diff options
Diffstat (limited to 'net')
119 files changed, 1196 insertions, 863 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 6089f0cf23b4..9096bcb08132 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -403,6 +403,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, break; case NETDEV_DOWN: + if (dev->features & NETIF_F_HW_VLAN_FILTER) + vlan_vid_del(dev, 0); + /* Put all VLANs for this dev in the down state too. */ for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 9ee48cb30179..3d33ecf13327 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -368,7 +368,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, const char *sptr = va_arg(ap, const char *); uint16_t len = 0; if (sptr) - len = min_t(uint16_t, strlen(sptr), + len = min_t(size_t, strlen(sptr), USHRT_MAX); errcode = p9pdu_writef(pdu, proto_version, diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 5af18d11b518..2a167658bb95 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -192,10 +192,10 @@ static int pack_sg_list(struct scatterlist *sg, int start, s = rest_of_page(data); if (s > count) s = count; + BUG_ON(index > limit); sg_set_buf(&sg[index++], data, s); count -= s; data += s; - BUG_ON(index > limit); } return index-start; diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 0301b328cf0f..86852963b7f7 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1208,9 +1208,7 @@ static int atalk_connect(struct socket *sock, struct sockaddr *uaddr, if (addr->sat_addr.s_node == ATADDR_BCAST && !sock_flag(sk, SOCK_BROADCAST)) { #if 1 - printk(KERN_WARNING "%s is broken and did not set " - "SO_BROADCAST. It will break when 2.2 is " - "released.\n", + pr_warn("atalk_connect: %s is broken and did not set SO_BROADCAST.\n", current->comm); #else return -EACCES; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 051f7abae66d..779095ded689 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -842,6 +842,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, case AX25_P_NETROM: if (ax25_protocol_is_registered(AX25_P_NETROM)) return -ESOCKTNOSUPPORT; + break; #endif #ifdef CONFIG_ROSE_MODULE case AX25_P_ROSE: diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 8bf97515a77d..c5863f499133 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1351,6 +1351,7 @@ void bla_free(struct bat_priv *bat_priv) * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame + * @is_bcast: the packet came in a broadcast packet type. * * bla_rx avoidance checks if: * * we have to race for a claim @@ -1361,7 +1362,8 @@ void bla_free(struct bat_priv *bat_priv) * process the skb. * */ -int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) +int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid, + bool is_bcast) { struct ethhdr *ethhdr; struct claim search_claim, *claim = NULL; @@ -1380,7 +1382,7 @@ int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) if (unlikely(atomic_read(&bat_priv->bla_num_requests))) /* don't allow broadcasts while requests are in flight */ - if (is_multicast_ether_addr(ethhdr->h_dest)) + if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) goto handled; memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN); @@ -1406,8 +1408,13 @@ int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) } /* if it is a broadcast ... */ - if (is_multicast_ether_addr(ethhdr->h_dest)) { - /* ... drop it. the responsible gateway is in charge. */ + if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) { + /* ... drop it. the responsible gateway is in charge. + * + * We need to check is_bcast because with the gateway + * feature, broadcasts (like DHCP requests) may be sent + * using a unicast packet type. + */ goto handled; } else { /* seems the client considers us as its best gateway. diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index e39f93acc28f..dc5227b398d4 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -23,7 +23,8 @@ #define _NET_BATMAN_ADV_BLA_H_ #ifdef CONFIG_BATMAN_ADV_BLA -int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid); +int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid, + bool is_bcast); int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid); int bla_is_backbone_gw(struct sk_buff *skb, struct orig_node *orig_node, int hdr_size); @@ -41,7 +42,7 @@ void bla_free(struct bat_priv *bat_priv); #else /* ifdef CONFIG_BATMAN_ADV_BLA */ static inline int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, - short vid) + short vid, bool is_bcast) { return 0; } diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 840e2c64a301..015471d801b4 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -617,6 +617,8 @@ int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if) * changes */ if (skb_linearize(skb) < 0) goto out; + /* skb_linearize() possibly changed skb->data */ + tt_query = (struct tt_query_packet *)skb->data; tt_len = tt_query->tt_data * sizeof(struct tt_change); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 6e2530b02043..a0ec0e4ada4c 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -256,7 +256,11 @@ void interface_rx(struct net_device *soft_iface, struct bat_priv *bat_priv = netdev_priv(soft_iface); struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; + struct batman_header *batadv_header = (struct batman_header *)skb->data; short vid __maybe_unused = -1; + bool is_bcast; + + is_bcast = (batadv_header->packet_type == BAT_BCAST); /* check if enough space is available for pulling, and pull */ if (!pskb_may_pull(skb, hdr_size)) @@ -302,7 +306,7 @@ void interface_rx(struct net_device *soft_iface, /* Let the bridge loop avoidance check the packet. If will * not handle it, we can safely push it up. */ - if (bla_rx(bat_priv, skb, vid)) + if (bla_rx(bat_priv, skb, vid, is_bcast)) goto out; netif_rx(skb); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index a66c2dcd1088..2ab83d7fb1f8 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -141,13 +141,14 @@ static void tt_orig_list_entry_free_rcu(struct rcu_head *rcu) struct tt_orig_list_entry *orig_entry; orig_entry = container_of(rcu, struct tt_orig_list_entry, rcu); - atomic_dec(&orig_entry->orig_node->tt_size); orig_node_free_ref(orig_entry->orig_node); kfree(orig_entry); } static void tt_orig_list_entry_free_ref(struct tt_orig_list_entry *orig_entry) { + /* to avoid race conditions, immediately decrease the tt counter */ + atomic_dec(&orig_entry->orig_node->tt_size); call_rcu(&orig_entry->rcu, tt_orig_list_entry_free_rcu); } @@ -910,7 +911,6 @@ void tt_global_del_orig(struct bat_priv *bat_priv, } spin_unlock_bh(list_lock); } - atomic_set(&orig_node->tt_size, 0); orig_node->tt_initialised = false; } @@ -2031,10 +2031,10 @@ bool is_ap_isolated(struct bat_priv *bat_priv, uint8_t *src, uint8_t *dst) { struct tt_local_entry *tt_local_entry = NULL; struct tt_global_entry *tt_global_entry = NULL; - bool ret = true; + bool ret = false; if (!atomic_read(&bat_priv->ap_isolation)) - return false; + goto out; tt_local_entry = tt_local_hash_find(bat_priv, dst); if (!tt_local_entry) @@ -2044,10 +2044,10 @@ bool is_ap_isolated(struct bat_priv *bat_priv, uint8_t *src, uint8_t *dst) if (!tt_global_entry) goto out; - if (_is_ap_isolated(tt_local_entry, tt_global_entry)) + if (!_is_ap_isolated(tt_local_entry, tt_global_entry)) goto out; - ret = false; + ret = true; out: if (tt_global_entry) diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 46e7f86acfc9..3e18af4dadc4 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -210,7 +210,7 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) } if (sk->sk_state == BT_CONNECTED || !newsock || - test_bit(BT_DEFER_SETUP, &bt_sk(parent)->flags)) { + test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) { bt_accept_unlink(sk); if (newsock) sock_graft(sk, newsock); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 4eefb7f65cf6..94ad124a4ea3 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3043,6 +3043,50 @@ static inline void hci_extended_inquiry_result_evt(struct hci_dev *hdev, struct hci_dev_unlock(hdev); } +static void hci_key_refresh_complete_evt(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_ev_key_refresh_complete *ev = (void *) skb->data; + struct hci_conn *conn; + + BT_DBG("%s status %u handle %u", hdev->name, ev->status, + __le16_to_cpu(ev->handle)); + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); + if (!conn) + goto unlock; + + if (!ev->status) + conn->sec_level = conn->pending_sec_level; + + clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); + + if (ev->status && conn->state == BT_CONNECTED) { + hci_acl_disconn(conn, HCI_ERROR_AUTH_FAILURE); + hci_conn_put(conn); + goto unlock; + } + + if (conn->state == BT_CONFIG) { + if (!ev->status) + conn->state = BT_CONNECTED; + + hci_proto_connect_cfm(conn, ev->status); + hci_conn_put(conn); + } else { + hci_auth_cfm(conn, ev->status); + + hci_conn_hold(conn); + conn->disc_timeout = HCI_DISCONN_TIMEOUT; + hci_conn_put(conn); + } + +unlock: + hci_dev_unlock(hdev); +} + static inline u8 hci_get_auth_req(struct hci_conn *conn) { /* If remote requests dedicated bonding follow that lead */ @@ -3559,6 +3603,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) hci_extended_inquiry_result_evt(hdev, skb); break; + case HCI_EV_KEY_REFRESH_COMPLETE: + hci_key_refresh_complete_evt(hdev, skb); + break; + case HCI_EV_IO_CAPA_REQUEST: hci_io_capa_request_evt(hdev, skb); break; diff --git a/net/bluetooth/hidp/Kconfig b/net/bluetooth/hidp/Kconfig index 4deaca78e91e..9332bc7aa851 100644 --- a/net/bluetooth/hidp/Kconfig +++ b/net/bluetooth/hidp/Kconfig @@ -1,6 +1,6 @@ config BT_HIDP tristate "HIDP protocol support" - depends on BT && INPUT && HID_SUPPORT + depends on BT && INPUT select HID help HIDP (Human Interface Device Protocol) is a transport layer diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 24f144b72a96..4554e80d16a3 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1295,7 +1295,12 @@ static void security_timeout(struct work_struct *work) struct l2cap_conn *conn = container_of(work, struct l2cap_conn, security_timer.work); - l2cap_conn_del(conn->hcon, ETIMEDOUT); + BT_DBG("conn %p", conn); + + if (test_and_clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags)) { + smp_chan_destroy(conn); + l2cap_conn_del(conn->hcon, ETIMEDOUT); + } } static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status) @@ -2910,12 +2915,14 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) while (len >= L2CAP_CONF_OPT_SIZE) { len -= l2cap_get_conf_opt(&rsp, &type, &olen, &val); - switch (type) { - case L2CAP_CONF_RFC: - if (olen == sizeof(rfc)) - memcpy(&rfc, (void *)val, olen); - goto done; - } + if (type != L2CAP_CONF_RFC) + continue; + + if (olen != sizeof(rfc)) + break; + + memcpy(&rfc, (void *)val, olen); + goto done; } /* Use sane default values in case a misbehaving remote device diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 25d220776079..3e5e3362ea00 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1598,7 +1598,7 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, else conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->addr.bdaddr); - if (!conn) { + if (!conn || conn->state == BT_OPEN || conn->state == BT_CLOSED) { err = cmd_status(sk, hdev->id, MGMT_OP_DISCONNECT, MGMT_STATUS_NOT_CONNECTED); goto failed; @@ -1873,6 +1873,22 @@ static void pairing_complete_cb(struct hci_conn *conn, u8 status) pairing_complete(cmd, mgmt_status(status)); } +static void le_connect_complete_cb(struct hci_conn *conn, u8 status) +{ + struct pending_cmd *cmd; + + BT_DBG("status %u", status); + + if (!status) + return; + + cmd = find_pairing(conn); + if (!cmd) + BT_DBG("Unable to find a pending command"); + else + pairing_complete(cmd, mgmt_status(status)); +} + static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { @@ -1934,6 +1950,8 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, /* For LE, just connecting isn't a proof that the pairing finished */ if (cp->addr.type == BDADDR_BREDR) conn->connect_cfm_cb = pairing_complete_cb; + else + conn->connect_cfm_cb = le_connect_complete_cb; conn->security_cfm_cb = pairing_complete_cb; conn->disconn_cfm_cb = pairing_complete_cb; diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index aa5d73b786ac..d1820ff14aee 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -710,9 +710,9 @@ static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp) break; } - tty_unlock(tty); + tty_unlock(); schedule(); - tty_lock(tty); + tty_lock(); } set_current_state(TASK_RUNNING); remove_wait_queue(&dev->wait, &wait); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 6fc7c4708f3e..37df4e9b3896 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -648,7 +648,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) auth |= (req->auth_req | rsp->auth_req) & SMP_AUTH_MITM; - ret = tk_request(conn, 0, auth, rsp->io_capability, req->io_capability); + ret = tk_request(conn, 0, auth, req->io_capability, rsp->io_capability); if (ret) return SMP_UNSPECIFIED; @@ -703,7 +703,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) return 0; } -static u8 smp_ltk_encrypt(struct l2cap_conn *conn) +static u8 smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level) { struct smp_ltk *key; struct hci_conn *hcon = conn->hcon; @@ -712,6 +712,9 @@ static u8 smp_ltk_encrypt(struct l2cap_conn *conn) if (!key) return 0; + if (sec_level > BT_SECURITY_MEDIUM && !key->authenticated) + return 0; + if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->flags)) return 1; @@ -732,7 +735,7 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) hcon->pending_sec_level = authreq_to_seclevel(rp->auth_req); - if (smp_ltk_encrypt(conn)) + if (smp_ltk_encrypt(conn, hcon->pending_sec_level)) return 0; if (test_and_set_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags)) @@ -771,7 +774,7 @@ int smp_conn_security(struct l2cap_conn *conn, __u8 sec_level) return 1; if (hcon->link_mode & HCI_LM_MASTER) - if (smp_ltk_encrypt(conn)) + if (smp_ltk_encrypt(conn, sec_level)) goto done; if (test_and_set_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags)) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 0a942fbccc9a..e1144e1617be 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -240,6 +240,7 @@ int br_add_bridge(struct net *net, const char *name) return -ENOMEM; dev_net_set(dev, net); + dev->rtnl_link_ops = &br_link_ops; res = register_netdev(dev); if (res) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 2080485515f1..fe41260fbf38 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -208,7 +208,7 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static struct rtnl_link_ops br_link_ops __read_mostly = { +struct rtnl_link_ops br_link_ops __read_mostly = { .kind = "bridge", .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 1a8ad4fb9a6b..a768b2408edf 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -549,6 +549,7 @@ extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) #endif /* br_netlink.c */ +extern struct rtnl_link_ops br_link_ops; extern int br_netlink_init(void); extern void br_netlink_fini(void); extern void br_ifinfo_notify(int event, struct net_bridge_port *port); diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index aa6f716524fd..8c83c175b03a 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -4,8 +4,7 @@ * Author: Sjur Brendeland/sjur.brandeland@stericsson.com * License terms: GNU General Public License (GPL) version 2 * - * Borrowed heavily from file: pn_dev.c. Thanks to - * Remi Denis-Courmont <remi.denis-courmont@nokia.com> + * Borrowed heavily from file: pn_dev.c. Thanks to Remi Denis-Courmont * and Sakari Ailus <sakari.ailus@nokia.com> */ @@ -562,9 +561,9 @@ static int __init caif_device_init(void) static void __exit caif_device_exit(void) { - unregister_pernet_subsys(&caif_net_ops); unregister_netdevice_notifier(&caif_device_notifier); dev_remove_pack(&caif_packet_type); + unregister_pernet_subsys(&caif_net_ops); } module_init(caif_device_init); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index fb8944355264..78f1cdad5b33 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -220,6 +220,7 @@ static void caif_ctrl_cb(struct cflayer *layr, cfsk_hold, cfsk_put); cf_sk->sk.sk_state = CAIF_CONNECTED; set_tx_flow_on(cf_sk); + cf_sk->sk.sk_shutdown = 0; cf_sk->sk.sk_state_change(&cf_sk->sk); break; diff --git a/net/can/raw.c b/net/can/raw.c index cde1b4a20f75..46cca3a91d19 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -681,9 +681,6 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, if (err < 0) goto free_skb; - /* to be able to check the received tx sock reference in raw_rcv() */ - skb_shinfo(skb)->tx_flags |= SKBTX_DRV_NEEDS_SK_REF; - skb->dev = dev; skb->sk = sk; diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c index 214c2bb43d62..925ca583c09c 100644 --- a/net/ceph/auth_none.c +++ b/net/ceph/auth_none.c @@ -59,9 +59,7 @@ static int handle_reply(struct ceph_auth_client *ac, int result, */ static int ceph_auth_none_create_authorizer( struct ceph_auth_client *ac, int peer_type, - struct ceph_authorizer **a, - void **buf, size_t *len, - void **reply_buf, size_t *reply_len) + struct ceph_auth_handshake *auth) { struct ceph_auth_none_info *ai = ac->private; struct ceph_none_authorizer *au = &ai->au; @@ -82,11 +80,12 @@ static int ceph_auth_none_create_authorizer( dout("built authorizer len %d\n", au->buf_len); } - *a = (struct ceph_authorizer *)au; - *buf = au->buf; - *len = au->buf_len; - *reply_buf = au->reply_buf; - *reply_len = sizeof(au->reply_buf); + auth->authorizer = (struct ceph_authorizer *) au; + auth->authorizer_buf = au->buf; + auth->authorizer_buf_len = au->buf_len; + auth->authorizer_reply_buf = au->reply_buf; + auth->authorizer_reply_buf_len = sizeof (au->reply_buf); + return 0; bad2: diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 1587dc6010c6..a16bf14eb027 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -526,9 +526,7 @@ static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result, static int ceph_x_create_authorizer( struct ceph_auth_client *ac, int peer_type, - struct ceph_authorizer **a, - void **buf, size_t *len, - void **reply_buf, size_t *reply_len) + struct ceph_auth_handshake *auth) { struct ceph_x_authorizer *au; struct ceph_x_ticket_handler *th; @@ -548,11 +546,12 @@ static int ceph_x_create_authorizer( return ret; } - *a = (struct ceph_authorizer *)au; - *buf = au->buf->vec.iov_base; - *len = au->buf->vec.iov_len; - *reply_buf = au->reply_buf; - *reply_len = sizeof(au->reply_buf); + auth->authorizer = (struct ceph_authorizer *) au; + auth->authorizer_buf = au->buf->vec.iov_base; + auth->authorizer_buf_len = au->buf->vec.iov_len; + auth->authorizer_reply_buf = au->reply_buf; + auth->authorizer_reply_buf_len = sizeof (au->reply_buf); + return 0; } diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index a776f751edbf..ba4323bce0e9 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -504,13 +504,6 @@ void ceph_destroy_client(struct ceph_client *client) /* unmount */ ceph_osdc_stop(&client->osdc); - /* - * make sure osd connections close out before destroying the - * auth module, which is needed to free those connections' - * ceph_authorizers. - */ - ceph_msgr_flush(); - ceph_monc_stop(&client->monc); ceph_debugfs_client_cleanup(client); diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c index d6ebb13a18a4..089613234f03 100644 --- a/net/ceph/crush/crush.c +++ b/net/ceph/crush/crush.c @@ -26,9 +26,9 @@ const char *crush_bucket_alg_name(int alg) * @b: bucket pointer * @p: item index in bucket */ -int crush_get_bucket_item_weight(struct crush_bucket *b, int p) +int crush_get_bucket_item_weight(const struct crush_bucket *b, int p) { - if (p >= b->size) + if ((__u32)p >= b->size) return 0; switch (b->alg) { @@ -37,38 +37,13 @@ int crush_get_bucket_item_weight(struct crush_bucket *b, int p) case CRUSH_BUCKET_LIST: return ((struct crush_bucket_list *)b)->item_weights[p]; case CRUSH_BUCKET_TREE: - if (p & 1) - return ((struct crush_bucket_tree *)b)->node_weights[p]; - return 0; + return ((struct crush_bucket_tree *)b)->node_weights[crush_calc_tree_node(p)]; case CRUSH_BUCKET_STRAW: return ((struct crush_bucket_straw *)b)->item_weights[p]; } return 0; } -/** - * crush_calc_parents - Calculate parent vectors for the given crush map. - * @map: crush_map pointer - */ -void crush_calc_parents(struct crush_map *map) -{ - int i, b, c; - - for (b = 0; b < map->max_buckets; b++) { - if (map->buckets[b] == NULL) - continue; - for (i = 0; i < map->buckets[b]->size; i++) { - c = map->buckets[b]->items[i]; - BUG_ON(c >= map->max_devices || - c < -map->max_buckets); - if (c >= 0) - map->device_parents[c] = map->buckets[b]->id; - else - map->bucket_parents[-1-c] = map->buckets[b]->id; - } - } -} - void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b) { kfree(b->h.perm); @@ -87,6 +62,8 @@ void crush_destroy_bucket_list(struct crush_bucket_list *b) void crush_destroy_bucket_tree(struct crush_bucket_tree *b) { + kfree(b->h.perm); + kfree(b->h.items); kfree(b->node_weights); kfree(b); } @@ -124,10 +101,9 @@ void crush_destroy_bucket(struct crush_bucket *b) */ void crush_destroy(struct crush_map *map) { - int b; - /* buckets */ if (map->buckets) { + __s32 b; for (b = 0; b < map->max_buckets; b++) { if (map->buckets[b] == NULL) continue; @@ -138,13 +114,12 @@ void crush_destroy(struct crush_map *map) /* rules */ if (map->rules) { + __u32 b; for (b = 0; b < map->max_rules; b++) kfree(map->rules[b]); kfree(map->rules); } - kfree(map->bucket_parents); - kfree(map->device_parents); kfree(map); } diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 363f8f7e6c3c..d7edc24333b8 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -33,9 +33,9 @@ * @type: storage ruleset type (user defined) * @size: output set size */ -int crush_find_rule(struct crush_map *map, int ruleset, int type, int size) +int crush_find_rule(const struct crush_map *map, int ruleset, int type, int size) { - int i; + __u32 i; for (i = 0; i < map->max_rules; i++) { if (map->rules[i] && @@ -73,7 +73,7 @@ static int bucket_perm_choose(struct crush_bucket *bucket, unsigned int i, s; /* start a new permutation if @x has changed */ - if (bucket->perm_x != x || bucket->perm_n == 0) { + if (bucket->perm_x != (__u32)x || bucket->perm_n == 0) { dprintk("bucket %d new x=%d\n", bucket->id, x); bucket->perm_x = x; @@ -153,8 +153,8 @@ static int bucket_list_choose(struct crush_bucket_list *bucket, return bucket->h.items[i]; } - BUG_ON(1); - return 0; + dprintk("bad list sums for bucket %d\n", bucket->h.id); + return bucket->h.items[0]; } @@ -220,7 +220,7 @@ static int bucket_tree_choose(struct crush_bucket_tree *bucket, static int bucket_straw_choose(struct crush_bucket_straw *bucket, int x, int r) { - int i; + __u32 i; int high = 0; __u64 high_draw = 0; __u64 draw; @@ -240,6 +240,7 @@ static int bucket_straw_choose(struct crush_bucket_straw *bucket, static int crush_bucket_choose(struct crush_bucket *in, int x, int r) { dprintk(" crush_bucket_choose %d x=%d r=%d\n", in->id, x, r); + BUG_ON(in->size == 0); switch (in->alg) { case CRUSH_BUCKET_UNIFORM: return bucket_uniform_choose((struct crush_bucket_uniform *)in, @@ -254,7 +255,7 @@ static int crush_bucket_choose(struct crush_bucket *in, int x, int r) return bucket_straw_choose((struct crush_bucket_straw *)in, x, r); default: - BUG_ON(1); + dprintk("unknown bucket %d alg %d\n", in->id, in->alg); return in->items[0]; } } @@ -263,7 +264,7 @@ static int crush_bucket_choose(struct crush_bucket *in, int x, int r) * true if device is marked "out" (failed, fully offloaded) * of the cluster */ -static int is_out(struct crush_map *map, __u32 *weight, int item, int x) +static int is_out(const struct crush_map *map, const __u32 *weight, int item, int x) { if (weight[item] >= 0x10000) return 0; @@ -288,16 +289,16 @@ static int is_out(struct crush_map *map, __u32 *weight, int item, int x) * @recurse_to_leaf: true if we want one device under each item of given type * @out2: second output vector for leaf items (if @recurse_to_leaf) */ -static int crush_choose(struct crush_map *map, +static int crush_choose(const struct crush_map *map, struct crush_bucket *bucket, - __u32 *weight, + const __u32 *weight, int x, int numrep, int type, int *out, int outpos, int firstn, int recurse_to_leaf, int *out2) { int rep; - int ftotal, flocal; + unsigned int ftotal, flocal; int retry_descent, retry_bucket, skip_rep; struct crush_bucket *in = bucket; int r; @@ -305,7 +306,7 @@ static int crush_choose(struct crush_map *map, int item = 0; int itemtype; int collide, reject; - const int orig_tries = 5; /* attempts before we fall back to search */ + const unsigned int orig_tries = 5; /* attempts before we fall back to search */ dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "", bucket->id, x, outpos, numrep); @@ -326,7 +327,7 @@ static int crush_choose(struct crush_map *map, r = rep; if (in->alg == CRUSH_BUCKET_UNIFORM) { /* be careful */ - if (firstn || numrep >= in->size) + if (firstn || (__u32)numrep >= in->size) /* r' = r + f_total */ r += ftotal; else if (in->size % numrep == 0) @@ -355,7 +356,11 @@ static int crush_choose(struct crush_map *map, item = bucket_perm_choose(in, x, r); else item = crush_bucket_choose(in, x, r); - BUG_ON(item >= map->max_devices); + if (item >= map->max_devices) { + dprintk(" bad item %d\n", item); + skip_rep = 1; + break; + } /* desired type? */ if (item < 0) @@ -366,8 +371,12 @@ static int crush_choose(struct crush_map *map, /* keep going? */ if (itemtype != type) { - BUG_ON(item >= 0 || - (-1-item) >= map->max_buckets); + if (item >= 0 || + (-1-item) >= map->max_buckets) { + dprintk(" bad item type %d\n", type); + skip_rep = 1; + break; + } in = map->buckets[-1-item]; retry_bucket = 1; continue; @@ -416,7 +425,7 @@ reject: if (collide && flocal < 3) /* retry locally a few times */ retry_bucket = 1; - else if (flocal < in->size + orig_tries) + else if (flocal <= in->size + orig_tries) /* exhaustive bucket search */ retry_bucket = 1; else if (ftotal < 20) @@ -426,7 +435,7 @@ reject: /* else give up */ skip_rep = 1; dprintk(" reject %d collide %d " - "ftotal %d flocal %d\n", + "ftotal %u flocal %u\n", reject, collide, ftotal, flocal); } @@ -455,15 +464,12 @@ reject: * @x: hash input * @result: pointer to result vector * @result_max: maximum result size - * @force: force initial replica choice; -1 for none */ -int crush_do_rule(struct crush_map *map, +int crush_do_rule(const struct crush_map *map, int ruleno, int x, int *result, int result_max, - int force, __u32 *weight) + const __u32 *weight) { int result_len; - int force_context[CRUSH_MAX_DEPTH]; - int force_pos = -1; int a[CRUSH_MAX_SET]; int b[CRUSH_MAX_SET]; int c[CRUSH_MAX_SET]; @@ -474,66 +480,44 @@ int crush_do_rule(struct crush_map *map, int osize; int *tmp; struct crush_rule *rule; - int step; + __u32 step; int i, j; int numrep; int firstn; - BUG_ON(ruleno >= map->max_rules); + if ((__u32)ruleno >= map->max_rules) { + dprintk(" bad ruleno %d\n", ruleno); + return 0; + } rule = map->rules[ruleno]; result_len = 0; w = a; o = b; - /* - * determine hierarchical context of force, if any. note - * that this may or may not correspond to the specific types - * referenced by the crush rule. - */ - if (force >= 0 && - force < map->max_devices && - map->device_parents[force] != 0 && - !is_out(map, weight, force, x)) { - while (1) { - force_context[++force_pos] = force; - if (force >= 0) - force = map->device_parents[force]; - else - force = map->bucket_parents[-1-force]; - if (force == 0) - break; - } - } - for (step = 0; step < rule->len; step++) { + struct crush_rule_step *curstep = &rule->steps[step]; + firstn = 0; - switch (rule->steps[step].op) { + switch (curstep->op) { case CRUSH_RULE_TAKE: - w[0] = rule->steps[step].arg1; - - /* find position in force_context/hierarchy */ - while (force_pos >= 0 && - force_context[force_pos] != w[0]) - force_pos--; - /* and move past it */ - if (force_pos >= 0) - force_pos--; - + w[0] = curstep->arg1; wsize = 1; break; case CRUSH_RULE_CHOOSE_LEAF_FIRSTN: case CRUSH_RULE_CHOOSE_FIRSTN: firstn = 1; + /* fall through */ case CRUSH_RULE_CHOOSE_LEAF_INDEP: case CRUSH_RULE_CHOOSE_INDEP: - BUG_ON(wsize == 0); + if (wsize == 0) + break; recurse_to_leaf = - rule->steps[step].op == + curstep->op == CRUSH_RULE_CHOOSE_LEAF_FIRSTN || - rule->steps[step].op == + curstep->op == CRUSH_RULE_CHOOSE_LEAF_INDEP; /* reset output */ @@ -545,32 +529,18 @@ int crush_do_rule(struct crush_map *map, * basically, numrep <= 0 means relative to * the provided result_max */ - numrep = rule->steps[step].arg1; + numrep = curstep->arg1; if (numrep <= 0) { numrep += result_max; if (numrep <= 0) continue; } j = 0; - if (osize == 0 && force_pos >= 0) { - /* skip any intermediate types */ - while (force_pos && - force_context[force_pos] < 0 && - rule->steps[step].arg2 != - map->buckets[-1 - - force_context[force_pos]]->type) - force_pos--; - o[osize] = force_context[force_pos]; - if (recurse_to_leaf) - c[osize] = force_context[0]; - j++; - force_pos--; - } osize += crush_choose(map, map->buckets[-1-w[i]], weight, x, numrep, - rule->steps[step].arg2, + curstep->arg2, o+osize, j, firstn, recurse_to_leaf, c+osize); @@ -597,7 +567,9 @@ int crush_do_rule(struct crush_map *map, break; default: - BUG_ON(1); + dprintk(" unknown op %d at step %d\n", + curstep->op, step); + break; } } return result_len; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 36fa6bf68498..10255e81be79 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -563,6 +563,10 @@ static void prepare_write_message(struct ceph_connection *con) m->hdr.seq = cpu_to_le64(++con->out_seq); m->needs_out_seq = false; } +#ifdef CONFIG_BLOCK + else + m->bio_iter = NULL; +#endif dout("prepare_write_message %p seq %lld type %d len %d+%d+%d %d pgs\n", m, con->out_seq, le16_to_cpu(m->hdr.type), @@ -653,54 +657,57 @@ static void prepare_write_keepalive(struct ceph_connection *con) * Connection negotiation. */ -static int prepare_connect_authorizer(struct ceph_connection *con) +static struct ceph_auth_handshake *get_connect_authorizer(struct ceph_connection *con, + int *auth_proto) { - void *auth_buf; - int auth_len = 0; - int auth_protocol = 0; + struct ceph_auth_handshake *auth; + + if (!con->ops->get_authorizer) { + con->out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN; + con->out_connect.authorizer_len = 0; + + return NULL; + } + + /* Can't hold the mutex while getting authorizer */ mutex_unlock(&con->mutex); - if (con->ops->get_authorizer) - con->ops->get_authorizer(con, &auth_buf, &auth_len, - &auth_protocol, &con->auth_reply_buf, - &con->auth_reply_buf_len, - con->auth_retry); + + auth = con->ops->get_authorizer(con, auth_proto, con->auth_retry); + mutex_lock(&con->mutex); - if (test_bit(CLOSED, &con->state) || - test_bit(OPENING, &con->state)) - return -EAGAIN; + if (IS_ERR(auth)) + return auth; + if (test_bit(CLOSED, &con->state) || test_bit(OPENING, &con->state)) + return ERR_PTR(-EAGAIN); - con->out_connect.authorizer_protocol = cpu_to_le32(auth_protocol); - con->out_connect.authorizer_len = cpu_to_le32(auth_len); + con->auth_reply_buf = auth->authorizer_reply_buf; + con->auth_reply_buf_len = auth->authorizer_reply_buf_len; - if (auth_len) - ceph_con_out_kvec_add(con, auth_len, auth_buf); - return 0; + return auth; } /* * We connected to a peer and are saying hello. */ -static void prepare_write_banner(struct ceph_messenger *msgr, - struct ceph_connection *con) +static void prepare_write_banner(struct ceph_connection *con) { - ceph_con_out_kvec_reset(con); ceph_con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER); - ceph_con_out_kvec_add(con, sizeof (msgr->my_enc_addr), - &msgr->my_enc_addr); + ceph_con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr), + &con->msgr->my_enc_addr); con->out_more = 0; set_bit(WRITE_PENDING, &con->state); } -static int prepare_write_connect(struct ceph_messenger *msgr, - struct ceph_connection *con, - int include_banner) +static int prepare_write_connect(struct ceph_connection *con) { unsigned int global_seq = get_global_seq(con->msgr, 0); int proto; + int auth_proto; + struct ceph_auth_handshake *auth; switch (con->peer_name.type) { case CEPH_ENTITY_TYPE_MON: @@ -719,23 +726,32 @@ static int prepare_write_connect(struct ceph_messenger *msgr, dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con, con->connect_seq, global_seq, proto); - con->out_connect.features = cpu_to_le64(msgr->supported_features); + con->out_connect.features = cpu_to_le64(con->msgr->supported_features); con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT); con->out_connect.connect_seq = cpu_to_le32(con->connect_seq); con->out_connect.global_seq = cpu_to_le32(global_seq); con->out_connect.protocol_version = cpu_to_le32(proto); con->out_connect.flags = 0; - if (include_banner) - prepare_write_banner(msgr, con); - else - ceph_con_out_kvec_reset(con); - ceph_con_out_kvec_add(con, sizeof (con->out_connect), &con->out_connect); + auth_proto = CEPH_AUTH_UNKNOWN; + auth = get_connect_authorizer(con, &auth_proto); + if (IS_ERR(auth)) + return PTR_ERR(auth); + + con->out_connect.authorizer_protocol = cpu_to_le32(auth_proto); + con->out_connect.authorizer_len = auth ? + cpu_to_le32(auth->authorizer_buf_len) : 0; + + ceph_con_out_kvec_add(con, sizeof (con->out_connect), + &con->out_connect); + if (auth && auth->authorizer_buf_len) + ceph_con_out_kvec_add(con, auth->authorizer_buf_len, + auth->authorizer_buf); con->out_more = 0; set_bit(WRITE_PENDING, &con->state); - return prepare_connect_authorizer(con); + return 0; } /* @@ -992,11 +1008,10 @@ static int prepare_read_message(struct ceph_connection *con) static int read_partial(struct ceph_connection *con, - int *to, int size, void *object) + int end, int size, void *object) { - *to += size; - while (con->in_base_pos < *to) { - int left = *to - con->in_base_pos; + while (con->in_base_pos < end) { + int left = end - con->in_base_pos; int have = size - left; int ret = ceph_tcp_recvmsg(con->sock, object + have, left); if (ret <= 0) @@ -1012,37 +1027,52 @@ static int read_partial(struct ceph_connection *con, */ static int read_partial_banner(struct ceph_connection *con) { - int ret, to = 0; + int size; + int end; + int ret; dout("read_partial_banner %p at %d\n", con, con->in_base_pos); /* peer's banner */ - ret = read_partial(con, &to, strlen(CEPH_BANNER), con->in_banner); + size = strlen(CEPH_BANNER); + end = size; + ret = read_partial(con, end, size, con->in_banner); if (ret <= 0) goto out; - ret = read_partial(con, &to, sizeof(con->actual_peer_addr), - &con->actual_peer_addr); + + size = sizeof (con->actual_peer_addr); + end += size; + ret = read_partial(con, end, size, &con->actual_peer_addr); if (ret <= 0) goto out; - ret = read_partial(con, &to, sizeof(con->peer_addr_for_me), - &con->peer_addr_for_me); + + size = sizeof (con->peer_addr_for_me); + end += size; + ret = read_partial(con, end, size, &con->peer_addr_for_me); if (ret <= 0) goto out; + out: return ret; } static int read_partial_connect(struct ceph_connection *con) { - int ret, to = 0; + int size; + int end; + int ret; dout("read_partial_connect %p at %d\n", con, con->in_base_pos); - ret = read_partial(con, &to, sizeof(con->in_reply), &con->in_reply); + size = sizeof (con->in_reply); + end = size; + ret = read_partial(con, end, size, &con->in_reply); if (ret <= 0) goto out; - ret = read_partial(con, &to, le32_to_cpu(con->in_reply.authorizer_len), - con->auth_reply_buf); + + size = le32_to_cpu(con->in_reply.authorizer_len); + end += size; + ret = read_partial(con, end, size, con->auth_reply_buf); if (ret <= 0) goto out; @@ -1377,7 +1407,8 @@ static int process_connect(struct ceph_connection *con) return -1; } con->auth_retry = 1; - ret = prepare_write_connect(con->msgr, con, 0); + ceph_con_out_kvec_reset(con); + ret = prepare_write_connect(con); if (ret < 0) return ret; prepare_read_connect(con); @@ -1392,12 +1423,15 @@ static int process_connect(struct ceph_connection *con) * dropped messages. */ dout("process_connect got RESET peer seq %u\n", - le32_to_cpu(con->in_connect.connect_seq)); + le32_to_cpu(con->in_reply.connect_seq)); pr_err("%s%lld %s connection reset\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr)); reset_connection(con); - prepare_write_connect(con->msgr, con, 0); + ceph_con_out_kvec_reset(con); + ret = prepare_write_connect(con); + if (ret < 0) + return ret; prepare_read_connect(con); /* Tell ceph about it. */ @@ -1416,11 +1450,14 @@ static int process_connect(struct ceph_connection *con) * If we sent a smaller connect_seq than the peer has, try * again with a larger value. */ - dout("process_connect got RETRY my seq = %u, peer_seq = %u\n", + dout("process_connect got RETRY_SESSION my seq %u, peer %u\n", le32_to_cpu(con->out_connect.connect_seq), - le32_to_cpu(con->in_connect.connect_seq)); - con->connect_seq = le32_to_cpu(con->in_connect.connect_seq); - prepare_write_connect(con->msgr, con, 0); + le32_to_cpu(con->in_reply.connect_seq)); + con->connect_seq = le32_to_cpu(con->in_reply.connect_seq); + ceph_con_out_kvec_reset(con); + ret = prepare_write_connect(con); + if (ret < 0) + return ret; prepare_read_connect(con); break; @@ -1431,10 +1468,13 @@ static int process_connect(struct ceph_connection *con) */ dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n", con->peer_global_seq, - le32_to_cpu(con->in_connect.global_seq)); + le32_to_cpu(con->in_reply.global_seq)); get_global_seq(con->msgr, - le32_to_cpu(con->in_connect.global_seq)); - prepare_write_connect(con->msgr, con, 0); + le32_to_cpu(con->in_reply.global_seq)); + ceph_con_out_kvec_reset(con); + ret = prepare_write_connect(con); + if (ret < 0) + return ret; prepare_read_connect(con); break; @@ -1491,10 +1531,10 @@ static int process_connect(struct ceph_connection *con) */ static int read_partial_ack(struct ceph_connection *con) { - int to = 0; + int size = sizeof (con->in_temp_ack); + int end = size; - return read_partial(con, &to, sizeof(con->in_temp_ack), - &con->in_temp_ack); + return read_partial(con, end, size, &con->in_temp_ack); } @@ -1627,8 +1667,9 @@ static int read_partial_message_bio(struct ceph_connection *con, static int read_partial_message(struct ceph_connection *con) { struct ceph_msg *m = con->in_msg; + int size; + int end; int ret; - int to, left; unsigned int front_len, middle_len, data_len; bool do_datacrc = !con->msgr->nocrc; int skip; @@ -1638,15 +1679,11 @@ static int read_partial_message(struct ceph_connection *con) dout("read_partial_message con %p msg %p\n", con, m); /* header */ - while (con->in_base_pos < sizeof(con->in_hdr)) { - left = sizeof(con->in_hdr) - con->in_base_pos; - ret = ceph_tcp_recvmsg(con->sock, - (char *)&con->in_hdr + con->in_base_pos, - left); - if (ret <= 0) - return ret; - con->in_base_pos += ret; - } + size = sizeof (con->in_hdr); + end = size; + ret = read_partial(con, end, size, &con->in_hdr); + if (ret <= 0) + return ret; crc = crc32c(0, &con->in_hdr, offsetof(struct ceph_msg_header, crc)); if (cpu_to_le32(crc) != con->in_hdr.crc) { @@ -1759,16 +1796,12 @@ static int read_partial_message(struct ceph_connection *con) } /* footer */ - to = sizeof(m->hdr) + sizeof(m->footer); - while (con->in_base_pos < to) { - left = to - con->in_base_pos; - ret = ceph_tcp_recvmsg(con->sock, (char *)&m->footer + - (con->in_base_pos - sizeof(m->hdr)), - left); - if (ret <= 0) - return ret; - con->in_base_pos += ret; - } + size = sizeof (m->footer); + end += size; + ret = read_partial(con, end, size, &m->footer); + if (ret <= 0) + return ret; + dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n", m, front_len, m->footer.front_crc, middle_len, m->footer.middle_crc, data_len, m->footer.data_crc); @@ -1835,7 +1868,6 @@ static void process_message(struct ceph_connection *con) */ static int try_write(struct ceph_connection *con) { - struct ceph_messenger *msgr = con->msgr; int ret = 1; dout("try_write start %p state %lu nref %d\n", con, con->state, @@ -1846,7 +1878,11 @@ more: /* open the socket first? */ if (con->sock == NULL) { - prepare_write_connect(msgr, con, 1); + ceph_con_out_kvec_reset(con); + prepare_write_banner(con); + ret = prepare_write_connect(con); + if (ret < 0) + goto out; prepare_read_banner(con); set_bit(CONNECTING, &con->state); clear_bit(NEGOTIATING, &con->state); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 10d6008d31f2..d0649a9655be 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -847,6 +847,14 @@ void ceph_monc_stop(struct ceph_mon_client *monc) mutex_unlock(&monc->mutex); + /* + * flush msgr queue before we destroy ourselves to ensure that: + * - any work that references our embedded con is finished. + * - any osd_client or other work that may reference an authorizer + * finishes before we shut down the auth subsystem. + */ + ceph_msgr_flush(); + ceph_auth_destroy(monc->auth); ceph_msg_put(monc->m_auth); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 1b0ef3c4d393..ca59e66c9787 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -139,15 +139,15 @@ void ceph_osdc_release_request(struct kref *kref) if (req->r_request) ceph_msg_put(req->r_request); - if (req->r_reply) - ceph_msg_put(req->r_reply); if (req->r_con_filling_msg) { dout("release_request revoking pages %p from con %p\n", req->r_pages, req->r_con_filling_msg); ceph_con_revoke_message(req->r_con_filling_msg, req->r_reply); - ceph_con_put(req->r_con_filling_msg); + req->r_con_filling_msg->ops->put(req->r_con_filling_msg); } + if (req->r_reply) + ceph_msg_put(req->r_reply); if (req->r_own_pages) ceph_release_page_vector(req->r_pages, req->r_num_pages); @@ -278,7 +278,7 @@ static void osd_req_encode_op(struct ceph_osd_request *req, { dst->op = cpu_to_le16(src->op); - switch (dst->op) { + switch (src->op) { case CEPH_OSD_OP_READ: case CEPH_OSD_OP_WRITE: dst->extent.offset = @@ -664,11 +664,11 @@ static void put_osd(struct ceph_osd *osd) { dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref), atomic_read(&osd->o_ref) - 1); - if (atomic_dec_and_test(&osd->o_ref)) { + if (atomic_dec_and_test(&osd->o_ref) && osd->o_auth.authorizer) { struct ceph_auth_client *ac = osd->o_osdc->client->monc.auth; - if (osd->o_authorizer) - ac->ops->destroy_authorizer(ac, osd->o_authorizer); + if (ac->ops && ac->ops->destroy_authorizer) + ac->ops->destroy_authorizer(ac, osd->o_auth.authorizer); kfree(osd); } } @@ -841,6 +841,12 @@ static void register_request(struct ceph_osd_client *osdc, static void __unregister_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { + if (RB_EMPTY_NODE(&req->r_node)) { + dout("__unregister_request %p tid %lld not registered\n", + req, req->r_tid); + return; + } + dout("__unregister_request %p tid %lld\n", req, req->r_tid); rb_erase(&req->r_node, &osdc->requests); osdc->num_requests--; @@ -1210,7 +1216,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, if (req->r_con_filling_msg == con && req->r_reply == msg) { dout(" dropping con_filling_msg ref %p\n", con); req->r_con_filling_msg = NULL; - ceph_con_put(con); + con->ops->put(con); } if (!req->r_got_reply) { @@ -2022,7 +2028,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, dout("get_reply revoking msg %p from old con %p\n", req->r_reply, req->r_con_filling_msg); ceph_con_revoke_message(req->r_con_filling_msg, req->r_reply); - ceph_con_put(req->r_con_filling_msg); + req->r_con_filling_msg->ops->put(req->r_con_filling_msg); req->r_con_filling_msg = NULL; } @@ -2057,7 +2063,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, #endif } *skip = 0; - req->r_con_filling_msg = ceph_con_get(con); + req->r_con_filling_msg = con->ops->get(con); dout("get_reply tid %lld %p\n", tid, m); out: @@ -2108,37 +2114,32 @@ static void put_osd_con(struct ceph_connection *con) /* * authentication */ -static int get_authorizer(struct ceph_connection *con, - void **buf, int *len, int *proto, - void **reply_buf, int *reply_len, int force_new) +/* + * Note: returned pointer is the address of a structure that's + * managed separately. Caller must *not* attempt to free it. + */ +static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, + int *proto, int force_new) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; - int ret = 0; + struct ceph_auth_handshake *auth = &o->o_auth; - if (force_new && o->o_authorizer) { - ac->ops->destroy_authorizer(ac, o->o_authorizer); - o->o_authorizer = NULL; - } - if (o->o_authorizer == NULL) { - ret = ac->ops->create_authorizer( - ac, CEPH_ENTITY_TYPE_OSD, - &o->o_authorizer, - &o->o_authorizer_buf, - &o->o_authorizer_buf_len, - &o->o_authorizer_reply_buf, - &o->o_authorizer_reply_buf_len); + if (force_new && auth->authorizer) { + if (ac->ops && ac->ops->destroy_authorizer) + ac->ops->destroy_authorizer(ac, auth->authorizer); + auth->authorizer = NULL; + } + if (!auth->authorizer && ac->ops && ac->ops->create_authorizer) { + int ret = ac->ops->create_authorizer(ac, CEPH_ENTITY_TYPE_OSD, + auth); if (ret) - return ret; + return ERR_PTR(ret); } - *proto = ac->protocol; - *buf = o->o_authorizer_buf; - *len = o->o_authorizer_buf_len; - *reply_buf = o->o_authorizer_reply_buf; - *reply_len = o->o_authorizer_reply_buf_len; - return 0; + + return auth; } @@ -2148,7 +2149,11 @@ static int verify_authorizer_reply(struct ceph_connection *con, int len) struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; - return ac->ops->verify_authorizer_reply(ac, o->o_authorizer, len); + /* + * XXX If ac->ops or ac->ops->verify_authorizer_reply is null, + * XXX which do we do: succeed or fail? + */ + return ac->ops->verify_authorizer_reply(ac, o->o_auth.authorizer, len); } static int invalidate_authorizer(struct ceph_connection *con) @@ -2157,7 +2162,7 @@ static int invalidate_authorizer(struct ceph_connection *con) struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; - if (ac->ops->invalidate_authorizer) + if (ac->ops && ac->ops->invalidate_authorizer) ac->ops->invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD); return ceph_monc_validate_auth(&osdc->client->monc); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 56e561a69004..81e3b84a77ef 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -161,13 +161,6 @@ static struct crush_map *crush_decode(void *pbyval, void *end) c->max_rules = ceph_decode_32(p); c->max_devices = ceph_decode_32(p); - c->device_parents = kcalloc(c->max_devices, sizeof(u32), GFP_NOFS); - if (c->device_parents == NULL) - goto badmem; - c->bucket_parents = kcalloc(c->max_buckets, sizeof(u32), GFP_NOFS); - if (c->bucket_parents == NULL) - goto badmem; - c->buckets = kcalloc(c->max_buckets, sizeof(*c->buckets), GFP_NOFS); if (c->buckets == NULL) goto badmem; @@ -890,8 +883,12 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, pglen = ceph_decode_32(p); if (pglen) { - /* insert */ ceph_decode_need(p, end, pglen*sizeof(u32), bad); + + /* removing existing (if any) */ + (void) __remove_pg_mapping(&map->pg_temp, pgid); + + /* insert */ pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS); if (!pg) { err = -ENOMEM; @@ -1000,7 +997,6 @@ int ceph_calc_object_layout(struct ceph_object_layout *ol, { unsigned int num, num_mask; struct ceph_pg pgid; - s32 preferred = (s32)le32_to_cpu(fl->fl_pg_preferred); int poolid = le32_to_cpu(fl->fl_pg_pool); struct ceph_pg_pool_info *pool; unsigned int ps; @@ -1011,23 +1007,13 @@ int ceph_calc_object_layout(struct ceph_object_layout *ol, if (!pool) return -EIO; ps = ceph_str_hash(pool->v.object_hash, oid, strlen(oid)); - if (preferred >= 0) { - ps += preferred; - num = le32_to_cpu(pool->v.lpg_num); - num_mask = pool->lpg_num_mask; - } else { - num = le32_to_cpu(pool->v.pg_num); - num_mask = pool->pg_num_mask; - } + num = le32_to_cpu(pool->v.pg_num); + num_mask = pool->pg_num_mask; pgid.ps = cpu_to_le16(ps); - pgid.preferred = cpu_to_le16(preferred); + pgid.preferred = cpu_to_le16(-1); pgid.pool = fl->fl_pg_pool; - if (preferred >= 0) - dout("calc_object_layout '%s' pgid %d.%xp%d\n", oid, poolid, ps, - (int)preferred); - else - dout("calc_object_layout '%s' pgid %d.%x\n", oid, poolid, ps); + dout("calc_object_layout '%s' pgid %d.%x\n", oid, poolid, ps); ol->ol_pgid = pgid; ol->ol_stripe_unit = fl->fl_object_stripe_unit; @@ -1045,24 +1031,18 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, struct ceph_pg_mapping *pg; struct ceph_pg_pool_info *pool; int ruleno; - unsigned int poolid, ps, pps, t; - int preferred; + unsigned int poolid, ps, pps, t, r; poolid = le32_to_cpu(pgid.pool); ps = le16_to_cpu(pgid.ps); - preferred = (s16)le16_to_cpu(pgid.preferred); pool = __lookup_pg_pool(&osdmap->pg_pools, poolid); if (!pool) return NULL; /* pg_temp? */ - if (preferred >= 0) - t = ceph_stable_mod(ps, le32_to_cpu(pool->v.lpg_num), - pool->lpgp_num_mask); - else - t = ceph_stable_mod(ps, le32_to_cpu(pool->v.pg_num), - pool->pgp_num_mask); + t = ceph_stable_mod(ps, le32_to_cpu(pool->v.pg_num), + pool->pgp_num_mask); pgid.ps = cpu_to_le16(t); pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid); if (pg) { @@ -1080,23 +1060,20 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, return NULL; } - /* don't forcefeed bad device ids to crush */ - if (preferred >= osdmap->max_osd || - preferred >= osdmap->crush->max_devices) - preferred = -1; - - if (preferred >= 0) - pps = ceph_stable_mod(ps, - le32_to_cpu(pool->v.lpgp_num), - pool->lpgp_num_mask); - else - pps = ceph_stable_mod(ps, - le32_to_cpu(pool->v.pgp_num), - pool->pgp_num_mask); + pps = ceph_stable_mod(ps, + le32_to_cpu(pool->v.pgp_num), + pool->pgp_num_mask); pps += poolid; - *num = crush_do_rule(osdmap->crush, ruleno, pps, osds, - min_t(int, pool->v.size, *num), - preferred, osdmap->osd_weight); + r = crush_do_rule(osdmap->crush, ruleno, pps, osds, + min_t(int, pool->v.size, *num), + osdmap->osd_weight); + if (r < 0) { + pr_err("error %d from crush rule: pool %d ruleset %d type %d" + " size %d\n", r, poolid, pool->v.crush_ruleset, + pool->v.type, pool->v.size); + return NULL; + } + *num = r; return osds; } diff --git a/net/core/dev.c b/net/core/dev.c index cd0981977f5c..1cb0d8a6aa6c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1136,8 +1136,8 @@ void dev_load(struct net *net, const char *name) no_module = request_module("netdev-%s", name); if (no_module && capable(CAP_SYS_MODULE)) { if (!request_module("%s", name)) - pr_err("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", - name); + pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", + name); } } EXPORT_SYMBOL(dev_load); @@ -2089,25 +2089,6 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) return 0; } -/* - * Try to orphan skb early, right before transmission by the device. - * We cannot orphan skb if tx timestamp is requested or the sk-reference - * is needed on driver level for other reasons, e.g. see net/can/raw.c - */ -static inline void skb_orphan_try(struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - - if (sk && !skb_shinfo(skb)->tx_flags) { - /* skb_tx_hash() wont be able to get sk. - * We copy sk_hash into skb->rxhash - */ - if (!skb->rxhash) - skb->rxhash = sk->sk_hash; - skb_orphan(skb); - } -} - static bool can_checksum_protocol(netdev_features_t features, __be16 protocol) { return ((features & NETIF_F_GEN_CSUM) || @@ -2193,8 +2174,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, if (!list_empty(&ptype_all)) dev_queue_xmit_nit(skb, dev); - skb_orphan_try(skb); - features = netif_skb_features(skb); if (vlan_tx_tag_present(skb) && @@ -2304,7 +2283,7 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, if (skb->sk && skb->sk->sk_hash) hash = skb->sk->sk_hash; else - hash = (__force u16) skb->protocol ^ skb->rxhash; + hash = (__force u16) skb->protocol; hash = jhash_1word(hash, hashrnd); return (u16) (((u64) hash * qcount) >> 32) + qoffset; @@ -2465,8 +2444,12 @@ static void skb_update_prio(struct sk_buff *skb) { struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); - if ((!skb->priority) && (skb->sk) && map) - skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx]; + if (!skb->priority && skb->sk && map) { + unsigned int prioidx = skb->sk->sk_cgrp_prioidx; + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; + } } #else #define skb_update_prio(skb) @@ -6300,7 +6283,8 @@ static struct hlist_head *netdev_create_hash(void) /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { - INIT_LIST_HEAD(&net->dev_base_head); + if (net != &init_net) + INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 3252e7e0a005..d23b6682f4e9 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -36,9 +36,6 @@ #define TRACE_ON 1 #define TRACE_OFF 0 -static void send_dm_alert(struct work_struct *unused); - - /* * Globals, our netlink socket pointer * and the work handle that will send up @@ -48,11 +45,10 @@ static int trace_state = TRACE_OFF; static DEFINE_MUTEX(trace_state_mutex); struct per_cpu_dm_data { - struct work_struct dm_alert_work; - struct sk_buff __rcu *skb; - atomic_t dm_hit_count; - struct timer_list send_timer; - int cpu; + spinlock_t lock; + struct sk_buff *skb; + struct work_struct dm_alert_work; + struct timer_list send_timer; }; struct dm_hw_stat_delta { @@ -78,13 +74,13 @@ static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static LIST_HEAD(hw_stats_list); -static void reset_per_cpu_data(struct per_cpu_dm_data *data) +static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; struct net_dm_alert_msg *msg; struct nlattr *nla; struct sk_buff *skb; - struct sk_buff *oskb = rcu_dereference_protected(data->skb, 1); + unsigned long flags; al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); @@ -99,65 +95,40 @@ static void reset_per_cpu_data(struct per_cpu_dm_data *data) sizeof(struct net_dm_alert_msg)); msg = nla_data(nla); memset(msg, 0, al); - } else - schedule_work_on(data->cpu, &data->dm_alert_work); - - /* - * Don't need to lock this, since we are guaranteed to only - * run this on a single cpu at a time. - * Note also that we only update data->skb if the old and new skb - * pointers don't match. This ensures that we don't continually call - * synchornize_rcu if we repeatedly fail to alloc a new netlink message. - */ - if (skb != oskb) { - rcu_assign_pointer(data->skb, skb); - - synchronize_rcu(); - - atomic_set(&data->dm_hit_count, dm_hit_limit); + } else { + mod_timer(&data->send_timer, jiffies + HZ / 10); } + spin_lock_irqsave(&data->lock, flags); + swap(data->skb, skb); + spin_unlock_irqrestore(&data->lock, flags); + + return skb; } -static void send_dm_alert(struct work_struct *unused) +static void send_dm_alert(struct work_struct *work) { struct sk_buff *skb; - struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); + struct per_cpu_dm_data *data; - WARN_ON_ONCE(data->cpu != smp_processor_id()); + data = container_of(work, struct per_cpu_dm_data, dm_alert_work); - /* - * Grab the skb we're about to send - */ - skb = rcu_dereference_protected(data->skb, 1); - - /* - * Replace it with a new one - */ - reset_per_cpu_data(data); + skb = reset_per_cpu_data(data); - /* - * Ship it! - */ if (skb) genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL); - - put_cpu_var(dm_cpu_data); } /* * This is the timer function to delay the sending of an alert * in the event that more drops will arrive during the - * hysteresis period. Note that it operates under the timer interrupt - * so we don't need to disable preemption here + * hysteresis period. */ -static void sched_send_work(unsigned long unused) +static void sched_send_work(unsigned long _data) { - struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); - - schedule_work_on(smp_processor_id(), &data->dm_alert_work); + struct per_cpu_dm_data *data = (struct per_cpu_dm_data *)_data; - put_cpu_var(dm_cpu_data); + schedule_work(&data->dm_alert_work); } static void trace_drop_common(struct sk_buff *skb, void *location) @@ -167,33 +138,28 @@ static void trace_drop_common(struct sk_buff *skb, void *location) struct nlattr *nla; int i; struct sk_buff *dskb; - struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); - + struct per_cpu_dm_data *data; + unsigned long flags; - rcu_read_lock(); - dskb = rcu_dereference(data->skb); + local_irq_save(flags); + data = &__get_cpu_var(dm_cpu_data); + spin_lock(&data->lock); + dskb = data->skb; if (!dskb) goto out; - if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) { - /* - * we're already at zero, discard this hit - */ - goto out; - } - nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); for (i = 0; i < msg->entries; i++) { if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { msg->points[i].count++; - atomic_inc(&data->dm_hit_count); goto out; } } - + if (msg->entries == dm_hit_limit) + goto out; /* * We need to create a new entry */ @@ -205,13 +171,11 @@ static void trace_drop_common(struct sk_buff *skb, void *location) if (!timer_pending(&data->send_timer)) { data->send_timer.expires = jiffies + dm_delay * HZ; - add_timer_on(&data->send_timer, smp_processor_id()); + add_timer(&data->send_timer); } out: - rcu_read_unlock(); - put_cpu_var(dm_cpu_data); - return; + spin_unlock_irqrestore(&data->lock, flags); } static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location) @@ -418,11 +382,11 @@ static int __init init_net_drop_monitor(void) for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); - data->cpu = cpu; INIT_WORK(&data->dm_alert_work, send_dm_alert); init_timer(&data->send_timer); - data->send_timer.data = cpu; + data->send_timer.data = (unsigned long)data; data->send_timer.function = sched_send_work; + spin_lock_init(&data->lock); reset_per_cpu_data(data); } @@ -468,3 +432,4 @@ module_exit(exit_net_drop_monitor); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>"); +MODULE_ALIAS_GENL_FAMILY("NET_DM"); diff --git a/net/core/filter.c b/net/core/filter.c index a3eddb515d1b..d4ce2dc712e3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -616,9 +616,9 @@ static int __sk_prepare_filter(struct sk_filter *fp) /** * sk_unattached_filter_create - create an unattached filter * @fprog: the filter program - * @sk: the socket to use + * @pfp: the unattached filter that is created * - * Create a filter independent ofr any socket. We first run some + * Create a filter independent of any socket. We first run some * sanity checks on it to make sure it does not explode on us later. * If an error occurs or there is insufficient memory for the filter * a negative errno code is returned. On success the return is zero. diff --git a/net/core/neighbour.c b/net/core/neighbour.c index eb09f8bbbf07..d81d026138f0 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2219,9 +2219,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - for (h = 0; h < (1 << nht->hash_shift); h++) { - if (h < s_h) - continue; + for (h = s_h; h < (1 << nht->hash_shift); h++) { if (h > s_h) s_idx = 0; for (n = rcu_dereference_bh(nht->hash_buckets[h]), idx = 0; @@ -2260,9 +2258,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, read_lock_bh(&tbl->lock); - for (h = 0; h <= PNEIGH_HASHMASK; h++) { - if (h < s_h) - continue; + for (h = s_h; h <= PNEIGH_HASHMASK; h++) { if (h > s_h) s_idx = 0; for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) { @@ -2297,7 +2293,7 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) struct neigh_table *tbl; int t, family, s_t; int proxy = 0; - int err = 0; + int err; read_lock(&neigh_tbl_lock); family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; @@ -2311,7 +2307,7 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; - for (tbl = neigh_tables, t = 0; tbl && (err >= 0); + for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) { if (t < s_t || (family && tbl->family != family)) continue; @@ -2322,6 +2318,8 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) err = pneigh_dump_table(tbl, skb, cb); else err = neigh_dump_table(tbl, skb, cb); + if (err < 0) + break; } read_unlock(&neigh_tbl_lock); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index dddbacb8f28c..42f1e1c7514f 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -27,7 +27,9 @@ static DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); -struct net init_net; +struct net init_net = { + .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head), +}; EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 3d84fb9d8873..f9f40b932e4b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -362,22 +362,23 @@ EXPORT_SYMBOL(netpoll_send_skb_on_dev); void netpoll_send_udp(struct netpoll *np, const char *msg, int len) { - int total_len, eth_len, ip_len, udp_len; + int total_len, ip_len, udp_len; struct sk_buff *skb; struct udphdr *udph; struct iphdr *iph; struct ethhdr *eth; udp_len = len + sizeof(*udph); - ip_len = eth_len = udp_len + sizeof(*iph); - total_len = eth_len + ETH_HLEN + NET_IP_ALIGN; + ip_len = udp_len + sizeof(*iph); + total_len = ip_len + LL_RESERVED_SPACE(np->dev); - skb = find_skb(np, total_len, total_len - len); + skb = find_skb(np, total_len + np->dev->needed_tailroom, + total_len - len); if (!skb) return; skb_copy_to_linear_data(skb, msg, len); - skb->len += len; + skb_put(skb, len); skb_push(skb, sizeof(*udph)); skb_reset_transport_header(skb); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 5b8aa2fae48b..b2e9caa1ad1a 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -49,8 +49,9 @@ static int get_prioidx(u32 *prio) return -ENOSPC; } set_bit(prioidx, prioidx_map); + if (atomic_read(&max_prioidx) < prioidx) + atomic_set(&max_prioidx, prioidx); spin_unlock_irqrestore(&prioidx_map_lock, flags); - atomic_set(&max_prioidx, prioidx); *prio = prioidx; return 0; } @@ -64,7 +65,7 @@ static void put_prioidx(u32 idx) spin_unlock_irqrestore(&prioidx_map_lock, flags); } -static void extend_netdev_table(struct net_device *dev, u32 new_len) +static int extend_netdev_table(struct net_device *dev, u32 new_len) { size_t new_size = sizeof(struct netprio_map) + ((sizeof(u32) * new_len)); @@ -76,7 +77,7 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len) if (!new_priomap) { pr_warn("Unable to alloc new priomap!\n"); - return; + return -ENOMEM; } for (i = 0; @@ -89,46 +90,79 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len) rcu_assign_pointer(dev->priomap, new_priomap); if (old_priomap) kfree_rcu(old_priomap, rcu); + return 0; } -static void update_netdev_tables(void) +static int write_update_netdev_table(struct net_device *dev) { + int ret = 0; + u32 max_len; + struct netprio_map *map; + + rtnl_lock(); + max_len = atomic_read(&max_prioidx) + 1; + map = rtnl_dereference(dev->priomap); + if (!map || map->priomap_len < max_len) + ret = extend_netdev_table(dev, max_len); + rtnl_unlock(); + + return ret; +} + +static int update_netdev_tables(void) +{ + int ret = 0; struct net_device *dev; - u32 max_len = atomic_read(&max_prioidx) + 1; + u32 max_len; struct netprio_map *map; rtnl_lock(); + max_len = atomic_read(&max_prioidx) + 1; for_each_netdev(&init_net, dev) { map = rtnl_dereference(dev->priomap); - if ((!map) || - (map->priomap_len < max_len)) - extend_netdev_table(dev, max_len); + /* + * don't allocate priomap if we didn't + * change net_prio.ifpriomap (map == NULL), + * this will speed up skb_update_prio. + */ + if (map && map->priomap_len < max_len) { + ret = extend_netdev_table(dev, max_len); + if (ret < 0) + break; + } } rtnl_unlock(); + return ret; } static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp) { struct cgroup_netprio_state *cs; - int ret; + int ret = -EINVAL; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); - if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) { - kfree(cs); - return ERR_PTR(-EINVAL); - } + if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) + goto out; ret = get_prioidx(&cs->prioidx); - if (ret != 0) { + if (ret < 0) { pr_warn("No space in priority index array\n"); - kfree(cs); - return ERR_PTR(ret); + goto out; + } + + ret = update_netdev_tables(); + if (ret < 0) { + put_prioidx(cs->prioidx); + goto out; } return &cs->css; +out: + kfree(cs); + return ERR_PTR(ret); } static void cgrp_destroy(struct cgroup *cgrp) @@ -141,7 +175,7 @@ static void cgrp_destroy(struct cgroup *cgrp) rtnl_lock(); for_each_netdev(&init_net, dev) { map = rtnl_dereference(dev->priomap); - if (map) + if (map && cs->prioidx < map->priomap_len) map->priomap[cs->prioidx] = 0; } rtnl_unlock(); @@ -165,7 +199,7 @@ static int read_priomap(struct cgroup *cont, struct cftype *cft, rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { map = rcu_dereference(dev->priomap); - priority = map ? map->priomap[prioidx] : 0; + priority = (map && prioidx < map->priomap_len) ? map->priomap[prioidx] : 0; cb->fill(cb, dev->name, priority); } rcu_read_unlock(); @@ -220,13 +254,17 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft, if (!dev) goto out_free_devname; - update_netdev_tables(); - ret = 0; + ret = write_update_netdev_table(dev); + if (ret < 0) + goto out_put_dev; + rcu_read_lock(); map = rcu_dereference(dev->priomap); if (map) map->priomap[prioidx] = priority; rcu_read_unlock(); + +out_put_dev: dev_put(dev); out_free_devname: diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 016694d62484..d124306b81fd 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -353,7 +353,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - if (fragsz <= PAGE_SIZE && !(gfp_mask & __GFP_WAIT)) { + if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) { void *data = netdev_alloc_frag(fragsz); if (likely(data)) { @@ -1755,6 +1755,7 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = MAX_SKB_FRAGS, .flags = flags, .ops = &sock_pipe_buf_ops, .spd_release = sock_spd_release, @@ -3361,7 +3362,7 @@ EXPORT_SYMBOL(kfree_skb_partial); * @to: prior buffer * @from: buffer to add * @fragstolen: pointer to boolean - * + * @delta_truesize: how much more was allocated than was requested */ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize) diff --git a/net/core/sock.c b/net/core/sock.c index 653f8c0aedc5..9e5b71fda6ec 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1592,6 +1592,11 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, gfp_t gfp_mask; long timeo; int err; + int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; + + err = -EMSGSIZE; + if (npages > MAX_SKB_FRAGS) + goto failure; gfp_mask = sk->sk_allocation; if (gfp_mask & __GFP_WAIT) @@ -1610,14 +1615,12 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { skb = alloc_skb(header_len, gfp_mask); if (skb) { - int npages; int i; /* No pages, we're done... */ if (!data_len) break; - npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; skb->truesize += data_len; skb_shinfo(skb)->nr_frags = npages; for (i = 0; i < npages; i++) { diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 6fbb2ad7bb6d..16705611589a 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -230,6 +230,12 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, mtu = dev->mtu; pr_debug("name = %s, mtu = %u\n", dev->name, mtu); + if (size > mtu) { + pr_debug("size = %Zu, mtu = %u\n", size, mtu); + err = -EINVAL; + goto out_dev; + } + hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = sock_alloc_send_skb(sk, hlen + tlen + size, @@ -258,12 +264,6 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, if (err < 0) goto out_skb; - if (size > mtu) { - pr_debug("size = %Zu, mtu = %u\n", size, mtu); - err = -EINVAL; - goto out_skb; - } - skb->dev = dev; skb->sk = sk; skb->protocol = htons(ETH_P_IEEE802154); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index c48adc565e92..667c1d4ca984 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1725,8 +1725,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) case CIPSO_V4_TAG_LOCAL: /* This is a non-standard tag that we only allow for * local connections, so if the incoming interface is - * not the loopback device drop the packet. */ - if (!(skb->dev->flags & IFF_LOOPBACK)) { + * not the loopback device drop the packet. Further, + * there is no legitimate reason for setting this from + * userspace so reject it if skb is NULL. */ + if (skb == NULL || !(skb->dev->flags & IFF_LOOPBACK)) { err_offset = opt_iter; goto validate_return_locked; } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 89a47b35905d..cb982a61536f 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -459,28 +459,22 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu) struct esp_data *esp = x->data; u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4); u32 align = max_t(u32, blksize, esp->padlen); - u32 rem; - - mtu -= x->props.header_len + crypto_aead_authsize(esp->aead); - rem = mtu & (align - 1); - mtu &= ~(align - 1); + unsigned int net_adj; switch (x->props.mode) { - case XFRM_MODE_TUNNEL: - break; - default: case XFRM_MODE_TRANSPORT: - /* The worst case */ - mtu -= blksize - 4; - mtu += min_t(u32, blksize - 4, rem); - break; case XFRM_MODE_BEET: - /* The worst case. */ - mtu += min_t(u32, IPV4_BEET_PHMAXLEN, rem); + net_adj = sizeof(struct iphdr); break; + case XFRM_MODE_TUNNEL: + net_adj = 0; + break; + default: + BUG(); } - return mtu - 2; + return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) - + net_adj) & ~(align - 1)) + (net_adj - 2); } static void esp4_err(struct sk_buff *skb, u32 info) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 95e61596e605..f9ee7417f6a0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -377,7 +377,8 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, - sk->sk_protocol, inet_sk_flowi_flags(sk), + sk->sk_protocol, + inet_sk_flowi_flags(sk) & ~FLOWI_FLAG_PRECOW_METRICS, (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr, ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport); security_req_classify_flow(req, flowi4_to_flowi(fl4)); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d4d61b694fab..dfba343b2509 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -560,6 +560,17 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout) } EXPORT_SYMBOL(inet_peer_xrlim_allow); +static void inetpeer_inval_rcu(struct rcu_head *head) +{ + struct inet_peer *p = container_of(head, struct inet_peer, gc_rcu); + + spin_lock_bh(&gc_lock); + list_add_tail(&p->gc_list, &gc_list); + spin_unlock_bh(&gc_lock); + + schedule_delayed_work(&gc_work, gc_delay); +} + void inetpeer_invalidate_tree(int family) { struct inet_peer *old, *new, *prev; @@ -576,10 +587,7 @@ void inetpeer_invalidate_tree(int family) prev = cmpxchg(&base->root, old, new); if (prev == old) { base->total = 0; - spin_lock(&gc_lock); - list_add_tail(&prev->gc_list, &gc_list); - spin_unlock(&gc_lock); - schedule_delayed_work(&gc_work, gc_delay); + call_rcu(&prev->gc_rcu, inetpeer_inval_rcu); } out: diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e5c44fc586ab..ab09b126423c 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -44,6 +44,7 @@ static int ip_forward_finish(struct sk_buff *skb) struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a9e519ad6db5..c94bbc6f2ba3 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1574,6 +1574,7 @@ static inline int ipmr_forward_finish(struct sk_buff *skb) struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a43b87dfe800..c8d28c433b2b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -824,7 +824,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, */ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, - struct request_values *rvp) + struct request_values *rvp, + u16 queue_mapping) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; @@ -840,6 +841,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, if (skb) { __tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr); + skb_set_queue_mapping(skb, queue_mapping); err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, ireq->rmt_addr, ireq->opt); @@ -854,7 +856,7 @@ static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v4_send_synack(sk, NULL, req, rvp); + return tcp_v4_send_synack(sk, NULL, req, rvp, 0); } /* @@ -1422,7 +1424,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_rsk(req)->snt_synack = tcp_time_stamp; if (tcp_v4_send_synack(sk, dst, req, - (struct request_values *)&tmp_ext) || + (struct request_values *)&tmp_ext, + skb_get_queue_mapping(skb)) || want_cookie) goto drop_and_free; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 1e62b7557b00..db1521fcda5b 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -413,19 +413,15 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu) struct esp_data *esp = x->data; u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4); u32 align = max_t(u32, blksize, esp->padlen); - u32 rem; + unsigned int net_adj; - mtu -= x->props.header_len + crypto_aead_authsize(esp->aead); - rem = mtu & (align - 1); - mtu &= ~(align - 1); - - if (x->props.mode != XFRM_MODE_TUNNEL) { - u32 padsize = ((blksize - 1) & 7) + 1; - mtu -= blksize - padsize; - mtu += min_t(u32, blksize - padsize, rem); - } + if (x->props.mode != XFRM_MODE_TUNNEL) + net_adj = sizeof(struct ipv6hdr); + else + net_adj = 0; - return mtu - 2; + return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) - + net_adj) & ~(align - 1)) + (net_adj - 2); } static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 0c220a416626..608327661960 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1349,8 +1349,8 @@ static int fib6_walk_continue(struct fib6_walker_t *w) if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; - if (w->count < w->skip) { - w->count++; + if (w->skip) { + w->skip--; continue; } @@ -1561,7 +1561,7 @@ static int fib6_age(struct rt6_info *rt, void *arg) neigh_flags = neigh->flags; neigh_release(neigh); } - if (neigh_flags & NTF_ROUTER) { + if (!(neigh_flags & NTF_ROUTER)) { RT6_TRACE("purging route %p via non-router but gateway\n", rt); return -1; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d99fdc699625..decc21d19c53 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -526,6 +526,7 @@ int ip6_forward(struct sk_buff *skb) hdr->hop_limit--; IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len); return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev, ip6_forward_finish); @@ -1187,6 +1188,29 @@ static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src, return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; } +static void ip6_append_data_mtu(int *mtu, + int *maxfraglen, + unsigned int fragheaderlen, + struct sk_buff *skb, + struct rt6_info *rt) +{ + if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { + if (skb == NULL) { + /* first fragment, reserve header_len */ + *mtu = *mtu - rt->dst.header_len; + + } else { + /* + * this fragment is not first, the headers + * space is regarded as data space. + */ + *mtu = dst_mtu(rt->dst.path); + } + *maxfraglen = ((*mtu - fragheaderlen) & ~7) + + fragheaderlen - sizeof(struct frag_hdr); + } +} + int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, @@ -1196,7 +1220,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct inet_cork *cork; - struct sk_buff *skb; + struct sk_buff *skb, *skb_prev = NULL; unsigned int maxfraglen, fragheaderlen; int exthdrlen; int dst_exthdrlen; @@ -1253,8 +1277,12 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, inet->cork.fl.u.ip6 = *fl6; np->cork.hop_limit = hlimit; np->cork.tclass = tclass; - mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(&rt->dst); + if (rt->dst.flags & DST_XFRM_TUNNEL) + mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? + rt->dst.dev->mtu : dst_mtu(&rt->dst); + else + mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? + rt->dst.dev->mtu : dst_mtu(rt->dst.path); if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; @@ -1350,25 +1378,27 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; - struct sk_buff *skb_prev; alloc_new_skb: - skb_prev = skb; - /* There's no room in the current skb */ - if (skb_prev) - fraggap = skb_prev->len - maxfraglen; + if (skb) + fraggap = skb->len - maxfraglen; else fraggap = 0; + /* update mtu and maxfraglen if necessary */ + if (skb == NULL || skb_prev == NULL) + ip6_append_data_mtu(&mtu, &maxfraglen, + fragheaderlen, skb, rt); + + skb_prev = skb; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; - if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) - datalen = maxfraglen - fragheaderlen; - fraglen = datalen + fragheaderlen; + if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) + datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; @@ -1377,13 +1407,16 @@ alloc_new_skb: alloclen += dst_exthdrlen; - /* - * The last fragment gets additional space at tail. - * Note: we overallocate on fragments with MSG_MODE - * because we have no idea if we're the last one. - */ - if (datalen == length + fraggap) - alloclen += rt->dst.trailer_len; + if (datalen != length + fraggap) { + /* + * this is not the last fragment, the trailer + * space is regarded as data space. + */ + datalen += rt->dst.trailer_len; + } + + alloclen += rt->dst.trailer_len; + fraglen = datalen + fragheaderlen; /* * We just reserve space for fragment header. diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index b15dc08643a4..461e47c8e956 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1886,6 +1886,8 @@ static inline int ip6mr_forward2_finish(struct sk_buff *skb) { IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP6_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTOCTETS, skb->len); return dst_output(skb); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 999a982ad3fd..becb048d18d4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2957,10 +2957,6 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ; net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; -#ifdef CONFIG_PROC_FS - proc_net_fops_create(net, "ipv6_route", 0, &ipv6_route_proc_fops); - proc_net_fops_create(net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops); -#endif net->ipv6.ip6_rt_gc_expire = 30*HZ; ret = 0; @@ -2981,10 +2977,6 @@ out_ip6_dst_ops: static void __net_exit ip6_route_net_exit(struct net *net) { -#ifdef CONFIG_PROC_FS - proc_net_remove(net, "ipv6_route"); - proc_net_remove(net, "rt6_stats"); -#endif kfree(net->ipv6.ip6_null_entry); #ifdef CONFIG_IPV6_MULTIPLE_TABLES kfree(net->ipv6.ip6_prohibit_entry); @@ -2993,11 +2985,33 @@ static void __net_exit ip6_route_net_exit(struct net *net) dst_entries_destroy(&net->ipv6.ip6_dst_ops); } +static int __net_init ip6_route_net_init_late(struct net *net) +{ +#ifdef CONFIG_PROC_FS + proc_net_fops_create(net, "ipv6_route", 0, &ipv6_route_proc_fops); + proc_net_fops_create(net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops); +#endif + return 0; +} + +static void __net_exit ip6_route_net_exit_late(struct net *net) +{ +#ifdef CONFIG_PROC_FS + proc_net_remove(net, "ipv6_route"); + proc_net_remove(net, "rt6_stats"); +#endif +} + static struct pernet_operations ip6_route_net_ops = { .init = ip6_route_net_init, .exit = ip6_route_net_exit, }; +static struct pernet_operations ip6_route_net_late_ops = { + .init = ip6_route_net_init_late, + .exit = ip6_route_net_exit_late, +}; + static struct notifier_block ip6_route_dev_notifier = { .notifier_call = ip6_route_dev_notify, .priority = 0, @@ -3047,19 +3061,25 @@ int __init ip6_route_init(void) if (ret) goto xfrm6_init; + ret = register_pernet_subsys(&ip6_route_net_late_ops); + if (ret) + goto fib6_rules_init; + ret = -ENOBUFS; if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, NULL) || __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, NULL) || __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL, NULL)) - goto fib6_rules_init; + goto out_register_late_subsys; ret = register_netdevice_notifier(&ip6_route_dev_notifier); if (ret) - goto fib6_rules_init; + goto out_register_late_subsys; out: return ret; +out_register_late_subsys: + unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_init: fib6_rules_cleanup(); xfrm6_init: @@ -3078,6 +3098,7 @@ out_kmem_cache: void ip6_route_cleanup(void) { unregister_netdevice_notifier(&ip6_route_dev_notifier); + unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_cleanup(); xfrm6_fini(); fib6_gc_cleanup(); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 554d5999abc4..9df64a50b075 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -476,7 +476,8 @@ out: static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, - struct request_values *rvp) + struct request_values *rvp, + u16 queue_mapping) { struct inet6_request_sock *treq = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); @@ -513,6 +514,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); fl6.daddr = treq->rmt_addr; + skb_set_queue_mapping(skb, queue_mapping); err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); err = net_xmit_eval(err); } @@ -528,7 +530,7 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req, struct request_values *rvp) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); - return tcp_v6_send_synack(sk, req, rvp); + return tcp_v6_send_synack(sk, req, rvp, 0); } static void tcp_v6_reqsk_destructor(struct request_sock *req) @@ -1210,10 +1212,12 @@ have_isn: tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->snt_synack = tcp_time_stamp; - security_inet_conn_request(sk, skb, req); + if (security_inet_conn_request(sk, skb, req)) + goto drop_and_release; if (tcp_v6_send_synack(sk, req, - (struct request_values *)&tmp_ext) || + (struct request_values *)&tmp_ext, + skb_get_queue_mapping(skb)) || want_cookie) goto drop_and_free; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 07d7d55a1b93..cd6f7a991d80 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -372,7 +372,6 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, skb_trim(skb, skb->dev->mtu); } skb->protocol = ETH_P_AF_IUCV; - skb_shinfo(skb)->tx_flags |= SKBTX_DRV_NEEDS_SK_REF; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 443591d629ca..47b259fccd27 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -42,6 +42,11 @@ struct l2tp_eth { struct sock *tunnel_sock; struct l2tp_session *session; struct list_head list; + atomic_long_t tx_bytes; + atomic_long_t tx_packets; + atomic_long_t rx_bytes; + atomic_long_t rx_packets; + atomic_long_t rx_errors; }; /* via l2tp_session_priv() */ @@ -88,24 +93,40 @@ static int l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct l2tp_eth *priv = netdev_priv(dev); struct l2tp_session *session = priv->session; + atomic_long_add(skb->len, &priv->tx_bytes); + atomic_long_inc(&priv->tx_packets); + l2tp_xmit_skb(session, skb, session->hdr_len); - dev->stats.tx_bytes += skb->len; - dev->stats.tx_packets++; + return NETDEV_TX_OK; +} - return 0; +static struct rtnl_link_stats64 *l2tp_eth_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct l2tp_eth *priv = netdev_priv(dev); + + stats->tx_bytes = atomic_long_read(&priv->tx_bytes); + stats->tx_packets = atomic_long_read(&priv->tx_packets); + stats->rx_bytes = atomic_long_read(&priv->rx_bytes); + stats->rx_packets = atomic_long_read(&priv->rx_packets); + stats->rx_errors = atomic_long_read(&priv->rx_errors); + return stats; } + static struct net_device_ops l2tp_eth_netdev_ops = { .ndo_init = l2tp_eth_dev_init, .ndo_uninit = l2tp_eth_dev_uninit, .ndo_start_xmit = l2tp_eth_dev_xmit, + .ndo_get_stats64 = l2tp_eth_get_stats64, }; static void l2tp_eth_dev_setup(struct net_device *dev) { ether_setup(dev); - dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->features |= NETIF_F_LLTX; dev->netdev_ops = &l2tp_eth_netdev_ops; dev->destructor = free_netdev; } @@ -114,17 +135,17 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, { struct l2tp_eth_sess *spriv = l2tp_session_priv(session); struct net_device *dev = spriv->dev; + struct l2tp_eth *priv = netdev_priv(dev); if (session->debug & L2TP_MSG_DATA) { unsigned int length; - u8 *ptr = skb->data; length = min(32u, skb->len); if (!pskb_may_pull(skb, length)) goto error; pr_debug("%s: eth recv\n", session->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); + print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length); } if (!pskb_may_pull(skb, sizeof(ETH_HLEN))) @@ -139,15 +160,15 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, nf_reset(skb); if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) { - dev->stats.rx_packets++; - dev->stats.rx_bytes += data_len; - } else - dev->stats.rx_errors++; - + atomic_long_inc(&priv->rx_packets); + atomic_long_add(data_len, &priv->rx_bytes); + } else { + atomic_long_inc(&priv->rx_errors); + } return; error: - dev->stats.rx_errors++; + atomic_long_inc(&priv->rx_errors); kfree_skb(skb); } @@ -162,6 +183,7 @@ static void l2tp_eth_delete(struct l2tp_session *session) if (dev) { unregister_netdev(dev); spriv->dev = NULL; + module_put(THIS_MODULE); } } } @@ -249,6 +271,7 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p if (rc < 0) goto out_del_dev; + __module_get(THIS_MODULE); /* Must be done after register_netdev() */ strlcpy(session->ifname, dev->name, IFNAMSIZ); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 889f5d13d7ba..61d8b75d2686 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -239,9 +239,16 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *) uaddr; - int ret = -EINVAL; + int ret; int chk_addr_ret; + if (!sock_flag(sk, SOCK_ZAPPED)) + return -EINVAL; + if (addr_len < sizeof(struct sockaddr_l2tpip)) + return -EINVAL; + if (addr->l2tp_family != AF_INET) + return -EINVAL; + ret = -EADDRINUSE; read_lock_bh(&l2tp_ip_lock); if (__l2tp_ip_bind_lookup(&init_net, addr->l2tp_addr.s_addr, sk->sk_bound_dev_if, addr->l2tp_conn_id)) @@ -272,6 +279,8 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); ret = 0; + sock_reset_flag(sk, SOCK_ZAPPED); + out: release_sock(sk); @@ -288,6 +297,9 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr; int rc; + if (sock_flag(sk, SOCK_ZAPPED)) /* Must bind first - autobinding does not work */ + return -EINVAL; + if (addr_len < sizeof(*lsa)) return -EINVAL; @@ -311,6 +323,14 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len return rc; } +static int l2tp_ip_disconnect(struct sock *sk, int flags) +{ + if (sock_flag(sk, SOCK_ZAPPED)) + return 0; + + return udp_disconnect(sk, flags); +} + static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer) { @@ -444,10 +464,12 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; - if (connected) + if (connected) { sk_setup_caps(sk, &rt->dst); - else - dst_release(&rt->dst); /* safe since we hold rcu_read_lock */ + } else { + skb_dst_set(skb, &rt->dst); + goto xmit; + } } /* We dont need to clone dst here, it is guaranteed to not disappear. @@ -455,6 +477,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m */ skb_dst_set_noref(skb, &rt->dst); +xmit: /* Queue the packet to IP for output */ rc = ip_queue_xmit(skb, &inet->cork.fl); rcu_read_unlock(); @@ -530,7 +553,7 @@ static struct proto l2tp_ip_prot = { .close = l2tp_ip_close, .bind = l2tp_ip_bind, .connect = l2tp_ip_connect, - .disconnect = udp_disconnect, + .disconnect = l2tp_ip_disconnect, .ioctl = udp_ioctl, .destroy = l2tp_ip_destroy_sock, .setsockopt = ip_setsockopt, diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 0291d8d85f30..35e1e4bde587 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -258,6 +258,10 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) int addr_type; int err; + if (!sock_flag(sk, SOCK_ZAPPED)) + return -EINVAL; + if (addr->l2tp_family != AF_INET6) + return -EINVAL; if (addr_len < sizeof(*addr)) return -EINVAL; @@ -331,6 +335,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk_del_node_init(sk); write_unlock_bh(&l2tp_ip6_lock); + sock_reset_flag(sk, SOCK_ZAPPED); release_sock(sk); return 0; @@ -354,6 +359,9 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_type; int rc; + if (sock_flag(sk, SOCK_ZAPPED)) /* Must bind first - autobinding does not work */ + return -EINVAL; + if (addr_len < sizeof(*lsa)) return -EINVAL; @@ -383,6 +391,14 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, return rc; } +static int l2tp_ip6_disconnect(struct sock *sk, int flags) +{ + if (sock_flag(sk, SOCK_ZAPPED)) + return 0; + + return udp_disconnect(sk, flags); +} + static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer) { @@ -689,7 +705,7 @@ static struct proto l2tp_ip6_prot = { .close = l2tp_ip6_close, .bind = l2tp_ip6_bind, .connect = l2tp_ip6_connect, - .disconnect = udp_disconnect, + .disconnect = l2tp_ip6_disconnect, .ioctl = udp_ioctl, .destroy = l2tp_ip6_destroy_sock, .setsockopt = ipv6_setsockopt, diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 8577264378fe..ddc553e76671 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -923,5 +923,4 @@ MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP netlink"); MODULE_LICENSE("GPL"); MODULE_VERSION("1.0"); -MODULE_ALIAS("net-pf-" __stringify(PF_NETLINK) "-proto-" \ - __stringify(NETLINK_GENERIC) "-type-" "l2tp"); +MODULE_ALIAS_GENL_FAMILY("l2tp"); diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 26ddb699d693..c649188314cc 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -145,15 +145,20 @@ static void sta_rx_agg_session_timer_expired(unsigned long data) struct tid_ampdu_rx *tid_rx; unsigned long timeout; + rcu_read_lock(); tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[*ptid]); - if (!tid_rx) + if (!tid_rx) { + rcu_read_unlock(); return; + } timeout = tid_rx->last_rx + TU_TO_JIFFIES(tid_rx->timeout); if (time_is_after_jiffies(timeout)) { mod_timer(&tid_rx->session_timer, timeout); + rcu_read_unlock(); return; } + rcu_read_unlock(); #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "rx session timer expired on tid %d\n", (u16)*ptid); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 495831ee48f1..7d5108a867ad 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -533,16 +533,16 @@ static void ieee80211_get_et_stats(struct wiphy *wiphy, sinfo.filled = 0; sta_set_sinfo(sta, &sinfo); - if (sinfo.filled | STATION_INFO_TX_BITRATE) + if (sinfo.filled & STATION_INFO_TX_BITRATE) data[i] = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate); i++; - if (sinfo.filled | STATION_INFO_RX_BITRATE) + if (sinfo.filled & STATION_INFO_RX_BITRATE) data[i] = 100000 * cfg80211_calculate_bitrate(&sinfo.rxrate); i++; - if (sinfo.filled | STATION_INFO_SIGNAL_AVG) + if (sinfo.filled & STATION_INFO_SIGNAL_AVG) data[i] = (u8)sinfo.signal_avg; i++; } else { @@ -2093,6 +2093,9 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); int i, ret; + if (!ieee80211_sdata_running(sdata)) + return -ENETDOWN; + if (local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL) { ret = drv_set_bitrate_mask(local, sdata, mask); if (ret) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index d4c19a7773db..8664111d0566 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -637,6 +637,18 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_configure_filter(local); break; default: + mutex_lock(&local->mtx); + if (local->hw_roc_dev == sdata->dev && + local->hw_roc_channel) { + /* ignore return value since this is racy */ + drv_cancel_remain_on_channel(local); + ieee80211_queue_work(&local->hw, &local->hw_roc_done); + } + mutex_unlock(&local->mtx); + + flush_work(&local->hw_roc_start); + flush_work(&local->hw_roc_done); + flush_work(&sdata->work); /* * When we get here, the interface is marked down. diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index b3b3c264ff66..0db5d34a06b6 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1220,6 +1220,22 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, sdata->vif.bss_conf.qos = true; } +static void __ieee80211_stop_poll(struct ieee80211_sub_if_data *sdata) +{ + lockdep_assert_held(&sdata->local->mtx); + + sdata->u.mgd.flags &= ~(IEEE80211_STA_CONNECTION_POLL | + IEEE80211_STA_BEACON_POLL); + ieee80211_run_deferred_scan(sdata->local); +} + +static void ieee80211_stop_poll(struct ieee80211_sub_if_data *sdata) +{ + mutex_lock(&sdata->local->mtx); + __ieee80211_stop_poll(sdata); + mutex_unlock(&sdata->local->mtx); +} + static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata, u16 capab, bool erp_valid, u8 erp) { @@ -1285,8 +1301,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, sdata->u.mgd.flags |= IEEE80211_STA_RESET_SIGNAL_AVE; /* just to be sure */ - sdata->u.mgd.flags &= ~(IEEE80211_STA_CONNECTION_POLL | - IEEE80211_STA_BEACON_POLL); + ieee80211_stop_poll(sdata); ieee80211_led_assoc(local, 1); @@ -1327,7 +1342,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct sta_info *sta; u32 changed = 0; - u8 bssid[ETH_ALEN]; ASSERT_MGD_MTX(ifmgd); @@ -1337,10 +1351,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, if (WARN_ON(!ifmgd->associated)) return; - memcpy(bssid, ifmgd->associated->bssid, ETH_ALEN); + ieee80211_stop_poll(sdata); ifmgd->associated = NULL; - memset(ifmgd->bssid, 0, ETH_ALEN); /* * we need to commit the associated = NULL change because the @@ -1360,7 +1373,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, netif_carrier_off(sdata->dev); mutex_lock(&local->sta_mtx); - sta = sta_info_get(sdata, bssid); + sta = sta_info_get(sdata, ifmgd->bssid); if (sta) { set_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_sta_tear_down_BA_sessions(sta, tx); @@ -1369,13 +1382,16 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, /* deauthenticate/disassociate now */ if (tx || frame_buf) - ieee80211_send_deauth_disassoc(sdata, bssid, stype, reason, - tx, frame_buf); + ieee80211_send_deauth_disassoc(sdata, ifmgd->bssid, stype, + reason, tx, frame_buf); /* flush out frame */ if (tx) drv_flush(local, false); + /* clear bssid only after building the needed mgmt frames */ + memset(ifmgd->bssid, 0, ETH_ALEN); + /* remove AP and TDLS peers */ sta_info_flush(local, sdata); @@ -1456,8 +1472,7 @@ static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) return; } - ifmgd->flags &= ~(IEEE80211_STA_CONNECTION_POLL | - IEEE80211_STA_BEACON_POLL); + __ieee80211_stop_poll(sdata); mutex_lock(&local->iflist_mtx); ieee80211_recalc_ps(local, -1); @@ -1477,7 +1492,6 @@ static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME)); out: - ieee80211_run_deferred_scan(local); mutex_unlock(&local->mtx); } @@ -1522,6 +1536,8 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) * anymore. The timeout will be reset if the frame is ACKed by * the AP. */ + ifmgd->probe_send_count++; + if (sdata->local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) { ifmgd->nullfunc_failed = false; ieee80211_send_nullfunc(sdata->local, sdata, 0); @@ -1538,7 +1554,6 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) 0, (u32) -1, true, false); } - ifmgd->probe_send_count++; ifmgd->probe_timeout = jiffies + msecs_to_jiffies(probe_wait_ms); run_again(ifmgd, ifmgd->probe_timeout); if (sdata->local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) @@ -2159,15 +2174,13 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, sdata->name, mgmt->sa, status_code); ieee80211_destroy_assoc_data(sdata, false); } else { - printk(KERN_DEBUG "%s: associated\n", sdata->name); - if (!ieee80211_assoc_success(sdata, *bss, mgmt, len)) { /* oops -- internal error -- send timeout for now */ - ieee80211_destroy_assoc_data(sdata, true); - sta_info_destroy_addr(sdata, mgmt->bssid); + ieee80211_destroy_assoc_data(sdata, false); cfg80211_put_bss(*bss); return RX_MGMT_CFG80211_ASSOC_TIMEOUT; } + printk(KERN_DEBUG "%s: associated\n", sdata->name); /* * destroy assoc_data afterwards, as otherwise an idle @@ -2407,7 +2420,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, net_dbg_ratelimited("%s: cancelling probereq poll due to a received beacon\n", sdata->name); #endif + mutex_lock(&local->mtx); ifmgd->flags &= ~IEEE80211_STA_BEACON_POLL; + ieee80211_run_deferred_scan(local); + mutex_unlock(&local->mtx); + mutex_lock(&local->iflist_mtx); ieee80211_recalc_ps(local, -1); mutex_unlock(&local->iflist_mtx); @@ -2594,9 +2611,6 @@ static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[DEAUTH_DISASSOC_LEN]; - ifmgd->flags &= ~(IEEE80211_STA_CONNECTION_POLL | - IEEE80211_STA_BEACON_POLL); - ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, reason, false, frame_buf); mutex_unlock(&ifmgd->mtx); @@ -2873,8 +2887,7 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) u32 flags; if (sdata->vif.type == NL80211_IFTYPE_STATION) { - sdata->u.mgd.flags &= ~(IEEE80211_STA_BEACON_POLL | - IEEE80211_STA_CONNECTION_POLL); + __ieee80211_stop_poll(sdata); /* let's probe the connection once */ flags = sdata->local->hw.flags; @@ -2943,7 +2956,10 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) if (test_and_clear_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running)) add_timer(&ifmgd->chswitch_timer); ieee80211_sta_reset_beacon_monitor(sdata); + + mutex_lock(&sdata->local->mtx); ieee80211_restart_sta_timer(sdata); + mutex_unlock(&sdata->local->mtx); } #endif @@ -3105,7 +3121,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, } local->oper_channel = cbss->channel; - ieee80211_hw_config(local, 0); + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); if (!have_sta) { u32 rates = 0, basic_rates = 0; diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index f054e94901a2..935aa4b6deee 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -234,6 +234,22 @@ static void ieee80211_hw_roc_done(struct work_struct *work) return; } + /* was never transmitted */ + if (local->hw_roc_skb) { + u64 cookie; + + cookie = local->hw_roc_cookie ^ 2; + + cfg80211_mgmt_tx_status(local->hw_roc_dev, cookie, + local->hw_roc_skb->data, + local->hw_roc_skb->len, false, + GFP_KERNEL); + + kfree_skb(local->hw_roc_skb); + local->hw_roc_skb = NULL; + local->hw_roc_skb_for_status = NULL; + } + if (!local->hw_roc_for_tx) cfg80211_remain_on_channel_expired(local->hw_roc_dev, local->hw_roc_cookie, diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 2d1acc6c5445..f9e51ef8dfa2 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -809,7 +809,7 @@ minstrel_ht_alloc_sta(void *priv, struct ieee80211_sta *sta, gfp_t gfp) max_rates = sband->n_bitrates; } - msp = kzalloc(sizeof(struct minstrel_ht_sta), gfp); + msp = kzalloc(sizeof(*msp), gfp); if (!msp) return NULL; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 7bcecf73aafb..965e6ec0adb6 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2455,7 +2455,7 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx) * frames that we didn't handle, including returning unknown * ones. For all other modes we will return them to the sender, * setting the 0x80 bit in the action category, as required by - * 802.11-2007 7.3.1.11. + * 802.11-2012 9.24.4. * Newer versions of hostapd shall also use the management frame * registration mechanisms, but older ones still use cooked * monitor interfaces so push all frames there. @@ -2465,6 +2465,9 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx) sdata->vif.type == NL80211_IFTYPE_AP_VLAN)) return RX_DROP_MONITOR; + if (is_multicast_ether_addr(mgmt->da)) + return RX_DROP_MONITOR; + /* do not return rejected action frames */ if (mgmt->u.action.category & 0x80) return RX_DROP_UNUSABLE; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f5b1638fbf80..de455f8bbb91 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -378,7 +378,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) /* make the station visible */ sta_info_hash_add(local, sta); - list_add(&sta->list, &local->sta_list); + list_add_rcu(&sta->list, &local->sta_list); set_sta_flag(sta, WLAN_STA_INSERTED); @@ -688,7 +688,7 @@ int __must_check __sta_info_destroy(struct sta_info *sta) if (ret) return ret; - list_del(&sta->list); + list_del_rcu(&sta->list); mutex_lock(&local->key_mtx); for (i = 0; i < NUM_DEFAULT_KEYS; i++) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 3bb24a121c95..a470e1123a55 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -271,6 +271,9 @@ struct sta_ampdu_mlme { * @plink_timer: peer link watch timer * @plink_timer_was_running: used by suspend/resume to restore timers * @t_offset: timing offset relative to this host + * @t_offset_setpoint: reference timing offset of this sta to be used when + * calculating clockdrift + * @ch_type: peer's channel type * @debugfs: debug filesystem info * @dead: set to true when sta is unlinked * @uploaded: set to true when sta is uploaded to the driver @@ -278,6 +281,8 @@ struct sta_ampdu_mlme { * @sta: station information we share with the driver * @sta_state: duplicates information about station state (for debug) * @beacon_loss_count: number of times beacon loss has triggered + * @supports_40mhz: tracks whether the station advertised 40 MHz support + * as we overwrite its HT parameters with the currently used value */ struct sta_info { /* General information, mostly static */ diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 5f827a6b0d8d..e453212fa17f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -153,7 +153,7 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, /* Don't calculate ACKs for QoS Frames with NoAck Policy set */ if (ieee80211_is_data_qos(hdr->frame_control) && - *(ieee80211_get_qos_ctl(hdr)) | IEEE80211_QOS_CTL_ACK_POLICY_NOACK) + *(ieee80211_get_qos_ctl(hdr)) & IEEE80211_QOS_CTL_ACK_POLICY_NOACK) dur = 0; else /* Time needed to transmit ACK @@ -1737,7 +1737,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, __le16 fc; struct ieee80211_hdr hdr; struct ieee80211s_hdr mesh_hdr __maybe_unused; - struct mesh_path __maybe_unused *mppath = NULL; + struct mesh_path __maybe_unused *mppath = NULL, *mpath = NULL; const u8 *encaps_data; int encaps_len, skip_header_bytes; int nh_pos, h_pos; @@ -1803,8 +1803,11 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, goto fail; } rcu_read_lock(); - if (!is_multicast_ether_addr(skb->data)) - mppath = mpp_path_lookup(skb->data, sdata); + if (!is_multicast_ether_addr(skb->data)) { + mpath = mesh_path_lookup(skb->data, sdata); + if (!mpath) + mppath = mpp_path_lookup(skb->data, sdata); + } /* * Use address extension if it is a packet from diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 22f2216b397e..8dd4712620ff 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1271,7 +1271,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) enum ieee80211_sta_state state; for (state = IEEE80211_STA_NOTEXIST; - state < sta->sta_state - 1; state++) + state < sta->sta_state; state++) WARN_ON(drv_sta_state(local, sta->sdata, sta, state, state + 1)); } @@ -1371,6 +1371,12 @@ int ieee80211_reconfig(struct ieee80211_local *local) } } + /* add back keys */ + list_for_each_entry(sdata, &local->interfaces, list) + if (ieee80211_sdata_running(sdata)) + ieee80211_enable_keys(sdata); + + wake_up: /* * Clear the WLAN_STA_BLOCK_BA flag so new aggregation * sessions can be established after a resume. @@ -1392,12 +1398,6 @@ int ieee80211_reconfig(struct ieee80211_local *local) mutex_unlock(&local->sta_mtx); } - /* add back keys */ - list_for_each_entry(sdata, &local->interfaces, list) - if (ieee80211_sdata_running(sdata)) - ieee80211_enable_keys(sdata); - - wake_up: ieee80211_wake_queues_by_reason(hw, IEEE80211_QUEUE_STOP_REASON_SUSPEND); diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 8781d8f904d9..434b6873b352 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -83,9 +83,10 @@ netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb, { struct xmit_work *work; - if (!(priv->phy->channels_supported[page] & (1 << chan))) + if (!(priv->phy->channels_supported[page] & (1 << chan))) { WARN_ON(1); return NETDEV_TX_OK; + } if (!(priv->hw.flags & IEEE802154_HW_OMIT_CKSUM)) { u16 crc = crc_ccitt(0, skb->data, skb->len); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 819c342f5b30..9730882697aa 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -640,6 +640,14 @@ find_free_id(const char *name, ip_set_id_t *index, struct ip_set **set) } static int +ip_set_none(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + return -EOPNOTSUPP; +} + +static int ip_set_create(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const attr[]) @@ -1539,6 +1547,10 @@ nlmsg_failure: } static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = { + [IPSET_CMD_NONE] = { + .call = ip_set_none, + .attr_count = IPSET_ATTR_CMD_MAX, + }, [IPSET_CMD_CREATE] = { .call = ip_set_create, .attr_count = IPSET_ATTR_CMD_MAX, diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index ee863943c826..d5d3607ae7bc 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -38,30 +38,6 @@ struct iface_node { #define iface_data(n) (rb_entry(n, struct iface_node, node)->iface) -static inline long -ifname_compare(const char *_a, const char *_b) -{ - const long *a = (const long *)_a; - const long *b = (const long *)_b; - - BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); - if (a[0] != b[0]) - return a[0] - b[0]; - if (IFNAMSIZ > sizeof(long)) { - if (a[1] != b[1]) - return a[1] - b[1]; - } - if (IFNAMSIZ > 2 * sizeof(long)) { - if (a[2] != b[2]) - return a[2] - b[2]; - } - if (IFNAMSIZ > 3 * sizeof(long)) { - if (a[3] != b[3]) - return a[3] - b[3]; - } - return 0; -} - static void rbtree_destroy(struct rb_root *root) { @@ -99,7 +75,7 @@ iface_test(struct rb_root *root, const char **iface) while (n) { const char *d = iface_data(n); - long res = ifname_compare(*iface, d); + int res = strcmp(*iface, d); if (res < 0) n = n->rb_left; @@ -121,7 +97,7 @@ iface_add(struct rb_root *root, const char **iface) while (*n) { char *ifname = iface_data(*n); - long res = ifname_compare(*iface, ifname); + int res = strcmp(*iface, ifname); p = *n; if (res < 0) @@ -366,7 +342,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netiface4_elem data = { .cidr = HOST_MASK }; u32 ip = 0, ip_to, last; u32 timeout = h->timeout; - char iface[IFNAMSIZ] = {}; + char iface[IFNAMSIZ]; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || @@ -663,7 +639,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface6_elem data = { .cidr = HOST_MASK }; u32 timeout = h->timeout; - char iface[IFNAMSIZ] = {}; + char iface[IFNAMSIZ]; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index dd811b8dd97c..84444dda194b 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -76,19 +76,19 @@ static void __ip_vs_del_service(struct ip_vs_service *svc); #ifdef CONFIG_IP_VS_IPV6 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ -static int __ip_vs_addr_is_local_v6(struct net *net, - const struct in6_addr *addr) +static bool __ip_vs_addr_is_local_v6(struct net *net, + const struct in6_addr *addr) { - struct rt6_info *rt; struct flowi6 fl6 = { .daddr = *addr, }; + struct dst_entry *dst = ip6_route_output(net, NULL, &fl6); + bool is_local; - rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6); - if (rt && rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK)) - return 1; + is_local = !dst->error && dst->dev && (dst->dev->flags & IFF_LOOPBACK); - return 0; + dst_release(dst); + return is_local; } #endif @@ -1521,11 +1521,12 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = ptr; struct net *net = dev_net(dev); + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_service *svc; struct ip_vs_dest *dest; unsigned int idx; - if (event != NETDEV_UNREGISTER) + if (event != NETDEV_UNREGISTER || !ipvs) return NOTIFY_DONE; IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); EnterFunction(2); @@ -1551,7 +1552,7 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, } } - list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) { + list_for_each_entry(dest, &ipvs->dest_trash, n_list) { __ip_vs_dev_reset(dest, dev); } mutex_unlock(&__ip_vs_mutex); diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 46d69d7f1bb4..31f50bc3a312 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -270,9 +270,8 @@ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, return 0; /* RTP port is even */ - port &= htons(~1); - rtp_port = port; - rtcp_port = htons(ntohs(port) + 1); + rtp_port = port & ~htons(1); + rtcp_port = port | htons(1); /* Create expect for RTP */ if ((rtp_exp = nf_ct_expect_alloc(ct)) == NULL) diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 3e797d1fcb94..791d56bbd74a 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -169,8 +169,10 @@ replay: err = nla_parse(cda, ss->cb[cb_id].attr_count, attr, attrlen, ss->cb[cb_id].policy); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); return err; + } if (nc->call_rcu) { err = nc->call_rcu(net->nfnl, skb, nlh, diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c index 0a96a43108ed..1686ca1b53a1 100644 --- a/net/netfilter/xt_HMARK.c +++ b/net/netfilter/xt_HMARK.c @@ -32,13 +32,13 @@ MODULE_ALIAS("ipt_HMARK"); MODULE_ALIAS("ip6t_HMARK"); struct hmark_tuple { - u32 src; - u32 dst; + __be32 src; + __be32 dst; union hmark_ports uports; - uint8_t proto; + u8 proto; }; -static inline u32 hmark_addr6_mask(const __u32 *addr32, const __u32 *mask) +static inline __be32 hmark_addr6_mask(const __be32 *addr32, const __be32 *mask) { return (addr32[0] & mask[0]) ^ (addr32[1] & mask[1]) ^ @@ -46,8 +46,8 @@ static inline u32 hmark_addr6_mask(const __u32 *addr32, const __u32 *mask) (addr32[3] & mask[3]); } -static inline u32 -hmark_addr_mask(int l3num, const __u32 *addr32, const __u32 *mask) +static inline __be32 +hmark_addr_mask(int l3num, const __be32 *addr32, const __be32 *mask) { switch (l3num) { case AF_INET: @@ -58,6 +58,22 @@ hmark_addr_mask(int l3num, const __u32 *addr32, const __u32 *mask) return 0; } +static inline void hmark_swap_ports(union hmark_ports *uports, + const struct xt_hmark_info *info) +{ + union hmark_ports hp; + u16 src, dst; + + hp.b32 = (uports->b32 & info->port_mask.b32) | info->port_set.b32; + src = ntohs(hp.b16.src); + dst = ntohs(hp.b16.dst); + + if (dst > src) + uports->v32 = (dst << 16) | src; + else + uports->v32 = (src << 16) | dst; +} + static int hmark_ct_set_htuple(const struct sk_buff *skb, struct hmark_tuple *t, const struct xt_hmark_info *info) @@ -74,22 +90,19 @@ hmark_ct_set_htuple(const struct sk_buff *skb, struct hmark_tuple *t, otuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; rtuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - t->src = hmark_addr_mask(otuple->src.l3num, otuple->src.u3.all, - info->src_mask.all); - t->dst = hmark_addr_mask(otuple->src.l3num, rtuple->src.u3.all, - info->dst_mask.all); + t->src = hmark_addr_mask(otuple->src.l3num, otuple->src.u3.ip6, + info->src_mask.ip6); + t->dst = hmark_addr_mask(otuple->src.l3num, rtuple->src.u3.ip6, + info->dst_mask.ip6); if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3)) return 0; t->proto = nf_ct_protonum(ct); if (t->proto != IPPROTO_ICMP) { - t->uports.p16.src = otuple->src.u.all; - t->uports.p16.dst = rtuple->src.u.all; - t->uports.v32 = (t->uports.v32 & info->port_mask.v32) | - info->port_set.v32; - if (t->uports.p16.dst < t->uports.p16.src) - swap(t->uports.p16.dst, t->uports.p16.src); + t->uports.b16.src = otuple->src.u.all; + t->uports.b16.dst = rtuple->src.u.all; + hmark_swap_ports(&t->uports, info); } return 0; @@ -98,15 +111,19 @@ hmark_ct_set_htuple(const struct sk_buff *skb, struct hmark_tuple *t, #endif } +/* This hash function is endian independent, to ensure consistent hashing if + * the cluster is composed of big and little endian systems. */ static inline u32 hmark_hash(struct hmark_tuple *t, const struct xt_hmark_info *info) { u32 hash; + u32 src = ntohl(t->src); + u32 dst = ntohl(t->dst); - if (t->dst < t->src) - swap(t->src, t->dst); + if (dst < src) + swap(src, dst); - hash = jhash_3words(t->src, t->dst, t->uports.v32, info->hashrnd); + hash = jhash_3words(src, dst, t->uports.v32, info->hashrnd); hash = hash ^ (t->proto & info->proto_mask); return (((u64)hash * info->hmodulus) >> 32) + info->hoffset; @@ -126,11 +143,7 @@ hmark_set_tuple_ports(const struct sk_buff *skb, unsigned int nhoff, if (skb_copy_bits(skb, nhoff, &t->uports, sizeof(t->uports)) < 0) return; - t->uports.v32 = (t->uports.v32 & info->port_mask.v32) | - info->port_set.v32; - - if (t->uports.p16.dst < t->uports.p16.src) - swap(t->uports.p16.dst, t->uports.p16.src); + hmark_swap_ports(&t->uports, info); } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) @@ -178,8 +191,8 @@ hmark_pkt_set_htuple_ipv6(const struct sk_buff *skb, struct hmark_tuple *t, return -1; } noicmp: - t->src = hmark_addr6_mask(ip6->saddr.s6_addr32, info->src_mask.all); - t->dst = hmark_addr6_mask(ip6->daddr.s6_addr32, info->dst_mask.all); + t->src = hmark_addr6_mask(ip6->saddr.s6_addr32, info->src_mask.ip6); + t->dst = hmark_addr6_mask(ip6->daddr.s6_addr32, info->dst_mask.ip6); if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3)) return 0; @@ -255,11 +268,8 @@ hmark_pkt_set_htuple_ipv4(const struct sk_buff *skb, struct hmark_tuple *t, } } - t->src = (__force u32) ip->saddr; - t->dst = (__force u32) ip->daddr; - - t->src &= info->src_mask.ip; - t->dst &= info->dst_mask.ip; + t->src = ip->saddr & info->src_mask.ip; + t->dst = ip->daddr & info->dst_mask.ip; if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3)) return 0; diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 035960ec5cb9..c6f7db720d84 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -16,6 +16,7 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); @@ -310,7 +311,8 @@ set_target_v2(struct sk_buff *skb, const struct xt_action_param *par) info->del_set.flags, 0, UINT_MAX); /* Normalize to fit into jiffies */ - if (add_opt.timeout > UINT_MAX/MSEC_PER_SEC) + if (add_opt.timeout != IPSET_NO_TIMEOUT && + add_opt.timeout > UINT_MAX/MSEC_PER_SEC) add_opt.timeout = UINT_MAX/MSEC_PER_SEC; if (info->add_set.index != IPSET_INVALID_ID) ip_set_add(info->add_set.index, skb, par, &add_opt); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 8340ace837f2..2cc7c1ee7690 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -836,7 +836,7 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) #ifdef CONFIG_MODULES if (res == NULL) { genl_unlock(); - request_module("net-pf-%d-proto-%d-type-%s", + request_module("net-pf-%d-proto-%d-family-%s", PF_NETLINK, NETLINK_GENERIC, name); genl_lock(); res = genl_family_find_byname(name); diff --git a/net/nfc/llcp/sock.c b/net/nfc/llcp/sock.c index 3f339b19d140..e06d458fc719 100644 --- a/net/nfc/llcp/sock.c +++ b/net/nfc/llcp/sock.c @@ -292,6 +292,9 @@ static int llcp_sock_getname(struct socket *sock, struct sockaddr *addr, pr_debug("%p\n", sk); + if (llcp_sock == NULL || llcp_sock->dev == NULL) + return -EBADFD; + addr->sa_family = AF_NFC; *len = sizeof(struct sockaddr_nfc_llcp); diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index cb2646179e5f..2ab196a9f228 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -106,7 +106,7 @@ static __u8 *nci_extract_rf_params_nfca_passive_poll(struct nci_dev *ndev, nfca_poll->sens_res = __le16_to_cpu(*((__u16 *)data)); data += 2; - nfca_poll->nfcid1_len = *data++; + nfca_poll->nfcid1_len = min_t(__u8, *data++, NFC_NFCID1_MAXSIZE); pr_debug("sens_res 0x%x, nfcid1_len %d\n", nfca_poll->sens_res, nfca_poll->nfcid1_len); @@ -130,7 +130,7 @@ static __u8 *nci_extract_rf_params_nfcb_passive_poll(struct nci_dev *ndev, struct rf_tech_specific_params_nfcb_poll *nfcb_poll, __u8 *data) { - nfcb_poll->sensb_res_len = *data++; + nfcb_poll->sensb_res_len = min_t(__u8, *data++, NFC_SENSB_RES_MAXSIZE); pr_debug("sensb_res_len %d\n", nfcb_poll->sensb_res_len); @@ -145,7 +145,7 @@ static __u8 *nci_extract_rf_params_nfcf_passive_poll(struct nci_dev *ndev, __u8 *data) { nfcf_poll->bit_rate = *data++; - nfcf_poll->sensf_res_len = *data++; + nfcf_poll->sensf_res_len = min_t(__u8, *data++, NFC_SENSF_RES_MAXSIZE); pr_debug("bit_rate %d, sensf_res_len %d\n", nfcf_poll->bit_rate, nfcf_poll->sensf_res_len); @@ -331,7 +331,7 @@ static int nci_extract_activation_params_iso_dep(struct nci_dev *ndev, switch (ntf->activation_rf_tech_and_mode) { case NCI_NFC_A_PASSIVE_POLL_MODE: nfca_poll = &ntf->activation_params.nfca_poll_iso_dep; - nfca_poll->rats_res_len = *data++; + nfca_poll->rats_res_len = min_t(__u8, *data++, 20); pr_debug("rats_res_len %d\n", nfca_poll->rats_res_len); if (nfca_poll->rats_res_len > 0) { memcpy(nfca_poll->rats_res, @@ -341,7 +341,7 @@ static int nci_extract_activation_params_iso_dep(struct nci_dev *ndev, case NCI_NFC_B_PASSIVE_POLL_MODE: nfcb_poll = &ntf->activation_params.nfcb_poll_iso_dep; - nfcb_poll->attrib_res_len = *data++; + nfcb_poll->attrib_res_len = min_t(__u8, *data++, 50); pr_debug("attrib_res_len %d\n", nfcb_poll->attrib_res_len); if (nfcb_poll->attrib_res_len > 0) { memcpy(nfcb_poll->attrib_res, diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index ec1134c9e07f..8b8a6a2b2bad 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -54,7 +54,10 @@ static int rawsock_release(struct socket *sock) { struct sock *sk = sock->sk; - pr_debug("sock=%p\n", sock); + pr_debug("sock=%p sk=%p\n", sock, sk); + + if (!sk) + return 0; sock_orphan(sk); sock_put(sk); diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index 779ce4ff92ec..5a940dbd74a3 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -5,8 +5,8 @@ * * Copyright (C) 2008 Nokia Corporation. * - * Contact: Remi Denis-Courmont <remi.denis-courmont@nokia.com> - * Original author: Sakari Ailus <sakari.ailus@nokia.com> + * Authors: Sakari Ailus <sakari.ailus@nokia.com> + * Rémi Denis-Courmont * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index bf35b4e1a14c..12c30f3e643e 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -5,8 +5,8 @@ * * Copyright (C) 2008 Nokia Corporation. * - * Contact: Remi Denis-Courmont <remi.denis-courmont@nokia.com> - * Original author: Sakari Ailus <sakari.ailus@nokia.com> + * Authors: Sakari Ailus <sakari.ailus@nokia.com> + * Rémi Denis-Courmont * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c index d01208968c83..a2fba7edfd1f 100644 --- a/net/phonet/pep-gprs.c +++ b/net/phonet/pep-gprs.c @@ -5,7 +5,7 @@ * * Copyright (C) 2008 Nokia Corporation. * - * Author: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> + * Author: Rémi Denis-Courmont * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 9dd4f926f7d1..576f22c9c76e 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -5,7 +5,7 @@ * * Copyright (C) 2008 Nokia Corporation. * - * Author: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> + * Author: Rémi Denis-Courmont * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 36f75a9e2c3d..5bf6341e2dd4 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -5,8 +5,8 @@ * * Copyright (C) 2008 Nokia Corporation. * - * Contact: Remi Denis-Courmont <remi.denis-courmont@nokia.com> - * Original author: Sakari Ailus <sakari.ailus@nokia.com> + * Authors: Sakari Ailus <sakari.ailus@nokia.com> + * Rémi Denis-Courmont * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index cfdf135fcd69..7dd762a464e5 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -5,8 +5,8 @@ * * Copyright (C) 2008 Nokia Corporation. * - * Contact: Remi Denis-Courmont <remi.denis-courmont@nokia.com> - * Original author: Sakari Ailus <sakari.ailus@nokia.com> + * Authors: Sakari Ailus <sakari.ailus@nokia.com> + * Remi Denis-Courmont * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 89cfa9ce4939..0acc943f713a 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -5,8 +5,8 @@ * * Copyright (C) 2008 Nokia Corporation. * - * Contact: Remi Denis-Courmont <remi.denis-courmont@nokia.com> - * Original author: Sakari Ailus <sakari.ailus@nokia.com> + * Authors: Sakari Ailus <sakari.ailus@nokia.com> + * Rémi Denis-Courmont * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c index 696348fd31a1..d6bbbbd0af18 100644 --- a/net/phonet/sysctl.c +++ b/net/phonet/sysctl.c @@ -5,7 +5,7 @@ * * Copyright (C) 2008 Nokia Corporation. * - * Contact: Remi Denis-Courmont <remi.denis-courmont@nokia.com> + * Author: Rémi Denis-Courmont * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/net/rds/ib.h b/net/rds/ib.h index edfaaaf164eb..8d2b3d5a7c21 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -186,8 +186,7 @@ struct rds_ib_device { struct work_struct free_work; }; -#define pcidev_to_node(pcidev) pcibus_to_node(pcidev->bus) -#define ibdev_to_node(ibdev) pcidev_to_node(to_pci_dev(ibdev->dma_device)) +#define ibdev_to_node(ibdev) dev_to_node(ibdev->dma_device) #define rdsibdev_to_node(rdsibdev) ibdev_to_node(rdsibdev->dev) /* bits for i_ack_flags */ diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c index 2754f098d436..bebaa43484bc 100644 --- a/net/rxrpc/ar-peer.c +++ b/net/rxrpc/ar-peer.c @@ -229,7 +229,7 @@ found_UDP_peer: return peer; new_UDP_peer: - _net("Rx UDP DGRAM from NEW peer %d", peer->debug_id); + _net("Rx UDP DGRAM from NEW peer"); read_unlock_bh(&rxrpc_peer_lock); _leave(" = -EBUSY [new]"); return ERR_PTR(-EBUSY); diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 8522a4793374..ca8e0a57d945 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -16,8 +16,6 @@ #include <net/netlink.h> #include <net/pkt_sched.h> -extern struct socket *sockfd_lookup(int fd, int *err); /* @@@ fix this */ - /* * The ATM queuing discipline provides a framework for invoking classifiers * (aka "filters"), which in turn select classes of this queuing discipline. diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index a2a95aabf9c2..c412ad0d0308 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -331,29 +331,22 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche return PSCHED_NS2TICKS(ticks); } -static int tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) +static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct sk_buff_head *list = &sch->q; psched_time_t tnext = netem_skb_cb(nskb)->time_to_send; - struct sk_buff *skb; - - if (likely(skb_queue_len(list) < sch->limit)) { - skb = skb_peek_tail(list); - /* Optimize for add at tail */ - if (likely(!skb || tnext >= netem_skb_cb(skb)->time_to_send)) - return qdisc_enqueue_tail(nskb, sch); + struct sk_buff *skb = skb_peek_tail(list); - skb_queue_reverse_walk(list, skb) { - if (tnext >= netem_skb_cb(skb)->time_to_send) - break; - } + /* Optimize for add at tail */ + if (likely(!skb || tnext >= netem_skb_cb(skb)->time_to_send)) + return __skb_queue_tail(list, nskb); - __skb_queue_after(list, skb, nskb); - sch->qstats.backlog += qdisc_pkt_len(nskb); - return NET_XMIT_SUCCESS; + skb_queue_reverse_walk(list, skb) { + if (tnext >= netem_skb_cb(skb)->time_to_send) + break; } - return qdisc_reshape_fail(nskb, sch); + __skb_queue_after(list, skb, nskb); } /* @@ -368,7 +361,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; struct sk_buff *skb2; - int ret; int count = 1; /* Random duplication */ @@ -419,6 +411,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8); } + if (unlikely(skb_queue_len(&sch->q) >= sch->limit)) + return qdisc_reshape_fail(skb, sch); + + sch->qstats.backlog += qdisc_pkt_len(skb); + cb = netem_skb_cb(skb); if (q->gap == 0 || /* not doing reordering */ q->counter < q->gap - 1 || /* inside last reordering gap */ @@ -450,7 +447,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) cb->time_to_send = now + delay; ++q->counter; - ret = tfifo_enqueue(skb, sch); + tfifo_enqueue(skb, sch); } else { /* * Do re-ordering by putting one out of N packets at the front @@ -460,16 +457,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) q->counter = 0; __skb_queue_head(&sch->q, skb); - sch->qstats.backlog += qdisc_pkt_len(skb); sch->qstats.requeues++; - ret = NET_XMIT_SUCCESS; - } - - if (ret != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(ret)) { - sch->qstats.drops++; - return ret; - } } return NET_XMIT_SUCCESS; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 74305c883bd3..30ea4674cabd 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -570,6 +570,8 @@ static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) sch->qstats.backlog = q->qdisc->qstats.backlog; opts = nla_nest_start(skb, TCA_OPTIONS); + if (opts == NULL) + goto nla_put_failure; if (nla_put(skb, TCA_SFB_PARMS, sizeof(opt), &opt)) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5bc9ab161b37..b16517ee1aaf 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -271,6 +271,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a */ asoc->peer.sack_needed = 1; asoc->peer.sack_cnt = 0; + asoc->peer.sack_generation = 1; /* Assume that the peer will tell us if he recognizes ASCONF * as part of INIT exchange. diff --git a/net/sctp/input.c b/net/sctp/input.c index 80564fe03024..8b9b6790a3df 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -736,15 +736,12 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) epb = &ep->base; - if (hlist_unhashed(&epb->node)) - return; - epb->hashent = sctp_ep_hashfn(epb->bind_addr.port); head = &sctp_ep_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - __hlist_del(&epb->node); + hlist_del_init(&epb->node); sctp_write_unlock(&head->lock); } @@ -825,7 +822,7 @@ static void __sctp_unhash_established(struct sctp_association *asoc) head = &sctp_assoc_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - __hlist_del(&epb->node); + hlist_del_init(&epb->node); sctp_write_unlock(&head->lock); } diff --git a/net/sctp/output.c b/net/sctp/output.c index f1b7d4bb591e..6ae47acaaec6 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -248,6 +248,11 @@ static sctp_xmit_t sctp_packet_bundle_sack(struct sctp_packet *pkt, /* If the SACK timer is running, we have a pending SACK */ if (timer_pending(timer)) { struct sctp_chunk *sack; + + if (pkt->transport->sack_generation != + pkt->transport->asoc->peer.sack_generation) + return retval; + asoc->a_rwnd = asoc->rwnd; sack = sctp_make_sack(asoc); if (sack) { diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 5942d27b1444..9c90811d1134 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -673,7 +673,9 @@ void sctp_addr_wq_timeout_handler(unsigned long arg) SCTP_DEBUG_PRINTK("sctp_addrwq_timo_handler: sctp_asconf_mgmt failed\n"); sctp_bh_unlock_sock(sk); } +#if IS_ENABLED(CONFIG_IPV6) free_next: +#endif list_del(&addrw->list); kfree(addrw); } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index a85eeeb55dd0..b6de71efb140 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -734,8 +734,10 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) int len; __u32 ctsn; __u16 num_gabs, num_dup_tsns; + struct sctp_association *aptr = (struct sctp_association *)asoc; struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map; struct sctp_gap_ack_block gabs[SCTP_MAX_GABS]; + struct sctp_transport *trans; memset(gabs, 0, sizeof(gabs)); ctsn = sctp_tsnmap_get_ctsn(map); @@ -805,6 +807,20 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns, sctp_tsnmap_get_dups(map)); + /* Once we have a sack generated, check to see what our sack + * generation is, if its 0, reset the transports to 0, and reset + * the association generation to 1 + * + * The idea is that zero is never used as a valid generation for the + * association so no transport will match after a wrap event like this, + * Until the next sack + */ + if (++aptr->peer.sack_generation == 0) { + list_for_each_entry(trans, &asoc->peer.transport_addr_list, + transports) + trans->sack_generation = 0; + aptr->peer.sack_generation = 1; + } nodata: return retval; } diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index c96d1a81cf42..8716da1a8592 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1268,7 +1268,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_REPORT_TSN: /* Record the arrival of a TSN. */ error = sctp_tsnmap_mark(&asoc->peer.tsn_map, - cmd->obj.u32); + cmd->obj.u32, NULL); break; case SCTP_CMD_REPORT_FWDTSN: diff --git a/net/sctp/socket.c b/net/sctp/socket.c index b3b8a8d813eb..31c7bfcd9b58 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1231,8 +1231,14 @@ out_free: SCTP_DEBUG_PRINTK("About to exit __sctp_connect() free asoc: %p" " kaddrs: %p err: %d\n", asoc, kaddrs, err); - if (asoc) + if (asoc) { + /* sctp_primitive_ASSOCIATE may have added this association + * To the hash table, try to unhash it, just in case, its a noop + * if it wasn't hashed so we're safe + */ + sctp_unhash_established(asoc); sctp_association_free(asoc); + } return err; } @@ -1942,8 +1948,10 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, goto out_unlock; out_free: - if (new_asoc) + if (new_asoc) { + sctp_unhash_established(asoc); sctp_association_free(asoc); + } out_unlock: sctp_release_sock(sk); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index b026ba0c6992..1dcceb6e0ce6 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -68,6 +68,8 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, peer->af_specific = sctp_get_af_specific(addr->sa.sa_family); memset(&peer->saddr, 0, sizeof(union sctp_addr)); + peer->sack_generation = 0; + /* From 6.3.1 RTO Calculation: * * C1) Until an RTT measurement has been made for a packet sent to the diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c index f1e40cebc981..b5fb7c409023 100644 --- a/net/sctp/tsnmap.c +++ b/net/sctp/tsnmap.c @@ -114,7 +114,8 @@ int sctp_tsnmap_check(const struct sctp_tsnmap *map, __u32 tsn) /* Mark this TSN as seen. */ -int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn) +int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn, + struct sctp_transport *trans) { u16 gap; @@ -133,6 +134,9 @@ int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn) */ map->max_tsn_seen++; map->cumulative_tsn_ack_point++; + if (trans) + trans->sack_generation = + trans->asoc->peer.sack_generation; map->base_tsn++; } else { /* Either we already have a gap, or about to record a gap, so diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 8a84017834c2..33d894776192 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -715,7 +715,8 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, * can mark it as received so the tsn_map is updated correctly. */ if (sctp_tsnmap_mark(&asoc->peer.tsn_map, - ntohl(chunk->subh.data_hdr->tsn))) + ntohl(chunk->subh.data_hdr->tsn), + chunk->transport)) goto fail_mark; /* First calculate the padding, so we don't inadvertently diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index f2d1de7f2ffb..f5a6a4f4faf7 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -1051,7 +1051,7 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, if (chunk && (freed >= needed)) { __u32 tsn; tsn = ntohl(chunk->subh.data_hdr->tsn); - sctp_tsnmap_mark(&asoc->peer.tsn_map, tsn); + sctp_tsnmap_mark(&asoc->peer.tsn_map, tsn, chunk->transport); sctp_ulpq_tail_data(ulpq, chunk, gfp); sctp_ulpq_partial_delivery(ulpq, chunk, gfp); diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 38f388c39dce..107c4528654f 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -381,21 +381,53 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) } /* - * We cannot currently handle tokens with rotated data. We need a - * generalized routine to rotate the data in place. It is anticipated - * that we won't encounter rotated data in the general case. + * We can shift data by up to LOCAL_BUF_LEN bytes in a pass. If we need + * to do more than that, we shift repeatedly. Kevin Coffman reports + * seeing 28 bytes as the value used by Microsoft clients and servers + * with AES, so this constant is chosen to allow handling 28 in one pass + * without using too much stack space. + * + * If that proves to a problem perhaps we could use a more clever + * algorithm. */ -static u32 -rotate_left(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, u16 rrc) +#define LOCAL_BUF_LEN 32u + +static void rotate_buf_a_little(struct xdr_buf *buf, unsigned int shift) { - unsigned int realrrc = rrc % (buf->len - offset - GSS_KRB5_TOK_HDR_LEN); + char head[LOCAL_BUF_LEN]; + char tmp[LOCAL_BUF_LEN]; + unsigned int this_len, i; + + BUG_ON(shift > LOCAL_BUF_LEN); - if (realrrc == 0) - return 0; + read_bytes_from_xdr_buf(buf, 0, head, shift); + for (i = 0; i + shift < buf->len; i += LOCAL_BUF_LEN) { + this_len = min(LOCAL_BUF_LEN, buf->len - (i + shift)); + read_bytes_from_xdr_buf(buf, i+shift, tmp, this_len); + write_bytes_to_xdr_buf(buf, i, tmp, this_len); + } + write_bytes_to_xdr_buf(buf, buf->len - shift, head, shift); +} - dprintk("%s: cannot process token with rotated data: " - "rrc %u, realrrc %u\n", __func__, rrc, realrrc); - return 1; +static void _rotate_left(struct xdr_buf *buf, unsigned int shift) +{ + int shifted = 0; + int this_shift; + + shift %= buf->len; + while (shifted < shift) { + this_shift = min(shift - shifted, LOCAL_BUF_LEN); + rotate_buf_a_little(buf, this_shift); + shifted += this_shift; + } +} + +static void rotate_left(u32 base, struct xdr_buf *buf, unsigned int shift) +{ + struct xdr_buf subbuf; + + xdr_buf_subsegment(buf, &subbuf, base, buf->len - base); + _rotate_left(&subbuf, shift); } static u32 @@ -495,11 +527,8 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) seqnum = be64_to_cpup((__be64 *)(ptr + 8)); - if (rrc != 0) { - err = rotate_left(kctx, offset, buf, rrc); - if (err) - return GSS_S_FAILURE; - } + if (rrc != 0) + rotate_left(offset + 16, buf, rrc); err = (*kctx->gk5e->decrypt_v2)(kctx, offset, buf, &headskip, &tailskip); diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 28b62dbb6d1e..73e957386600 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -336,7 +336,6 @@ struct rsc { struct svc_cred cred; struct gss_svc_seq_data seqdata; struct gss_ctx *mechctx; - char *client_name; }; static struct rsc *rsc_update(struct cache_detail *cd, struct rsc *new, struct rsc *old); @@ -347,9 +346,7 @@ static void rsc_free(struct rsc *rsci) kfree(rsci->handle.data); if (rsci->mechctx) gss_delete_sec_context(&rsci->mechctx); - if (rsci->cred.cr_group_info) - put_group_info(rsci->cred.cr_group_info); - kfree(rsci->client_name); + free_svc_cred(&rsci->cred); } static void rsc_put(struct kref *ref) @@ -387,7 +384,7 @@ rsc_init(struct cache_head *cnew, struct cache_head *ctmp) tmp->handle.data = NULL; new->mechctx = NULL; new->cred.cr_group_info = NULL; - new->client_name = NULL; + new->cred.cr_principal = NULL; } static void @@ -402,8 +399,8 @@ update_rsc(struct cache_head *cnew, struct cache_head *ctmp) spin_lock_init(&new->seqdata.sd_lock); new->cred = tmp->cred; tmp->cred.cr_group_info = NULL; - new->client_name = tmp->client_name; - tmp->client_name = NULL; + new->cred.cr_principal = tmp->cred.cr_principal; + tmp->cred.cr_principal = NULL; } static struct cache_head * @@ -501,8 +498,8 @@ static int rsc_parse(struct cache_detail *cd, /* get client name */ len = qword_get(&mesg, buf, mlen); if (len > 0) { - rsci.client_name = kstrdup(buf, GFP_KERNEL); - if (!rsci.client_name) + rsci.cred.cr_principal = kstrdup(buf, GFP_KERNEL); + if (!rsci.cred.cr_principal) goto out; } @@ -932,16 +929,6 @@ struct gss_svc_data { struct rsc *rsci; }; -char *svc_gss_principal(struct svc_rqst *rqstp) -{ - struct gss_svc_data *gd = (struct gss_svc_data *)rqstp->rq_auth_data; - - if (gd && gd->rsci) - return gd->rsci->client_name; - return NULL; -} -EXPORT_SYMBOL_GPL(svc_gss_principal); - static int svcauth_gss_set_client(struct svc_rqst *rqstp) { @@ -969,16 +956,17 @@ svcauth_gss_set_client(struct svc_rqst *rqstp) } static inline int -gss_write_init_verf(struct cache_detail *cd, struct svc_rqst *rqstp, struct rsi *rsip) +gss_write_init_verf(struct cache_detail *cd, struct svc_rqst *rqstp, + struct xdr_netobj *out_handle, int *major_status) { struct rsc *rsci; int rc; - if (rsip->major_status != GSS_S_COMPLETE) + if (*major_status != GSS_S_COMPLETE) return gss_write_null_verf(rqstp); - rsci = gss_svc_searchbyctx(cd, &rsip->out_handle); + rsci = gss_svc_searchbyctx(cd, out_handle); if (rsci == NULL) { - rsip->major_status = GSS_S_NO_CONTEXT; + *major_status = GSS_S_NO_CONTEXT; return gss_write_null_verf(rqstp); } rc = gss_write_verf(rqstp, rsci->mechctx, GSS_SEQ_WIN); @@ -986,22 +974,13 @@ gss_write_init_verf(struct cache_detail *cd, struct svc_rqst *rqstp, struct rsi return rc; } -/* - * Having read the cred already and found we're in the context - * initiation case, read the verifier and initiate (or check the results - * of) upcalls to userspace for help with context initiation. If - * the upcall results are available, write the verifier and result. - * Otherwise, drop the request pending an answer to the upcall. - */ -static int svcauth_gss_handle_init(struct svc_rqst *rqstp, - struct rpc_gss_wire_cred *gc, __be32 *authp) +static inline int +gss_read_verf(struct rpc_gss_wire_cred *gc, + struct kvec *argv, __be32 *authp, + struct xdr_netobj *in_handle, + struct xdr_netobj *in_token) { - struct kvec *argv = &rqstp->rq_arg.head[0]; - struct kvec *resv = &rqstp->rq_res.head[0]; struct xdr_netobj tmpobj; - struct rsi *rsip, rsikey; - int ret; - struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id); /* Read the verifier; should be NULL: */ *authp = rpc_autherr_badverf; @@ -1011,24 +990,67 @@ static int svcauth_gss_handle_init(struct svc_rqst *rqstp, return SVC_DENIED; if (svc_getnl(argv) != 0) return SVC_DENIED; - /* Martial context handle and token for upcall: */ *authp = rpc_autherr_badcred; if (gc->gc_proc == RPC_GSS_PROC_INIT && gc->gc_ctx.len != 0) return SVC_DENIED; - memset(&rsikey, 0, sizeof(rsikey)); - if (dup_netobj(&rsikey.in_handle, &gc->gc_ctx)) + if (dup_netobj(in_handle, &gc->gc_ctx)) return SVC_CLOSE; *authp = rpc_autherr_badverf; if (svc_safe_getnetobj(argv, &tmpobj)) { - kfree(rsikey.in_handle.data); + kfree(in_handle->data); return SVC_DENIED; } - if (dup_netobj(&rsikey.in_token, &tmpobj)) { - kfree(rsikey.in_handle.data); + if (dup_netobj(in_token, &tmpobj)) { + kfree(in_handle->data); return SVC_CLOSE; } + return 0; +} + +static inline int +gss_write_resv(struct kvec *resv, size_t size_limit, + struct xdr_netobj *out_handle, struct xdr_netobj *out_token, + int major_status, int minor_status) +{ + if (resv->iov_len + 4 > size_limit) + return -1; + svc_putnl(resv, RPC_SUCCESS); + if (svc_safe_putnetobj(resv, out_handle)) + return -1; + if (resv->iov_len + 3 * 4 > size_limit) + return -1; + svc_putnl(resv, major_status); + svc_putnl(resv, minor_status); + svc_putnl(resv, GSS_SEQ_WIN); + if (svc_safe_putnetobj(resv, out_token)) + return -1; + return 0; +} + +/* + * Having read the cred already and found we're in the context + * initiation case, read the verifier and initiate (or check the results + * of) upcalls to userspace for help with context initiation. If + * the upcall results are available, write the verifier and result. + * Otherwise, drop the request pending an answer to the upcall. + */ +static int svcauth_gss_handle_init(struct svc_rqst *rqstp, + struct rpc_gss_wire_cred *gc, __be32 *authp) +{ + struct kvec *argv = &rqstp->rq_arg.head[0]; + struct kvec *resv = &rqstp->rq_res.head[0]; + struct rsi *rsip, rsikey; + int ret; + struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id); + + memset(&rsikey, 0, sizeof(rsikey)); + ret = gss_read_verf(gc, argv, authp, + &rsikey.in_handle, &rsikey.in_token); + if (ret) + return ret; + /* Perform upcall, or find upcall result: */ rsip = rsi_lookup(sn->rsi_cache, &rsikey); rsi_free(&rsikey); @@ -1040,19 +1062,12 @@ static int svcauth_gss_handle_init(struct svc_rqst *rqstp, ret = SVC_CLOSE; /* Got an answer to the upcall; use it: */ - if (gss_write_init_verf(sn->rsc_cache, rqstp, rsip)) - goto out; - if (resv->iov_len + 4 > PAGE_SIZE) + if (gss_write_init_verf(sn->rsc_cache, rqstp, + &rsip->out_handle, &rsip->major_status)) goto out; - svc_putnl(resv, RPC_SUCCESS); - if (svc_safe_putnetobj(resv, &rsip->out_handle)) - goto out; - if (resv->iov_len + 3 * 4 > PAGE_SIZE) - goto out; - svc_putnl(resv, rsip->major_status); - svc_putnl(resv, rsip->minor_status); - svc_putnl(resv, GSS_SEQ_WIN); - if (svc_safe_putnetobj(resv, &rsip->out_token)) + if (gss_write_resv(resv, PAGE_SIZE, + &rsip->out_handle, &rsip->out_token, + rsip->major_status, rsip->minor_status)) goto out; ret = SVC_COMPLETE; @@ -1192,7 +1207,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) } svcdata->rsci = rsci; cache_get(&rsci->h); - rqstp->rq_flavor = gss_svc_to_pseudoflavor( + rqstp->rq_cred.cr_flavor = gss_svc_to_pseudoflavor( rsci->mechctx->mech_type, gc->gc_svc); ret = SVC_OK; goto out; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 04040476082e..21fde99e5c56 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -71,7 +71,9 @@ static void rpc_purge_list(wait_queue_head_t *waitq, struct list_head *head, msg->errno = err; destroy_msg(msg); } while (!list_empty(head)); - wake_up(waitq); + + if (waitq) + wake_up(waitq); } static void @@ -91,11 +93,9 @@ rpc_timeout_upcall_queue(struct work_struct *work) } dentry = dget(pipe->dentry); spin_unlock(&pipe->lock); - if (dentry) { - rpc_purge_list(&RPC_I(dentry->d_inode)->waitq, - &free_list, destroy_msg, -ETIMEDOUT); - dput(dentry); - } + rpc_purge_list(dentry ? &RPC_I(dentry->d_inode)->waitq : NULL, + &free_list, destroy_msg, -ETIMEDOUT); + dput(dentry); } ssize_t rpc_pipe_generic_upcall(struct file *filp, struct rpc_pipe_msg *msg, diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 3c0653439f3d..92509ffe15fc 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -180,14 +180,16 @@ void rpcb_put_local(struct net *net) struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_clnt *clnt = sn->rpcb_local_clnt; struct rpc_clnt *clnt4 = sn->rpcb_local_clnt4; - int shutdown; + int shutdown = 0; spin_lock(&sn->rpcb_clnt_lock); - if (--sn->rpcb_users == 0) { - sn->rpcb_local_clnt = NULL; - sn->rpcb_local_clnt4 = NULL; + if (sn->rpcb_users) { + if (--sn->rpcb_users == 0) { + sn->rpcb_local_clnt = NULL; + sn->rpcb_local_clnt4 = NULL; + } + shutdown = !sn->rpcb_users; } - shutdown = !sn->rpcb_users; spin_unlock(&sn->rpcb_clnt_lock); if (shutdown) { diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 017c0117d154..3ee7461926d8 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -407,6 +407,14 @@ static int svc_uses_rpcbind(struct svc_serv *serv) return 0; } +int svc_bind(struct svc_serv *serv, struct net *net) +{ + if (!svc_uses_rpcbind(serv)) + return 0; + return svc_rpcb_setup(serv, net); +} +EXPORT_SYMBOL_GPL(svc_bind); + /* * Create an RPC service */ @@ -471,15 +479,8 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, spin_lock_init(&pool->sp_lock); } - if (svc_uses_rpcbind(serv)) { - if (svc_rpcb_setup(serv, current->nsproxy->net_ns) < 0) { - kfree(serv->sv_pools); - kfree(serv); - return NULL; - } - if (!serv->sv_shutdown) - serv->sv_shutdown = svc_rpcb_cleanup; - } + if (svc_uses_rpcbind(serv) && (!serv->sv_shutdown)) + serv->sv_shutdown = svc_rpcb_cleanup; return serv; } @@ -536,8 +537,6 @@ EXPORT_SYMBOL_GPL(svc_shutdown_net); void svc_destroy(struct svc_serv *serv) { - struct net *net = current->nsproxy->net_ns; - dprintk("svc: svc_destroy(%s, %d)\n", serv->sv_program->pg_name, serv->sv_nrthreads); @@ -552,8 +551,6 @@ svc_destroy(struct svc_serv *serv) del_timer_sync(&serv->sv_temptimer); - svc_shutdown_net(serv, net); - /* * The last user is gone and thus all sockets have to be destroyed to * the point. Check this. @@ -1377,7 +1374,8 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, sizeof(req->rq_snd_buf)); return bc_send(req); } else { - /* Nothing to do to drop request */ + /* drop request */ + xprt_free_bc_request(req); return 0; } } diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index b98ee3514912..88f2bf671960 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -598,6 +598,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) /* now allocate needed pages. If we get a failure, sleep briefly */ pages = (serv->sv_max_mesg + PAGE_SIZE) / PAGE_SIZE; + BUG_ON(pages >= RPCSVC_MAXPAGES); for (i = 0; i < pages ; i++) while (rqstp->rq_pages[i] == NULL) { struct page *p = alloc_page(GFP_KERNEL); @@ -612,7 +613,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) rqstp->rq_pages[i] = p; } rqstp->rq_pages[i++] = NULL; /* this might be seen in nfs_read_actor */ - BUG_ON(pages >= RPCSVC_MAXPAGES); /* Make arg->head point to first page and arg->pages point to rest */ arg = &rqstp->rq_arg; @@ -973,7 +973,7 @@ void svc_close_net(struct svc_serv *serv, struct net *net) svc_clear_pools(serv, net); /* * At this point the sp_sockets lists will stay empty, since - * svc_enqueue will not add new entries without taking the + * svc_xprt_enqueue will not add new entries without taking the * sp_lock and checking XPT_BUSY. */ svc_clear_list(&serv->sv_tempsocks, net); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 71ec8530ec8c..2777fa896645 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -347,17 +347,12 @@ static inline int ip_map_update(struct net *net, struct ip_map *ipm, return __ip_map_update(sn->ip_map_cache, ipm, udom, expiry); } - -void svcauth_unix_purge(void) +void svcauth_unix_purge(struct net *net) { - struct net *net; - - for_each_net(net) { - struct sunrpc_net *sn; + struct sunrpc_net *sn; - sn = net_generic(net, sunrpc_net_id); - cache_purge(sn->ip_map_cache); - } + sn = net_generic(net, sunrpc_net_id); + cache_purge(sn->ip_map_cache); } EXPORT_SYMBOL_GPL(svcauth_unix_purge); @@ -751,6 +746,7 @@ svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp) struct svc_cred *cred = &rqstp->rq_cred; cred->cr_group_info = NULL; + cred->cr_principal = NULL; rqstp->rq_client = NULL; if (argv->iov_len < 3*4) @@ -778,7 +774,7 @@ svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp) svc_putnl(resv, RPC_AUTH_NULL); svc_putnl(resv, 0); - rqstp->rq_flavor = RPC_AUTH_NULL; + rqstp->rq_cred.cr_flavor = RPC_AUTH_NULL; return SVC_OK; } @@ -816,6 +812,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) int len = argv->iov_len; cred->cr_group_info = NULL; + cred->cr_principal = NULL; rqstp->rq_client = NULL; if ((len -= 3*4) < 0) @@ -852,7 +849,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) svc_putnl(resv, RPC_AUTH_NULL); svc_putnl(resv, 0); - rqstp->rq_flavor = RPC_AUTH_UNIX; + rqstp->rq_cred.cr_flavor = RPC_AUTH_UNIX; return SVC_OK; badcred: diff --git a/net/wanrouter/Kconfig b/net/wanrouter/Kconfig index 61ceae0b9566..a157a2e64e18 100644 --- a/net/wanrouter/Kconfig +++ b/net/wanrouter/Kconfig @@ -3,7 +3,7 @@ # config WAN_ROUTER - tristate "WAN router" + tristate "WAN router (DEPRECATED)" depends on EXPERIMENTAL ---help--- Wide Area Networks (WANs), such as X.25, frame relay and leased diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index d2a19b0ff71f..89baa3328411 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -42,6 +42,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid) cfg80211_hold_bss(bss_from_pub(bss)); wdev->current_bss = bss_from_pub(bss); + wdev->sme_state = CFG80211_SME_CONNECTED; cfg80211_upload_connect_keys(wdev); nl80211_send_ibss_bssid(wiphy_to_dev(wdev->wiphy), dev, bssid, @@ -60,7 +61,7 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) struct cfg80211_event *ev; unsigned long flags; - CFG80211_DEV_WARN_ON(!wdev->ssid_len); + CFG80211_DEV_WARN_ON(wdev->sme_state != CFG80211_SME_CONNECTING); ev = kzalloc(sizeof(*ev), gfp); if (!ev) @@ -115,9 +116,11 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, #ifdef CONFIG_CFG80211_WEXT wdev->wext.ibss.channel = params->channel; #endif + wdev->sme_state = CFG80211_SME_CONNECTING; err = rdev->ops->join_ibss(&rdev->wiphy, dev, params); if (err) { wdev->connect_keys = NULL; + wdev->sme_state = CFG80211_SME_IDLE; return err; } @@ -169,6 +172,7 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext) } wdev->current_bss = NULL; + wdev->sme_state = CFG80211_SME_IDLE; wdev->ssid_len = 0; #ifdef CONFIG_CFG80211_WEXT if (!nowext) diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 15f347477a99..baf5704740ee 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1389,7 +1389,7 @@ static void reg_set_request_processed(void) spin_unlock(®_requests_lock); if (last_request->initiator == NL80211_REGDOM_SET_BY_USER) - cancel_delayed_work_sync(®_timeout); + cancel_delayed_work(®_timeout); if (need_more_processing) schedule_work(®_work); diff --git a/net/wireless/util.c b/net/wireless/util.c index 55d99466babb..316cfd00914f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -804,7 +804,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, ntype == NL80211_IFTYPE_P2P_CLIENT)) return -EBUSY; - if (ntype != otype) { + if (ntype != otype && netif_running(dev)) { err = cfg80211_can_change_interface(rdev, dev->ieee80211_ptr, ntype); if (err) @@ -935,6 +935,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype) { struct wireless_dev *wdev_iter; + u32 used_iftypes = BIT(iftype); int num[NUM_NL80211_IFTYPES]; int total = 1; int i, j; @@ -961,6 +962,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, num[wdev_iter->iftype]++; total++; + used_iftypes |= BIT(wdev_iter->iftype); } mutex_unlock(&rdev->devlist_mtx); @@ -970,6 +972,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, for (i = 0; i < rdev->wiphy.n_iface_combinations; i++) { const struct ieee80211_iface_combination *c; struct ieee80211_iface_limit *limits; + u32 all_iftypes = 0; c = &rdev->wiphy.iface_combinations[i]; @@ -984,6 +987,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, if (rdev->wiphy.software_iftypes & BIT(iftype)) continue; for (j = 0; j < c->n_limits; j++) { + all_iftypes |= limits[j].types; if (!(limits[j].types & BIT(iftype))) continue; if (limits[j].max < num[iftype]) @@ -991,7 +995,20 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, limits[j].max -= num[iftype]; } } - /* yay, it fits */ + + /* + * Finally check that all iftypes that we're currently + * using are actually part of this combination. If they + * aren't then we can't use this combination and have + * to continue to the next. + */ + if ((all_iftypes & used_iftypes) != used_iftypes) + goto cont; + + /* + * This combination covered all interface types and + * supported the requested numbers, so we're good. + */ kfree(limits); return 0; cont: diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index c53e8f42aa75..ccfbd328a69d 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1921,6 +1921,9 @@ no_transform: } ok: xfrm_pols_put(pols, drop_pols); + if (dst && dst->xfrm && + dst->xfrm->props.mode == XFRM_MODE_TUNNEL) + dst->flags |= DST_XFRM_TUNNEL; return dst; nopol: |