diff options
Diffstat (limited to 'net')
154 files changed, 1611 insertions, 1086 deletions
diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 798beac7f100..1e308f210928 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -178,27 +178,24 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, break; case 's':{ char **sptr = va_arg(ap, char **); - int16_t len; - int size; + uint16_t len; errcode = p9pdu_readf(pdu, proto_version, "w", &len); if (errcode) break; - size = max_t(int16_t, len, 0); - - *sptr = kmalloc(size + 1, GFP_KERNEL); + *sptr = kmalloc(len + 1, GFP_KERNEL); if (*sptr == NULL) { errcode = -EFAULT; break; } - if (pdu_read(pdu, *sptr, size)) { + if (pdu_read(pdu, *sptr, len)) { errcode = -EFAULT; kfree(*sptr); *sptr = NULL; } else - (*sptr)[size] = 0; + (*sptr)[len] = 0; } break; case 'Q':{ @@ -234,14 +231,14 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, } break; case 'D':{ - int32_t *count = va_arg(ap, int32_t *); + uint32_t *count = va_arg(ap, uint32_t *); void **data = va_arg(ap, void **); errcode = p9pdu_readf(pdu, proto_version, "d", count); if (!errcode) { *count = - min_t(int32_t, *count, + min_t(uint32_t, *count, pdu->size - pdu->offset); *data = &pdu->sdata[pdu->offset]; } @@ -404,9 +401,10 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, break; case 's':{ const char *sptr = va_arg(ap, const char *); - int16_t len = 0; + uint16_t len = 0; if (sptr) - len = min_t(int16_t, strlen(sptr), USHRT_MAX); + len = min_t(uint16_t, strlen(sptr), + USHRT_MAX); errcode = p9pdu_writef(pdu, proto_version, "w", len); @@ -438,7 +436,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, stbuf->n_gid, stbuf->n_muid); } break; case 'D':{ - int32_t count = va_arg(ap, int32_t); + uint32_t count = va_arg(ap, uint32_t); const void *data = va_arg(ap, const void *); errcode = p9pdu_writef(pdu, proto_version, "d", diff --git a/net/Kconfig b/net/Kconfig index ad0aafe903f8..72840626284b 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -253,7 +253,9 @@ config NET_TCPPROBE what was just said, you don't need it: say N. Documentation on how to use TCP connection probing can be found - at http://linux-net.osdl.org/index.php/TcpProbe + at: + + http://www.linuxfoundation.org/collaborate/workgroups/networking/tcpprobe To compile this code as a module, choose M here: the module will be called tcp_probe. diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index bb86d2932394..6da5daeebab7 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1392,7 +1392,7 @@ static int ax25_getname(struct socket *sock, struct sockaddr *uaddr, ax25_cb *ax25; int err = 0; - memset(fsa, 0, sizeof(fsa)); + memset(fsa, 0, sizeof(*fsa)); lock_sock(sk); ax25 = ax25_sk(sk); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index d4d9926c2201..65106fb61b8f 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -151,9 +151,9 @@ int debug_log(struct bat_priv *bat_priv, char *fmt, ...); } \ while (0) #else /* !CONFIG_BATMAN_ADV_DEBUG */ -static inline void bat_dbg(char type __attribute__((unused)), - struct bat_priv *bat_priv __attribute__((unused)), - char *fmt __attribute__((unused)), ...) +static inline void bat_dbg(char type __always_unused, + struct bat_priv *bat_priv __always_unused, + char *fmt __always_unused, ...) { } #endif diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index b49fdf70a6d5..2284e8129cb2 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -63,7 +63,7 @@ struct batman_packet { uint8_t num_hna; uint8_t gw_flags; /* flags related to gateway class */ uint8_t align; -} __attribute__((packed)); +} __packed; #define BAT_PACKET_LEN sizeof(struct batman_packet) @@ -76,7 +76,7 @@ struct icmp_packet { uint8_t orig[6]; uint16_t seqno; uint8_t uid; -} __attribute__((packed)); +} __packed; #define BAT_RR_LEN 16 @@ -93,14 +93,14 @@ struct icmp_packet_rr { uint8_t uid; uint8_t rr_cur; uint8_t rr[BAT_RR_LEN][ETH_ALEN]; -} __attribute__((packed)); +} __packed; struct unicast_packet { uint8_t packet_type; uint8_t version; /* batman version field */ uint8_t dest[6]; uint8_t ttl; -} __attribute__((packed)); +} __packed; struct unicast_frag_packet { uint8_t packet_type; @@ -110,7 +110,7 @@ struct unicast_frag_packet { uint8_t flags; uint8_t orig[6]; uint16_t seqno; -} __attribute__((packed)); +} __packed; struct bcast_packet { uint8_t packet_type; @@ -118,7 +118,7 @@ struct bcast_packet { uint8_t orig[6]; uint8_t ttl; uint32_t seqno; -} __attribute__((packed)); +} __packed; struct vis_packet { uint8_t packet_type; @@ -131,6 +131,6 @@ struct vis_packet { * neighbors */ uint8_t target_orig[6]; /* who should receive this packet */ uint8_t sender_orig[6]; /* who sent or rebroadcasted this packet */ -} __attribute__((packed)); +} __packed; #endif /* _NET_BATMAN_ADV_PACKET_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 97cb23dd3e69..bf3f6f5a12c4 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -246,13 +246,13 @@ struct vis_info { /* this packet might be part of the vis send queue. */ struct sk_buff *skb_packet; /* vis_info may follow here*/ -} __attribute__((packed)); +} __packed; struct vis_info_entry { uint8_t src[ETH_ALEN]; uint8_t dest[ETH_ALEN]; uint8_t quality; /* quality = 0 means HNA */ -} __attribute__((packed)); +} __packed; struct recvlist_node { struct list_head list; diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index dc2e28bed844..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) @@ -229,10 +234,12 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, if (!bat_priv->primary_if) goto dropped; - unicast_packet = (struct unicast_packet *) skb->data; + frag_skb = dev_alloc_skb(data_len - (data_len / 2) + ucf_hdr_len); + if (!frag_skb) + goto dropped; + unicast_packet = (struct unicast_packet *) skb->data; memcpy(&tmp_uc, unicast_packet, uc_hdr_len); - frag_skb = dev_alloc_skb(data_len - (data_len / 2) + ucf_hdr_len); skb_split(skb, frag_skb, data_len / 2); if (my_skb_head_push(skb, ucf_hdr_len - uc_hdr_len) < 0 || 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/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/caif_socket.c b/net/caif/caif_socket.c index 1bf0cf503796..8184c031d028 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -740,12 +740,12 @@ static int setsockopt(struct socket *sock, if (cf_sk->sk.sk_protocol != CAIFPROTO_UTIL) return -ENOPROTOOPT; lock_sock(&(cf_sk->sk)); - cf_sk->conn_req.param.size = ol; if (ol > sizeof(cf_sk->conn_req.param.data) || copy_from_user(&cf_sk->conn_req.param.data, ov, ol)) { release_sock(&cf_sk->sk); return -EINVAL; } + cf_sk->conn_req.param.size = ol; release_sock(&cf_sk->sk); return 0; diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index 21ede141018a..c665de778b60 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -191,6 +191,7 @@ int cfcnfg_disconn_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer) struct cflayer *servl = NULL; struct cfcnfg_phyinfo *phyinfo = NULL; u8 phyid = 0; + caif_assert(adap_layer != NULL); channel_id = adap_layer->id; if (adap_layer->dn == NULL || channel_id == 0) { @@ -199,16 +200,16 @@ int cfcnfg_disconn_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer) goto end; } servl = cfmuxl_remove_uplayer(cnfg->mux, channel_id); - if (servl == NULL) - goto end; - layer_set_up(servl, NULL); - ret = cfctrl_linkdown_req(cnfg->ctrl, channel_id, adap_layer); if (servl == NULL) { pr_err("PROTOCOL ERROR - Error removing service_layer Channel_Id(%d)", channel_id); ret = -EINVAL; goto end; } + layer_set_up(servl, NULL); + ret = cfctrl_linkdown_req(cnfg->ctrl, channel_id, adap_layer); + if (ret) + goto end; caif_assert(channel_id == servl->id); if (adap_layer->dn != NULL) { phyid = cfsrvl_getphyid(adap_layer->dn); diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 84a422c98941..6008d6dc18a0 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -76,6 +76,8 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) struct chnl_net *priv = container_of(layr, struct chnl_net, chnl); int pktlen; int err = 0; + const u8 *ip_version; + u8 buf; priv = container_of(layr, struct chnl_net, chnl); @@ -90,7 +92,21 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) * send the packet to the net stack. */ skb->dev = priv->netdev; - skb->protocol = htons(ETH_P_IP); + + /* check the version of IP */ + ip_version = skb_header_pointer(skb, 0, 1, &buf); + if (!ip_version) + return -EINVAL; + switch (*ip_version >> 4) { + case 4: + skb->protocol = htons(ETH_P_IP); + break; + case 6: + skb->protocol = htons(ETH_P_IPV6); + break; + default: + return -EINVAL; + } /* If we change the header in loop mode, the checksum is corrupted. */ if (priv->conn_req.protocol == CAIFPROTO_DATAGRAM_LOOP) @@ -378,9 +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); } @@ -437,6 +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/can/bcm.c b/net/can/bcm.c index 9d5e8accfab1..092dc88a7c64 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1256,6 +1256,9 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock, struct sockaddr_can *addr = (struct sockaddr_can *)msg->msg_name; + if (msg->msg_namelen < sizeof(*addr)) + return -EINVAL; + if (addr->can_family != AF_CAN) return -EINVAL; diff --git a/net/can/raw.c b/net/can/raw.c index e88f610fdb7b..883e9d74fddf 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -649,6 +649,9 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, struct sockaddr_can *addr = (struct sockaddr_can *)msg->msg_name; + if (msg->msg_namelen < sizeof(*addr)) + return -EINVAL; + if (addr->can_family != AF_CAN) return -EINVAL; diff --git a/net/ceph/ceph_hash.c b/net/ceph/ceph_hash.c index 815ef8826796..0a1b53bce76d 100644 --- a/net/ceph/ceph_hash.c +++ b/net/ceph/ceph_hash.c @@ -1,5 +1,6 @@ #include <linux/ceph/types.h> +#include <linux/module.h> /* * Robert Jenkin's hash function. @@ -104,6 +105,7 @@ unsigned ceph_str_hash(int type, const char *s, unsigned len) return -1; } } +EXPORT_SYMBOL(ceph_str_hash); const char *ceph_str_hash_name(int type) { @@ -116,3 +118,4 @@ const char *ceph_str_hash_name(int type) return "unknown"; } } +EXPORT_SYMBOL(ceph_str_hash_name); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index b6ff4a1519ab..05f357828a2f 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -96,7 +96,7 @@ struct workqueue_struct *ceph_msgr_wq; int ceph_msgr_init(void) { - ceph_msgr_wq = create_workqueue("ceph-msgr"); + ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_NON_REENTRANT, 0); if (!ceph_msgr_wq) { pr_err("msgr_init failed to create workqueue\n"); return -ENOMEM; @@ -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: @@ -1920,20 +1909,6 @@ bad_tag: /* * Atomically queue work on a connection. Bump @con reference to * avoid races with connection teardown. - * - * There is some trickery going on with QUEUED and BUSY because we - * only want a _single_ thread operating on each connection at any - * point in time, but we want to use all available CPUs. - * - * The worker thread only proceeds if it can atomically set BUSY. It - * clears QUEUED and does it's thing. When it thinks it's done, it - * clears BUSY, then rechecks QUEUED.. if it's set again, it loops - * (tries again to set BUSY). - * - * To queue work, we first set QUEUED, _then_ if BUSY isn't set, we - * try to queue work. If that fails (work is already queued, or BUSY) - * we give up (work also already being done or is queued) but leave QUEUED - * set so that the worker thread will loop if necessary. */ static void queue_con(struct ceph_connection *con) { @@ -1948,11 +1923,7 @@ static void queue_con(struct ceph_connection *con) return; } - set_bit(QUEUED, &con->state); - if (test_bit(BUSY, &con->state)) { - dout("queue_con %p - already BUSY\n", con); - con->ops->put(con); - } else if (!queue_work(ceph_msgr_wq, &con->work.work)) { + if (!queue_delayed_work(ceph_msgr_wq, &con->work, 0)) { dout("queue_con %p - already queued\n", con); con->ops->put(con); } else { @@ -1967,18 +1938,26 @@ static void con_work(struct work_struct *work) { struct ceph_connection *con = container_of(work, struct ceph_connection, work.work); - int backoff = 0; - -more: - if (test_and_set_bit(BUSY, &con->state) != 0) { - dout("con_work %p BUSY already set\n", con); - goto out; - } - dout("con_work %p start, clearing QUEUED\n", con); - clear_bit(QUEUED, &con->state); 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); @@ -1994,28 +1973,13 @@ more: try_read(con) < 0 || try_write(con) < 0) { mutex_unlock(&con->mutex); - backoff = 1; ceph_fault(con); /* error/fault path */ goto done_unlocked; } done: mutex_unlock(&con->mutex); - done_unlocked: - clear_bit(BUSY, &con->state); - dout("con->state=%lu\n", con->state); - if (test_bit(QUEUED, &con->state)) { - if (!backoff || test_bit(OPENING, &con->state)) { - dout("con_work %p QUEUED reset, looping\n", con); - goto more; - } - dout("con_work %p QUEUED reset, but just faulted\n", con); - clear_bit(QUEUED, &con->state); - } - dout("con_work %p done\n", con); - -out: con->ops->put(con); } @@ -2050,10 +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. */ @@ -2061,11 +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: @@ -2136,6 +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. */ @@ -2168,6 +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); } @@ -2233,6 +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/osdmap.c b/net/ceph/osdmap.c index d73f3f6efa36..71603ac3dff5 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -605,8 +605,10 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) goto bad; } err = __decode_pool(p, end, pi); - if (err < 0) + if (err < 0) { + kfree(pi); goto bad; + } __insert_pg_pool(&map->pg_pools, pi); } 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 a215269d2e35..8ae6631abcc2 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 * @@ -1279,10 +1280,13 @@ 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 +1328,7 @@ 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); @@ -1732,33 +1736,6 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); -static bool can_checksum_protocol(unsigned long features, __be16 protocol) -{ - return ((features & NETIF_F_NO_CSUM) || - ((features & NETIF_F_V4_CSUM) && - protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_V6_CSUM) && - protocol == htons(ETH_P_IPV6)) || - ((features & NETIF_F_FCOE_CRC) && - protocol == htons(ETH_P_FCOE))); -} - -static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) -{ - __be16 protocol = skb->protocol; - int features = dev->features; - - if (vlan_tx_tag_present(skb)) { - features &= dev->vlan_features; - } else if (protocol == htons(ETH_P_8021Q)) { - struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; - protocol = veh->h_vlan_encapsulated_proto; - features &= dev->vlan_features; - } - - return can_checksum_protocol(features, protocol); -} - /** * skb_dev_set -- assign a new device to a buffer * @skb: buffer for the new device @@ -1971,16 +1948,14 @@ static void dev_gso_skb_destructor(struct sk_buff *skb) /** * dev_gso_segment - Perform emulated hardware segmentation on skb. * @skb: buffer to segment + * @features: device features as applicable to this skb * * This function segments the given skb and stores the list of segments * in skb->next. */ -static int dev_gso_segment(struct sk_buff *skb) +static int dev_gso_segment(struct sk_buff *skb, int features) { - struct net_device *dev = skb->dev; struct sk_buff *segs; - int features = dev->features & ~(illegal_highdma(dev, skb) ? - NETIF_F_SG : 0); segs = skb_gso_segment(skb, features); @@ -2017,22 +1992,52 @@ static inline void skb_orphan_try(struct sk_buff *skb) } } -int netif_get_vlan_features(struct sk_buff *skb, struct net_device *dev) +static bool can_checksum_protocol(unsigned long features, __be16 protocol) +{ + return ((features & NETIF_F_GEN_CSUM) || + ((features & NETIF_F_V4_CSUM) && + protocol == htons(ETH_P_IP)) || + ((features & NETIF_F_V6_CSUM) && + protocol == htons(ETH_P_IPV6)) || + ((features & NETIF_F_FCOE_CRC) && + protocol == htons(ETH_P_FCOE))); +} + +static int harmonize_features(struct sk_buff *skb, __be16 protocol, int features) +{ + if (!can_checksum_protocol(features, protocol)) { + features &= ~NETIF_F_ALL_CSUM; + features &= ~NETIF_F_SG; + } else if (illegal_highdma(skb->dev, skb)) { + features &= ~NETIF_F_SG; + } + + return features; +} + +int netif_skb_features(struct sk_buff *skb) { __be16 protocol = skb->protocol; + int features = skb->dev->features; if (protocol == htons(ETH_P_8021Q)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; - } else if (!skb->vlan_tci) - return dev->features; + } else if (!vlan_tx_tag_present(skb)) { + return harmonize_features(skb, protocol, features); + } - if (protocol != htons(ETH_P_8021Q)) - return dev->features & dev->vlan_features; - else - return 0; + features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_TX); + + if (protocol != htons(ETH_P_8021Q)) { + return harmonize_features(skb, protocol, features); + } else { + features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | + NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_TX; + return harmonize_features(skb, protocol, features); + } } -EXPORT_SYMBOL(netif_get_vlan_features); +EXPORT_SYMBOL(netif_skb_features); /* * Returns true if either: @@ -2042,22 +2047,13 @@ EXPORT_SYMBOL(netif_get_vlan_features); * support DMA from it. */ static inline int skb_needs_linearize(struct sk_buff *skb, - struct net_device *dev) + int features) { - if (skb_is_nonlinear(skb)) { - int features = dev->features; - - if (vlan_tx_tag_present(skb)) - features &= dev->vlan_features; - - return (skb_has_frag_list(skb) && - !(features & NETIF_F_FRAGLIST)) || + return skb_is_nonlinear(skb) && + ((skb_has_frag_list(skb) && + !(features & NETIF_F_FRAGLIST)) || (skb_shinfo(skb)->nr_frags && - (!(features & NETIF_F_SG) || - illegal_highdma(dev, skb))); - } - - return 0; + !(features & NETIF_F_SG))); } int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, @@ -2067,6 +2063,8 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int rc = NETDEV_TX_OK; if (likely(!skb->next)) { + int features; + /* * If device doesnt need skb->dst, release it right now while * its hot in this cpu cache @@ -2079,8 +2077,10 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, skb_orphan_try(skb); + features = netif_skb_features(skb); + if (vlan_tx_tag_present(skb) && - !(dev->features & NETIF_F_HW_VLAN_TX)) { + !(features & NETIF_F_HW_VLAN_TX)) { skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb)); if (unlikely(!skb)) goto out; @@ -2088,13 +2088,13 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, skb->vlan_tci = 0; } - if (netif_needs_gso(dev, skb)) { - if (unlikely(dev_gso_segment(skb))) + if (netif_needs_gso(skb, features)) { + if (unlikely(dev_gso_segment(skb, features))) goto out_kfree_skb; if (skb->next) goto gso; } else { - if (skb_needs_linearize(skb, dev) && + if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto out_kfree_skb; @@ -2105,7 +2105,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_set_transport_header(skb, skb_checksum_start_offset(skb)); - if (!dev_can_checksum(dev, skb) && + if (!(features & NETIF_F_ALL_CSUM) && skb_checksum_help(skb)) goto out_kfree_skb; } @@ -2301,7 +2301,10 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, */ if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE)) skb_dst_force(skb); - __qdisc_update_bstats(q, skb->len); + + qdisc_skb_cb(skb)->pkt_len = skb->len; + qdisc_bstats_update(q, skb); + if (sch_direct_xmit(skb, q, dev, txq, root_lock)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -2563,7 +2566,8 @@ 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; @@ -3424,6 +3428,8 @@ 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; } @@ -5060,6 +5066,7 @@ 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) @@ -5524,34 +5531,6 @@ void netdev_run_todo(void) } } -/** - * dev_txq_stats_fold - fold tx_queues stats - * @dev: device to get statistics from - * @stats: struct rtnl_link_stats64 to hold results - */ -void dev_txq_stats_fold(const struct net_device *dev, - struct rtnl_link_stats64 *stats) -{ - u64 tx_bytes = 0, tx_packets = 0, tx_dropped = 0; - unsigned int i; - struct netdev_queue *txq; - - for (i = 0; i < dev->num_tx_queues; i++) { - txq = netdev_get_tx_queue(dev, i); - spin_lock_bh(&txq->_xmit_lock); - tx_bytes += txq->tx_bytes; - tx_packets += txq->tx_packets; - tx_dropped += txq->tx_dropped; - spin_unlock_bh(&txq->_xmit_lock); - } - if (tx_bytes || tx_packets || tx_dropped) { - stats->tx_bytes = tx_bytes; - stats->tx_packets = tx_packets; - stats->tx_dropped = tx_dropped; - } -} -EXPORT_SYMBOL(dev_txq_stats_fold); - /* Convert net_device_stats to rtnl_link_stats64. They have the same * fields in the same order, with only the type differing. */ @@ -5595,7 +5574,6 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); } else { netdev_stats_to_stats64(storage, &dev->stats); - dev_txq_stats_fold(dev, storage); } storage->rx_dropped += atomic_long_read(&dev->rx_dropped); return storage; @@ -5621,18 +5599,20 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) } /** - * alloc_netdev_mq - allocate network device + * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for * @name: device name format string * @setup: callback to initialize device - * @queue_count: the number of subqueues to allocate + * @txqs: the number of TX subqueues to allocate + * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use * and performs basic initialization. Also allocates subquue structs - * for each queue on the device at the end of the netdevice. + * for each queue on the device. */ -struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, - void (*setup)(struct net_device *), unsigned int queue_count) +struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, + void (*setup)(struct net_device *), + unsigned int txqs, unsigned int rxqs) { struct net_device *dev; size_t alloc_size; @@ -5640,12 +5620,20 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, BUG_ON(strlen(name) >= sizeof(dev->name)); - if (queue_count < 1) { + if (txqs < 1) { pr_err("alloc_netdev: Unable to allocate device " "with zero queues.\n"); return NULL; } +#ifdef CONFIG_RPS + if (rxqs < 1) { + pr_err("alloc_netdev: Unable to allocate device " + "with zero RX queues.\n"); + return NULL; + } +#endif + alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ @@ -5676,18 +5664,6 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); - dev->num_tx_queues = queue_count; - dev->real_num_tx_queues = queue_count; - if (netif_alloc_netdev_queues(dev)) - goto free_pcpu; - -#ifdef CONFIG_RPS - dev->num_rx_queues = queue_count; - dev->real_num_rx_queues = queue_count; - if (netif_alloc_rx_queues(dev)) - goto free_pcpu; -#endif - dev->gso_max_size = GSO_MAX_SIZE; INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); @@ -5697,9 +5673,26 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, 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_all; + +#ifdef CONFIG_RPS + dev->num_rx_queues = rxqs; + dev->real_num_rx_queues = rxqs; + if (netif_alloc_rx_queues(dev)) + goto free_all; +#endif + strcpy(dev->name, name); return dev; +free_all: + free_netdev(dev); + return NULL; + free_pcpu: free_percpu(dev->pcpu_refcnt); kfree(dev->_tx); @@ -5711,7 +5704,7 @@ free_p: kfree(p); return NULL; } -EXPORT_SYMBOL(alloc_netdev_mq); +EXPORT_SYMBOL(alloc_netdev_mqs); /** * free_netdev - free network device @@ -6209,7 +6202,7 @@ static void __net_exit default_device_exit(struct net *net) static void __net_exit default_device_exit_batch(struct list_head *net_list) { /* At exit all network devices most be removed from a network - * namespace. Do this in the reverse order of registeration. + * namespace. Do this in the reverse order of registration. * Do this across as many network namespaces as possible to * improve batching efficiency. */ @@ -6227,6 +6220,7 @@ 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/filter.c b/net/core/filter.c index 2b27d4efdd48..afc58374ca96 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -158,7 +158,7 @@ EXPORT_SYMBOL(sk_filter); /** * sk_run_filter - run a filter on a socket * @skb: buffer to run the filter on - * @filter: filter to apply + * @fentry: filter to apply * * Decode and apply filter instructions to the skb->data. * Return length to keep, 0 for none. @skb is the data we are 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/skbuff.c b/net/core/skbuff.c index 19d6c21220fd..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; @@ -380,6 +381,8 @@ static void skb_release_head_state(struct sk_buff *skb) } #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb->nfct); +#endif +#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED nf_conntrack_put_reasm(skb->nfct_reasm); #endif #ifdef CONFIG_BRIDGE_NETFILTER @@ -2742,8 +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/core/sock.c b/net/core/sock.c index a658aeb6d554..7dfed792434d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -157,7 +157,7 @@ static const char *const af_family_key_strings[AF_MAX+1] = { "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" , "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , - "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , + "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , "sk_lock-AF_MAX" }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { @@ -173,7 +173,7 @@ static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-27" , "slock-28" , "slock-AF_CAN" , "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , - "slock-AF_IEEE802154", "slock-AF_CAIF" , + "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , "slock-AF_MAX" }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { @@ -189,7 +189,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-27" , "clock-28" , "clock-AF_CAN" , "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , - "clock-AF_IEEE802154", "clock-AF_CAIF" , + "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , "clock-AF_MAX" }; 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/Kconfig b/net/dccp/Kconfig index ad6dffd9070e..b75968a04017 100644 --- a/net/dccp/Kconfig +++ b/net/dccp/Kconfig @@ -49,7 +49,9 @@ config NET_DCCPPROBE what was just said, you don't need it: say N. Documentation on how to use DCCP connection probing can be found - at http://linux-net.osdl.org/index.php/DccpProbe + at: + + http://www.linuxfoundation.org/collaborate/workgroups/networking/dccpprobe To compile this code as a module, choose M here: the module will be called dccp_probe. diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 45087052d894..5fdb07229017 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -426,7 +426,8 @@ static inline void dccp_update_gsr(struct sock *sk, u64 seq) { struct dccp_sock *dp = dccp_sk(sk); - dp->dccps_gsr = seq; + if (after48(seq, dp->dccps_gsr)) + dp->dccps_gsr = seq; /* Sequence validity window depends on remote Sequence Window (7.5.1) */ dp->dccps_swl = SUB48(ADD48(dp->dccps_gsr, 1), dp->dccps_r_seq_win / 4); /* diff --git a/net/dccp/input.c b/net/dccp/input.c index 15af247ea007..4222e7a654b0 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -260,7 +260,7 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) */ if (time_before(now, (dp->dccps_rate_last + sysctl_dccp_sync_ratelimit))) - return 0; + return -1; DCCP_WARN("Step 6 failed for %s packet, " "(LSWL(%llu) <= P.seqno(%llu) <= S.SWH(%llu)) and " @@ -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/dccp/sysctl.c b/net/dccp/sysctl.c index 563943822e58..42348824ee31 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -21,7 +21,8 @@ /* Boundary values */ static int zero = 0, u8_max = 0xFF; -static unsigned long seqw_min = 32; +static unsigned long seqw_min = DCCPF_SEQ_WMIN, + seqw_max = 0xFFFFFFFF; /* maximum on 32 bit */ static struct ctl_table dccp_default_table[] = { { @@ -31,6 +32,7 @@ static struct ctl_table dccp_default_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &seqw_min, /* RFC 4340, 7.5.2 */ + .extra2 = &seqw_max, }, { .procname = "rx_ccid", diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 0ba15633c418..0dcaa903e00e 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -1130,7 +1130,7 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) /* * This processes a device up event. We only start up * the loopback device & ethernet devices with correct - * MAC addreses automatically. Others must be started + * MAC addresses automatically. Others must be started * specifically. * * FIXME: How should we configure the loopback address ? If we could dispense 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/dsa/dsa.c b/net/dsa/dsa.c index 0c877a74e1f4..3fb14b7c13cf 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -428,7 +428,7 @@ static void __exit dsa_cleanup_module(void) } module_exit(dsa_cleanup_module); -MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>") +MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>"); MODULE_DESCRIPTION("Driver for Distributed Switch Architecture switch chips"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:dsa"); 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/ethernet/eth.c b/net/ethernet/eth.c index f00ef2f1d814..44d2b42fda56 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -347,10 +347,11 @@ void ether_setup(struct net_device *dev) EXPORT_SYMBOL(ether_setup); /** - * alloc_etherdev_mq - Allocates and sets up an Ethernet device + * alloc_etherdev_mqs - Allocates and sets up an Ethernet device * @sizeof_priv: Size of additional driver-private structure to be allocated * for this Ethernet device - * @queue_count: The number of queues this device has. + * @txqs: The number of TX queues this device has. + * @rxqs: The number of RX queues this device has. * * Fill in the fields of the device structure with Ethernet-generic * values. Basically does everything except registering the device. @@ -360,11 +361,12 @@ EXPORT_SYMBOL(ether_setup); * this private data area. */ -struct net_device *alloc_etherdev_mq(int sizeof_priv, unsigned int queue_count) +struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, + unsigned int rxqs) { - return alloc_netdev_mq(sizeof_priv, "eth%d", ether_setup, queue_count); + return alloc_netdev_mqs(sizeof_priv, "eth%d", ether_setup, txqs, rxqs); } -EXPORT_SYMBOL(alloc_etherdev_mq); +EXPORT_SYMBOL(alloc_etherdev_mqs); static size_t _format_mac_addr(char *buf, int buflen, const unsigned char *addr, int len) diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 9e95d7fb6d5a..a5a1050595d1 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -432,7 +432,9 @@ config INET_DIAG ---help--- Support for INET (TCP, DCCP, etc) socket monitoring interface used by native Linux tools such as ss. ss is included in iproute2, currently - downloadable at <http://linux-net.osdl.org/index.php/Iproute2>. + downloadable at: + + http://www.linuxfoundation.org/collaborate/workgroups/networking/iproute2 If unsure, say Y. 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/ah4.c b/net/ipv4/ah4.c index 880a5ec6dce0..86961bec70ab 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -314,14 +314,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb->ip_summed = CHECKSUM_NONE; - ah = (struct ip_auth_hdr *)skb->data; - iph = ip_hdr(skb); - ihl = ip_hdrlen(skb); if ((err = skb_cow_data(skb, 0, &trailer)) < 0) goto out; nfrags = err; + ah = (struct ip_auth_hdr *)skb->data; + iph = ip_hdr(skb); + ihl = ip_hdrlen(skb); + work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len); if (!work_iph) goto out; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index a2fc7b961dbc..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) { @@ -1143,6 +1142,23 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) return err; } +int arp_invalidate(struct net_device *dev, __be32 ip) +{ + struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev); + int err = -ENXIO; + + if (neigh) { + if (neigh->nud_state & ~NUD_NOARP) + err = neigh_update(neigh, NULL, NUD_FAILED, + NEIGH_UPDATE_F_OVERRIDE| + NEIGH_UPDATE_F_ADMIN); + neigh_release(neigh); + } + + return err; +} +EXPORT_SYMBOL(arp_invalidate); + static int arp_req_delete_public(struct net *net, struct arpreq *r, struct net_device *dev) { @@ -1163,7 +1179,6 @@ static int arp_req_delete(struct net *net, struct arpreq *r, { int err; __be32 ip; - struct neighbour *neigh; if (r->arp_flags & ATF_PUBL) return arp_req_delete_public(net, r, dev); @@ -1181,16 +1196,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r, if (!dev) return -EINVAL; } - err = -ENXIO; - neigh = neigh_lookup(&arp_tbl, &ip, dev); - if (neigh) { - if (neigh->nud_state & ~NUD_NOARP) - err = neigh_update(neigh, NULL, NUD_FAILED, - NEIGH_UPDATE_F_OVERRIDE| - NEIGH_UPDATE_F_ADMIN); - neigh_release(neigh); - } - return err; + return arp_invalidate(dev, ip); } /* @@ -1226,10 +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; @@ -1256,7 +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..df4616fce929 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -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_address, dev, + ifa->ifa_address, 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_connection_sock.c b/net/ipv4/inet_connection_sock.c index 25e318153f14..97e5fb765265 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -73,7 +73,7 @@ int inet_csk_bind_conflict(const struct sock *sk, !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { if (!reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) { + ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) { const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) || sk2_rcv_saddr == sk_rcv_saddr(sk)) @@ -122,7 +122,8 @@ again: (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; smallest_rover = rover; - if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) { + if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 && + !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) { spin_unlock(&head->lock); snum = smallest_rover; goto have_snum; 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..6613edfac28c 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)) { 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/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 3fac340a28d5..e855fffaed95 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -710,42 +710,25 @@ static void get_counters(const struct xt_table_info *t, struct arpt_entry *iter; unsigned int cpu; unsigned int i; - unsigned int curcpu = get_cpu(); - - /* Instead of clearing (by a previous call to memset()) - * the counters and using adds, we set the counters - * with data used by 'current' CPU - * - * Bottom half has to be disabled to prevent deadlock - * if new softirq were to run and call ipt_do_table - */ - local_bh_disable(); - i = 0; - xt_entry_foreach(iter, t->entries[curcpu], t->size) { - SET_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); - ++i; - } - local_bh_enable(); - /* Processing counters from other cpus, we can let bottom half enabled, - * (preemption is disabled) - */ for_each_possible_cpu(cpu) { - if (cpu == curcpu) - continue; + seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock; + i = 0; - local_bh_disable(); - xt_info_wrlock(cpu); xt_entry_foreach(iter, t->entries[cpu], t->size) { - ADD_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); + u64 bcnt, pcnt; + unsigned int start; + + do { + start = read_seqbegin(lock); + bcnt = iter->counters.bcnt; + pcnt = iter->counters.pcnt; + } while (read_seqretry(lock, start)); + + ADD_COUNTER(counters[i], bcnt, pcnt); ++i; } - xt_info_wrunlock(cpu); - local_bh_enable(); } - put_cpu(); } static struct xt_counters *alloc_counters(const struct xt_table *table) @@ -759,7 +742,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) * about). */ countersize = sizeof(struct xt_counters) * private->number; - counters = vmalloc(countersize); + counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); @@ -1007,7 +990,7 @@ static int __do_replace(struct net *net, const char *name, struct arpt_entry *iter; ret = 0; - counters = vmalloc(num_counters * sizeof(struct xt_counters)); + counters = vzalloc(num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; goto out; 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/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index a846d633b3b6..652efea013dc 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -884,42 +884,25 @@ get_counters(const struct xt_table_info *t, struct ipt_entry *iter; unsigned int cpu; unsigned int i; - unsigned int curcpu = get_cpu(); - - /* Instead of clearing (by a previous call to memset()) - * the counters and using adds, we set the counters - * with data used by 'current' CPU. - * - * Bottom half has to be disabled to prevent deadlock - * if new softirq were to run and call ipt_do_table - */ - local_bh_disable(); - i = 0; - xt_entry_foreach(iter, t->entries[curcpu], t->size) { - SET_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); - ++i; - } - local_bh_enable(); - /* Processing counters from other cpus, we can let bottom half enabled, - * (preemption is disabled) - */ for_each_possible_cpu(cpu) { - if (cpu == curcpu) - continue; + seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock; + i = 0; - local_bh_disable(); - xt_info_wrlock(cpu); xt_entry_foreach(iter, t->entries[cpu], t->size) { - ADD_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); + u64 bcnt, pcnt; + unsigned int start; + + do { + start = read_seqbegin(lock); + bcnt = iter->counters.bcnt; + pcnt = iter->counters.pcnt; + } while (read_seqretry(lock, start)); + + ADD_COUNTER(counters[i], bcnt, pcnt); ++i; /* macro does multi eval of i */ } - xt_info_wrunlock(cpu); - local_bh_enable(); } - put_cpu(); } static struct xt_counters *alloc_counters(const struct xt_table *table) @@ -932,7 +915,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; - counters = vmalloc(countersize); + counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); @@ -1203,7 +1186,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct ipt_entry *iter; ret = 0; - counters = vmalloc(num_counters * sizeof(struct xt_counters)); + counters = vzalloc(num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; goto out; 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 dc7c096ddfef..dfa5beb0c1c8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1350,7 +1350,7 @@ static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, return 0; } -/* Intialize TSO state of a skb. +/* Initialize TSO state of a skb. * This must be invoked the first time we consider transmitting * SKB onto the wire. */ @@ -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 5b189c97c2fc..fd6782e3a038 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -420,9 +420,6 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) dev->type == ARPHRD_TUNNEL6 || dev->type == ARPHRD_SIT || dev->type == ARPHRD_NONE) { - printk(KERN_INFO - "%s: Disabled Privacy Extensions\n", - dev->name); ndev->cnf.use_tempaddr = -1; } else { in6_dev_hold(ndev); @@ -2664,14 +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) @@ -2692,6 +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 */ @@ -2725,52 +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); @@ -4159,8 +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/af_inet6.c b/net/ipv6/af_inet6.c index 059a3de647db..978e80e2c4a8 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -300,7 +300,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - /* Reproduce AF_INET checks to make the bindings consitant */ + /* Reproduce AF_INET checks to make the bindings consistent */ v4addr = addr->sin6_addr.s6_addr32[3]; chk_addr_ret = inet_addr_type(net, v4addr); if (!sysctl_ip_nonlocal_bind && diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index ee82d4ef26ce..1aba54ae53c4 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -538,14 +538,16 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, ah_hlen)) goto out; - ip6h = ipv6_hdr(skb); - - skb_push(skb, hdr_len); if ((err = skb_cow_data(skb, 0, &trailer)) < 0) goto out; nfrags = err; + ah = (struct ip_auth_hdr *)skb->data; + ip6h = ipv6_hdr(skb); + + skb_push(skb, hdr_len); + work_iph = ah_alloc_tmp(ahash, nfrags, hdr_len + ahp->icv_trunc_len); if (!work_iph) goto out; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index e46305d1815a..d144e629d2b4 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -44,7 +44,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if) && (!sk->sk_reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) && + ((1 << sk2->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) && ipv6_rcv_saddr_equal(sk, sk2)) break; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 94b5bf132b2e..5f8d242be3f3 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -401,6 +401,9 @@ int ip6_forward(struct sk_buff *skb) goto drop; } + if (skb->pkt_type != PACKET_HOST) + goto drop; + skb_forward_csum(skb); /* 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/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 455582384ece..7d227c644f72 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -897,42 +897,25 @@ get_counters(const struct xt_table_info *t, struct ip6t_entry *iter; unsigned int cpu; unsigned int i; - unsigned int curcpu = get_cpu(); - - /* Instead of clearing (by a previous call to memset()) - * the counters and using adds, we set the counters - * with data used by 'current' CPU - * - * Bottom half has to be disabled to prevent deadlock - * if new softirq were to run and call ipt_do_table - */ - local_bh_disable(); - i = 0; - xt_entry_foreach(iter, t->entries[curcpu], t->size) { - SET_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); - ++i; - } - local_bh_enable(); - /* Processing counters from other cpus, we can let bottom half enabled, - * (preemption is disabled) - */ for_each_possible_cpu(cpu) { - if (cpu == curcpu) - continue; + seqlock_t *lock = &per_cpu(xt_info_locks, cpu).lock; + i = 0; - local_bh_disable(); - xt_info_wrlock(cpu); xt_entry_foreach(iter, t->entries[cpu], t->size) { - ADD_COUNTER(counters[i], iter->counters.bcnt, - iter->counters.pcnt); + u64 bcnt, pcnt; + unsigned int start; + + do { + start = read_seqbegin(lock); + bcnt = iter->counters.bcnt; + pcnt = iter->counters.pcnt; + } while (read_seqretry(lock, start)); + + ADD_COUNTER(counters[i], bcnt, pcnt); ++i; } - xt_info_wrunlock(cpu); - local_bh_enable(); } - put_cpu(); } static struct xt_counters *alloc_counters(const struct xt_table *table) @@ -945,7 +928,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; - counters = vmalloc(countersize); + counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); @@ -1216,7 +1199,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct ip6t_entry *iter; ret = 0; - counters = vmalloc(num_counters * sizeof(struct xt_counters)); + counters = vzalloc(num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; goto out; 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/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index 99abfb53bab9..97c5b21b9674 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -19,13 +19,15 @@ #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_core.h> -#include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#endif +#include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, @@ -33,8 +35,10 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, { u16 zone = NF_CT_DEFAULT_ZONE; +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) if (skb->nfct) zone = nf_ct_zone((struct nf_conn *)skb->nfct); +#endif #ifdef CONFIG_BRIDGE_NETFILTER if (skb->nf_bridge && @@ -56,9 +60,11 @@ static unsigned int ipv6_defrag(unsigned int hooknum, { struct sk_buff *reasm; +#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) /* Previously seen (loopback)? */ if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct)) return NF_ACCEPT; +#endif reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); /* queued */ 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..904312e25a3c 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 +739,8 @@ 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 nrt = rt6_alloc_clone(rt, &fl->fl6_dst); -#else - goto out2; -#endif - } dst_release(&rt->dst); rt = nrt ? : net->ipv6.ip6_null_entry; @@ -2561,14 +2557,16 @@ 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 +2653,7 @@ 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/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/Kconfig b/net/mac80211/Kconfig index 9109262abd24..c766056d0488 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -20,7 +20,7 @@ config MAC80211_HAS_RC def_bool n config MAC80211_RC_PID - bool "PID controller based rate control algorithm" if EMBEDDED + bool "PID controller based rate control algorithm" if EXPERT select MAC80211_HAS_RC ---help--- This option enables a TX rate control algorithm for @@ -28,14 +28,14 @@ config MAC80211_RC_PID rate. config MAC80211_RC_MINSTREL - bool "Minstrel" if EMBEDDED + bool "Minstrel" if EXPERT select MAC80211_HAS_RC default y ---help--- This option enables the 'minstrel' TX rate control algorithm config MAC80211_RC_MINSTREL_HT - bool "Minstrel 802.11n support" if EMBEDDED + bool "Minstrel 802.11n support" if EXPERT depends on MAC80211_RC_MINSTREL default y ---help--- diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index f138b195d657..227ca82eef72 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -185,8 +185,6 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, struct ieee80211_mgmt *mgmt, size_t len) { - struct ieee80211_hw *hw = &local->hw; - struct ieee80211_conf *conf = &hw->conf; struct tid_ampdu_rx *tid_agg_rx; u16 capab, tid, timeout, ba_policy, buf_size, start_seq_num, status; u8 dialog_token; @@ -231,13 +229,8 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, goto end_no_lock; } /* determine default buffer size */ - if (buf_size == 0) { - struct ieee80211_supported_band *sband; - - sband = local->hw.wiphy->bands[conf->channel->band]; - buf_size = IEEE80211_MIN_AMPDU_BUF; - buf_size = buf_size << sband->ht_cap.ampdu_factor; - } + if (buf_size == 0) + buf_size = IEEE80211_MAX_AMPDU_BUF; /* examine state machine */ 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/main.c b/net/mac80211/main.c index 485d36bc9a46..a46ff06d7cb8 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -39,6 +39,8 @@ module_param(ieee80211_disable_40mhz_24ghz, bool, 0644); MODULE_PARM_DESC(ieee80211_disable_40mhz_24ghz, "Disable 40MHz support in the 2.4GHz band"); +static struct lock_class_key ieee80211_rx_skb_queue_class; + void ieee80211_configure_filter(struct ieee80211_local *local) { u64 mc; @@ -569,7 +571,15 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, spin_lock_init(&local->filter_lock); spin_lock_init(&local->queue_stop_reason_lock); - skb_queue_head_init(&local->rx_skb_queue); + /* + * The rx_skb_queue is only accessed from tasklets, + * but other SKB queues are used from within IRQ + * context. Therefore, this one needs a different + * locking class so our direct, non-irq-safe use of + * the queue's lock doesn't throw lockdep warnings. + */ + skb_queue_head_init_class(&local->rx_skb_queue, + &ieee80211_rx_skb_queue_class); INIT_DELAYED_WORK(&local->scan_work, ieee80211_scan_work); 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 0cdba50c0d69..eead9db6f899 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -645,30 +645,29 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; - rcu_read_lock(); + spin_lock_bh(&nf_conntrack_lock); last = (struct nf_conn *)cb->args[1]; for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) { restart: - hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[cb->args[0]], + hlist_nulls_for_each_entry(h, n, &net->ct.hash[cb->args[0]], hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; ct = nf_ct_tuplehash_to_ctrack(h); - if (!atomic_inc_not_zero(&ct->ct_general.use)) - continue; /* Dump entries of a given L3 protocol number. * If it is not specified, ie. l3proto == 0, * then dump everything. */ if (l3proto && nf_ct_l3num(ct) != l3proto) - goto releasect; + continue; if (cb->args[1]) { if (ct != last) - goto releasect; + continue; cb->args[1] = 0; } 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; } @@ -681,8 +680,6 @@ restart: if (acct) memset(acct, 0, sizeof(struct nf_conn_counter[IP_CT_DIR_MAX])); } -releasect: - nf_ct_put(ct); } if (cb->args[1]) { cb->args[1] = 0; @@ -690,7 +687,7 @@ releasect: } } out: - rcu_read_unlock(); + spin_unlock_bh(&nf_conntrack_lock); if (last) nf_ct_put(last); @@ -976,7 +973,8 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, free: kfree_skb(skb2); out: - return err; + /* this avoids a loop in nfnetlink. */ + return err == -EAGAIN ? -ENOBUFS : err; } #ifdef CONFIG_NF_NAT_NEEDED 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/x_tables.c b/net/netfilter/x_tables.c index 80463507420e..c94237631077 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1325,7 +1325,8 @@ static int __init xt_init(void) for_each_possible_cpu(i) { struct xt_info_lock *lock = &per_cpu(xt_info_locks, i); - spin_lock_init(&lock->lock); + + seqlock_init(&lock->lock); lock->readers = 0; } 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/phonet/af_phonet.c b/net/phonet/af_phonet.c index fd95beb72f5d..1072b2c19d31 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -37,7 +37,7 @@ /* Transport protocol registration */ static struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly; -static struct phonet_protocol *phonet_proto_get(int protocol) +static struct phonet_protocol *phonet_proto_get(unsigned int protocol) { struct phonet_protocol *pp; @@ -458,7 +458,7 @@ static struct packet_type phonet_packet_type __read_mostly = { static DEFINE_MUTEX(proto_tab_lock); -int __init_or_module phonet_proto_register(int protocol, +int __init_or_module phonet_proto_register(unsigned int protocol, struct phonet_protocol *pp) { int err = 0; @@ -481,7 +481,7 @@ int __init_or_module phonet_proto_register(int protocol, } EXPORT_SYMBOL(phonet_proto_register); -void phonet_proto_unregister(int protocol, struct phonet_protocol *pp) +void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp) { mutex_lock(&proto_tab_lock); BUG_ON(proto_tab[protocol] != pp); diff --git a/net/rfkill/Kconfig b/net/rfkill/Kconfig index eaf765876458..7fce6dfd2180 100644 --- a/net/rfkill/Kconfig +++ b/net/rfkill/Kconfig @@ -18,7 +18,7 @@ config RFKILL_LEDS default y config RFKILL_INPUT - bool "RF switch input support" if EMBEDDED + bool "RF switch input support" if EXPERT depends on RFKILL depends on INPUT = y || RFKILL = INPUT - default y if !EMBEDDED + default y if !EXPERT diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 0b9bb2085ce4..74c064c0dfdd 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -808,7 +808,7 @@ static int __init af_rxrpc_init(void) goto error_call_jar; } - rxrpc_workqueue = create_workqueue("krxrpcd"); + rxrpc_workqueue = alloc_workqueue("krxrpcd", 0, 1); if (!rxrpc_workqueue) { printk(KERN_NOTICE "RxRPC: Failed to allocate work queue\n"); goto error_work_queue; 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/Kconfig b/net/sched/Kconfig index a36270a994d7..f04d4a484d53 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -24,7 +24,7 @@ menuconfig NET_SCHED To administer these schedulers, you'll need the user-level utilities from the package iproute2+tc at <ftp://ftp.tux.org/pub/net/ip-routing/>. That package also contains some documentation; for more, check out - <http://linux-net.osdl.org/index.php/Iproute2>. + <http://www.linuxfoundation.org/collaborate/workgroups/networking/iproute2>. This Quality of Service (QoS) support will enable you to use Differentiated Services (diffserv) and Resource Reservation Protocol diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 67dc7ce9b63a..83ddfc07e45d 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -508,8 +508,7 @@ static int tcf_csum(struct sk_buff *skb, spin_lock(&p->tcf_lock); p->tcf_tm.lastuse = jiffies; - p->tcf_bstats.bytes += qdisc_pkt_len(skb); - p->tcf_bstats.packets++; + bstats_update(&p->tcf_bstats, skb); action = p->tcf_action; update_flags = p->update_flags; spin_unlock(&p->tcf_lock); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 8daef9632255..c2a7c20e81c1 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -209,8 +209,7 @@ static int tcf_ipt(struct sk_buff *skb, struct tc_action *a, spin_lock(&ipt->tcf_lock); ipt->tcf_tm.lastuse = jiffies; - ipt->tcf_bstats.bytes += qdisc_pkt_len(skb); - ipt->tcf_bstats.packets++; + bstats_update(&ipt->tcf_bstats, skb); /* yes, we have to worry about both in and out dev worry later - danger - this API seems to have changed diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 0c311be92827..d765067e99db 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -165,8 +165,7 @@ static int tcf_mirred(struct sk_buff *skb, struct tc_action *a, spin_lock(&m->tcf_lock); m->tcf_tm.lastuse = jiffies; - m->tcf_bstats.bytes += qdisc_pkt_len(skb); - m->tcf_bstats.packets++; + bstats_update(&m->tcf_bstats, skb); dev = m->tcfm_dev; if (!dev) { diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 186eb837e600..178a4bd7b7cb 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -125,8 +125,7 @@ static int tcf_nat(struct sk_buff *skb, struct tc_action *a, egress = p->flags & TCA_NAT_FLAG_EGRESS; action = p->tcf_action; - p->tcf_bstats.bytes += qdisc_pkt_len(skb); - p->tcf_bstats.packets++; + bstats_update(&p->tcf_bstats, skb); spin_unlock(&p->tcf_lock); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index a0593c9640db..445bef716f77 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -187,8 +187,7 @@ static int tcf_pedit(struct sk_buff *skb, struct tc_action *a, bad: p->tcf_qstats.overlimits++; done: - p->tcf_bstats.bytes += qdisc_pkt_len(skb); - p->tcf_bstats.packets++; + bstats_update(&p->tcf_bstats, skb); spin_unlock(&p->tcf_lock); return p->tcf_action; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 7ebf7439b478..e2f08b1e2e58 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -298,8 +298,7 @@ static int tcf_act_police(struct sk_buff *skb, struct tc_action *a, spin_lock(&police->tcf_lock); - police->tcf_bstats.bytes += qdisc_pkt_len(skb); - police->tcf_bstats.packets++; + bstats_update(&police->tcf_bstats, skb); if (police->tcfp_ewma_rate && police->tcf_rate_est.bps >= police->tcfp_ewma_rate) { diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 97e84f3ee775..7287cff7af3e 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -42,8 +42,7 @@ static int tcf_simp(struct sk_buff *skb, struct tc_action *a, struct tcf_result spin_lock(&d->tcf_lock); d->tcf_tm.lastuse = jiffies; - d->tcf_bstats.bytes += qdisc_pkt_len(skb); - d->tcf_bstats.packets++; + bstats_update(&d->tcf_bstats, skb); /* print policy string followed by _ then packet count * Example if this was the 3rd packet and the string was "hello" diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 66cbf4eb8855..836f5fee9e58 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -46,8 +46,7 @@ static int tcf_skbedit(struct sk_buff *skb, struct tc_action *a, spin_lock(&d->tcf_lock); d->tcf_tm.lastuse = jiffies; - d->tcf_bstats.bytes += qdisc_pkt_len(skb); - d->tcf_bstats.packets++; + bstats_update(&d->tcf_bstats, skb); if (d->flags & SKBEDIT_F_PRIORITY) skb->priority = d->priority; diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 282540778aa8..943d733409d0 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -422,10 +422,8 @@ drop: __maybe_unused } return ret; } - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; - flow->bstats.bytes += qdisc_pkt_len(skb); - flow->bstats.packets++; + qdisc_bstats_update(sch, skb); + bstats_update(&flow->bstats, skb); /* * Okay, this may seem weird. We pretend we've dropped the packet if * it goes via ATM. The reason for this is that the outer qdisc diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index eb7631590865..5f63ec58942c 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -390,8 +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++; - sch->bstats.packets++; - sch->bstats.bytes += qdisc_pkt_len(skb); cbq_mark_toplevel(q, cl); if (!cl->next_alive) cbq_activate_class(cl); @@ -650,8 +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++; - sch->bstats.packets++; - sch->bstats.bytes += qdisc_pkt_len(skb); if (!cl->next_alive) cbq_activate_class(cl); return 0; @@ -973,6 +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 aa8b5313f8cf..6b7fe4a84f13 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -351,7 +351,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl; - unsigned int len; int err; cl = drr_classify(skb, sch, &err); @@ -362,7 +361,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch) return err; } - len = qdisc_pkt_len(skb); err = qdisc_enqueue(skb, cl->qdisc); if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { @@ -377,10 +375,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch) cl->deficit = cl->quantum; } - cl->bstats.packets++; - cl->bstats.bytes += len; - sch->bstats.packets++; - sch->bstats.bytes += len; + bstats_update(&cl->bstats, skb); sch->q.qlen++; return err; @@ -407,6 +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 1d295d62bb5c..0f7bf3fdfea5 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -260,8 +260,6 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) return err; } - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; sch->q.qlen++; return NET_XMIT_SUCCESS; @@ -284,6 +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 069c62b7bb36..14a799de1c35 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1599,10 +1599,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (cl->qdisc->q.qlen == 1) set_active(cl, qdisc_pkt_len(skb)); - cl->bstats.packets++; - cl->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; - sch->bstats.bytes += qdisc_pkt_len(skb); + bstats_update(&cl->bstats, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; @@ -1668,6 +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 01b519d6c52d..fc12fe6f5597 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -569,15 +569,11 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) } return ret; } else { - cl->bstats.packets += - skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1; - cl->bstats.bytes += qdisc_pkt_len(skb); + bstats_update(&cl->bstats, skb); htb_activate(q, cl); } sch->q.qlen++; - sch->bstats.packets += skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1; - sch->bstats.bytes += qdisc_pkt_len(skb); return NET_XMIT_SUCCESS; } @@ -648,12 +644,10 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl, htb_add_to_wait_tree(q, cl, diff); } - /* update byte stats except for leaves which are already updated */ - if (cl->level) { - cl->bstats.bytes += bytes; - cl->bstats.packets += skb_is_gso(skb)? - skb_shinfo(skb)->gso_segs:1; - } + /* update basic stats except for leaves which are already updated */ + if (cl->level) + bstats_update(&cl->bstats, skb); + cl = cl->parent; } } @@ -847,7 +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; @@ -856,6 +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; @@ -889,11 +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_ingress.c b/net/sched/sch_ingress.c index f10e34a68445..bce1665239b8 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -63,8 +63,7 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch) result = tc_classify(skb, p->filter_list, &res); - sch->bstats.packets++; - sch->bstats.bytes += qdisc_pkt_len(skb); + qdisc_bstats_update(sch, skb); switch (result) { case TC_ACT_SHOT: result = TC_ACT_SHOT; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 32690deab5d0..436a2e75b322 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -83,8 +83,6 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = qdisc_enqueue(skb, qdisc); if (ret == NET_XMIT_SUCCESS) { - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; sch->q.qlen++; return NET_XMIT_SUCCESS; } @@ -113,6 +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 e5593c083a78..6a3006b38dc5 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -240,8 +240,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (likely(ret == NET_XMIT_SUCCESS)) { sch->q.qlen++; - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; } else if (net_xmit_drop_count(ret)) { sch->qstats.drops++; } @@ -290,6 +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; } @@ -477,8 +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); - sch->bstats.bytes += qdisc_pkt_len(nskb); - sch->bstats.packets++; return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index b1c95bce33ce..fbd710d619bf 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -84,8 +84,6 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = qdisc_enqueue(skb, qdisc); if (ret == NET_XMIT_SUCCESS) { - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; sch->q.qlen++; return NET_XMIT_SUCCESS; } @@ -117,6 +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 a67ba3c5a0cc..9f98dbd32d4c 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -94,8 +94,6 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) ret = qdisc_enqueue(skb, child); if (likely(ret == NET_XMIT_SUCCESS)) { - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; sch->q.qlen++; } else if (net_xmit_drop_count(ret)) { q->stats.pdrop++; @@ -115,11 +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 d54ac94066c2..edea8cefec6c 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -402,11 +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) { - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; + if (++sch->q.qlen <= q->limit) return NET_XMIT_SUCCESS; - } sfq_drop(sch); return NET_XMIT_CN; @@ -446,6 +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 641a30d64635..e93165820c3f 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -134,8 +134,6 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) } sch->q.qlen++; - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; return NET_XMIT_SUCCESS; } @@ -188,6 +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 106479a7c94a..d84e7329660f 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -59,6 +59,10 @@ struct teql_master struct net_device *dev; struct Qdisc *slaves; struct list_head master_list; + unsigned long tx_bytes; + unsigned long tx_packets; + unsigned long tx_errors; + unsigned long tx_dropped; }; struct teql_sched_data @@ -83,8 +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); - sch->bstats.bytes += qdisc_pkt_len(skb); - sch->bstats.packets++; return NET_XMIT_SUCCESS; } @@ -108,6 +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; @@ -275,7 +279,6 @@ static inline int teql_resolve(struct sk_buff *skb, static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev) { struct teql_master *master = netdev_priv(dev); - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); struct Qdisc *start, *q; int busy; int nores; @@ -315,8 +318,8 @@ restart: __netif_tx_unlock(slave_txq); master->slaves = NEXT_SLAVE(q); netif_wake_queue(dev); - txq->tx_packets++; - txq->tx_bytes += length; + master->tx_packets++; + master->tx_bytes += length; return NETDEV_TX_OK; } __netif_tx_unlock(slave_txq); @@ -343,10 +346,10 @@ restart: netif_stop_queue(dev); return NETDEV_TX_BUSY; } - dev->stats.tx_errors++; + master->tx_errors++; drop: - txq->tx_dropped++; + master->tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -399,6 +402,18 @@ static int teql_master_close(struct net_device *dev) return 0; } +static struct rtnl_link_stats64 *teql_master_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct teql_master *m = netdev_priv(dev); + + stats->tx_packets = m->tx_packets; + stats->tx_bytes = m->tx_bytes; + stats->tx_errors = m->tx_errors; + stats->tx_dropped = m->tx_dropped; + return stats; +} + static int teql_master_mtu(struct net_device *dev, int new_mtu) { struct teql_master *m = netdev_priv(dev); @@ -423,6 +438,7 @@ static const struct net_device_ops teql_netdev_ops = { .ndo_open = teql_master_open, .ndo_stop = teql_master_close, .ndo_start_xmit = teql_master_xmit, + .ndo_get_stats64 = teql_master_stats64, .ndo_change_mtu = teql_master_mtu, }; 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/sctp/socket.c b/net/sctp/socket.c index a09b0dd25f50..8e02550ff3e8 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3428,7 +3428,7 @@ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname, retval = sctp_setsockopt_peer_addr_params(sk, optval, optlen); break; - case SCTP_DELAYED_ACK: + case SCTP_DELAYED_SACK: retval = sctp_setsockopt_delayed_ack(sk, optval, optlen); break; case SCTP_PARTIAL_DELIVERY_POINT: @@ -5333,7 +5333,7 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_peer_addr_params(sk, len, optval, optlen); break; - case SCTP_DELAYED_ACK: + case SCTP_DELAYED_SACK: retval = sctp_getsockopt_delayed_ack(sk, len, optval, optlen); break; diff --git a/net/socket.c b/net/socket.c index ccc576a6a508..ac2219f90d5d 100644 --- a/net/socket.c +++ b/net/socket.c @@ -306,20 +306,6 @@ static const struct super_operations sockfs_ops = { .statfs = simple_statfs, }; -static struct dentry *sockfs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) -{ - return mount_pseudo(fs_type, "socket:", &sockfs_ops, SOCKFS_MAGIC); -} - -static struct vfsmount *sock_mnt __read_mostly; - -static struct file_system_type sock_fs_type = { - .name = "sockfs", - .mount = sockfs_mount, - .kill_sb = kill_anon_super, -}; - /* * sockfs_dname() is called from d_path(). */ @@ -333,6 +319,21 @@ static const struct dentry_operations sockfs_dentry_operations = { .d_dname = sockfs_dname, }; +static struct dentry *sockfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) +{ + return mount_pseudo(fs_type, "socket:", &sockfs_ops, + &sockfs_dentry_operations, SOCKFS_MAGIC); +} + +static struct vfsmount *sock_mnt __read_mostly; + +static struct file_system_type sock_fs_type = { + .name = "sockfs", + .mount = sockfs_mount, + .kill_sb = kill_anon_super, +}; + /* * Obtains the first available file descriptor and sets it up for use. * @@ -368,7 +369,6 @@ static int sock_alloc_file(struct socket *sock, struct file **f, int flags) } path.mnt = mntget(sock_mnt); - d_set_d_op(path.dentry, &sockfs_dentry_operations); d_instantiate(path.dentry, SOCK_INODE(sock)); SOCK_INODE(sock)->i_fop = &socket_file_ops; diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index afe67849269f..67e31276682a 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -563,8 +563,17 @@ rpcauth_checkverf(struct rpc_task *task, __be32 *p) return cred->cr_ops->crvalidate(task, p); } +static void rpcauth_wrap_req_encode(kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *data, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_encode(&xdr, &rqstp->rq_snd_buf, data); + encode(rqstp, &xdr, obj); +} + int -rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, +rpcauth_wrap_req(struct rpc_task *task, kxdreproc_t encode, void *rqstp, __be32 *data, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; @@ -574,11 +583,22 @@ rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, if (cred->cr_ops->crwrap_req) return cred->cr_ops->crwrap_req(task, encode, rqstp, data, obj); /* By default, we encode the arguments normally. */ - return encode(rqstp, data, obj); + rpcauth_wrap_req_encode(encode, rqstp, data, obj); + return 0; +} + +static int +rpcauth_unwrap_req_decode(kxdrdproc_t decode, struct rpc_rqst *rqstp, + __be32 *data, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, data); + return decode(rqstp, &xdr, obj); } int -rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp, +rpcauth_unwrap_resp(struct rpc_task *task, kxdrdproc_t decode, void *rqstp, __be32 *data, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; @@ -589,7 +609,7 @@ rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp, return cred->cr_ops->crunwrap_resp(task, decode, rqstp, data, obj); /* By default, we decode the arguments normally. */ - return decode(rqstp, data, obj); + return rpcauth_unwrap_req_decode(decode, rqstp, data, obj); } int diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 3835ce35e224..45dbf1521b9a 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1231,9 +1231,19 @@ out_bad: return NULL; } +static void gss_wrap_req_encode(kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_encode(&xdr, &rqstp->rq_snd_buf, p); + encode(rqstp, &xdr, obj); +} + static inline int gss_wrap_req_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx, - kxdrproc_t encode, struct rpc_rqst *rqstp, __be32 *p, void *obj) + kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) { struct xdr_buf *snd_buf = &rqstp->rq_snd_buf; struct xdr_buf integ_buf; @@ -1249,9 +1259,7 @@ gss_wrap_req_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx, offset = (u8 *)p - (u8 *)snd_buf->head[0].iov_base; *p++ = htonl(rqstp->rq_seqno); - status = encode(rqstp, p, obj); - if (status) - return status; + gss_wrap_req_encode(encode, rqstp, p, obj); if (xdr_buf_subsegment(snd_buf, &integ_buf, offset, snd_buf->len - offset)) @@ -1325,7 +1333,8 @@ out: static inline int gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, - kxdrproc_t encode, struct rpc_rqst *rqstp, __be32 *p, void *obj) + kxdreproc_t encode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) { struct xdr_buf *snd_buf = &rqstp->rq_snd_buf; u32 offset; @@ -1342,9 +1351,7 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, offset = (u8 *)p - (u8 *)snd_buf->head[0].iov_base; *p++ = htonl(rqstp->rq_seqno); - status = encode(rqstp, p, obj); - if (status) - return status; + gss_wrap_req_encode(encode, rqstp, p, obj); status = alloc_enc_pages(rqstp); if (status) @@ -1394,7 +1401,7 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, static int gss_wrap_req(struct rpc_task *task, - kxdrproc_t encode, void *rqstp, __be32 *p, void *obj) + kxdreproc_t encode, void *rqstp, __be32 *p, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; struct gss_cred *gss_cred = container_of(cred, struct gss_cred, @@ -1407,12 +1414,14 @@ gss_wrap_req(struct rpc_task *task, /* The spec seems a little ambiguous here, but I think that not * wrapping context destruction requests makes the most sense. */ - status = encode(rqstp, p, obj); + gss_wrap_req_encode(encode, rqstp, p, obj); + status = 0; goto out; } switch (gss_cred->gc_service) { case RPC_GSS_SVC_NONE: - status = encode(rqstp, p, obj); + gss_wrap_req_encode(encode, rqstp, p, obj); + status = 0; break; case RPC_GSS_SVC_INTEGRITY: status = gss_wrap_req_integ(cred, ctx, encode, @@ -1494,10 +1503,19 @@ gss_unwrap_resp_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, return 0; } +static int +gss_unwrap_req_decode(kxdrdproc_t decode, struct rpc_rqst *rqstp, + __be32 *p, void *obj) +{ + struct xdr_stream xdr; + + xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p); + return decode(rqstp, &xdr, obj); +} static int gss_unwrap_resp(struct rpc_task *task, - kxdrproc_t decode, void *rqstp, __be32 *p, void *obj) + kxdrdproc_t decode, void *rqstp, __be32 *p, void *obj) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; struct gss_cred *gss_cred = container_of(cred, struct gss_cred, @@ -1528,7 +1546,7 @@ gss_unwrap_resp(struct rpc_task *task, cred->cr_auth->au_rslack = cred->cr_auth->au_verfsize + (p - savedp) + (savedlen - head->iov_len); out_decode: - status = decode(rqstp, p, obj); + status = gss_unwrap_req_decode(decode, rqstp, p, obj); out: gss_put_ctx(ctx); dprintk("RPC: %5u gss_unwrap_resp returning %d\n", task->tk_pid, diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 75ee993ea057..9576f35ab701 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -137,7 +137,7 @@ arcfour_hmac_md5_usage_to_salt(unsigned int usage, u8 salt[4]) ms_usage = 13; break; default: - return EINVAL;; + return -EINVAL; } salt[0] = (ms_usage >> 0) & 0xff; salt[1] = (ms_usage >> 8) & 0xff; diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index dec2a6fc7c12..bcdae78fdfc6 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -67,7 +67,6 @@ static int netobj_equal(struct xdr_netobj *a, struct xdr_netobj *b) #define RSI_HASHBITS 6 #define RSI_HASHMAX (1<<RSI_HASHBITS) -#define RSI_HASHMASK (RSI_HASHMAX-1) struct rsi { struct cache_head h; @@ -319,7 +318,6 @@ static struct rsi *rsi_update(struct rsi *new, struct rsi *old) #define RSC_HASHBITS 10 #define RSC_HASHMAX (1<<RSC_HASHBITS) -#define RSC_HASHMASK (RSC_HASHMAX-1) #define GSS_SEQ_WIN 128 diff --git a/net/sunrpc/bc_svc.c b/net/sunrpc/bc_svc.c index 7dcfe0cc3500..1dd1a6890007 100644 --- a/net/sunrpc/bc_svc.c +++ b/net/sunrpc/bc_svc.c @@ -59,8 +59,8 @@ int bc_send(struct rpc_rqst *req) ret = task->tk_status; rpc_put_task(task); } - return ret; dprintk("RPC: bc_send ret= %d\n", ret); + return ret; } #endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index e433e7580e27..72ad836e4fe0 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -37,7 +37,7 @@ #define RPCDBG_FACILITY RPCDBG_CACHE -static void cache_defer_req(struct cache_req *req, struct cache_head *item); +static bool cache_defer_req(struct cache_req *req, struct cache_head *item); static void cache_revisit_request(struct cache_head *item); static void cache_init(struct cache_head *h) @@ -128,6 +128,7 @@ static void cache_fresh_locked(struct cache_head *head, time_t expiry) { head->expiry_time = expiry; head->last_refresh = seconds_since_boot(); + smp_wmb(); /* paired with smp_rmb() in cache_is_valid() */ set_bit(CACHE_VALID, &head->flags); } @@ -208,11 +209,36 @@ static inline int cache_is_valid(struct cache_detail *detail, struct cache_head /* entry is valid */ if (test_bit(CACHE_NEGATIVE, &h->flags)) return -ENOENT; - else + else { + /* + * In combination with write barrier in + * sunrpc_cache_update, ensures that anyone + * using the cache entry after this sees the + * updated contents: + */ + smp_rmb(); return 0; + } } } +static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h) +{ + int rv; + + write_lock(&detail->hash_lock); + rv = cache_is_valid(detail, h); + if (rv != -EAGAIN) { + write_unlock(&detail->hash_lock); + return rv; + } + set_bit(CACHE_NEGATIVE, &h->flags); + cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY); + write_unlock(&detail->hash_lock); + cache_fresh_unlocked(h, detail); + return -ENOENT; +} + /* * This is the generic cache management routine for all * the authentication caches. @@ -251,14 +277,8 @@ int cache_check(struct cache_detail *detail, case -EINVAL: clear_bit(CACHE_PENDING, &h->flags); cache_revisit_request(h); - if (rv == -EAGAIN) { - set_bit(CACHE_NEGATIVE, &h->flags); - cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY); - cache_fresh_unlocked(h, detail); - rv = -ENOENT; - } + rv = try_to_negate_entry(detail, h); break; - case -EAGAIN: clear_bit(CACHE_PENDING, &h->flags); cache_revisit_request(h); @@ -268,9 +288,11 @@ int cache_check(struct cache_detail *detail, } if (rv == -EAGAIN) { - cache_defer_req(rqstp, h); - if (!test_bit(CACHE_PENDING, &h->flags)) { - /* Request is not deferred */ + if (!cache_defer_req(rqstp, h)) { + /* + * Request was not deferred; handle it as best + * we can ourselves: + */ rv = cache_is_valid(detail, h); if (rv == -EAGAIN) rv = -ETIMEDOUT; @@ -618,18 +640,19 @@ static void cache_limit_defers(void) discard->revisit(discard, 1); } -static void cache_defer_req(struct cache_req *req, struct cache_head *item) +/* Return true if and only if a deferred request is queued. */ +static bool cache_defer_req(struct cache_req *req, struct cache_head *item) { struct cache_deferred_req *dreq; if (req->thread_wait) { cache_wait_req(req, item); if (!test_bit(CACHE_PENDING, &item->flags)) - return; + return false; } dreq = req->defer(req); if (dreq == NULL) - return; + return false; setup_deferral(dreq, item, 1); if (!test_bit(CACHE_PENDING, &item->flags)) /* Bit could have been cleared before we managed to @@ -638,6 +661,7 @@ static void cache_defer_req(struct cache_req *req, struct cache_head *item) cache_revisit_request(item); cache_limit_defers(); + return true; } static void cache_revisit_request(struct cache_head *item) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 92ce94f5146b..57d344cf2256 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1095,7 +1095,7 @@ static void rpc_xdr_encode(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; - kxdrproc_t encode; + kxdreproc_t encode; __be32 *p; dprint_status(task); @@ -1535,7 +1535,7 @@ call_decode(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; struct rpc_rqst *req = task->tk_rqstp; - kxdrproc_t decode = task->tk_msg.rpc_proc->p_decode; + kxdrdproc_t decode = task->tk_msg.rpc_proc->p_decode; __be32 *p; dprintk("RPC: %5u call_decode (status %d)\n", @@ -1776,12 +1776,11 @@ out_overflow: goto out_garbage; } -static int rpcproc_encode_null(void *rqstp, __be32 *data, void *obj) +static void rpcproc_encode_null(void *rqstp, struct xdr_stream *xdr, void *obj) { - return 0; } -static int rpcproc_decode_null(void *rqstp, __be32 *data, void *obj) +static int rpcproc_decode_null(void *rqstp, struct xdr_stream *xdr, void *obj) { return 0; } @@ -1830,23 +1829,15 @@ static void rpc_show_task(const struct rpc_clnt *clnt, const struct rpc_task *task) { const char *rpc_waitq = "none"; - char *p, action[KSYM_SYMBOL_LEN]; if (RPC_IS_QUEUED(task)) rpc_waitq = rpc_qname(task->tk_waitqueue); - /* map tk_action pointer to a function name; then trim off - * the "+0x0 [sunrpc]" */ - sprint_symbol(action, (unsigned long)task->tk_action); - p = strchr(action, '+'); - if (p) - *p = '\0'; - - printk(KERN_INFO "%5u %04x %6d %8p %8p %8ld %8p %sv%u %s a:%s q:%s\n", + printk(KERN_INFO "%5u %04x %6d %8p %8p %8ld %8p %sv%u %s a:%ps q:%s\n", task->tk_pid, task->tk_flags, task->tk_status, clnt, task->tk_rqstp, task->tk_timeout, task->tk_ops, clnt->cl_protname, clnt->cl_vers, rpc_proc_name(task), - action, rpc_waitq); + task->tk_action, rpc_waitq); } void rpc_show_tasks(void) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 09f01f41e55a..72bc53683965 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -474,7 +474,7 @@ static int __rpc_create_common(struct inode *dir, struct dentry *dentry, { struct inode *inode; - BUG_ON(!d_unhashed(dentry)); + d_drop(dentry); inode = rpc_get_inode(dir->i_sb, mode); if (!inode) goto out_err; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index fa6d7ca2c851..c652e4cc9fe9 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -57,10 +57,6 @@ enum { RPCBPROC_GETSTAT, }; -#define RPCB_HIGHPROC_2 RPCBPROC_CALLIT -#define RPCB_HIGHPROC_3 RPCBPROC_TADDR2UADDR -#define RPCB_HIGHPROC_4 RPCBPROC_GETSTAT - /* * r_owner * @@ -693,46 +689,37 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) * XDR functions for rpcbind */ -static int rpcb_enc_mapping(struct rpc_rqst *req, __be32 *p, - const struct rpcbind_args *rpcb) +static void rpcb_enc_mapping(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct rpcbind_args *rpcb) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; + __be32 *p; dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n", task->tk_pid, task->tk_msg.rpc_proc->p_name, rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port); - xdr_init_encode(&xdr, &req->rq_snd_buf, p); - - p = xdr_reserve_space(&xdr, sizeof(__be32) * RPCB_mappingargs_sz); - if (unlikely(p == NULL)) - return -EIO; - - *p++ = htonl(rpcb->r_prog); - *p++ = htonl(rpcb->r_vers); - *p++ = htonl(rpcb->r_prot); - *p = htonl(rpcb->r_port); - - return 0; + p = xdr_reserve_space(xdr, RPCB_mappingargs_sz << 2); + *p++ = cpu_to_be32(rpcb->r_prog); + *p++ = cpu_to_be32(rpcb->r_vers); + *p++ = cpu_to_be32(rpcb->r_prot); + *p = cpu_to_be32(rpcb->r_port); } -static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, +static int rpcb_dec_getport(struct rpc_rqst *req, struct xdr_stream *xdr, struct rpcbind_args *rpcb) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; unsigned long port; - - xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + __be32 *p; rpcb->r_port = 0; - p = xdr_inline_decode(&xdr, sizeof(__be32)); + p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) return -EIO; - port = ntohl(*p); + port = be32_to_cpup(p); dprintk("RPC: %5u PMAP_%s result: %lu\n", task->tk_pid, task->tk_msg.rpc_proc->p_name, port); if (unlikely(port > USHRT_MAX)) @@ -742,20 +729,18 @@ static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, return 0; } -static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p, +static int rpcb_dec_set(struct rpc_rqst *req, struct xdr_stream *xdr, unsigned int *boolp) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; - - xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + __be32 *p; - p = xdr_inline_decode(&xdr, sizeof(__be32)); + p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) return -EIO; *boolp = 0; - if (*p) + if (*p != xdr_zero) *boolp = 1; dprintk("RPC: %5u RPCB_%s call %s\n", @@ -764,73 +749,53 @@ static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p, return 0; } -static int encode_rpcb_string(struct xdr_stream *xdr, const char *string, - const u32 maxstrlen) +static void encode_rpcb_string(struct xdr_stream *xdr, const char *string, + const u32 maxstrlen) { - u32 len; __be32 *p; + u32 len; - if (unlikely(string == NULL)) - return -EIO; len = strlen(string); - if (unlikely(len > maxstrlen)) - return -EIO; - - p = xdr_reserve_space(xdr, sizeof(__be32) + len); - if (unlikely(p == NULL)) - return -EIO; + BUG_ON(len > maxstrlen); + p = xdr_reserve_space(xdr, 4 + len); xdr_encode_opaque(p, string, len); - - return 0; } -static int rpcb_enc_getaddr(struct rpc_rqst *req, __be32 *p, - const struct rpcbind_args *rpcb) +static void rpcb_enc_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, + const struct rpcbind_args *rpcb) { struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; + __be32 *p; dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n", task->tk_pid, task->tk_msg.rpc_proc->p_name, rpcb->r_prog, rpcb->r_vers, rpcb->r_netid, rpcb->r_addr); - xdr_init_encode(&xdr, &req->rq_snd_buf, p); - - p = xdr_reserve_space(&xdr, - sizeof(__be32) * (RPCB_program_sz + RPCB_version_sz)); - if (unlikely(p == NULL)) - return -EIO; - *p++ = htonl(rpcb->r_prog); - *p = htonl(rpcb->r_vers); - - if (encode_rpcb_string(&xdr, rpcb->r_netid, RPCBIND_MAXNETIDLEN)) - return -EIO; - if (encode_rpcb_string(&xdr, rpcb->r_addr, RPCBIND_MAXUADDRLEN)) - return -EIO; - if (encode_rpcb_string(&xdr, rpcb->r_owner, RPCB_MAXOWNERLEN)) - return -EIO; + p = xdr_reserve_space(xdr, (RPCB_program_sz + RPCB_version_sz) << 2); + *p++ = cpu_to_be32(rpcb->r_prog); + *p = cpu_to_be32(rpcb->r_vers); - return 0; + encode_rpcb_string(xdr, rpcb->r_netid, RPCBIND_MAXNETIDLEN); + encode_rpcb_string(xdr, rpcb->r_addr, RPCBIND_MAXUADDRLEN); + encode_rpcb_string(xdr, rpcb->r_owner, RPCB_MAXOWNERLEN); } -static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p, +static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, struct rpcbind_args *rpcb) { struct sockaddr_storage address; struct sockaddr *sap = (struct sockaddr *)&address; struct rpc_task *task = req->rq_task; - struct xdr_stream xdr; + __be32 *p; u32 len; rpcb->r_port = 0; - xdr_init_decode(&xdr, &req->rq_rcv_buf, p); - - p = xdr_inline_decode(&xdr, sizeof(__be32)); + p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) goto out_fail; - len = ntohl(*p); + len = be32_to_cpup(p); /* * If the returned universal address is a null string, @@ -845,7 +810,7 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p, if (unlikely(len > RPCBIND_MAXUADDRLEN)) goto out_fail; - p = xdr_inline_decode(&xdr, len); + p = xdr_inline_decode(xdr, len); if (unlikely(p == NULL)) goto out_fail; dprintk("RPC: %5u RPCB_%s reply: %s\n", task->tk_pid, @@ -871,8 +836,8 @@ out_fail: static struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdrproc_t)rpcb_enc_mapping, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -881,8 +846,8 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdrproc_t)rpcb_enc_mapping, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -891,8 +856,8 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_GETPORT] = { .p_proc = RPCBPROC_GETPORT, - .p_encode = (kxdrproc_t)rpcb_enc_mapping, - .p_decode = (kxdrproc_t)rpcb_dec_getport, + .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_decode = (kxdrdproc_t)rpcb_dec_getport, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_getportres_sz, .p_statidx = RPCBPROC_GETPORT, @@ -904,8 +869,8 @@ static struct rpc_procinfo rpcb_procedures2[] = { static struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -914,8 +879,8 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -924,8 +889,8 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, @@ -937,8 +902,8 @@ static struct rpc_procinfo rpcb_procedures3[] = { static struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -947,8 +912,8 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -957,8 +922,8 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdrproc_t)rpcb_enc_getaddr, - .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, @@ -993,19 +958,19 @@ static struct rpcb_info rpcb_next_version6[] = { static struct rpc_version rpcb_version2 = { .number = RPCBVERS_2, - .nrprocs = RPCB_HIGHPROC_2, + .nrprocs = ARRAY_SIZE(rpcb_procedures2), .procs = rpcb_procedures2 }; static struct rpc_version rpcb_version3 = { .number = RPCBVERS_3, - .nrprocs = RPCB_HIGHPROC_3, + .nrprocs = ARRAY_SIZE(rpcb_procedures3), .procs = rpcb_procedures3 }; static struct rpc_version rpcb_version4 = { .number = RPCBVERS_4, - .nrprocs = RPCB_HIGHPROC_4, + .nrprocs = ARRAY_SIZE(rpcb_procedures4), .procs = rpcb_procedures4 }; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 6359c42c4941..08e05a8ce025 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -488,10 +488,6 @@ svc_destroy(struct svc_serv *serv) if (svc_serv_is_pooled(serv)) svc_pool_map_put(); -#if defined(CONFIG_NFS_V4_1) - svc_sock_destroy(serv->bc_xprt); -#endif /* CONFIG_NFS_V4_1 */ - svc_unregister(serv); kfree(serv->sv_pools); kfree(serv); @@ -1005,6 +1001,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) rqstp->rq_splice_ok = 1; /* Will be turned off only when NFSv4 Sessions are used */ rqstp->rq_usedeferral = 1; + rqstp->rq_dropme = false; /* Setup reply header */ rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); @@ -1106,7 +1103,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) *statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); /* Encode reply */ - if (*statp == rpc_drop_reply) { + if (rqstp->rq_dropme) { if (procp->pc_release) procp->pc_release(rqstp, NULL, rqstp->rq_resp); goto dropit; @@ -1147,7 +1144,6 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) dropit: svc_authorise(rqstp); /* doesn't hurt to call this twice */ dprintk("svc: svc_process dropit\n"); - svc_drop(rqstp); return 0; err_short_len: @@ -1218,7 +1214,6 @@ svc_process(struct svc_rqst *rqstp) struct kvec *resv = &rqstp->rq_res.head[0]; struct svc_serv *serv = rqstp->rq_server; u32 dir; - int error; /* * Setup response xdr_buf. @@ -1246,11 +1241,13 @@ svc_process(struct svc_rqst *rqstp) return 0; } - error = svc_process_common(rqstp, argv, resv); - if (error <= 0) - return error; - - return svc_send(rqstp); + /* Returns 1 for send, 0 for drop */ + if (svc_process_common(rqstp, argv, resv)) + return svc_send(rqstp); + else { + svc_drop(rqstp); + return 0; + } } #if defined(CONFIG_NFS_V4_1) @@ -1264,10 +1261,9 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; - int error; /* Build the svc_rqst used by the common processing routine */ - rqstp->rq_xprt = serv->bc_xprt; + rqstp->rq_xprt = serv->sv_bc_xprt; rqstp->rq_xid = req->rq_xid; rqstp->rq_prot = req->rq_xprt->prot; rqstp->rq_server = serv; @@ -1292,12 +1288,15 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, svc_getu32(argv); /* XID */ svc_getnl(argv); /* CALLDIR */ - error = svc_process_common(rqstp, argv, resv); - if (error <= 0) - return error; - - memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf)); - return bc_send(req); + /* Returns 1 for send, 0 for drop */ + if (svc_process_common(rqstp, argv, resv)) { + memcpy(&req->rq_snd_buf, &rqstp->rq_res, + sizeof(req->rq_snd_buf)); + return bc_send(req); + } else { + /* Nothing to do to drop request */ + return 0; + } } EXPORT_SYMBOL(bc_svc_process); #endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 3f2c5559ca1a..ab86b7927f84 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -13,6 +13,7 @@ #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svc_xprt.h> #include <linux/sunrpc/svcsock.h> +#include <linux/sunrpc/xprt.h> #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -128,6 +129,9 @@ static void svc_xprt_free(struct kref *kref) if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)) svcauth_unix_info_release(xprt); put_net(xprt->xpt_net); + /* See comment on corresponding get in xs_setup_bc_tcp(): */ + if (xprt->xpt_bc_xprt) + xprt_put(xprt->xpt_bc_xprt); xprt->xpt_ops->xpo_free(xprt); module_put(owner); } @@ -303,6 +307,15 @@ static void svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp) list_del(&rqstp->rq_list); } +static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt) +{ + if (xprt->xpt_flags & ((1<<XPT_CONN)|(1<<XPT_CLOSE))) + return true; + if (xprt->xpt_flags & ((1<<XPT_DATA)|(1<<XPT_DEFERRED))) + return xprt->xpt_ops->xpo_has_wspace(xprt); + return false; +} + /* * Queue up a transport with data pending. If there are idle nfsd * processes, wake 'em up. @@ -315,8 +328,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) struct svc_rqst *rqstp; int cpu; - if (!(xprt->xpt_flags & - ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED)))) + if (!svc_xprt_has_something_to_do(xprt)) return; cpu = get_cpu(); @@ -343,28 +355,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) dprintk("svc: transport %p busy, not enqueued\n", xprt); goto out_unlock; } - BUG_ON(xprt->xpt_pool != NULL); - xprt->xpt_pool = pool; - - /* Handle pending connection */ - if (test_bit(XPT_CONN, &xprt->xpt_flags)) - goto process; - - /* Handle close in-progress */ - if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) - goto process; - - /* Check if we have space to reply to a request */ - if (!xprt->xpt_ops->xpo_has_wspace(xprt)) { - /* Don't enqueue while not enough space for reply */ - dprintk("svc: no write space, transport %p not enqueued\n", - xprt); - xprt->xpt_pool = NULL; - clear_bit(XPT_BUSY, &xprt->xpt_flags); - goto out_unlock; - } - process: if (!list_empty(&pool->sp_threads)) { rqstp = list_entry(pool->sp_threads.next, struct svc_rqst, @@ -381,13 +372,11 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) rqstp->rq_reserved = serv->sv_max_mesg; atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); pool->sp_stats.threads_woken++; - BUG_ON(xprt->xpt_pool != pool); wake_up(&rqstp->rq_wait); } else { dprintk("svc: transport %p put into queue\n", xprt); list_add_tail(&xprt->xpt_ready, &pool->sp_sockets); pool->sp_stats.sockets_queued++; - BUG_ON(xprt->xpt_pool != pool); } out_unlock: @@ -426,7 +415,6 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool) void svc_xprt_received(struct svc_xprt *xprt) { BUG_ON(!test_bit(XPT_BUSY, &xprt->xpt_flags)); - xprt->xpt_pool = NULL; /* As soon as we clear busy, the xprt could be closed and * 'put', so we need a reference to call svc_xprt_enqueue with: */ @@ -722,7 +710,10 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) { dprintk("svc_recv: found XPT_CLOSE\n"); svc_delete_xprt(xprt); - } else if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) { + /* Leave XPT_BUSY set on the dead xprt: */ + goto out; + } + if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) { struct svc_xprt *newxpt; newxpt = xprt->xpt_ops->xpo_accept(xprt); if (newxpt) { @@ -747,28 +738,23 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) spin_unlock_bh(&serv->sv_lock); svc_xprt_received(newxpt); } - svc_xprt_received(xprt); - } else { + } else if (xprt->xpt_ops->xpo_has_wspace(xprt)) { dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n", rqstp, pool->sp_id, xprt, atomic_read(&xprt->xpt_ref.refcount)); rqstp->rq_deferred = svc_deferred_dequeue(xprt); - if (rqstp->rq_deferred) { - svc_xprt_received(xprt); + if (rqstp->rq_deferred) len = svc_deferred_recv(rqstp); - } else { + else len = xprt->xpt_ops->xpo_recvfrom(rqstp); - svc_xprt_received(xprt); - } dprintk("svc: got len=%d\n", len); } + svc_xprt_received(xprt); /* No data, incomplete (TCP) read, or accept() */ - if (len == 0 || len == -EAGAIN) { - rqstp->rq_res.len = 0; - svc_xprt_release(rqstp); - return -EAGAIN; - } + if (len == 0 || len == -EAGAIN) + goto out; + clear_bit(XPT_OLD, &xprt->xpt_flags); rqstp->rq_secure = svc_port_is_privileged(svc_addr(rqstp)); @@ -777,6 +763,10 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) if (serv->sv_stats) serv->sv_stats->netcnt++; return len; +out: + rqstp->rq_res.len = 0; + svc_xprt_release(rqstp); + return -EAGAIN; } EXPORT_SYMBOL_GPL(svc_recv); @@ -935,7 +925,12 @@ void svc_close_xprt(struct svc_xprt *xprt) if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) /* someone else will have to effect the close */ return; - + /* + * We expect svc_close_xprt() to work even when no threads are + * running (e.g., while configuring the server before starting + * any threads), so if the transport isn't busy, we delete + * it ourself: + */ svc_delete_xprt(xprt); } EXPORT_SYMBOL_GPL(svc_close_xprt); @@ -945,16 +940,16 @@ void svc_close_all(struct list_head *xprt_list) struct svc_xprt *xprt; struct svc_xprt *tmp; + /* + * The server is shutting down, and no more threads are running. + * svc_xprt_enqueue() might still be running, but at worst it + * will re-add the xprt to sp_sockets, which will soon get + * freed. So we don't bother with any more locking, and don't + * leave the close to the (nonexistent) server threads: + */ list_for_each_entry_safe(xprt, tmp, xprt_list, xpt_list) { set_bit(XPT_CLOSE, &xprt->xpt_flags); - if (test_bit(XPT_BUSY, &xprt->xpt_flags)) { - /* Waiting to be processed, but no threads left, - * So just remove it from the waiting list - */ - list_del_init(&xprt->xpt_ready); - clear_bit(XPT_BUSY, &xprt->xpt_flags); - } - svc_close_xprt(xprt); + svc_delete_xprt(xprt); } } @@ -1028,6 +1023,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) } svc_xprt_get(rqstp->rq_xprt); dr->xprt = rqstp->rq_xprt; + rqstp->rq_dropme = true; dr->handle.revisit = svc_revisit; return &dr->handle; @@ -1065,14 +1061,13 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt) if (!test_bit(XPT_DEFERRED, &xprt->xpt_flags)) return NULL; spin_lock(&xprt->xpt_lock); - clear_bit(XPT_DEFERRED, &xprt->xpt_flags); if (!list_empty(&xprt->xpt_deferred)) { dr = list_entry(xprt->xpt_deferred.next, struct svc_deferred_req, handle.recent); list_del_init(&dr->handle.recent); - set_bit(XPT_DEFERRED, &xprt->xpt_flags); - } + } else + clear_bit(XPT_DEFERRED, &xprt->xpt_flags); spin_unlock(&xprt->xpt_lock); return dr; } diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 4e9393c24687..7963569fc04f 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -118,7 +118,6 @@ EXPORT_SYMBOL_GPL(svc_auth_unregister); #define DN_HASHBITS 6 #define DN_HASHMAX (1<<DN_HASHBITS) -#define DN_HASHMASK (DN_HASHMAX-1) static struct hlist_head auth_domain_table[DN_HASHMAX]; static spinlock_t auth_domain_lock = diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 560677d187f1..30916b06c12b 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -30,7 +30,9 @@ struct unix_domain { struct auth_domain h; +#ifdef CONFIG_NFSD_DEPRECATED int addr_changes; +#endif /* CONFIG_NFSD_DEPRECATED */ /* other stuff later */ }; @@ -64,7 +66,9 @@ struct auth_domain *unix_domain_find(char *name) return NULL; } new->h.flavour = &svcauth_unix; +#ifdef CONFIG_NFSD_DEPRECATED new->addr_changes = 0; +#endif /* CONFIG_NFSD_DEPRECATED */ rv = auth_domain_lookup(name, &new->h); } } @@ -85,14 +89,15 @@ static void svcauth_unix_domain_release(struct auth_domain *dom) */ #define IP_HASHBITS 8 #define IP_HASHMAX (1<<IP_HASHBITS) -#define IP_HASHMASK (IP_HASHMAX-1) struct ip_map { struct cache_head h; char m_class[8]; /* e.g. "nfsd" */ struct in6_addr m_addr; struct unix_domain *m_client; +#ifdef CONFIG_NFSD_DEPRECATED int m_add_change; +#endif /* CONFIG_NFSD_DEPRECATED */ }; static void ip_map_put(struct kref *kref) @@ -146,7 +151,9 @@ static void update(struct cache_head *cnew, struct cache_head *citem) kref_get(&item->m_client->h.ref); new->m_client = item->m_client; +#ifdef CONFIG_NFSD_DEPRECATED new->m_add_change = item->m_add_change; +#endif /* CONFIG_NFSD_DEPRECATED */ } static struct cache_head *ip_map_alloc(void) { @@ -331,6 +338,7 @@ static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm, ip.h.flags = 0; if (!udom) set_bit(CACHE_NEGATIVE, &ip.h.flags); +#ifdef CONFIG_NFSD_DEPRECATED else { ip.m_add_change = udom->addr_changes; /* if this is from the legacy set_client system call, @@ -339,6 +347,7 @@ static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm, if (expiry == NEVER) ip.m_add_change++; } +#endif /* CONFIG_NFSD_DEPRECATED */ ip.h.expiry_time = expiry; ch = sunrpc_cache_update(cd, &ip.h, &ipm->h, hash_str(ipm->m_class, IP_HASHBITS) ^ @@ -358,6 +367,7 @@ static inline int ip_map_update(struct net *net, struct ip_map *ipm, return __ip_map_update(sn->ip_map_cache, ipm, udom, expiry); } +#ifdef CONFIG_NFSD_DEPRECATED int auth_unix_add_addr(struct net *net, struct in6_addr *addr, struct auth_domain *dom) { struct unix_domain *udom; @@ -402,8 +412,7 @@ struct auth_domain *auth_unix_lookup(struct net *net, struct in6_addr *addr) return NULL; if ((ipm->m_client->addr_changes - ipm->m_add_change) >0) { - if (test_and_set_bit(CACHE_NEGATIVE, &ipm->h.flags) == 0) - auth_domain_put(&ipm->m_client->h); + sunrpc_invalidate(&ipm->h, sn->ip_map_cache); rv = NULL; } else { rv = &ipm->m_client->h; @@ -413,6 +422,7 @@ struct auth_domain *auth_unix_lookup(struct net *net, struct in6_addr *addr) return rv; } EXPORT_SYMBOL_GPL(auth_unix_lookup); +#endif /* CONFIG_NFSD_DEPRECATED */ void svcauth_unix_purge(void) { @@ -497,7 +507,6 @@ svcauth_unix_info_release(struct svc_xprt *xpt) */ #define GID_HASHBITS 8 #define GID_HASHMAX (1<<GID_HASHBITS) -#define GID_HASHMASK (GID_HASHMAX - 1) struct unix_gid { struct cache_head h; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 07919e16be3e..d802e941d365 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -66,6 +66,13 @@ static void svc_sock_free(struct svc_xprt *); static struct svc_xprt *svc_create_socket(struct svc_serv *, int, struct net *, struct sockaddr *, int, int); +#if defined(CONFIG_NFS_V4_1) +static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int, + struct net *, struct sockaddr *, + int, int); +static void svc_bc_sock_free(struct svc_xprt *xprt); +#endif /* CONFIG_NFS_V4_1 */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key svc_key[2]; static struct lock_class_key svc_slock_key[2]; @@ -324,19 +331,21 @@ int svc_sock_names(struct svc_serv *serv, char *buf, const size_t buflen, len = onelen; break; } - if (toclose && strcmp(toclose, buf + len) == 0) + if (toclose && strcmp(toclose, buf + len) == 0) { closesk = svsk; - else + svc_xprt_get(&closesk->sk_xprt); + } else len += onelen; } spin_unlock_bh(&serv->sv_lock); - if (closesk) + if (closesk) { /* Should unregister with portmap, but you cannot * unregister just one protocol... */ svc_close_xprt(&closesk->sk_xprt); - else if (toclose) + svc_xprt_put(&closesk->sk_xprt); + } else if (toclose) return -ENOENT; return len; } @@ -985,15 +994,17 @@ static int svc_process_calldir(struct svc_sock *svsk, struct svc_rqst *rqstp, vec[0] = rqstp->rq_arg.head[0]; } else { /* REPLY */ - if (svsk->sk_bc_xprt) - req = xprt_lookup_rqst(svsk->sk_bc_xprt, xid); + struct rpc_xprt *bc_xprt = svsk->sk_xprt.xpt_bc_xprt; + + if (bc_xprt) + req = xprt_lookup_rqst(bc_xprt, xid); if (!req) { printk(KERN_NOTICE "%s: Got unrecognized reply: " - "calldir 0x%x sk_bc_xprt %p xid %08x\n", + "calldir 0x%x xpt_bc_xprt %p xid %08x\n", __func__, ntohl(calldir), - svsk->sk_bc_xprt, xid); + bc_xprt, xid); vec[0] = rqstp->rq_arg.head[0]; goto out; } @@ -1184,6 +1195,57 @@ static struct svc_xprt *svc_tcp_create(struct svc_serv *serv, return svc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags); } +#if defined(CONFIG_NFS_V4_1) +static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int, + struct net *, struct sockaddr *, + int, int); +static void svc_bc_sock_free(struct svc_xprt *xprt); + +static struct svc_xprt *svc_bc_tcp_create(struct svc_serv *serv, + struct net *net, + struct sockaddr *sa, int salen, + int flags) +{ + return svc_bc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags); +} + +static void svc_bc_tcp_sock_detach(struct svc_xprt *xprt) +{ +} + +static struct svc_xprt_ops svc_tcp_bc_ops = { + .xpo_create = svc_bc_tcp_create, + .xpo_detach = svc_bc_tcp_sock_detach, + .xpo_free = svc_bc_sock_free, + .xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr, +}; + +static struct svc_xprt_class svc_tcp_bc_class = { + .xcl_name = "tcp-bc", + .xcl_owner = THIS_MODULE, + .xcl_ops = &svc_tcp_bc_ops, + .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, +}; + +static void svc_init_bc_xprt_sock(void) +{ + svc_reg_xprt_class(&svc_tcp_bc_class); +} + +static void svc_cleanup_bc_xprt_sock(void) +{ + svc_unreg_xprt_class(&svc_tcp_bc_class); +} +#else /* CONFIG_NFS_V4_1 */ +static void svc_init_bc_xprt_sock(void) +{ +} + +static void svc_cleanup_bc_xprt_sock(void) +{ +} +#endif /* CONFIG_NFS_V4_1 */ + static struct svc_xprt_ops svc_tcp_ops = { .xpo_create = svc_tcp_create, .xpo_recvfrom = svc_tcp_recvfrom, @@ -1207,12 +1269,14 @@ void svc_init_xprt_sock(void) { svc_reg_xprt_class(&svc_tcp_class); svc_reg_xprt_class(&svc_udp_class); + svc_init_bc_xprt_sock(); } void svc_cleanup_xprt_sock(void) { svc_unreg_xprt_class(&svc_tcp_class); svc_unreg_xprt_class(&svc_udp_class); + svc_cleanup_bc_xprt_sock(); } static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) @@ -1509,41 +1573,43 @@ static void svc_sock_free(struct svc_xprt *xprt) kfree(svsk); } +#if defined(CONFIG_NFS_V4_1) /* - * Create a svc_xprt. - * - * For internal use only (e.g. nfsv4.1 backchannel). - * Callers should typically use the xpo_create() method. + * Create a back channel svc_xprt which shares the fore channel socket. */ -struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot) +static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv, + int protocol, + struct net *net, + struct sockaddr *sin, int len, + int flags) { struct svc_sock *svsk; - struct svc_xprt *xprt = NULL; + struct svc_xprt *xprt; + + if (protocol != IPPROTO_TCP) { + printk(KERN_WARNING "svc: only TCP sockets" + " supported on shared back channel\n"); + return ERR_PTR(-EINVAL); + } - dprintk("svc: %s\n", __func__); svsk = kzalloc(sizeof(*svsk), GFP_KERNEL); if (!svsk) - goto out; + return ERR_PTR(-ENOMEM); xprt = &svsk->sk_xprt; - if (prot == IPPROTO_TCP) - svc_xprt_init(&svc_tcp_class, xprt, serv); - else if (prot == IPPROTO_UDP) - svc_xprt_init(&svc_udp_class, xprt, serv); - else - BUG(); -out: - dprintk("svc: %s return %p\n", __func__, xprt); + svc_xprt_init(&svc_tcp_bc_class, xprt, serv); + + serv->sv_bc_xprt = xprt; + return xprt; } -EXPORT_SYMBOL_GPL(svc_sock_create); /* - * Destroy a svc_sock. + * Free a back channel svc_sock. */ -void svc_sock_destroy(struct svc_xprt *xprt) +static void svc_bc_sock_free(struct svc_xprt *xprt) { if (xprt) kfree(container_of(xprt, struct svc_sock, sk_xprt)); } -EXPORT_SYMBOL_GPL(svc_sock_destroy); +#endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index cd9e841e7492..679cd674b81d 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -552,6 +552,74 @@ void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int b } EXPORT_SYMBOL_GPL(xdr_write_pages); +static void xdr_set_iov(struct xdr_stream *xdr, struct kvec *iov, + __be32 *p, unsigned int len) +{ + if (len > iov->iov_len) + len = iov->iov_len; + if (p == NULL) + p = (__be32*)iov->iov_base; + xdr->p = p; + xdr->end = (__be32*)(iov->iov_base + len); + xdr->iov = iov; + xdr->page_ptr = NULL; +} + +static int xdr_set_page_base(struct xdr_stream *xdr, + unsigned int base, unsigned int len) +{ + unsigned int pgnr; + unsigned int maxlen; + unsigned int pgoff; + unsigned int pgend; + void *kaddr; + + maxlen = xdr->buf->page_len; + if (base >= maxlen) + return -EINVAL; + maxlen -= base; + if (len > maxlen) + len = maxlen; + + base += xdr->buf->page_base; + + pgnr = base >> PAGE_SHIFT; + xdr->page_ptr = &xdr->buf->pages[pgnr]; + kaddr = page_address(*xdr->page_ptr); + + pgoff = base & ~PAGE_MASK; + xdr->p = (__be32*)(kaddr + pgoff); + + pgend = pgoff + len; + if (pgend > PAGE_SIZE) + pgend = PAGE_SIZE; + xdr->end = (__be32*)(kaddr + pgend); + xdr->iov = NULL; + return 0; +} + +static void xdr_set_next_page(struct xdr_stream *xdr) +{ + unsigned int newbase; + + newbase = (1 + xdr->page_ptr - xdr->buf->pages) << PAGE_SHIFT; + newbase -= xdr->buf->page_base; + + if (xdr_set_page_base(xdr, newbase, PAGE_SIZE) < 0) + xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len); +} + +static bool xdr_set_next_buffer(struct xdr_stream *xdr) +{ + if (xdr->page_ptr != NULL) + xdr_set_next_page(xdr); + else if (xdr->iov == xdr->buf->head) { + if (xdr_set_page_base(xdr, 0, PAGE_SIZE) < 0) + xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len); + } + return xdr->p != xdr->end; +} + /** * xdr_init_decode - Initialize an xdr_stream for decoding data. * @xdr: pointer to xdr_stream struct @@ -560,41 +628,67 @@ EXPORT_SYMBOL_GPL(xdr_write_pages); */ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p) { - struct kvec *iov = buf->head; - unsigned int len = iov->iov_len; - - if (len > buf->len) - len = buf->len; xdr->buf = buf; - xdr->iov = iov; - xdr->p = p; - xdr->end = (__be32 *)((char *)iov->iov_base + len); + xdr->scratch.iov_base = NULL; + xdr->scratch.iov_len = 0; + if (buf->head[0].iov_len != 0) + xdr_set_iov(xdr, buf->head, p, buf->len); + else if (buf->page_len != 0) + xdr_set_page_base(xdr, 0, buf->len); } EXPORT_SYMBOL_GPL(xdr_init_decode); -/** - * xdr_inline_peek - Allow read-ahead in the XDR data stream - * @xdr: pointer to xdr_stream struct - * @nbytes: number of bytes of data to decode - * - * Check if the input buffer is long enough to enable us to decode - * 'nbytes' more bytes of data starting at the current position. - * If so return the current pointer without updating the current - * pointer position. - */ -__be32 * xdr_inline_peek(struct xdr_stream *xdr, size_t nbytes) +static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) { __be32 *p = xdr->p; __be32 *q = p + XDR_QUADLEN(nbytes); if (unlikely(q > xdr->end || q < p)) return NULL; + xdr->p = q; return p; } -EXPORT_SYMBOL_GPL(xdr_inline_peek); /** - * xdr_inline_decode - Retrieve non-page XDR data to decode + * xdr_set_scratch_buffer - Attach a scratch buffer for decoding data. + * @xdr: pointer to xdr_stream struct + * @buf: pointer to an empty buffer + * @buflen: size of 'buf' + * + * The scratch buffer is used when decoding from an array of pages. + * If an xdr_inline_decode() call spans across page boundaries, then + * we copy the data into the scratch buffer in order to allow linear + * access. + */ +void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen) +{ + xdr->scratch.iov_base = buf; + xdr->scratch.iov_len = buflen; +} +EXPORT_SYMBOL_GPL(xdr_set_scratch_buffer); + +static __be32 *xdr_copy_to_scratch(struct xdr_stream *xdr, size_t nbytes) +{ + __be32 *p; + void *cpdest = xdr->scratch.iov_base; + size_t cplen = (char *)xdr->end - (char *)xdr->p; + + if (nbytes > xdr->scratch.iov_len) + return NULL; + memcpy(cpdest, xdr->p, cplen); + cpdest += cplen; + nbytes -= cplen; + if (!xdr_set_next_buffer(xdr)) + return NULL; + p = __xdr_inline_decode(xdr, nbytes); + if (p == NULL) + return NULL; + memcpy(cpdest, p, nbytes); + return xdr->scratch.iov_base; +} + +/** + * xdr_inline_decode - Retrieve XDR data to decode * @xdr: pointer to xdr_stream struct * @nbytes: number of bytes of data to decode * @@ -605,13 +699,16 @@ EXPORT_SYMBOL_GPL(xdr_inline_peek); */ __be32 * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) { - __be32 *p = xdr->p; - __be32 *q = p + XDR_QUADLEN(nbytes); + __be32 *p; - if (unlikely(q > xdr->end || q < p)) + if (nbytes == 0) + return xdr->p; + if (xdr->p == xdr->end && !xdr_set_next_buffer(xdr)) return NULL; - xdr->p = q; - return p; + p = __xdr_inline_decode(xdr, nbytes); + if (p != NULL) + return p; + return xdr_copy_to_scratch(xdr, nbytes); } EXPORT_SYMBOL_GPL(xdr_inline_decode); @@ -671,16 +768,12 @@ EXPORT_SYMBOL_GPL(xdr_read_pages); */ void xdr_enter_page(struct xdr_stream *xdr, unsigned int len) { - char * kaddr = page_address(xdr->buf->pages[0]); xdr_read_pages(xdr, len); /* * Position current pointer at beginning of tail, and * set remaining message length. */ - if (len > PAGE_CACHE_SIZE - xdr->buf->page_base) - len = PAGE_CACHE_SIZE - xdr->buf->page_base; - xdr->p = (__be32 *)(kaddr + xdr->buf->page_base); - xdr->end = (__be32 *)((char *)xdr->p + len); + xdr_set_page_base(xdr, 0, len); } EXPORT_SYMBOL_GPL(xdr_enter_page); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 4c8f18aff7c3..856274d7e85c 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -965,6 +965,7 @@ struct rpc_xprt *xprt_alloc(struct net *net, int size, int max_req) xprt = kzalloc(size, GFP_KERNEL); if (xprt == NULL) goto out; + kref_init(&xprt->kref); xprt->max_reqs = max_req; xprt->slot = kcalloc(max_req, sizeof(struct rpc_rqst), GFP_KERNEL); @@ -1101,8 +1102,10 @@ found: -PTR_ERR(xprt)); return xprt; } + if (test_and_set_bit(XPRT_INITIALIZED, &xprt->state)) + /* ->setup returned a pre-initialized xprt: */ + return xprt; - kref_init(&xprt->kref); spin_lock_init(&xprt->transport_lock); spin_lock_init(&xprt->reserve_lock); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 96549df836ee..c431f5a57960 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2359,6 +2359,15 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) struct svc_sock *bc_sock; struct rpc_xprt *ret; + if (args->bc_xprt->xpt_bc_xprt) { + /* + * This server connection already has a backchannel + * export; we can't create a new one, as we wouldn't be + * able to match replies based on xid any more. So, + * reuse the already-existing one: + */ + return args->bc_xprt->xpt_bc_xprt; + } xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries); if (IS_ERR(xprt)) return xprt; @@ -2375,16 +2384,6 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) xprt->reestablish_timeout = 0; xprt->idle_timeout = 0; - /* - * The backchannel uses the same socket connection as the - * forechannel - */ - xprt->bc_xprt = args->bc_xprt; - bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt); - bc_sock->sk_bc_xprt = xprt; - transport->sock = bc_sock->sk_sock; - transport->inet = bc_sock->sk_sk; - xprt->ops = &bc_tcp_ops; switch (addr->sa_family) { @@ -2407,6 +2406,20 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) xprt->address_strings[RPC_DISPLAY_PROTO]); /* + * Once we've associated a backchannel xprt with a connection, + * we want to keep it around as long as long as the connection + * lasts, in case we need to start using it for a backchannel + * again; this reference won't be dropped until bc_xprt is + * destroyed. + */ + xprt_get(xprt); + args->bc_xprt->xpt_bc_xprt = xprt; + xprt->bc_xprt = args->bc_xprt; + bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt); + transport->sock = bc_sock->sk_sock; + transport->inet = bc_sock->sk_sk; + + /* * Since we don't want connections for the backchannel, we set * the xprt status to connected */ @@ -2415,6 +2428,7 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) if (try_module_get(THIS_MODULE)) return xprt; + xprt_put(xprt); ret = ERR_PTR(-EINVAL); out_err: xprt_free(xprt); diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index d0ee29063e5d..1f1ef70f34f2 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -95,7 +95,7 @@ config CFG80211_DEBUGFS If unsure, say N. config CFG80211_INTERNAL_REGDB - bool "use statically compiled regulatory rules database" if EMBEDDED + bool "use statically compiled regulatory rules database" if EXPERT default n depends on CFG80211 ---help--- 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; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 8eb889510916..61291965c5f6 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -26,6 +26,7 @@ #include <net/sock.h> #include <net/xfrm.h> #include <net/netlink.h> +#include <net/ah.h> #include <asm/uaccess.h> #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) #include <linux/in6.h> @@ -302,7 +303,8 @@ static int attach_auth_trunc(struct xfrm_algo_auth **algpp, u8 *props, algo = xfrm_aalg_get_byname(ualg->alg_name, 1); if (!algo) return -ENOSYS; - if (ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits) + if ((ualg->alg_trunc_len / 8) > MAX_AH_AUTH_LEN || + ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits) return -EINVAL; *props = algo->desc.sadb_alg_id; |