rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci) break; case BT_DISCONN: - /* When socket is closed and we are not RFCOMM - * initiator rfcomm_process_rx already calls - * rfcomm_session_put() */ - if (s->sock->sk->sk_state != BT_CLOSED) - if (list_empty(&s->dlcs)) - rfcomm_session_put(s); + /* rfcomm_session_put is called later so don't do + * anything here otherwise we will mess up the session + * reference counter: + * + * (a) when we are the initiator dlc_unlink will drive + * the reference counter to 0 (there is no initial put + * after session_add) + * + * (b) when we are not the initiator rfcomm_rx_process + * will explicitly call put to balance the initial hold + * done after session add. + */ break; } } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index f066678faeee..22169c3f1482 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -956,6 +956,8 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * if (!sk) goto done; + bt_sock_reclassify_lock(sk, BTPROTO_RFCOMM); + rfcomm_sock_init(sk, parent); bacpy(&bt_sk(sk)->src, &src); bacpy(&bt_sk(sk)->dst, &dst); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 568d5bf17534..702a1ae9220b 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -446,8 +446,11 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1)); - ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, - &ip6h->saddr); + if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, + &ip6h->saddr)) { + kfree_skb(skb); + return NULL; + } ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); hopopt = (u8 *)(ip6h + 1); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 84122472656c..dec4f3817133 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -62,6 +62,15 @@ static int brnf_filter_pppoe_tagged __read_mostly = 0; #define brnf_filter_pppoe_tagged 0 #endif +#define IS_IP(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IP)) + +#define IS_IPV6(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6)) + +#define IS_ARP(skb) \ + (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_ARP)) + static inline __be16 vlan_proto(const struct sk_buff *skb) { if (vlan_tx_tag_present(skb)) @@ -639,8 +648,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, return NF_DROP; br = p->br; - if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) || - IS_PPPOE_IPV6(skb)) { + if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) { if (!brnf_call_ip6tables && !br->nf_call_ip6tables) return NF_ACCEPT; @@ -651,8 +659,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, if (!brnf_call_iptables && !br->nf_call_iptables) return NF_ACCEPT; - if (skb->protocol != htons(ETH_P_IP) && !IS_VLAN_IP(skb) && - !IS_PPPOE_IP(skb)) + if (!IS_IP(skb) && !IS_VLAN_IP(skb) && !IS_PPPOE_IP(skb)) return NF_ACCEPT; nf_bridge_pull_encap_header_rcsum(skb); @@ -701,7 +708,7 @@ static int br_nf_forward_finish(struct sk_buff *skb) struct nf_bridge_info *nf_bridge = skb->nf_bridge; struct net_device *in; - if (skb->protocol != htons(ETH_P_ARP) && !IS_VLAN_ARP(skb)) { + if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) { in = nf_bridge->physindev; if (nf_bridge->mask & BRNF_PKT_TYPE) { skb->pkt_type = PACKET_OTHERHOST; @@ -718,6 +725,7 @@ static int br_nf_forward_finish(struct sk_buff *skb) return 0; } + /* This is the 'purely bridged' case. For IP, we pass the packet to * netfilter with indev and outdev set to the bridge device, * but we are still able to filter on the 'real' indev/outdev @@ -744,11 +752,9 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, if (!parent) return NF_DROP; - if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) || - IS_PPPOE_IP(skb)) + if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb)) pf = PF_INET; - else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) || - IS_PPPOE_IPV6(skb)) + else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) pf = PF_INET6; else return NF_ACCEPT; @@ -795,7 +801,7 @@ static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb, if (!brnf_call_arptables && !br->nf_call_arptables) return NF_ACCEPT; - if (skb->protocol != htons(ETH_P_ARP)) { + if (!IS_ARP(skb)) { if (!IS_VLAN_ARP(skb)) return NF_ACCEPT; nf_bridge_pull_encap_header(skb); @@ -853,11 +859,9 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, if (!realoutdev) return NF_DROP; - if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb) || - IS_PPPOE_IP(skb)) + if (IS_IP(skb) || IS_VLAN_IP(skb) || IS_PPPOE_IP(skb)) pf = PF_INET; - else if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb) || - IS_PPPOE_IPV6(skb)) + else if (IS_IPV6(skb) || IS_VLAN_IPV6(skb) || IS_PPPOE_IPV6(skb)) pf = PF_INET6; else return NF_ACCEPT; diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index dd147d78a588..8c836d96ba76 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -17,9 +17,9 @@ #include "br_private_stp.h" /* since time values in bpdu are in jiffies and then scaled (1/256) - * before sending, make sure that is at least one. + * before sending, make sure that is at least one STP tick. */ -#define MESSAGE_AGE_INCR ((HZ < 256) ? 1 : (HZ/256)) +#define MESSAGE_AGE_INCR ((HZ / 256) + 1) static const char *const br_port_state_names[] = { [BR_STATE_DISABLED] = "disabled", @@ -31,7 +31,7 @@ static const char *const br_port_state_names[] = { void br_log_state(const struct net_bridge_port *p) { - br_info(p->br, "port %u(%s) entering %s state\n", + br_info(p->br, "port %u(%s) entered %s state\n", (unsigned) p->port_no, p->dev->name, br_port_state_names[p->state]); } @@ -186,7 +186,7 @@ static void br_record_config_information(struct net_bridge_port *p, p->designated_cost = bpdu->root_path_cost; p->designated_bridge = bpdu->bridge_id; p->designated_port = bpdu->port_id; - p->designated_age = jiffies + bpdu->message_age; + p->designated_age = jiffies - bpdu->message_age; mod_timer(&p->message_age_timer, jiffies + (p->br->max_age - bpdu->message_age)); diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 19308e305d85..f494496373d6 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -98,14 +98,13 @@ void br_stp_disable_port(struct net_bridge_port *p) struct net_bridge *br = p->br; int wasroot; - br_log_state(p); - wasroot = br_is_root_bridge(br); br_become_designated_port(p); p->state = BR_STATE_DISABLED; p->topology_change_ack = 0; p->config_pending = 0; + br_log_state(p); br_ifinfo_notify(RTM_NEWLINK, p); del_timer(&p->message_age_timer); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 5864cc491369..5fe2ff3b01ef 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1335,7 +1335,12 @@ static inline int ebt_make_matchname(const struct ebt_entry_match *m, const char *base, char __user *ubase) { char __user *hlp = ubase + ((char *)m - base); - if (copy_to_user(hlp, m->u.match->name, EBT_FUNCTION_MAXNAMELEN)) + char name[EBT_FUNCTION_MAXNAMELEN] = {}; + + /* ebtables expects 32 bytes long names but xt_match names are 29 bytes + long. Copy 29 bytes and fill remaining bytes with zeroes. */ + strncpy(name, m->u.match->name, sizeof(name)); + if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) return -EFAULT; return 0; } @@ -1344,7 +1349,10 @@ static inline int ebt_make_watchername(const struct ebt_entry_watcher *w, const char *base, char __user *ubase) { char __user *hlp = ubase + ((char *)w - base); - if (copy_to_user(hlp , w->u.watcher->name, EBT_FUNCTION_MAXNAMELEN)) + char name[EBT_FUNCTION_MAXNAMELEN] = {}; + + strncpy(name, w->u.watcher->name, sizeof(name)); + if (copy_to_user(hlp , name, EBT_FUNCTION_MAXNAMELEN)) return -EFAULT; return 0; } @@ -1355,6 +1363,7 @@ ebt_make_names(struct ebt_entry *e, const char *base, char __user *ubase) int ret; char __user *hlp; const struct ebt_entry_target *t; + char name[EBT_FUNCTION_MAXNAMELEN] = {}; if (e->bitmask == 0) return 0; @@ -1368,7 +1377,8 @@ ebt_make_names(struct ebt_entry *e, const char *base, char __user *ubase) ret = EBT_WATCHER_ITERATE(e, ebt_make_watchername, base, ubase); if (ret != 0) return ret; - if (copy_to_user(hlp, t->u.target->name, EBT_FUNCTION_MAXNAMELEN)) + strncpy(name, t->u.target->name, sizeof(name)); + if (copy_to_user(hlp, name, EBT_FUNCTION_MAXNAMELEN)) return -EFAULT; return 0; } @@ -1893,10 +1903,7 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, switch (compat_mwt) { case EBT_COMPAT_MATCH: - match = try_then_request_module(xt_find_match(NFPROTO_BRIDGE, - name, 0), "ebt_%s", name); - if (match == NULL) - return -ENOENT; + match = xt_request_find_match(NFPROTO_BRIDGE, name, 0); if (IS_ERR(match)) return PTR_ERR(match); @@ -1915,10 +1922,7 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, break; case EBT_COMPAT_WATCHER: /* fallthrough */ case EBT_COMPAT_TARGET: - wt = try_then_request_module(xt_find_target(NFPROTO_BRIDGE, - name, 0), "ebt_%s", name); - if (wt == NULL) - return -ENOENT; + wt = xt_request_find_target(NFPROTO_BRIDGE, name, 0); if (IS_ERR(wt)) return PTR_ERR(wt); off = xt_compat_target_offset(wt); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e287346e0934..2a83914b0277 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -826,6 +826,8 @@ next_elt: write_unlock_bh(&tbl->lock); cond_resched(); write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); } /* Cycle through all hash buckets every base_reachable_time/2 ticks. * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 65aebd450027..f965dce6f20f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -60,7 +60,6 @@ struct rtnl_link { }; static DEFINE_MUTEX(rtnl_mutex); -static u16 min_ifinfo_dump_size; void rtnl_lock(void) { @@ -724,10 +723,11 @@ static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b) } /* All VF info */ -static inline int rtnl_vfinfo_size(const struct net_device *dev) +static inline int rtnl_vfinfo_size(const struct net_device *dev, + u32 ext_filter_mask) { - if (dev->dev.parent && dev_is_pci(dev->dev.parent)) { - + if (dev->dev.parent && dev_is_pci(dev->dev.parent) && + (ext_filter_mask & RTEXT_FILTER_VF)) { int num_vfs = dev_num_vf(dev->dev.parent); size_t size = nla_total_size(sizeof(struct nlattr)); size += nla_total_size(num_vfs * sizeof(struct nlattr)); @@ -766,7 +766,8 @@ static size_t rtnl_port_size(const struct net_device *dev) return port_self_size; } -static noinline size_t if_nlmsg_size(const struct net_device *dev) +static noinline size_t if_nlmsg_size(const struct net_device *dev, + u32 ext_filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ @@ -784,8 +785,9 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ - + nla_total_size(4) /* IFLA_NUM_VF */ - + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */ + + nla_total_size(ext_filter_mask + & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */ @@ -868,7 +870,7 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, - unsigned int flags) + unsigned int flags, u32 ext_filter_mask) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -941,10 +943,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; copy_rtnl_link_stats64(nla_data(attr), stats); - if (dev->dev.parent) + if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF)) NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)); - if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent + && (ext_filter_mask & RTEXT_FILTER_VF)) { int i; struct nlattr *vfinfo, *vf; @@ -1048,6 +1051,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; struct hlist_head *head; struct hlist_node *node; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -1055,6 +1060,13 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); cb->seq = net->dev_base_seq; + if (nlmsg_parse(cb->nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + ifla_policy) >= 0) { + + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + } + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; @@ -1064,7 +1076,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI) <= 0) + NLM_F_MULTI, + ext_filter_mask) <= 0) goto out; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -1100,6 +1113,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_VF_PORTS] = { .type = NLA_NESTED }, [IFLA_PORT_SELF] = { .type = NLA_NESTED }, [IFLA_AF_SPEC] = { .type = NLA_NESTED }, + [IFLA_EXT_MASK] = { .type = NLA_U32 }, }; EXPORT_SYMBOL(ifla_policy); @@ -1509,8 +1523,6 @@ errout: if (send_addr_notify) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - min_ifinfo_dump_size = max_t(u16, if_nlmsg_size(dev), - min_ifinfo_dump_size); return err; } @@ -1842,6 +1854,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) struct net_device *dev = NULL; struct sk_buff *nskb; int err; + u32 ext_filter_mask = 0; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); if (err < 0) @@ -1850,6 +1863,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); @@ -1861,12 +1877,12 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (dev == NULL) return -ENODEV; - nskb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL); + nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL); if (nskb == NULL) return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid, - nlh->nlmsg_seq, 0, 0); + nlh->nlmsg_seq, 0, 0, ext_filter_mask); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -1877,8 +1893,32 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) return err; } -static u16 rtnl_calcit(struct sk_buff *skb) +static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) { + struct net *net = sock_net(skb->sk); + struct net_device *dev; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; + u16 min_ifinfo_dump_size = 0; + + if (nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + ifla_policy) >= 0) { + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + } + + if (!ext_filter_mask) + return NLMSG_GOODSIZE; + /* + * traverse the list of net devices and compute the minimum + * buffer size based upon the filter mask. + */ + list_for_each_entry(dev, &net->dev_base_head, dev_list) { + min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size, + if_nlmsg_size(dev, + ext_filter_mask)); + } + return min_ifinfo_dump_size; } @@ -1913,13 +1953,11 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) int err = -ENOBUFS; size_t if_info_size; - skb = nlmsg_new((if_info_size = if_nlmsg_size(dev)), GFP_KERNEL); + skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), GFP_KERNEL); if (skb == NULL) goto errout; - min_ifinfo_dump_size = max_t(u16, if_info_size, min_ifinfo_dump_size); - - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1977,7 +2015,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EOPNOTSUPP; calcit = rtnl_get_calcit(family, type); if (calcit) - min_dump_alloc = calcit(skb); + min_dump_alloc = calcit(skb, nlh); __rtnl_unlock(); rtnl = net->rtnl; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index bf4a9c4808e1..d4d61b694fab 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/net.h> +#include <linux/workqueue.h> #include <net/ip.h> #include <net/inetpeer.h> #include <net/secure_seq.h> @@ -66,6 +67,11 @@ static struct kmem_cache *peer_cachep __read_mostly; +static LIST_HEAD(gc_list); +static const int gc_delay = 60 * HZ; +static struct delayed_work gc_work; +static DEFINE_SPINLOCK(gc_lock); + #define node_height(x) x->avl_height #define peer_avl_empty ((struct inet_peer *)&peer_fake_node) @@ -102,6 +108,50 @@ int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries m int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */ +static void inetpeer_gc_worker(struct work_struct *work) +{ + struct inet_peer *p, *n; + LIST_HEAD(list); + + spin_lock_bh(&gc_lock); + list_replace_init(&gc_list, &list); + spin_unlock_bh(&gc_lock); + + if (list_empty(&list)) + return; + + list_for_each_entry_safe(p, n, &list, gc_list) { + + if(need_resched()) + cond_resched(); + + if (p->avl_left != peer_avl_empty) { + list_add_tail(&p->avl_left->gc_list, &list); + p->avl_left = peer_avl_empty; + } + + if (p->avl_right != peer_avl_empty) { + list_add_tail(&p->avl_right->gc_list, &list); + p->avl_right = peer_avl_empty; + } + + n = list_entry(p->gc_list.next, struct inet_peer, gc_list); + + if (!atomic_read(&p->refcnt)) { + list_del(&p->gc_list); + kmem_cache_free(peer_cachep, p); + } + } + + if (list_empty(&list)) + return; + + spin_lock_bh(&gc_lock); + list_splice(&list, &gc_list); + spin_unlock_bh(&gc_lock); + + schedule_delayed_work(&gc_work, gc_delay); +} /* Called from ip_output.c:ip_init */ void __init inet_initpeers(void) @@ -126,6 +176,7 @@ void __init inet_initpeers(void) 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + INIT_DELAYED_WORK_DEFERRABLE(&gc_work, inetpeer_gc_worker); } static int addr_compare(const struct inetpeer_addr *a, @@ -447,9 +498,8 @@ relookup: p->rate_last = 0; p->pmtu_expires = 0; p->pmtu_orig = 0; - p->redirect_genid = 0; memset(&p->redirect_learned, 0, sizeof(p->redirect_learned)); - + INIT_LIST_HEAD(&p->gc_list); /* Link the node. */ link_to_pool(p, base); @@ -509,3 +559,30 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout) return rc; } EXPORT_SYMBOL(inet_peer_xrlim_allow); + +void inetpeer_invalidate_tree(int family) +{ + struct inet_peer *old, *new, *prev; + struct inet_peer_base *base = family_to_base(family); + + write_seqlock_bh(&base->lock); + + old = base->root; + if (old == peer_avl_empty_rcu) + goto out; + + new = peer_avl_empty_rcu; + + prev = cmpxchg(&base->root, old, new); + if (prev == old) { + base->total = 0; + spin_lock(&gc_lock); + list_add_tail(&prev->gc_list, &gc_list); + spin_unlock(&gc_lock); + schedule_delayed_work(&gc_work, gc_delay); + } + +out: + write_sequnlock_bh(&base->lock); +} +EXPORT_SYMBOL(inetpeer_invalidate_tree); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 6b3ca5ba4450..38673d2860e2 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -65,7 +65,7 @@ it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), and silently drop packet when it expires. It is a good - solution, but it supposes maintaing new variable in ALL + solution, but it supposes maintaining new variable in ALL skb, even if no tunneling is used. Current solution: xmit_recursion breaks dead loops. This is a percpu @@ -91,14 +91,14 @@ One of them is to parse packet trying to detect inner encapsulation made by our node. It is difficult or even impossible, especially, - taking into account fragmentation. TO be short, tt is not solution at all. + taking into account fragmentation. TO be short, ttl is not solution at all. Current solution: The solution was UNEXPECTEDLY SIMPLE. We force DF flag on tunnels with preconfigured hop limit, that is ALL. :-) Well, it does not remove the problem completely, but exponential growth of network traffic is changed to linear (branches, that exceed pmtu are pruned) and tunnel mtu - fastly degrades to value <68, where looping stops. + rapidly degrades to value <68, where looping stops. Yes, it is not good if there exists a router in the loop, which does not force DF, even when encapsulating packets have DF set. But it is not our problem! Nobody could accuse us, we made @@ -457,8 +457,8 @@ static void ipgre_err(struct sk_buff *skb, u32 info) GRE tunnels with enabled checksum. Tell them "thank you". Well, I wonder, rfc1812 was written by Cisco employee, - what the hell these idiots break standrads established - by themself??? + what the hell these idiots break standards established + by themselves??? */ const struct iphdr *iph = (const struct iphdr *)skb->data; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index aea5a199c37a..b072386cee21 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -630,6 +630,7 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num); + err = -EOPNOTSUPP; if (flags & MSG_OOB) goto out; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bcacf54e5418..019774796174 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -132,7 +132,6 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int rt_chain_length_max __read_mostly = 20; -static int redirect_genid; static struct delayed_work expires_work; static unsigned long expires_ljiffies; @@ -937,7 +936,7 @@ static void rt_cache_invalidate(struct net *net) get_random_bytes(&shuffle, sizeof(shuffle)); atomic_add(shuffle + 1U, &net->ipv4.rt_genid); - redirect_genid++; + inetpeer_invalidate_tree(AF_INET); } /* @@ -1485,10 +1484,8 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, peer = rt->peer; if (peer) { - if (peer->redirect_learned.a4 != new_gw || - peer->redirect_genid != redirect_genid) { + if (peer->redirect_learned.a4 != new_gw) { peer->redirect_learned.a4 = new_gw; - peer->redirect_genid = redirect_genid; atomic_inc(&__rt_peer_genid); } check_peer_redir(&rt->dst, peer); @@ -1793,8 +1790,6 @@ static void ipv4_validate_peer(struct rtable *rt) if (peer) { check_peer_pmtu(&rt->dst, peer); - if (peer->redirect_genid != redirect_genid) - peer->redirect_learned.a4 = 0; if (peer->redirect_learned.a4 && peer->redirect_learned.a4 != rt->rt_gateway) check_peer_redir(&rt->dst, peer); @@ -1958,8 +1953,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, dst_init_metrics(&rt->dst, peer->metrics, false); check_peer_pmtu(&rt->dst, peer); - if (peer->redirect_genid != redirect_genid) - peer->redirect_learned.a4 = 0; + if (peer->redirect_learned.a4 && peer->redirect_learned.a4 != rt->rt_gateway) { rt->rt_gateway = peer->redirect_learned.a4; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 37755ccc0e96..22ef5f9fd2ff 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3240,7 +3240,8 @@ void __init tcp_init(void) { struct sk_buff *skb = NULL; unsigned long limit; - int i, max_share, cnt; + int max_share, cnt; + unsigned int i; unsigned long jiffy = jiffies; BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); @@ -3283,7 +3284,7 @@ void __init tcp_init(void) &tcp_hashinfo.bhash_size, NULL, 64 * 1024); - tcp_hashinfo.bhash_size = 1 << tcp_hashinfo.bhash_size; + tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 53c8ce4046b2..b5e315f13641 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1403,8 +1403,16 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, BUG_ON(!pcount); - /* Adjust hint for FACK. Non-FACK is handled in tcp_sacktag_one(). */ - if (tcp_is_fack(tp) && (skb == tp->lost_skb_hint)) + /* Adjust counters and hints for the newly sacked sequence + * range but discard the return value since prev is already + * marked. We must tag the range first because the seq + * advancement below implicitly advances + * tcp_highest_sack_seq() when skb is highest_sack. + */ + tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, + start_seq, end_seq, dup_sack, pcount); + + if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; TCP_SKB_CB(prev)->end_seq += shifted; @@ -1430,12 +1438,6 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, skb_shinfo(skb)->gso_type = 0; } - /* Adjust counters and hints for the newly sacked sequence range but - * discard the return value since prev is already marked. - */ - tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, - start_seq, end_seq, dup_sack, pcount); - /* Difference in this won't matter, both ACKed by the same cumul. ACK */ TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS); @@ -1583,6 +1585,10 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, } } + /* tcp_sacktag_one() won't SACK-tag ranges below snd_una */ + if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una)) + goto fallback; + if (!skb_shift(prev, skb, len)) goto fallback; if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack)) @@ -2567,6 +2573,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) if (cnt > packets) { if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) || + (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || (oldcnt >= packets)) break; diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index 63418185f524..e3db3f915114 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -110,10 +110,7 @@ static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); - - memmove(skb->data - skb->mac_len, skb_mac_header(skb), - skb->mac_len); - skb_set_mac_header(skb, -skb->mac_len); + skb_mac_header_rebuild(skb); xfrm4_beet_make_header(skb); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 534972e114ac..ed4bf11ef9f4 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -66,7 +66,6 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - const unsigned char *old_mac; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) @@ -84,10 +83,9 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!(x->props.flags & XFRM_STATE_NOECN)) ipip_ecn_decapsulate(skb); - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + err = 0; out: diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c02280a4d126..6b8ebc5da0e1 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -434,6 +434,10 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) /* Join all-node multicast group */ ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes); + /* Join all-router multicast group if forwarding is set */ + if (ndev->cnf.forwarding && dev && (dev->flags & IFF_MULTICAST)) + ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); + return ndev; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index c7e95c8c579f..5aa3981a3922 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1926,8 +1926,10 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, }; dst = ip6_route_output(net, NULL, &fl6); - if (!dst) + if (dst->error) { + dst_release(dst); goto out_free; + } skb_dst_drop(skb); skb_dst_set(skb, dst); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d8f02ef88e59..c964958ac470 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1545,9 +1545,10 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); dst = ip6_route_output(net, NULL, &fl6); - if (dst == NULL) + if (dst->error) { + dst_release(dst); return; - + } dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) return; diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index a81ce9450750..9949a356d62c 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -80,7 +80,6 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) { struct ipv6hdr *ip6h; - const unsigned char *old_mac; int size = sizeof(struct ipv6hdr); int err; @@ -90,10 +89,7 @@ static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) __skb_push(skb, size); skb_reset_network_header(skb); - - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); + skb_mac_header_rebuild(skb); xfrm6_beet_make_header(skb); diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 261e6e6f487e..9f2095b19ad0 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -63,7 +63,6 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; - const unsigned char *old_mac; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6) goto out; @@ -80,10 +79,9 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + err = 0; out: diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 2406b3e7393f..d86217d56bd7 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -63,14 +63,14 @@ static ssize_t sta_flags_read(struct file *file, char __user *userbuf, test_sta_flag(sta, WLAN_STA_##flg) ? #flg "\n" : "" int res = scnprintf(buf, sizeof(buf), - "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", + "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", TEST(AUTH), TEST(ASSOC), TEST(PS_STA), TEST(PS_DRIVER), TEST(AUTHORIZED), TEST(SHORT_PREAMBLE), TEST(WME), TEST(WDS), TEST(CLEAR_PS_FILT), TEST(MFP), TEST(BLOCK_BA), TEST(PSPOLL), TEST(UAPSD), TEST(SP), TEST(TDLS_PEER), - TEST(TDLS_PEER_AUTH)); + TEST(TDLS_PEER_AUTH), TEST(RATE_CONTROL)); #undef TEST return simple_read_from_buffer(userbuf, count, ppos, buf, res); } diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 01a21c2f6ab3..8e2137bd87e2 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1332,6 +1332,9 @@ u32 __ieee80211_recalc_idle(struct ieee80211_local *local) hw_roc = true; list_for_each_entry(sdata, &local->interfaces, list) { + if (sdata->vif.type == NL80211_IFTYPE_MONITOR || + sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + continue; if (sdata->old_idle == sdata->vif.bss_conf.idle) continue; if (!ieee80211_sdata_running(sdata)) diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 5a5a7767d541..f9b8e819ca63 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -336,7 +336,7 @@ void rate_control_get_rate(struct ieee80211_sub_if_data *sdata, int i; u32 mask; - if (sta) { + if (sta && test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) { ista = &sta->sta; priv_sta = sta->rate_ctrl_priv; } @@ -344,7 +344,7 @@ void rate_control_get_rate(struct ieee80211_sub_if_data *sdata, for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { info->control.rates[i].idx = -1; info->control.rates[i].flags = 0; - info->control.rates[i].count = 1; + info->control.rates[i].count = 0; } if (sdata->local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL) diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 168427b0ffdc..80cfc006dd74 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -41,7 +41,7 @@ static inline void rate_control_tx_status(struct ieee80211_local *local, struct ieee80211_sta *ista = &sta->sta; void *priv_sta = sta->rate_ctrl_priv; - if (!ref) + if (!ref || !test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) return; ref->ops->tx_status(ref->priv, sband, ista, priv_sta, skb); @@ -62,6 +62,7 @@ static inline void rate_control_rate_init(struct sta_info *sta) sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; ref->ops->rate_init(ref->priv, sband, ista, priv_sta); + set_sta_flag(sta, WLAN_STA_RATE_CONTROL); } static inline void rate_control_rate_update(struct ieee80211_local *local, diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 6f77f12dc3fc..bfed851d0d36 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -52,6 +52,7 @@ * @WLAN_STA_SP: Station is in a service period, so don't try to * reply to other uAPSD trigger frames or PS-Poll. * @WLAN_STA_4ADDR_EVENT: 4-addr event was already sent for this frame. + * @WLAN_STA_RATE_CONTROL: rate control was initialized for this station. */ enum ieee80211_sta_info_flags { WLAN_STA_AUTH, @@ -71,6 +72,7 @@ enum ieee80211_sta_info_flags { WLAN_STA_UAPSD, WLAN_STA_SP, WLAN_STA_4ADDR_EVENT, + WLAN_STA_RATE_CONTROL, }; enum ieee80211_sta_state { diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 611c3359b94d..2555816e7788 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -232,6 +232,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, __be16 dport = 0; /* destination port to forward */ unsigned int flags; struct ip_vs_conn_param param; + const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; union nf_inet_addr snet; /* source network of the client, after masking */ @@ -267,7 +268,6 @@ ip_vs_sched_persist(struct ip_vs_service *svc, { int protocol = iph.protocol; const union nf_inet_addr *vaddr = &iph.daddr; - const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; __be16 vport = 0; if (dst_port == svc->port) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 76613f5a55c0..fa4b82c8ae80 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -404,19 +404,49 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct, &net->ct.hash[repl_hash]); } -void nf_conntrack_hash_insert(struct nf_conn *ct) +int +nf_conntrack_hash_check_insert(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); unsigned int hash, repl_hash; + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; u16 zone; zone = nf_ct_zone(ct); - hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + repl_hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + + spin_lock_bh(&nf_conntrack_lock); + + /* See if there's one in the list already, including reverse */ + hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode) + if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &h->tuple) && + zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + goto out; + hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode) + if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, + &h->tuple) && + zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + goto out; + add_timer(&ct->timeout); + nf_conntrack_get(&ct->ct_general); __nf_conntrack_hash_insert(ct, hash, repl_hash); + NF_CT_STAT_INC(net, insert); + spin_unlock_bh(&nf_conntrack_lock); + + return 0; + +out: + NF_CT_STAT_INC(net, insert_failed); + spin_unlock_bh(&nf_conntrack_lock); + return -EEXIST; } -EXPORT_SYMBOL_GPL(nf_conntrack_hash_insert); +EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); /* Confirm a connection given skb; places it in hash table */ int @@ -605,8 +635,12 @@ static noinline int early_drop(struct net *net, unsigned int hash) if (del_timer(&ct->timeout)) { death_by_timeout((unsigned long)ct); - dropped = 1; - NF_CT_STAT_INC_ATOMIC(net, early_drop); + /* Check if we indeed killed this entry. Reliable event + delivery may have inserted it into the dying list. */ + if (test_bit(IPS_DYING_BIT, &ct->status)) { + dropped = 1; + NF_CT_STAT_INC_ATOMIC(net, early_drop); + } } nf_ct_put(ct); return dropped; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 9307b033c0c9..10687692831e 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1041,16 +1041,13 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, if (!parse_nat_setup) { #ifdef CONFIG_MODULES rcu_read_unlock(); - spin_unlock_bh(&nf_conntrack_lock); nfnl_unlock(); if (request_module("nf-nat-ipv4") < 0) { nfnl_lock(); - spin_lock_bh(&nf_conntrack_lock); rcu_read_lock(); return -EOPNOTSUPP; } nfnl_lock(); - spin_lock_bh(&nf_conntrack_lock); rcu_read_lock(); if (nfnetlink_parse_nat_setup_hook) return -EAGAIN; @@ -1367,15 +1364,12 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); - spin_unlock_bh(&nf_conntrack_lock); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { - spin_lock_bh(&nf_conntrack_lock); err = -EOPNOTSUPP; goto err1; } - spin_lock_bh(&nf_conntrack_lock); rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), @@ -1468,8 +1462,10 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, if (tstamp) tstamp->start = ktime_to_ns(ktime_get_real()); - add_timer(&ct->timeout); - nf_conntrack_hash_insert(ct); + err = nf_conntrack_hash_check_insert(ct); + if (err < 0) + goto err2; + rcu_read_unlock(); return ct; @@ -1490,6 +1486,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nf_conn *ct; u_int8_t u3 = nfmsg->nfgen_family; u16 zone; int err; @@ -1510,27 +1507,22 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; } - spin_lock_bh(&nf_conntrack_lock); if (cda[CTA_TUPLE_ORIG]) - h = __nf_conntrack_find(net, zone, &otuple); + h = nf_conntrack_find_get(net, zone, &otuple); else if (cda[CTA_TUPLE_REPLY]) - h = __nf_conntrack_find(net, zone, &rtuple); + h = nf_conntrack_find_get(net, zone, &rtuple); if (h == NULL) { err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) { - struct nf_conn *ct; enum ip_conntrack_events events; ct = ctnetlink_create_conntrack(net, zone, cda, &otuple, &rtuple, u3); - if (IS_ERR(ct)) { - err = PTR_ERR(ct); - goto out_unlock; - } + if (IS_ERR(ct)) + return PTR_ERR(ct); + err = 0; - nf_conntrack_get(&ct->ct_general); - spin_unlock_bh(&nf_conntrack_lock); if (test_bit(IPS_EXPECTED_BIT, &ct->status)) events = IPCT_RELATED; else @@ -1545,23 +1537,19 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, ct, NETLINK_CB(skb).pid, nlmsg_report(nlh)); nf_ct_put(ct); - } else - spin_unlock_bh(&nf_conntrack_lock); + } return err; } /* implicit 'else' */ - /* We manipulate the conntrack inside the global conntrack table lock, - * so there's no need to increase the refcount */ err = -EEXIST; + ct = nf_ct_tuplehash_to_ctrack(h); if (!(nlh->nlmsg_flags & NLM_F_EXCL)) { - struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); - + spin_lock_bh(&nf_conntrack_lock); err = ctnetlink_change_conntrack(ct, cda); + spin_unlock_bh(&nf_conntrack_lock); if (err == 0) { - nf_conntrack_get(&ct->ct_general); - spin_unlock_bh(&nf_conntrack_lock); nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | @@ -1570,15 +1558,10 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, (1 << IPCT_MARK), ct, NETLINK_CB(skb).pid, nlmsg_report(nlh)); - nf_ct_put(ct); - } else - spin_unlock_bh(&nf_conntrack_lock); - - return err; + } } -out_unlock: - spin_unlock_bh(&nf_conntrack_lock); + nf_ct_put(ct); return err; } diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index b3a7db678b8d..ce60cf0f6c11 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -203,6 +203,27 @@ err: return status; } +#ifdef CONFIG_BRIDGE_NETFILTER +/* When called from bridge netfilter, skb->data must point to MAC header + * before calling skb_gso_segment(). Else, original MAC header is lost + * and segmented skbs will be sent to wrong destination. + */ +static void nf_bridge_adjust_skb_data(struct sk_buff *skb) +{ + if (skb->nf_bridge) + __skb_push(skb, skb->network_header - skb->mac_header); +} + +static void nf_bridge_adjust_segmented_data(struct sk_buff *skb) +{ + if (skb->nf_bridge) + __skb_pull(skb, skb->network_header - skb->mac_header); +} +#else +#define nf_bridge_adjust_skb_data(s) do {} while (0) +#define nf_bridge_adjust_segmented_data(s) do {} while (0) +#endif + int nf_queue(struct sk_buff *skb, struct list_head *elem, u_int8_t pf, unsigned int hook, @@ -212,7 +233,7 @@ int nf_queue(struct sk_buff *skb, unsigned int queuenum) { struct sk_buff *segs; - int err; + int err = -EINVAL; unsigned int queued; if (!skb_is_gso(skb)) @@ -228,23 +249,25 @@ int nf_queue(struct sk_buff *skb, break; } + nf_bridge_adjust_skb_data(skb); segs = skb_gso_segment(skb, 0); /* Does not use PTR_ERR to limit the number of error codes that can be * returned by nf_queue. For instance, callers rely on -ECANCELED to mean * 'ignore this hook'. */ if (IS_ERR(segs)) - return -EINVAL; - + goto out_err; queued = 0; err = 0; do { struct sk_buff *nskb = segs->next; segs->next = NULL; - if (err == 0) + if (err == 0) { + nf_bridge_adjust_segmented_data(segs); err = __nf_queue(segs, elem, pf, hook, indev, outdev, okfn, queuenum); + } if (err == 0) queued++; else @@ -252,11 +275,12 @@ int nf_queue(struct sk_buff *skb, segs = nskb; } while (segs); - /* also free orig skb if only some segments were queued */ - if (unlikely(err && queued)) - err = 0; - if (err == 0) + if (queued) { kfree_skb(skb); + return 0; + } + out_err: + nf_bridge_adjust_segmented_data(skb); return err; } diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 3aae66facf9f..4d5057902839 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -152,9 +152,10 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info) fl6.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) | (iph->flow_lbl[1] << 8) | iph->flow_lbl[2]; dst = ip6_route_output(net, NULL, &fl6); - if (dst == NULL) + if (dst->error) { + dst_release(dst); return false; - + } skb_dst_drop(skb); skb_dst_set(skb, dst); skb->dev = dst->dev; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2725d1bdf291..48badffaafc1 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 Nicira Networks. + * Copyright (c) 2007-2012 Nicira Networks. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -145,9 +145,16 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb, *addr, new_addr, 1); } else if (nh->protocol == IPPROTO_UDP) { - if (likely(transport_len >= sizeof(struct udphdr))) - inet_proto_csum_replace4(&udp_hdr(skb)->check, skb, - *addr, new_addr, 1); + if (likely(transport_len >= sizeof(struct udphdr))) { + struct udphdr *uh = udp_hdr(skb); + + if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { + inet_proto_csum_replace4(&uh->check, skb, + *addr, new_addr, 1); + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } + } } csum_replace4(&nh->check, *addr, new_addr); @@ -197,8 +204,22 @@ static void set_tp_port(struct sk_buff *skb, __be16 *port, skb->rxhash = 0; } -static int set_udp_port(struct sk_buff *skb, - const struct ovs_key_udp *udp_port_key) +static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port) +{ + struct udphdr *uh = udp_hdr(skb); + + if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) { + set_tp_port(skb, port, new_port, &uh->check); + + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } else { + *port = new_port; + skb->rxhash = 0; + } +} + +static int set_udp(struct sk_buff *skb, const struct ovs_key_udp *udp_port_key) { struct udphdr *uh; int err; @@ -210,16 +231,15 @@ static int set_udp_port(struct sk_buff *skb, uh = udp_hdr(skb); if (udp_port_key->udp_src != uh->source) - set_tp_port(skb, &uh->source, udp_port_key->udp_src, &uh->check); + set_udp_port(skb, &uh->source, udp_port_key->udp_src); if (udp_port_key->udp_dst != uh->dest) - set_tp_port(skb, &uh->dest, udp_port_key->udp_dst, &uh->check); + set_udp_port(skb, &uh->dest, udp_port_key->udp_dst); return 0; } -static int set_tcp_port(struct sk_buff *skb, - const struct ovs_key_tcp *tcp_port_key) +static int set_tcp(struct sk_buff *skb, const struct ovs_key_tcp *tcp_port_key) { struct tcphdr *th; int err; @@ -328,11 +348,11 @@ static int execute_set_action(struct sk_buff *skb, break; case OVS_KEY_ATTR_TCP: - err = set_tcp_port(skb, nla_data(nested_attr)); + err = set_tcp(skb, nla_data(nested_attr)); break; case OVS_KEY_ATTR_UDP: - err = set_udp_port(skb, nla_data(nested_attr)); + err = set_udp(skb, nla_data(nested_attr)); break; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index ce64c18b8c79..2c030505b335 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1521,6 +1521,9 @@ static struct vport *lookup_vport(struct ovs_header *ovs_header, vport = ovs_vport_locate(nla_data(a[OVS_VPORT_ATTR_NAME])); if (!vport) return ERR_PTR(-ENODEV); + if (ovs_header->dp_ifindex && + ovs_header->dp_ifindex != get_dpifindex(vport->dp)) + return ERR_PTR(-ENODEV); return vport; } else if (a[OVS_VPORT_ATTR_PORT_NO]) { u32 port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index e83d61ca78ca..5da548fa7ae9 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -501,9 +501,8 @@ tfifo_dequeue: /* if more time remaining? */ if (cb->time_to_send <= psched_get_time()) { - skb = qdisc_dequeue_tail(sch); - if (unlikely(!skb)) - goto qdisc_dequeue; + __skb_unlink(skb, &sch->q); + sch->qstats.backlog -= qdisc_pkt_len(skb); #ifdef CONFIG_NET_CLS_ACT /* @@ -539,7 +538,6 @@ deliver: qdisc_watchdog_schedule(&q->watchdog, cb->time_to_send); } -qdisc_dequeue: if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); if (skb) |