diff options
Diffstat (limited to 'net')
275 files changed, 4091 insertions, 2343 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 9424f3718ea7..86abb2e59aea 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -305,9 +305,11 @@ static void vlan_sync_address(struct net_device *dev, static void vlan_transfer_features(struct net_device *dev, struct net_device *vlandev) { + struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); + vlandev->gso_max_size = dev->gso_max_size; - if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) + if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto)) vlandev->hard_header_len = dev->hard_header_len; else vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 8a15eaadc4bd..42ef36a85e69 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -9,7 +9,7 @@ bool vlan_do_receive(struct sk_buff **skbp) { struct sk_buff *skb = *skbp; __be16 vlan_proto = skb->vlan_proto; - u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK; + u16 vlan_id = vlan_tx_tag_get_id(skb); struct net_device *vlan_dev; struct vlan_pcpu_stats *rx_stats; @@ -103,8 +103,11 @@ EXPORT_SYMBOL(vlan_dev_vlan_id); static struct sk_buff *vlan_reorder_header(struct sk_buff *skb) { - if (skb_cow(skb, skb_headroom(skb)) < 0) + if (skb_cow(skb, skb_headroom(skb)) < 0) { + kfree_skb(skb); return NULL; + } + memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); skb->mac_header += VLAN_HLEN; return skb; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 3a8c8fd63c88..698e922f41ea 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -73,6 +73,8 @@ vlan_dev_get_egress_qos_mask(struct net_device *dev, struct sk_buff *skb) { struct vlan_priority_tci_mapping *mp; + smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */ + mp = vlan_dev_priv(dev)->egress_priority_map[(skb->priority & 0xF)]; while (mp) { if (mp->priority == skb->priority) { @@ -249,6 +251,11 @@ int vlan_dev_set_egress_priority(const struct net_device *dev, np->next = mp; np->priority = skb_prio; np->vlan_qos = vlan_qos; + /* Before inserting this element in hash table, make sure all its fields + * are committed to memory. + * coupled with smp_rmb() in vlan_dev_get_egress_qos_mask() + */ + smp_wmb(); vlan->egress_priority_map[skb_prio & 0xF] = np; if (vlan_qos) vlan->nr_egress_mappings++; @@ -505,10 +512,48 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change) } } +static int vlan_calculate_locking_subclass(struct net_device *real_dev) +{ + int subclass = 0; + + while (is_vlan_dev(real_dev)) { + subclass++; + real_dev = vlan_dev_priv(real_dev)->real_dev; + } + + return subclass; +} + +static void vlan_dev_mc_sync(struct net_device *to, struct net_device *from) +{ + int err = 0, subclass; + + subclass = vlan_calculate_locking_subclass(to); + + spin_lock_nested(&to->addr_list_lock, subclass); + err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + spin_unlock(&to->addr_list_lock); +} + +static void vlan_dev_uc_sync(struct net_device *to, struct net_device *from) +{ + int err = 0, subclass; + + subclass = vlan_calculate_locking_subclass(to); + + spin_lock_nested(&to->addr_list_lock, subclass); + err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + spin_unlock(&to->addr_list_lock); +} + static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) { - dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); - dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); + vlan_dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); + vlan_dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } /* @@ -542,6 +587,26 @@ static const struct header_ops vlan_header_ops = { .parse = eth_header_parse, }; +static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev, + unsigned short type, + const void *daddr, const void *saddr, + unsigned int len) +{ + struct vlan_dev_priv *vlan = vlan_dev_priv(dev); + struct net_device *real_dev = vlan->real_dev; + + if (saddr == NULL) + saddr = dev->dev_addr; + + return dev_hard_header(skb, real_dev, type, daddr, saddr, len); +} + +static const struct header_ops vlan_passthru_header_ops = { + .create = vlan_passthru_hard_header, + .rebuild = dev_rebuild_header, + .parse = eth_header_parse, +}; + static struct device_type vlan_type = { .name = "vlan", }; @@ -584,8 +649,9 @@ static int vlan_dev_init(struct net_device *dev) #endif dev->needed_headroom = real_dev->needed_headroom; - if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) { - dev->header_ops = real_dev->header_ops; + if (vlan_hw_offload_capable(real_dev->features, + vlan_dev_priv(dev)->vlan_proto)) { + dev->header_ops = &vlan_passthru_header_ops; dev->hard_header_len = real_dev->hard_header_len; } else { dev->header_ops = &vlan_header_ops; @@ -596,9 +662,7 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - if (is_vlan_dev(real_dev)) - subclass = 1; - + subclass = vlan_calculate_locking_subclass(dev); vlan_dev_set_lockdep_class(dev, subclass); vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 309129732285..c7e634af8516 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -171,7 +171,7 @@ static size_t vlan_get_size(const struct net_device *dev) return nla_total_size(2) + /* IFLA_VLAN_PROTOCOL */ nla_total_size(2) + /* IFLA_VLAN_ID */ - sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */ + nla_total_size(sizeof(struct ifla_vlan_flags)) + /* IFLA_VLAN_FLAGS */ vlan_qos_map_size(vlan->nr_ingress_mappings) + vlan_qos_map_size(vlan->nr_egress_mappings); } diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index de8df957867d..2ee3879161b1 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -24,11 +24,11 @@ */ void p9_release_pages(struct page **pages, int nr_pages) { - int i = 0; - while (pages[i] && nr_pages--) { - put_page(pages[i]); - i++; - } + int i; + + for (i = 0; i < nr_pages; i++) + if (pages[i]) + put_page(pages[i]); } EXPORT_SYMBOL(p9_release_pages); diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index e1c26b101830..c76a4388a5d7 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -340,7 +340,10 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, int count = nr_pages; while (nr_pages) { s = rest_of_page(data); - pages[index++] = kmap_to_page(data); + if (is_vmalloc_addr(data)) + pages[index++] = vmalloc_to_page(data); + else + pages[index++] = kmap_to_page(data); data += s; nr_pages--; } @@ -577,6 +580,10 @@ static int p9_virtio_probe(struct virtio_device *vdev) mutex_lock(&virtio_9p_lock); list_add_tail(&chan->chan_list, &virtio_chan_list); mutex_unlock(&virtio_9p_lock); + + /* Let udev rules use the new mount_tag attribute. */ + kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE); + return 0; out_free_tag: @@ -654,6 +661,7 @@ static void p9_virtio_remove(struct virtio_device *vdev) list_del(&chan->chan_list); mutex_unlock(&virtio_9p_lock); sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr); + kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE); kfree(chan->tag); kfree(chan->vc_wq); kfree(chan); diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index ef12839a7cfe..8799e171addf 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1489,8 +1489,6 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev, goto drop; /* Queue packet (standard) */ - skb->sk = sock; - if (sock_queue_rcv_skb(sock, skb) < 0) goto drop; @@ -1644,7 +1642,6 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr if (!skb) goto out; - skb->sk = sk; skb_reserve(skb, ddp_dl->header_length); skb_reserve(skb, dev->hard_header_len); skb->dev = dev; @@ -1735,7 +1732,6 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr size_t size, int flags) { struct sock *sk = sock->sk; - struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name; struct ddpehdr *ddp; int copied = 0; int offset = 0; @@ -1764,14 +1760,13 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr } err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied); - if (!err) { - if (sat) { - sat->sat_family = AF_APPLETALK; - sat->sat_port = ddp->deh_sport; - sat->sat_addr.s_node = ddp->deh_snode; - sat->sat_addr.s_net = ddp->deh_snet; - } - msg->msg_namelen = sizeof(*sat); + if (!err && msg->msg_name) { + struct sockaddr_at *sat = msg->msg_name; + sat->sat_family = AF_APPLETALK; + sat->sat_port = ddp->deh_sport; + sat->sat_addr.s_node = ddp->deh_snode; + sat->sat_addr.s_net = ddp->deh_snet; + msg->msg_namelen = sizeof(*sat); } skb_free_datagram(sk, skb); /* Free the datagram. */ diff --git a/net/atm/common.c b/net/atm/common.c index 737bef59ce89..7b491006eaf4 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -531,8 +531,6 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, struct sk_buff *skb; int copied, error = -EINVAL; - msg->msg_namelen = 0; - if (sock->state != SS_CONNECTED) return -ENOTCONN; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index e277e38f736b..ba6db78a02b1 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1636,11 +1636,11 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock, skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); - if (msg->msg_namelen != 0) { - struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name; + if (msg->msg_name) { ax25_digi digi; ax25_address src; const unsigned char *mac = skb_mac_header(skb); + struct sockaddr_ax25 *sax = msg->msg_name; memset(sax, 0, sizeof(struct full_sockaddr_ax25)); ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL, diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 51aafd669cbb..f1cb1f56cda9 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -61,6 +61,7 @@ static int __init batadv_init(void) batadv_recv_handler_init(); batadv_iv_init(); + batadv_nc_init(); batadv_event_workqueue = create_singlethread_workqueue("bat_events"); @@ -138,7 +139,7 @@ int batadv_mesh_init(struct net_device *soft_iface) if (ret < 0) goto err; - ret = batadv_nc_init(bat_priv); + ret = batadv_nc_mesh_init(bat_priv); if (ret < 0) goto err; @@ -163,7 +164,7 @@ void batadv_mesh_free(struct net_device *soft_iface) batadv_vis_quit(bat_priv); batadv_gw_node_purge(bat_priv); - batadv_nc_free(bat_priv); + batadv_nc_mesh_free(bat_priv); batadv_dat_free(bat_priv); batadv_bla_free(bat_priv); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index e84629ece9b7..f97aeee2201c 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -35,6 +35,20 @@ static int batadv_nc_recv_coded_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); /** + * batadv_nc_init - one-time initialization for network coding + */ +int __init batadv_nc_init(void) +{ + int ret; + + /* Register our packet type */ + ret = batadv_recv_handler_register(BATADV_CODED, + batadv_nc_recv_coded_packet); + + return ret; +} + +/** * batadv_nc_start_timer - initialise the nc periodic worker * @bat_priv: the bat priv with all the soft interface information */ @@ -45,10 +59,10 @@ static void batadv_nc_start_timer(struct batadv_priv *bat_priv) } /** - * batadv_nc_init - initialise coding hash table and start house keeping + * batadv_nc_mesh_init - initialise coding hash table and start house keeping * @bat_priv: the bat priv with all the soft interface information */ -int batadv_nc_init(struct batadv_priv *bat_priv) +int batadv_nc_mesh_init(struct batadv_priv *bat_priv) { bat_priv->nc.timestamp_fwd_flush = jiffies; bat_priv->nc.timestamp_sniffed_purge = jiffies; @@ -70,11 +84,6 @@ int batadv_nc_init(struct batadv_priv *bat_priv) batadv_hash_set_lock_class(bat_priv->nc.coding_hash, &batadv_nc_decoding_hash_lock_class_key); - /* Register our packet type */ - if (batadv_recv_handler_register(BATADV_CODED, - batadv_nc_recv_coded_packet) < 0) - goto err; - INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker); batadv_nc_start_timer(bat_priv); @@ -1722,12 +1731,11 @@ free_nc_packet: } /** - * batadv_nc_free - clean up network coding memory + * batadv_nc_mesh_free - clean up network coding memory * @bat_priv: the bat priv with all the soft interface information */ -void batadv_nc_free(struct batadv_priv *bat_priv) +void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { - batadv_recv_handler_unregister(BATADV_CODED); cancel_delayed_work_sync(&bat_priv->nc.work); batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, NULL); diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 4fa6d0caddbd..bd4295fb960f 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -22,8 +22,9 @@ #ifdef CONFIG_BATMAN_ADV_NC -int batadv_nc_init(struct batadv_priv *bat_priv); -void batadv_nc_free(struct batadv_priv *bat_priv); +int batadv_nc_init(void); +int batadv_nc_mesh_init(struct batadv_priv *bat_priv); +void batadv_nc_mesh_free(struct batadv_priv *bat_priv); void batadv_nc_update_nc_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, @@ -47,12 +48,17 @@ int batadv_nc_init_debugfs(struct batadv_priv *bat_priv); #else /* ifdef CONFIG_BATMAN_ADV_NC */ -static inline int batadv_nc_init(struct batadv_priv *bat_priv) +static inline int batadv_nc_init(void) { return 0; } -static inline void batadv_nc_free(struct batadv_priv *bat_priv) +static inline int batadv_nc_mesh_init(struct batadv_priv *bat_priv) +{ + return 0; +} + +static inline void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { return; } diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 9096137c889c..6629cdc134dc 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -221,8 +221,6 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags & (MSG_OOB)) return -EOPNOTSUPP; - msg->msg_namelen = 0; - skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) @@ -287,8 +285,6 @@ int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags & MSG_OOB) return -EOPNOTSUPP; - msg->msg_namelen = 0; - BT_DBG("sk %p size %zu", sk, size); lock_sock(sk); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 6c7f36379722..8e7290aea8f8 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -652,14 +652,17 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { struct hci_cp_auth_requested cp; - /* encrypt must be pending if auth is also pending */ - set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); - cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); - if (conn->key_type != 0xff) + + /* If we're already encrypted set the REAUTH_PEND flag, + * otherwise set the ENCRYPT_PEND. + */ + if (conn->link_mode & HCI_LM_ENCRYPT) set_bit(HCI_CONN_REAUTH_PEND, &conn->flags); + else + set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); } return 0; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index ace5e55fe5a3..7c88f5f83598 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1123,7 +1123,11 @@ int hci_dev_open(__u16 dev) goto done; } - if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) { + /* Check for rfkill but allow the HCI setup stage to proceed + * (which in itself doesn't cause any RF activity). + */ + if (test_bit(HCI_RFKILLED, &hdev->dev_flags) && + !test_bit(HCI_SETUP, &hdev->dev_flags)) { ret = -ERFKILL; goto done; } @@ -1545,10 +1549,13 @@ static int hci_rfkill_set_block(void *data, bool blocked) BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked); - if (!blocked) - return 0; - - hci_dev_do_close(hdev); + if (blocked) { + set_bit(HCI_RFKILLED, &hdev->dev_flags); + if (!test_bit(HCI_SETUP, &hdev->dev_flags)) + hci_dev_do_close(hdev); + } else { + clear_bit(HCI_RFKILLED, &hdev->dev_flags); +} return 0; } @@ -1570,9 +1577,13 @@ static void hci_power_on(struct work_struct *work) return; } - if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) + if (test_bit(HCI_RFKILLED, &hdev->dev_flags)) { + clear_bit(HCI_AUTO_OFF, &hdev->dev_flags); + hci_dev_do_close(hdev); + } else if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) { queue_delayed_work(hdev->req_workqueue, &hdev->power_off, HCI_AUTO_OFF_TIMEOUT); + } if (test_and_clear_bit(HCI_SETUP, &hdev->dev_flags)) mgmt_index_added(hdev); @@ -2241,6 +2252,9 @@ int hci_register_dev(struct hci_dev *hdev) } } + if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) + set_bit(HCI_RFKILLED, &hdev->dev_flags); + set_bit(HCI_SETUP, &hdev->dev_flags); if (hdev->dev_type != HCI_AMP) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index b93cd2eb5d58..5daf7ab26710 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3051,6 +3051,12 @@ static void hci_key_refresh_complete_evt(struct hci_dev *hdev, if (!conn) goto unlock; + /* For BR/EDR the necessary steps are taken through the + * auth_complete event. + */ + if (conn->type != LE_LINK) + goto unlock; + if (!ev->status) conn->sec_level = conn->pending_sec_level; @@ -3212,8 +3218,11 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev, /* If we're not the initiators request authorization to * proceed from user space (mgmt_user_confirm with - * confirm_hint set to 1). */ - if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { + * confirm_hint set to 1). The exception is if neither + * side had MITM in which case we do auto-accept. + */ + if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) && + (loc_mitm || rem_mitm)) { BT_DBG("Confirming auto-accept as acceptor"); confirm_hint = 1; goto confirm; @@ -3611,11 +3620,21 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) cp.handle = cpu_to_le16(conn->handle); if (ltk->authenticated) - conn->sec_level = BT_SECURITY_HIGH; + conn->pending_sec_level = BT_SECURITY_HIGH; + else + conn->pending_sec_level = BT_SECURITY_MEDIUM; + + conn->enc_key_size = ltk->enc_size; hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp); - if (ltk->type & HCI_SMP_STK) { + /* Ref. Bluetooth Core SPEC pages 1975 and 2004. STK is a + * temporary key used to encrypt a connection following + * pairing. It is used during the Encrypted Session Setup to + * distribute the keys. Later, security can be re-established + * using a distributed LTK. + */ + if (ltk->type == HCI_SMP_STK_SLAVE) { list_del(<k->list); kfree(ltk); } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 9bd7d959e384..fa4bf6631425 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -752,8 +752,6 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return err; - msg->msg_namelen = 0; - copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 940f5acb6694..de030f50f72b 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -231,17 +231,22 @@ static void hidp_input_report(struct hidp_session *session, struct sk_buff *skb) static int hidp_send_report(struct hidp_session *session, struct hid_report *report) { - unsigned char buf[32], hdr; - int rsize; + unsigned char hdr; + u8 *buf; + int rsize, ret; - rsize = ((report->size - 1) >> 3) + 1 + (report->id > 0); - if (rsize > sizeof(buf)) + buf = hid_alloc_report_buf(report, GFP_ATOMIC); + if (!buf) return -EIO; hid_output_report(report, buf); hdr = HIDP_TRANS_DATA | HIDP_DATA_RTYPE_OUPUT; - return hidp_send_intr_message(session, hdr, buf, rsize); + rsize = ((report->size - 1) >> 3) + 1 + (report->id > 0); + ret = hidp_send_intr_message(session, hdr, buf, rsize); + + kfree(buf); + return ret; } static int hidp_get_raw_report(struct hid_device *hid, diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 36fed40c162c..5f36f70ce44d 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -887,7 +887,8 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) l2cap_chan_close(chan, 0); lock_sock(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } @@ -949,13 +950,16 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) /* Check for backlog size */ if (sk_acceptq_is_full(parent)) { BT_DBG("backlog full %d", parent->sk_ack_backlog); + release_sock(parent); return NULL; } sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, GFP_ATOMIC); - if (!sk) + if (!sk) { + release_sock(parent); return NULL; + } bt_sock_reclassify_lock(sk, BTPROTO_L2CAP); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index f8ecbc70293d..8208a13a9837 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2333,8 +2333,13 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev, } if (addr->type == BDADDR_LE_PUBLIC || addr->type == BDADDR_LE_RANDOM) { - /* Continue with pairing via SMP */ + /* Continue with pairing via SMP. The hdev lock must be + * released as SMP may try to recquire it for crypto + * purposes. + */ + hci_dev_unlock(hdev); err = smp_user_confirm_reply(conn, mgmt_op, passkey); + hci_dev_lock(hdev); if (!err) err = cmd_complete(sk, hdev->id, mgmt_op, diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index ca957d34b0c8..19ba192e9dbf 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1857,10 +1857,13 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s) /* Get data directly from socket receive queue without copying it. */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); - if (!skb_linearize(skb)) + if (!skb_linearize(skb)) { s = rfcomm_recv_frame(s, skb); - else + if (!s) + break; + } else { kfree_skb(skb); + } } if (s && (sk->sk_state == BT_CLOSED)) diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 30b3721dc6d7..7ca014daa5ab 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -608,7 +608,6 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { rfcomm_dlc_accept(d); - msg->msg_namelen = 0; return 0; } @@ -888,7 +887,8 @@ static int rfcomm_sock_shutdown(struct socket *sock, int how) sk->sk_shutdown = SHUTDOWN_MASK; __rfcomm_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } release_sock(sk); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index e7bd4eea575c..c9ae6b703c13 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -700,7 +700,6 @@ static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock, test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { sco_conn_defer_accept(pi->conn->hcon, 0); sk->sk_state = BT_CONFIG; - msg->msg_namelen = 0; release_sock(sk); return 0; @@ -859,7 +858,8 @@ static int sco_sock_shutdown(struct socket *sock, int how) sco_sock_clear_timer(sk); __sco_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } @@ -879,7 +879,8 @@ static int sco_sock_release(struct socket *sock) sco_sock_close(sk); - if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) { + if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && + !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); release_sock(sk); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index ebfa4443c69b..84dd783abe5c 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -161,7 +161,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) if (!pv) return; - for_each_set_bit_from(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) { + for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) { f = __br_fdb_get(br, br->dev->dev_addr, vid); if (f && f->is_local && !f->dst) fdb_delete(br, f); @@ -725,7 +725,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], /* VID was specified, so use it. */ err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); } else { - if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN)) { + if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) { err = __br_fdb_add(ndm, p, addr, nlh_flags, 0); goto out; } @@ -734,7 +734,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], * specify a VLAN. To be nice, add/update entry for every * vlan on this port. */ - for_each_set_bit(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) { + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); if (err) goto out; @@ -812,7 +812,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], err = __br_fdb_delete(p, addr, vid); } else { - if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN)) { + if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) { err = __br_fdb_delete(p, addr, 0); goto out; } @@ -822,7 +822,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], * vlan on this port. */ err = -ENOENT; - for_each_set_bit(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) { + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { err &= __br_fdb_delete(p, addr, vid); } } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 4cdba60926ff..32bd1e87f149 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -172,6 +172,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) del_nbp(p); } + br_fdb_delete_by_port(br, NULL, 1); + del_timer_sync(&br->gc_timer); br_sysfs_delbr(br->dev); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 828e2bcc1f52..0a3bc82782cf 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -71,7 +71,7 @@ int br_handle_frame_finish(struct sk_buff *skb) goto drop; if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid)) - goto drop; + goto out; /* insert into forwarding database after filtering to avoid spoofing */ br = p->br; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index d6448e35e027..81de0106528b 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1176,6 +1176,12 @@ static int br_ip6_multicast_query(struct net_bridge *br, br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr)); + /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */ + if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) { + err = -EINVAL; + goto out; + } + if (skb->len == sizeof(*mld)) { if (!pskb_may_pull(skb, sizeof(*mld))) { err = -EINVAL; @@ -1185,7 +1191,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay)); if (max_delay) group = &mld->mld_mca; - } else if (skb->len >= sizeof(*mld2q)) { + } else { if (!pskb_may_pull(skb, sizeof(*mld2q))) { err = -EINVAL; goto out; @@ -1193,7 +1199,8 @@ static int br_ip6_multicast_query(struct net_bridge *br, mld2q = (struct mld2_query *)icmp6_hdr(skb); if (!mld2q->mld2q_nsrcs) group = &mld2q->mld2q_mca; - max_delay = mld2q->mld2q_mrc ? MLDV2_MRC(ntohs(mld2q->mld2q_mrc)) : 1; + + max_delay = max(msecs_to_jiffies(MLDV2_MRC(ntohs(mld2q->mld2q_mrc))), 1UL); } if (!group) @@ -1838,7 +1845,7 @@ int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val) u32 old; struct net_bridge_mdb_htable *mdb; - spin_lock(&br->multicast_lock); + spin_lock_bh(&br->multicast_lock); if (!netif_running(br->dev)) goto unlock; @@ -1870,7 +1877,7 @@ rollback: } unlock: - spin_unlock(&br->multicast_lock); + spin_unlock_bh(&br->multicast_lock); return err; } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 8e3abf564798..f16e9e487750 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -128,7 +128,7 @@ static int br_fill_ifinfo(struct sk_buff *skb, else pv = br_get_vlan_info(br); - if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN)) + if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) goto done; af = nla_nest_start(skb, IFLA_AF_SPEC); @@ -136,7 +136,7 @@ static int br_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; pvid = br_get_pvid(pv); - for_each_set_bit(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) { + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { vinfo.vid = vid; vinfo.flags = 0; if (vid == pvid) @@ -203,7 +203,7 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask) { int err = 0; - struct net_bridge_port *port = br_port_get_rcu(dev); + struct net_bridge_port *port = br_port_get_rtnl(dev); /* not a bridge port and */ if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN)) @@ -438,12 +438,26 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } +static int br_dev_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net_bridge *br = netdev_priv(dev); + + if (tb[IFLA_ADDRESS]) { + spin_lock_bh(&br->lock); + br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); + spin_unlock_bh(&br->lock); + } + + return register_netdevice(dev); +} + static size_t br_get_link_af_size(const struct net_device *dev) { struct net_port_vlans *pv; if (br_port_exists(dev)) - pv = nbp_get_vlan_info(br_port_get_rcu(dev)); + pv = nbp_get_vlan_info(br_port_get_rtnl(dev)); else if (dev->priv_flags & IFF_EBRIDGE) pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); else @@ -466,6 +480,7 @@ struct rtnl_link_ops br_link_ops __read_mostly = { .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, .validate = br_validate, + .newlink = br_dev_newlink, .dellink = br_dev_delete, }; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d2c043a857b6..11ab6628027a 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -183,13 +183,10 @@ struct net_bridge_port static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev) { - struct net_bridge_port *port = - rcu_dereference_rtnl(dev->rx_handler_data); - - return br_port_exists(dev) ? port : NULL; + return rcu_dereference(dev->rx_handler_data); } -static inline struct net_bridge_port *br_port_get_rtnl(struct net_device *dev) +static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device *dev) { return br_port_exists(dev) ? rtnl_dereference(dev->rx_handler_data) : NULL; @@ -432,6 +429,16 @@ extern netdev_features_t br_features_recompute(struct net_bridge *br, extern int br_handle_frame_finish(struct sk_buff *skb); extern rx_handler_result_t br_handle_frame(struct sk_buff **pskb); +static inline bool br_rx_handler_check_rcu(const struct net_device *dev) +{ + return rcu_dereference(dev->rx_handler) == br_handle_frame; +} + +static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev) +{ + return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL; +} + /* br_ioctl.c */ extern int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *arg); @@ -714,6 +721,7 @@ extern struct net_bridge_port *br_get_port(struct net_bridge *br, extern void br_init_port(struct net_bridge_port *p); extern void br_become_designated_port(struct net_bridge_port *p); +extern void __br_set_forward_delay(struct net_bridge *br, unsigned long t); extern int br_set_forward_delay(struct net_bridge *br, unsigned long x); extern int br_set_hello_time(struct net_bridge *br, unsigned long x); extern int br_set_max_age(struct net_bridge *br, unsigned long x); diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 1c0a50f13229..3c86f0538cbb 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -209,7 +209,7 @@ static void br_record_config_information(struct net_bridge_port *p, p->designated_age = jiffies - bpdu->message_age; mod_timer(&p->message_age_timer, jiffies - + (p->br->max_age - bpdu->message_age)); + + (bpdu->max_age - bpdu->message_age)); } /* called under bridge lock */ @@ -544,18 +544,27 @@ int br_set_max_age(struct net_bridge *br, unsigned long val) } +void __br_set_forward_delay(struct net_bridge *br, unsigned long t) +{ + br->bridge_forward_delay = t; + if (br_is_root_bridge(br)) + br->forward_delay = br->bridge_forward_delay; +} + int br_set_forward_delay(struct net_bridge *br, unsigned long val) { unsigned long t = clock_t_to_jiffies(val); + int err = -ERANGE; + spin_lock_bh(&br->lock); if (br->stp_enabled != BR_NO_STP && (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY)) - return -ERANGE; + goto unlock; - spin_lock_bh(&br->lock); - br->bridge_forward_delay = t; - if (br_is_root_bridge(br)) - br->forward_delay = br->bridge_forward_delay; + __br_set_forward_delay(br, t); + err = 0; + +unlock: spin_unlock_bh(&br->lock); - return 0; + return err; } diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 8660ea3be705..bdb459d21ad8 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -153,7 +153,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0) goto err; - p = br_port_get_rcu(dev); + p = br_port_get_check_rcu(dev); if (!p) goto err; diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index d45e760141bb..656a6f3e40de 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -129,6 +129,14 @@ static void br_stp_start(struct net_bridge *br) char *envp[] = { NULL }; r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); + + spin_lock_bh(&br->lock); + + if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY) + __br_set_forward_delay(br, BR_MIN_FORWARD_DELAY); + else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY) + __br_set_forward_delay(br, BR_MAX_FORWARD_DELAY); + if (r == 0) { br->stp_enabled = BR_USER_STP; br_debug(br, "userspace STP started\n"); @@ -137,10 +145,10 @@ static void br_stp_start(struct net_bridge *br) br_debug(br, "using kernel STP\n"); /* To start timers on any ports left in blocking */ - spin_lock_bh(&br->lock); br_port_state_selection(br); - spin_unlock_bh(&br->lock); } + + spin_unlock_bh(&br->lock); } static void br_stp_stop(struct net_bridge *br) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index bd58b45f5f90..d8deb8bda736 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -108,7 +108,7 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid) clear_bit(vid, v->vlan_bitmap); v->num_vlans--; - if (bitmap_empty(v->vlan_bitmap, BR_VLAN_BITMAP_LEN)) { + if (bitmap_empty(v->vlan_bitmap, VLAN_N_VID)) { if (v->port_idx) rcu_assign_pointer(v->parent.port->vlan_info, NULL); else @@ -122,7 +122,7 @@ static void __vlan_flush(struct net_port_vlans *v) { smp_wmb(); v->pvid = 0; - bitmap_zero(v->vlan_bitmap, BR_VLAN_BITMAP_LEN); + bitmap_zero(v->vlan_bitmap, VLAN_N_VID); if (v->port_idx) rcu_assign_pointer(v->parent.port->vlan_info, NULL); else @@ -202,7 +202,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, * rejected. */ if (!v) - return false; + goto drop; if (br_vlan_get_tag(skb, vid)) { u16 pvid = br_get_pvid(v); @@ -212,7 +212,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, * traffic belongs to. */ if (pvid == VLAN_N_VID) - return false; + goto drop; /* PVID is set on this port. Any untagged ingress * frame is considered to belong to this vlan. @@ -224,7 +224,8 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, /* Frame had a valid vlan tag. See if vlan is allowed */ if (test_bit(*vid, v->vlan_bitmap)) return true; - +drop: + kfree_skb(skb); return false; } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 3d110c4fc787..6651a7797d46 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1044,10 +1044,9 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, if (repl->num_counters && copy_to_user(repl->counters, counterstmp, repl->num_counters * sizeof(struct ebt_counter))) { - ret = -EFAULT; + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("ebtables: counters copy to user failed while replacing table\n"); } - else - ret = 0; /* decrease module count and free resources */ EBT_ENTRY_ITERATE(table->entries, table->entries_size, diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 05a41c7ec304..526bf56f4d31 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -283,11 +283,9 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock, int copylen; ret = -EOPNOTSUPP; - if (m->msg_flags&MSG_OOB) + if (flags & MSG_OOB) goto read_error; - m->msg_namelen = 0; - skb = skb_recv_datagram(sk, flags, 0 , &ret); if (!skb) goto read_error; @@ -361,8 +359,6 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags&MSG_OOB) goto out; - msg->msg_namelen = 0; - /* * Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 2bd4b58f4372..0f455227da83 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -293,9 +293,10 @@ int cfctrl_linkup_request(struct cflayer *layer, count = cfctrl_cancel_req(&cfctrl->serv.layer, user_layer); - if (count != 1) + if (count != 1) { pr_err("Could not remove request (%d)", count); return -ENODEV; + } } return 0; } diff --git a/net/can/af_can.c b/net/can/af_can.c index c4e50852c9f4..d3668c55b088 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -57,6 +57,7 @@ #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> +#include <linux/can/skb.h> #include <linux/ratelimit.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -261,6 +262,9 @@ int can_send(struct sk_buff *skb, int loop) goto inval_skb; } + skb->ip_summed = CHECKSUM_UNNECESSARY; + + skb_reset_mac_header(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); @@ -290,7 +294,7 @@ int can_send(struct sk_buff *skb, int loop) return -ENOMEM; } - newskb->sk = skb->sk; + can_skb_set_owner(newskb, skb->sk); newskb->ip_summed = CHECKSUM_UNNECESSARY; newskb->pkt_type = PACKET_BROADCAST; } diff --git a/net/can/bcm.c b/net/can/bcm.c index 8f113e6ff327..35cf02d92766 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -268,7 +268,7 @@ static void bcm_can_tx(struct bcm_op *op) /* send with loopback */ skb->dev = dev; - skb->sk = op->sk; + can_skb_set_owner(skb, op->sk); can_send(skb, 1); /* update statistics */ @@ -1223,7 +1223,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk) can_skb_prv(skb)->ifindex = dev->ifindex; skb->dev = dev; - skb->sk = sk; + can_skb_set_owner(skb, sk); err = can_send(skb, 1); /* send with loopback */ dev_put(dev); diff --git a/net/can/gw.c b/net/can/gw.c index 3ee690e8c7d3..de25455b4e3e 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -784,7 +784,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh) struct cgw_job *gwj; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) @@ -876,7 +876,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh) struct can_can_gw ccgw; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c index 925ca583c09c..8c93fa8d81bc 100644 --- a/net/ceph/auth_none.c +++ b/net/ceph/auth_none.c @@ -39,6 +39,11 @@ static int should_authenticate(struct ceph_auth_client *ac) return xi->starting; } +static int build_request(struct ceph_auth_client *ac, void *buf, void *end) +{ + return 0; +} + /* * the generic auth code decode the global_id, and we carry no actual * authenticate state, so nothing happens here. @@ -106,6 +111,7 @@ static const struct ceph_auth_client_ops ceph_auth_none_ops = { .destroy = destroy, .is_authenticated = is_authenticated, .should_authenticate = should_authenticate, + .build_request = build_request, .handle_reply = handle_reply, .create_authorizer = ceph_auth_none_create_authorizer, .destroy_authorizer = ceph_auth_none_destroy_authorizer, diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 96238ba95f2b..de6662b14e1f 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -13,8 +13,6 @@ #include "auth_x.h" #include "auth_x_protocol.h" -#define TEMP_TICKET_BUF_LEN 256 - static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed); static int ceph_x_is_authenticated(struct ceph_auth_client *ac) @@ -64,7 +62,7 @@ static int ceph_x_encrypt(struct ceph_crypto_key *secret, } static int ceph_x_decrypt(struct ceph_crypto_key *secret, - void **p, void *end, void *obuf, size_t olen) + void **p, void *end, void **obuf, size_t olen) { struct ceph_x_encrypt_header head; size_t head_len = sizeof(head); @@ -75,8 +73,14 @@ static int ceph_x_decrypt(struct ceph_crypto_key *secret, return -EINVAL; dout("ceph_x_decrypt len %d\n", len); - ret = ceph_decrypt2(secret, &head, &head_len, obuf, &olen, - *p, len); + if (*obuf == NULL) { + *obuf = kmalloc(len, GFP_NOFS); + if (!*obuf) + return -ENOMEM; + olen = len; + } + + ret = ceph_decrypt2(secret, &head, &head_len, *obuf, &olen, *p, len); if (ret) return ret; if (head.struct_v != 1 || le64_to_cpu(head.magic) != CEPHX_ENC_MAGIC) @@ -129,139 +133,120 @@ static void remove_ticket_handler(struct ceph_auth_client *ac, kfree(th); } -static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac, - struct ceph_crypto_key *secret, - void *buf, void *end) +static int process_one_ticket(struct ceph_auth_client *ac, + struct ceph_crypto_key *secret, + void **p, void *end) { struct ceph_x_info *xi = ac->private; - int num; - void *p = buf; + int type; + u8 tkt_struct_v, blob_struct_v; + struct ceph_x_ticket_handler *th; + void *dbuf = NULL; + void *dp, *dend; + int dlen; + char is_enc; + struct timespec validity; + struct ceph_crypto_key old_key; + void *ticket_buf = NULL; + void *tp, *tpend; + struct ceph_timespec new_validity; + struct ceph_crypto_key new_session_key; + struct ceph_buffer *new_ticket_blob; + unsigned long new_expires, new_renew_after; + u64 new_secret_id; int ret; - char *dbuf; - char *ticket_buf; - u8 reply_struct_v; - dbuf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS); - if (!dbuf) - return -ENOMEM; + ceph_decode_need(p, end, sizeof(u32) + 1, bad); - ret = -ENOMEM; - ticket_buf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS); - if (!ticket_buf) - goto out_dbuf; + type = ceph_decode_32(p); + dout(" ticket type %d %s\n", type, ceph_entity_type_name(type)); - ceph_decode_need(&p, end, 1 + sizeof(u32), bad); - reply_struct_v = ceph_decode_8(&p); - if (reply_struct_v != 1) + tkt_struct_v = ceph_decode_8(p); + if (tkt_struct_v != 1) goto bad; - num = ceph_decode_32(&p); - dout("%d tickets\n", num); - while (num--) { - int type; - u8 tkt_struct_v, blob_struct_v; - struct ceph_x_ticket_handler *th; - void *dp, *dend; - int dlen; - char is_enc; - struct timespec validity; - struct ceph_crypto_key old_key; - void *tp, *tpend; - struct ceph_timespec new_validity; - struct ceph_crypto_key new_session_key; - struct ceph_buffer *new_ticket_blob; - unsigned long new_expires, new_renew_after; - u64 new_secret_id; - - ceph_decode_need(&p, end, sizeof(u32) + 1, bad); - - type = ceph_decode_32(&p); - dout(" ticket type %d %s\n", type, ceph_entity_type_name(type)); - - tkt_struct_v = ceph_decode_8(&p); - if (tkt_struct_v != 1) - goto bad; - - th = get_ticket_handler(ac, type); - if (IS_ERR(th)) { - ret = PTR_ERR(th); - goto out; - } - /* blob for me */ - dlen = ceph_x_decrypt(secret, &p, end, dbuf, - TEMP_TICKET_BUF_LEN); - if (dlen <= 0) { - ret = dlen; - goto out; - } - dout(" decrypted %d bytes\n", dlen); - dend = dbuf + dlen; - dp = dbuf; + th = get_ticket_handler(ac, type); + if (IS_ERR(th)) { + ret = PTR_ERR(th); + goto out; + } - tkt_struct_v = ceph_decode_8(&dp); - if (tkt_struct_v != 1) - goto bad; + /* blob for me */ + dlen = ceph_x_decrypt(secret, p, end, &dbuf, 0); + if (dlen <= 0) { + ret = dlen; + goto out; + } + dout(" decrypted %d bytes\n", dlen); + dp = dbuf; + dend = dp + dlen; - memcpy(&old_key, &th->session_key, sizeof(old_key)); - ret = ceph_crypto_key_decode(&new_session_key, &dp, dend); - if (ret) - goto out; + tkt_struct_v = ceph_decode_8(&dp); + if (tkt_struct_v != 1) + goto bad; - ceph_decode_copy(&dp, &new_validity, sizeof(new_validity)); - ceph_decode_timespec(&validity, &new_validity); - new_expires = get_seconds() + validity.tv_sec; - new_renew_after = new_expires - (validity.tv_sec / 4); - dout(" expires=%lu renew_after=%lu\n", new_expires, - new_renew_after); + memcpy(&old_key, &th->session_key, sizeof(old_key)); + ret = ceph_crypto_key_decode(&new_session_key, &dp, dend); + if (ret) + goto out; - /* ticket blob for service */ - ceph_decode_8_safe(&p, end, is_enc, bad); - tp = ticket_buf; - if (is_enc) { - /* encrypted */ - dout(" encrypted ticket\n"); - dlen = ceph_x_decrypt(&old_key, &p, end, ticket_buf, - TEMP_TICKET_BUF_LEN); - if (dlen < 0) { - ret = dlen; - goto out; - } - dlen = ceph_decode_32(&tp); - } else { - /* unencrypted */ - ceph_decode_32_safe(&p, end, dlen, bad); - ceph_decode_need(&p, end, dlen, bad); - ceph_decode_copy(&p, ticket_buf, dlen); + ceph_decode_copy(&dp, &new_validity, sizeof(new_validity)); + ceph_decode_timespec(&validity, &new_validity); + new_expires = get_seconds() + validity.tv_sec; + new_renew_after = new_expires - (validity.tv_sec / 4); + dout(" expires=%lu renew_after=%lu\n", new_expires, + new_renew_after); + + /* ticket blob for service */ + ceph_decode_8_safe(p, end, is_enc, bad); + if (is_enc) { + /* encrypted */ + dout(" encrypted ticket\n"); + dlen = ceph_x_decrypt(&old_key, p, end, &ticket_buf, 0); + if (dlen < 0) { + ret = dlen; + goto out; } - tpend = tp + dlen; - dout(" ticket blob is %d bytes\n", dlen); - ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad); - blob_struct_v = ceph_decode_8(&tp); - new_secret_id = ceph_decode_64(&tp); - ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend); - if (ret) + tp = ticket_buf; + dlen = ceph_decode_32(&tp); + } else { + /* unencrypted */ + ceph_decode_32_safe(p, end, dlen, bad); + ticket_buf = kmalloc(dlen, GFP_NOFS); + if (!ticket_buf) { + ret = -ENOMEM; goto out; - - /* all is well, update our ticket */ - ceph_crypto_key_destroy(&th->session_key); - if (th->ticket_blob) - ceph_buffer_put(th->ticket_blob); - th->session_key = new_session_key; - th->ticket_blob = new_ticket_blob; - th->validity = new_validity; - th->secret_id = new_secret_id; - th->expires = new_expires; - th->renew_after = new_renew_after; - dout(" got ticket service %d (%s) secret_id %lld len %d\n", - type, ceph_entity_type_name(type), th->secret_id, - (int)th->ticket_blob->vec.iov_len); - xi->have_keys |= th->service; + } + tp = ticket_buf; + ceph_decode_need(p, end, dlen, bad); + ceph_decode_copy(p, ticket_buf, dlen); } + tpend = tp + dlen; + dout(" ticket blob is %d bytes\n", dlen); + ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad); + blob_struct_v = ceph_decode_8(&tp); + new_secret_id = ceph_decode_64(&tp); + ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend); + if (ret) + goto out; + + /* all is well, update our ticket */ + ceph_crypto_key_destroy(&th->session_key); + if (th->ticket_blob) + ceph_buffer_put(th->ticket_blob); + th->session_key = new_session_key; + th->ticket_blob = new_ticket_blob; + th->validity = new_validity; + th->secret_id = new_secret_id; + th->expires = new_expires; + th->renew_after = new_renew_after; + dout(" got ticket service %d (%s) secret_id %lld len %d\n", + type, ceph_entity_type_name(type), th->secret_id, + (int)th->ticket_blob->vec.iov_len); + xi->have_keys |= th->service; - ret = 0; out: kfree(ticket_buf); -out_dbuf: kfree(dbuf); return ret; @@ -270,6 +255,34 @@ bad: goto out; } +static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac, + struct ceph_crypto_key *secret, + void *buf, void *end) +{ + void *p = buf; + u8 reply_struct_v; + u32 num; + int ret; + + ceph_decode_8_safe(&p, end, reply_struct_v, bad); + if (reply_struct_v != 1) + return -EINVAL; + + ceph_decode_32_safe(&p, end, num, bad); + dout("%d tickets\n", num); + + while (num--) { + ret = process_one_ticket(ac, secret, &p, end); + if (ret) + return ret; + } + + return 0; + +bad: + return -EINVAL; +} + static int ceph_x_build_authorizer(struct ceph_auth_client *ac, struct ceph_x_ticket_handler *th, struct ceph_x_authorizer *au) @@ -583,13 +596,14 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac, struct ceph_x_ticket_handler *th; int ret = 0; struct ceph_x_authorize_reply reply; + void *preply = &reply; void *p = au->reply_buf; void *end = p + sizeof(au->reply_buf); th = get_ticket_handler(ac, au->service); if (IS_ERR(th)) return PTR_ERR(th); - ret = ceph_x_decrypt(&th->session_key, &p, end, &reply, sizeof(reply)); + ret = ceph_x_decrypt(&th->session_key, &p, end, &preply, sizeof(reply)); if (ret < 0) return ret; if (ret != sizeof(reply)) diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 6e7a236525b6..06f19b9e159a 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -89,11 +89,82 @@ static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void) static const u8 *aes_iv = (u8 *)CEPH_AES_IV; +/* + * Should be used for buffers allocated with ceph_kvmalloc(). + * Currently these are encrypt out-buffer (ceph_buffer) and decrypt + * in-buffer (msg front). + * + * Dispose of @sgt with teardown_sgtable(). + * + * @prealloc_sg is to avoid memory allocation inside sg_alloc_table() + * in cases where a single sg is sufficient. No attempt to reduce the + * number of sgs by squeezing physically contiguous pages together is + * made though, for simplicity. + */ +static int setup_sgtable(struct sg_table *sgt, struct scatterlist *prealloc_sg, + const void *buf, unsigned int buf_len) +{ + struct scatterlist *sg; + const bool is_vmalloc = is_vmalloc_addr(buf); + unsigned int off = offset_in_page(buf); + unsigned int chunk_cnt = 1; + unsigned int chunk_len = PAGE_ALIGN(off + buf_len); + int i; + int ret; + + if (buf_len == 0) { + memset(sgt, 0, sizeof(*sgt)); + return -EINVAL; + } + + if (is_vmalloc) { + chunk_cnt = chunk_len >> PAGE_SHIFT; + chunk_len = PAGE_SIZE; + } + + if (chunk_cnt > 1) { + ret = sg_alloc_table(sgt, chunk_cnt, GFP_NOFS); + if (ret) + return ret; + } else { + WARN_ON(chunk_cnt != 1); + sg_init_table(prealloc_sg, 1); + sgt->sgl = prealloc_sg; + sgt->nents = sgt->orig_nents = 1; + } + + for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) { + struct page *page; + unsigned int len = min(chunk_len - off, buf_len); + + if (is_vmalloc) + page = vmalloc_to_page(buf); + else + page = virt_to_page(buf); + + sg_set_page(sg, page, len, off); + + off = 0; + buf += len; + buf_len -= len; + } + WARN_ON(buf_len != 0); + + return 0; +} + +static void teardown_sgtable(struct sg_table *sgt) +{ + if (sgt->orig_nents > 1) + sg_free_table(sgt); +} + static int ceph_aes_encrypt(const void *key, int key_len, void *dst, size_t *dst_len, const void *src, size_t src_len) { - struct scatterlist sg_in[2], sg_out[1]; + struct scatterlist sg_in[2], prealloc_sg; + struct sg_table sg_out; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; int ret; @@ -109,16 +180,18 @@ static int ceph_aes_encrypt(const void *key, int key_len, *dst_len = src_len + zero_padding; - crypto_blkcipher_setkey((void *)tfm, key, key_len); sg_init_table(sg_in, 2); sg_set_buf(&sg_in[0], src, src_len); sg_set_buf(&sg_in[1], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len); + if (ret) + goto out_tfm; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); + /* print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, key, key_len, 1); @@ -127,16 +200,22 @@ static int ceph_aes_encrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, pad, zero_padding, 1); */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in, src_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) + if (ret < 0) { pr_err("ceph_aes_crypt failed %d\n", ret); + goto out_sg; + } /* print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_out); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, @@ -144,7 +223,8 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, const void *src1, size_t src1_len, const void *src2, size_t src2_len) { - struct scatterlist sg_in[3], sg_out[1]; + struct scatterlist sg_in[3], prealloc_sg; + struct sg_table sg_out; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 }; int ret; @@ -160,17 +240,19 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, *dst_len = src1_len + src2_len + zero_padding; - crypto_blkcipher_setkey((void *)tfm, key, key_len); sg_init_table(sg_in, 3); sg_set_buf(&sg_in[0], src1, src1_len); sg_set_buf(&sg_in[1], src2, src2_len); sg_set_buf(&sg_in[2], pad, zero_padding); - sg_init_table(sg_out, 1); - sg_set_buf(sg_out, dst, *dst_len); + ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len); + if (ret) + goto out_tfm; + + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); + /* print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1, key, key_len, 1); @@ -181,23 +263,30 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst, print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1, pad, zero_padding, 1); */ - ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, + ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in, src1_len + src2_len + zero_padding); - crypto_free_blkcipher(tfm); - if (ret < 0) + if (ret < 0) { pr_err("ceph_aes_crypt2 failed %d\n", ret); + goto out_sg; + } /* print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_out); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_decrypt(const void *key, int key_len, void *dst, size_t *dst_len, const void *src, size_t src_len) { - struct scatterlist sg_in[1], sg_out[2]; + struct sg_table sg_in; + struct scatterlist sg_out[2], prealloc_sg; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm }; char pad[16]; @@ -209,16 +298,16 @@ static int ceph_aes_decrypt(const void *key, int key_len, if (IS_ERR(tfm)) return PTR_ERR(tfm); - crypto_blkcipher_setkey((void *)tfm, key, key_len); - sg_init_table(sg_in, 1); sg_init_table(sg_out, 2); - sg_set_buf(sg_in, src, src_len); sg_set_buf(&sg_out[0], dst, *dst_len); sg_set_buf(&sg_out[1], pad, sizeof(pad)); + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len); + if (ret) + goto out_tfm; + crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); /* @@ -227,12 +316,10 @@ static int ceph_aes_decrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, src, src_len, 1); */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len); if (ret < 0) { pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; + goto out_sg; } if (src_len <= *dst_len) @@ -250,7 +337,12 @@ static int ceph_aes_decrypt(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1, dst, *dst_len, 1); */ - return 0; + +out_sg: + teardown_sgtable(&sg_in); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } static int ceph_aes_decrypt2(const void *key, int key_len, @@ -258,7 +350,8 @@ static int ceph_aes_decrypt2(const void *key, int key_len, void *dst2, size_t *dst2_len, const void *src, size_t src_len) { - struct scatterlist sg_in[1], sg_out[3]; + struct sg_table sg_in; + struct scatterlist sg_out[3], prealloc_sg; struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher(); struct blkcipher_desc desc = { .tfm = tfm }; char pad[16]; @@ -270,17 +363,17 @@ static int ceph_aes_decrypt2(const void *key, int key_len, if (IS_ERR(tfm)) return PTR_ERR(tfm); - sg_init_table(sg_in, 1); - sg_set_buf(sg_in, src, src_len); sg_init_table(sg_out, 3); sg_set_buf(&sg_out[0], dst1, *dst1_len); sg_set_buf(&sg_out[1], dst2, *dst2_len); sg_set_buf(&sg_out[2], pad, sizeof(pad)); + ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len); + if (ret) + goto out_tfm; crypto_blkcipher_setkey((void *)tfm, key, key_len); iv = crypto_blkcipher_crt(tfm)->iv; ivsize = crypto_blkcipher_ivsize(tfm); - memcpy(iv, aes_iv, ivsize); /* @@ -289,12 +382,10 @@ static int ceph_aes_decrypt2(const void *key, int key_len, print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1, src, src_len, 1); */ - - ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len); - crypto_free_blkcipher(tfm); + ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len); if (ret < 0) { pr_err("ceph_aes_decrypt failed %d\n", ret); - return ret; + goto out_sg; } if (src_len <= *dst1_len) @@ -324,7 +415,11 @@ static int ceph_aes_decrypt2(const void *key, int key_len, dst2, *dst2_len, 1); */ - return 0; +out_sg: + teardown_sgtable(&sg_in); +out_tfm: + crypto_free_blkcipher(tfm); + return ret; } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index eb0a46a49bd4..e3bea2e0821a 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -290,7 +290,8 @@ int ceph_msgr_init(void) if (ceph_msgr_slab_init()) return -ENOMEM; - ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_NON_REENTRANT, 0); + ceph_msgr_wq = alloc_workqueue("ceph-msgr", + WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0); if (ceph_msgr_wq) return 0; @@ -556,7 +557,7 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov, return r; } -static int ceph_tcp_sendpage(struct socket *sock, struct page *page, +static int __ceph_tcp_sendpage(struct socket *sock, struct page *page, int offset, size_t size, bool more) { int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR); @@ -569,6 +570,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, return ret; } +static int ceph_tcp_sendpage(struct socket *sock, struct page *page, + int offset, size_t size, bool more) +{ + int ret; + struct kvec iov; + + /* sendpage cannot properly handle pages with page_count == 0, + * we need to fallback to sendmsg if that's the case */ + if (page_count(page) >= 1) + return __ceph_tcp_sendpage(sock, page, offset, size, more); + + iov.iov_base = kmap(page) + offset; + iov.iov_len = size; + ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more); + kunmap(page); + + return ret; +} /* * Shutdown/close the socket for the given connection. @@ -886,7 +905,7 @@ static void ceph_msg_data_pages_cursor_init(struct ceph_msg_data_cursor *cursor, BUG_ON(page_count > (int)USHRT_MAX); cursor->page_count = (unsigned short)page_count; BUG_ON(length > SIZE_MAX - cursor->page_offset); - cursor->last_piece = (size_t)cursor->page_offset + length <= PAGE_SIZE; + cursor->last_piece = cursor->page_offset + cursor->resid <= PAGE_SIZE; } static struct page * @@ -3126,7 +3145,7 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, INIT_LIST_HEAD(&m->data); /* front */ - m->front_max = front_len; + m->front_alloc_len = front_len; if (front_len) { if (front_len > PAGE_CACHE_SIZE) { m->front.iov_base = __vmalloc(front_len, flags, @@ -3301,8 +3320,8 @@ EXPORT_SYMBOL(ceph_msg_last_put); void ceph_msg_dump(struct ceph_msg *msg) { - pr_debug("msg_dump %p (front_max %d length %zd)\n", msg, - msg->front_max, msg->data_length); + pr_debug("msg_dump %p (front_alloc_len %d length %zd)\n", msg, + msg->front_alloc_len, msg->data_length); print_hex_dump(KERN_DEBUG, "header: ", DUMP_PREFIX_OFFSET, 16, 1, &msg->hdr, sizeof(msg->hdr), true); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 1fe25cd29d0e..dbcbf5a4707f 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -152,7 +152,7 @@ static int __open_session(struct ceph_mon_client *monc) /* initiatiate authentication handshake */ ret = ceph_auth_build_hello(monc->auth, monc->m_auth->front.iov_base, - monc->m_auth->front_max); + monc->m_auth->front_alloc_len); __send_prepared_auth_request(monc, ret); } else { dout("open_session mon%d already open\n", monc->cur_mon); @@ -196,7 +196,7 @@ static void __send_subscribe(struct ceph_mon_client *monc) int num; p = msg->front.iov_base; - end = p + msg->front_max; + end = p + msg->front_alloc_len; num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap; ceph_encode_32(&p, num); @@ -897,7 +897,7 @@ static void handle_auth_reply(struct ceph_mon_client *monc, ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base, msg->front.iov_len, monc->m_auth->front.iov_base, - monc->m_auth->front_max); + monc->m_auth->front_alloc_len); if (ret < 0) { monc->client->auth_err = ret; wake_up_all(&monc->client->auth_wq); @@ -939,7 +939,7 @@ static int __validate_auth(struct ceph_mon_client *monc) return 0; ret = ceph_build_auth(monc->auth, monc->m_auth->front.iov_base, - monc->m_auth->front_max); + monc->m_auth->front_alloc_len); if (ret <= 0) return ret; /* either an error, or no need to authenticate */ __send_prepared_auth_request(monc, ret); @@ -1041,7 +1041,15 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, if (!m) { pr_info("alloc_msg unknown type %d\n", type); *skip = 1; + } else if (front_len > m->front_alloc_len) { + pr_warning("mon_alloc_msg front %d > prealloc %d (%u#%llu)\n", + front_len, m->front_alloc_len, + (unsigned int)con->peer_name.type, + le64_to_cpu(con->peer_name.num)); + ceph_msg_put(m); + m = ceph_msg_new(type, front_len, GFP_NOFS, false); } + return m; } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 3a246a6cab47..1b51d9216e7e 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -733,12 +733,14 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, object_size = le32_to_cpu(layout->fl_object_size); object_base = off - objoff; - if (truncate_size <= object_base) { - truncate_size = 0; - } else { - truncate_size -= object_base; - if (truncate_size > object_size) - truncate_size = object_size; + if (!(truncate_seq == 1 && truncate_size == -1ULL)) { + if (truncate_size <= object_base) { + truncate_size = 0; + } else { + truncate_size -= object_base; + if (truncate_size > object_size) + truncate_size = object_size; + } } osd_req_op_extent_init(req, 0, opcode, objoff, objlen, @@ -965,12 +967,24 @@ static void put_osd(struct ceph_osd *osd) */ static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) { - dout("__remove_osd %p\n", osd); - BUG_ON(!list_empty(&osd->o_requests)); - rb_erase(&osd->o_node, &osdc->osds); + dout("%s %p osd%d\n", __func__, osd, osd->o_osd); + WARN_ON(!list_empty(&osd->o_requests)); + WARN_ON(!list_empty(&osd->o_linger_requests)); + list_del_init(&osd->o_osd_lru); - ceph_con_close(&osd->o_con); - put_osd(osd); + rb_erase(&osd->o_node, &osdc->osds); + RB_CLEAR_NODE(&osd->o_node); +} + +static void remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) +{ + dout("%s %p osd%d\n", __func__, osd, osd->o_osd); + + if (!RB_EMPTY_NODE(&osd->o_node)) { + ceph_con_close(&osd->o_con); + __remove_osd(osdc, osd); + put_osd(osd); + } } static void remove_all_osds(struct ceph_osd_client *osdc) @@ -980,7 +994,7 @@ static void remove_all_osds(struct ceph_osd_client *osdc) while (!RB_EMPTY_ROOT(&osdc->osds)) { struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds), struct ceph_osd, o_node); - __remove_osd(osdc, osd); + remove_osd(osdc, osd); } mutex_unlock(&osdc->request_mutex); } @@ -1010,7 +1024,7 @@ static void remove_old_osds(struct ceph_osd_client *osdc) list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) { if (time_before(jiffies, osd->lru_ttl)) break; - __remove_osd(osdc, osd); + remove_osd(osdc, osd); } mutex_unlock(&osdc->request_mutex); } @@ -1025,8 +1039,7 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) dout("__reset_osd %p osd%d\n", osd, osd->o_osd); if (list_empty(&osd->o_requests) && list_empty(&osd->o_linger_requests)) { - __remove_osd(osdc, osd); - + remove_osd(osdc, osd); return -ENODEV; } @@ -1174,6 +1187,7 @@ static void __register_linger_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { dout("__register_linger_request %p\n", req); + ceph_osdc_get_request(req); list_add_tail(&req->r_linger_item, &osdc->req_linger); if (req->r_osd) list_add_tail(&req->r_linger_osd, @@ -1196,6 +1210,7 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc, if (list_empty(&req->r_osd_item)) req->r_osd = NULL; } + ceph_osdc_put_request(req); } void ceph_osdc_unregister_linger_request(struct ceph_osd_client *osdc, @@ -1203,9 +1218,8 @@ void ceph_osdc_unregister_linger_request(struct ceph_osd_client *osdc, { mutex_lock(&osdc->request_mutex); if (req->r_linger) { - __unregister_linger_request(osdc, req); req->r_linger = 0; - ceph_osdc_put_request(req); + __unregister_linger_request(osdc, req); } mutex_unlock(&osdc->request_mutex); } @@ -1217,16 +1231,27 @@ void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc, if (!req->r_linger) { dout("set_request_linger %p\n", req); req->r_linger = 1; - /* - * caller is now responsible for calling - * unregister_linger_request - */ - ceph_osdc_get_request(req); } } EXPORT_SYMBOL(ceph_osdc_set_request_linger); /* + * Returns whether a request should be blocked from being sent + * based on the current osdmap and osd_client settings. + * + * Caller should hold map_sem for read. + */ +static bool __req_should_be_paused(struct ceph_osd_client *osdc, + struct ceph_osd_request *req) +{ + bool pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD); + bool pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) || + ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL); + return (req->r_flags & CEPH_OSD_FLAG_READ && pauserd) || + (req->r_flags & CEPH_OSD_FLAG_WRITE && pausewr); +} + +/* * Pick an osd (the first 'up' osd in the pg), allocate the osd struct * (as needed), and set the request r_osd appropriately. If there is * no up osd, set r_osd to NULL. Move the request to the appropriate list @@ -1243,6 +1268,7 @@ static int __map_request(struct ceph_osd_client *osdc, int acting[CEPH_PG_MAX_SIZE]; int o = -1, num = 0; int err; + bool was_paused; dout("map_request %p tid %lld\n", req, req->r_tid); err = ceph_calc_ceph_pg(&pgid, req->r_oid, osdc->osdmap, @@ -1259,12 +1285,18 @@ static int __map_request(struct ceph_osd_client *osdc, num = err; } + was_paused = req->r_paused; + req->r_paused = __req_should_be_paused(osdc, req); + if (was_paused && !req->r_paused) + force_resend = 1; + if ((!force_resend && req->r_osd && req->r_osd->o_osd == o && req->r_sent >= req->r_osd->o_incarnation && req->r_num_pg_osds == num && memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) || - (req->r_osd == NULL && o == -1)) + (req->r_osd == NULL && o == -1) || + req->r_paused) return 0; /* no change */ dout("map_request tid %llu pgid %lld.%x osd%d (was osd%d)\n", @@ -1339,10 +1371,6 @@ static void __send_request(struct ceph_osd_client *osdc, ceph_msg_get(req->r_request); /* send consumes a ref */ - /* Mark the request unsafe if this is the first timet's being sent. */ - - if (!req->r_sent && req->r_unsafe_callback) - req->r_unsafe_callback(req, true); req->r_sent = req->r_osd->o_incarnation; ceph_con_send(&req->r_osd->o_con, req->r_request); @@ -1433,8 +1461,6 @@ static void handle_osds_timeout(struct work_struct *work) static void complete_request(struct ceph_osd_request *req) { - if (req->r_unsafe_callback) - req->r_unsafe_callback(req, false); complete_all(&req->r_safe_completion); /* fsync waiter */ } @@ -1496,14 +1522,14 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, dout("handle_reply %p tid %llu req %p result %d\n", msg, tid, req, result); - ceph_decode_need(&p, end, 4, bad); + ceph_decode_need(&p, end, 4, bad_put); numops = ceph_decode_32(&p); if (numops > CEPH_OSD_MAX_OP) goto bad_put; if (numops != req->r_num_ops) goto bad_put; payload_len = 0; - ceph_decode_need(&p, end, numops * sizeof(struct ceph_osd_op), bad); + ceph_decode_need(&p, end, numops * sizeof(struct ceph_osd_op), bad_put); for (i = 0; i < numops; i++) { struct ceph_osd_op *op = p; int len; @@ -1521,11 +1547,13 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, goto bad_put; } - ceph_decode_need(&p, end, 4 + numops * 4, bad); + ceph_decode_need(&p, end, 4 + numops * 4, bad_put); retry_attempt = ceph_decode_32(&p); for (i = 0; i < numops; i++) req->r_reply_op_result[i] = ceph_decode_32(&p); + already_completed = req->r_got_reply; + if (!req->r_got_reply) { req->r_result = result; @@ -1556,19 +1584,23 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, ((flags & CEPH_OSD_FLAG_WRITE) == 0)) __unregister_request(osdc, req); - already_completed = req->r_completed; - req->r_completed = 1; mutex_unlock(&osdc->request_mutex); - if (already_completed) - goto done; - if (req->r_callback) - req->r_callback(req, msg); - else - complete_all(&req->r_completion); + if (!already_completed) { + if (req->r_unsafe_callback && + result >= 0 && !(flags & CEPH_OSD_FLAG_ONDISK)) + req->r_unsafe_callback(req, true); + if (req->r_callback) + req->r_callback(req, msg); + else + complete_all(&req->r_completion); + } - if (flags & CEPH_OSD_FLAG_ONDISK) + if (flags & CEPH_OSD_FLAG_ONDISK) { + if (req->r_unsafe_callback && already_completed) + req->r_unsafe_callback(req, false); complete_request(req); + } done: dout("req=%p req->r_linger=%d\n", req, req->r_linger); @@ -1589,6 +1621,7 @@ static void reset_changed_osds(struct ceph_osd_client *osdc) { struct rb_node *p, *n; + dout("%s %p\n", __func__, osdc); for (p = rb_first(&osdc->osds); p; p = n) { struct ceph_osd *osd = rb_entry(p, struct ceph_osd, o_node); @@ -1608,14 +1641,17 @@ static void reset_changed_osds(struct ceph_osd_client *osdc) * * Caller should hold map_sem for read. */ -static void kick_requests(struct ceph_osd_client *osdc, int force_resend) +static void kick_requests(struct ceph_osd_client *osdc, bool force_resend, + bool force_resend_writes) { struct ceph_osd_request *req, *nreq; struct rb_node *p; int needmap = 0; int err; + bool force_resend_req; - dout("kick_requests %s\n", force_resend ? " (force resend)" : ""); + dout("kick_requests %s %s\n", force_resend ? " (force resend)" : "", + force_resend_writes ? " (force resend writes)" : ""); mutex_lock(&osdc->request_mutex); for (p = rb_first(&osdc->requests); p; ) { req = rb_entry(p, struct ceph_osd_request, r_node); @@ -1633,12 +1669,17 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) dout("%p tid %llu restart on osd%d\n", req, req->r_tid, req->r_osd ? req->r_osd->o_osd : -1); + ceph_osdc_get_request(req); __unregister_request(osdc, req); __register_linger_request(osdc, req); + ceph_osdc_put_request(req); continue; } - err = __map_request(osdc, req, force_resend); + force_resend_req = force_resend || + (force_resend_writes && + req->r_flags & CEPH_OSD_FLAG_WRITE); + err = __map_request(osdc, req, force_resend_req); if (err < 0) continue; /* error */ if (req->r_osd == NULL) { @@ -1658,7 +1699,8 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) r_linger_item) { dout("linger req=%p req->r_osd=%p\n", req, req->r_osd); - err = __map_request(osdc, req, force_resend); + err = __map_request(osdc, req, + force_resend || force_resend_writes); dout("__map_request returned %d\n", err); if (err == 0) continue; /* no change and no osd was specified */ @@ -1700,6 +1742,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) struct ceph_osdmap *newmap = NULL, *oldmap; int err; struct ceph_fsid fsid; + bool was_full; dout("handle_map have %u\n", osdc->osdmap ? osdc->osdmap->epoch : 0); p = msg->front.iov_base; @@ -1713,6 +1756,8 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) down_write(&osdc->map_sem); + was_full = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL); + /* incremental maps */ ceph_decode_32_safe(&p, end, nr_maps, bad); dout(" %d inc maps\n", nr_maps); @@ -1737,7 +1782,10 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) ceph_osdmap_destroy(osdc->osdmap); osdc->osdmap = newmap; } - kick_requests(osdc, 0); + was_full = was_full || + ceph_osdmap_flag(osdc->osdmap, + CEPH_OSDMAP_FULL); + kick_requests(osdc, 0, was_full); } else { dout("ignoring incremental map %u len %d\n", epoch, maplen); @@ -1780,12 +1828,17 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) skipped_map = 1; ceph_osdmap_destroy(oldmap); } - kick_requests(osdc, skipped_map); + was_full = was_full || + ceph_osdmap_flag(osdc->osdmap, + CEPH_OSDMAP_FULL); + kick_requests(osdc, skipped_map, was_full); } p += maplen; nr_maps--; } + if (!osdc->osdmap) + goto bad; done: downgrade_write(&osdc->map_sem); ceph_monc_got_osdmap(&osdc->client->monc, osdc->osdmap->epoch); @@ -1795,7 +1848,9 @@ done: * we find out when we are no longer full and stop returning * ENOSPC. */ - if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) + if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) || + ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD) || + ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR)) ceph_monc_request_next_osdmap(&osdc->client->monc); mutex_lock(&osdc->request_mutex); @@ -2123,13 +2178,14 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, __register_request(osdc, req); req->r_sent = 0; req->r_got_reply = 0; - req->r_completed = 0; rc = __map_request(osdc, req, 0); if (rc < 0) { if (nofail) { dout("osdc_start_request failed map, " " will retry %lld\n", req->r_tid); rc = 0; + } else { + __unregister_request(osdc, req); } goto out_unlock; } @@ -2206,6 +2262,17 @@ void ceph_osdc_sync(struct ceph_osd_client *osdc) EXPORT_SYMBOL(ceph_osdc_sync); /* + * Call all pending notify callbacks - for use after a watch is + * unregistered, to make sure no more callbacks for it will be invoked + */ +extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc) +{ + flush_workqueue(osdc->notify_wq); +} +EXPORT_SYMBOL(ceph_osdc_flush_notifies); + + +/* * init, shutdown */ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) @@ -2254,12 +2321,10 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) if (err < 0) goto out_msgpool; + err = -ENOMEM; osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify"); - if (IS_ERR(osdc->notify_wq)) { - err = PTR_ERR(osdc->notify_wq); - osdc->notify_wq = NULL; + if (!osdc->notify_wq) goto out_msgpool; - } return 0; out_msgpool: diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 603ddd92db19..dbd9a4792427 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1129,7 +1129,7 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, /* pg_temp? */ pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num, - pool->pgp_num_mask); + pool->pg_num_mask); pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid); if (pg) { *num = pg->len; diff --git a/net/compat.c b/net/compat.c index f0a1ba6c8086..d12529050b29 100644 --- a/net/compat.c +++ b/net/compat.c @@ -71,6 +71,15 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg) __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; + + if (!tmp1) + kmsg->msg_namelen = 0; + + if (kmsg->msg_namelen < 0) + return -EINVAL; + + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) + kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_name = compat_ptr(tmp1); kmsg->msg_iov = compat_ptr(tmp2); kmsg->msg_control = compat_ptr(tmp3); @@ -83,7 +92,7 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov, { int tot_len; - if (kern_msg->msg_namelen) { + if (kern_msg->msg_name && kern_msg->msg_namelen) { if (mode == VERIFY_READ) { int err = move_addr_to_kernel(kern_msg->msg_name, kern_msg->msg_namelen, @@ -92,8 +101,10 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov, return err; } kern_msg->msg_name = kern_address; - } else + } else { kern_msg->msg_name = NULL; + kern_msg->msg_namelen = 0; + } tot_len = iov_from_user_compat_to_kern(kern_iov, (struct compat_iovec __user *)kern_msg->msg_iov, @@ -734,24 +745,18 @@ static unsigned char nas[21] = { asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; return __sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; return __sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } @@ -774,24 +779,16 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, int datagrams; struct timespec ktspec; - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - - if (COMPAT_USE_64BIT_TIME) - return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, - flags | MSG_CMSG_COMPAT, - (struct timespec *) timeout); - if (timeout == NULL) return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, NULL); - if (get_compat_timespec(&ktspec, timeout)) + if (compat_get_timespec(&ktspec, timeout)) return -EFAULT; datagrams = __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, &ktspec); - if (datagrams > 0 && put_compat_timespec(&ktspec, timeout)) + if (datagrams > 0 && compat_put_timespec(&ktspec, timeout)) datagrams = -EFAULT; return datagrams; diff --git a/net/core/dev.c b/net/core/dev.c index faebb398fb46..aeca8dd88b2a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -927,7 +927,7 @@ bool dev_valid_name(const char *name) return false; while (*name) { - if (*name == '/' || isspace(*name)) + if (*name == '/' || *name == ':' || isspace(*name)) return false; name++; } @@ -2374,7 +2374,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 2. No high memory really exists on this machine. */ -static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; @@ -2454,46 +2454,51 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) } static netdev_features_t harmonize_features(struct sk_buff *skb, - __be16 protocol, netdev_features_t features) + __be16 protocol, + const struct net_device *dev, + netdev_features_t features) { if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, protocol)) { features &= ~NETIF_F_ALL_CSUM; - } else if (illegal_highdma(skb->dev, skb)) { + } else if (illegal_highdma(dev, skb)) { features &= ~NETIF_F_SG; } return features; } -netdev_features_t netif_skb_features(struct sk_buff *skb) +netdev_features_t netif_skb_dev_features(struct sk_buff *skb, + const struct net_device *dev) { __be16 protocol = skb->protocol; - netdev_features_t features = skb->dev->features; + netdev_features_t features = dev->features; - if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, protocol, features); + return harmonize_features(skb, protocol, dev, features); } - features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD)) { - return harmonize_features(skb, protocol, features); + return harmonize_features(skb, protocol, dev, features); } else { features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - return harmonize_features(skb, protocol, features); + return harmonize_features(skb, protocol, dev, features); } + + return harmonize_features(skb, protocol, dev, features); } -EXPORT_SYMBOL(netif_skb_features); +EXPORT_SYMBOL(netif_skb_dev_features); /* * Returns true if either: @@ -3513,8 +3518,15 @@ ncls: } } - if (vlan_tx_nonzero_tag_present(skb)) - skb->pkt_type = PACKET_OTHERHOST; + if (unlikely(vlan_tx_tag_present(skb))) { + if (vlan_tx_tag_get_id(skb)) + skb->pkt_type = PACKET_OTHERHOST; + /* Note: we might in the future use prio bits + * and set skb->priority like in vlan_do_receive() + * For the time being, just ignore Priority Code Point + */ + skb->vlan_tci = 0; + } /* deliver only exact match when indicated */ null_or_dev = deliver_exact ? skb->dev : NULL; @@ -3886,6 +3898,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->vlan_tci = 0; skb->dev = napi->dev; skb->skb_iif = 0; + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); napi->skb = skb; } @@ -4471,7 +4484,7 @@ static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; - if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags) + if (ops->ndo_change_rx_flags) ops->ndo_change_rx_flags(dev, flags); } @@ -4622,6 +4635,7 @@ void __dev_set_rx_mode(struct net_device *dev) if (ops->ndo_set_rx_mode) ops->ndo_set_rx_mode(dev); } +EXPORT_SYMBOL(__dev_set_rx_mode); void dev_set_rx_mode(struct net_device *dev) { @@ -5813,6 +5827,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue); /** * unregister_netdevice_many - unregister many devices * @head: list of devices + * + * Note: As most callers use a stack allocated list_head, + * we force a list_del() to make sure stack wont be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { @@ -5822,6 +5839,7 @@ void unregister_netdevice_many(struct list_head *head) rollback_registered_many(head); list_for_each_entry(dev, head, unreg_list) net_set_todo(dev); + list_del(head); } } EXPORT_SYMBOL(unregister_netdevice_many); @@ -5997,10 +6015,20 @@ static int dev_cpu_callback(struct notifier_block *nfb, oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } - /* Append NAPI poll list from offline CPU. */ - if (!list_empty(&oldsd->poll_list)) { - list_splice_init(&oldsd->poll_list, &sd->poll_list); - raise_softirq_irqoff(NET_RX_SOFTIRQ); + /* Append NAPI poll list from offline CPU, with one exception : + * process_backlog() must be called by cpu owning percpu backlog. + * We properly handle process_queue & input_pkt_queue later. + */ + while (!list_empty(&oldsd->poll_list)) { + struct napi_struct *napi = list_first_entry(&oldsd->poll_list, + struct napi_struct, + poll_list); + + list_del_init(&napi->poll_list); + if (napi->poll == process_backlog) + napi->state = 0; + else + ____napi_schedule(sd, napi); } raise_softirq_irqoff(NET_TX_SOFTIRQ); @@ -6011,7 +6039,7 @@ static int dev_cpu_callback(struct notifier_block *nfb, netif_rx(skb); input_queue_head_incr(oldsd); } - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); input_queue_head_incr(oldsd); } @@ -6238,7 +6266,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) } } unregister_netdevice_many(&dev_kill_list); - list_del(&dev_kill_list); rtnl_unlock(); } diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index d23b6682f4e9..a974dfec4bf1 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -64,7 +64,6 @@ static struct genl_family net_drop_monitor_family = { .hdrsize = 0, .name = "NET_DM", .version = 2, - .maxattr = NET_DM_CMD_MAX, }; static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); diff --git a/net/core/dst.c b/net/core/dst.c index df9cc810ec8e..c0e021871df8 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -267,6 +267,15 @@ again: } EXPORT_SYMBOL(dst_destroy); +static void dst_destroy_rcu(struct rcu_head *head) +{ + struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); + + dst = dst_destroy(dst); + if (dst) + __dst_free(dst); +} + void dst_release(struct dst_entry *dst) { if (dst) { @@ -274,11 +283,8 @@ void dst_release(struct dst_entry *dst) newrefcnt = atomic_dec_return(&dst->__refcnt); WARN_ON(newrefcnt < 0); - if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) { - dst = dst_destroy(dst); - if (dst) - __dst_free(dst); - } + if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) + call_rcu(&dst->rcu_head, dst_destroy_rcu); } } EXPORT_SYMBOL(dst_release); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index d5a9f8ead0d8..55e08e2de3a1 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -445,7 +445,8 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) if (frh->action && (frh->action != rule->action)) continue; - if (frh->table && (frh_get_table(frh, tb) != rule->table)) + if (frh_get_table(frh, tb) && + (frh_get_table(frh, tb) != rule->table)) continue; if (tb[FRA_PRIORITY] && @@ -719,6 +720,13 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, attach_rules(&ops->rules_list, dev); break; + case NETDEV_CHANGENAME: + list_for_each_entry(ops, &net->rules_ops, list) { + detach_rules(&ops->rules_list, dev); + attach_rules(&ops->rules_list, dev); + } + break; + case NETDEV_UNREGISTER: list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); diff --git a/net/core/filter.c b/net/core/filter.c index 6438f29ff266..c6c18d8a2d88 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -36,7 +36,6 @@ #include <asm/uaccess.h> #include <asm/unaligned.h> #include <linux/filter.h> -#include <linux/reciprocal_div.h> #include <linux/ratelimit.h> #include <linux/seccomp.h> #include <linux/if_vlan.h> @@ -166,7 +165,7 @@ unsigned int sk_run_filter(const struct sk_buff *skb, A /= X; continue; case BPF_S_ALU_DIV_K: - A = reciprocal_divide(A, K); + A /= K; continue; case BPF_S_ALU_MOD_X: if (X == 0) @@ -356,6 +355,8 @@ load_b: if (skb_is_nonlinear(skb)) return 0; + if (skb->len < sizeof(struct nlattr)) + return 0; if (A > skb->len - sizeof(struct nlattr)) return 0; @@ -372,11 +373,13 @@ load_b: if (skb_is_nonlinear(skb)) return 0; + if (skb->len < sizeof(struct nlattr)) + return 0; if (A > skb->len - sizeof(struct nlattr)) return 0; nla = (struct nlattr *)&skb->data[A]; - if (nla->nla_len > A - skb->len) + if (nla->nla_len > skb->len - A) return 0; nla = nla_find_nested(nla, X); @@ -553,11 +556,6 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) /* Some instructions need special checks */ switch (code) { case BPF_S_ALU_DIV_K: - /* check for division by zero */ - if (ftest->k == 0) - return -EINVAL; - ftest->k = reciprocal_value(ftest->k); - break; case BPF_S_ALU_MOD_K: /* check for division by zero */ if (ftest->k == 0) @@ -853,27 +851,7 @@ void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to) to->code = decodes[code]; to->jt = filt->jt; to->jf = filt->jf; - - if (code == BPF_S_ALU_DIV_K) { - /* - * When loaded this rule user gave us X, which was - * translated into R = r(X). Now we calculate the - * RR = r(R) and report it back. If next time this - * value is loaded and RRR = r(RR) is calculated - * then the R == RRR will be true. - * - * One exception. X == 1 translates into R == 0 and - * we can't calculate RR out of it with r(). - */ - - if (filt->k == 0) - to->k = 1; - else - to->k = reciprocal_value(filt->k); - - BUG_ON(reciprocal_value(to->k) != filt->k); - } else - to->k = filt->k; + to->k = filt->k; } int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 00ee068efc1c..f97101b4d373 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -40,7 +40,7 @@ again: struct iphdr _iph; ip: iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); - if (!iph) + if (!iph || iph->ihl < 5) return false; if (ip_is_fragment(iph)) @@ -149,8 +149,8 @@ ipv6: if (poff >= 0) { __be32 *ports, _ports; - nhoff += poff; - ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports); + ports = skb_header_pointer(skb, nhoff + poff, + sizeof(_ports), &_ports); if (ports) flow->ports = *ports; } @@ -345,14 +345,9 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) if (new_index < 0) new_index = skb_tx_hash(dev, skb); - if (queue_index != new_index && sk) { - struct dst_entry *dst = - rcu_dereference_check(sk->sk_dst_cache, 1); - - if (dst && skb_dst(skb) == dst) - sk_tx_queue_set(sk, queue_index); - - } + if (queue_index != new_index && sk && + rcu_access_pointer(sk->sk_dst_cache)) + sk_tx_queue_set(sk, new_index); queue_index = new_index; } diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index ddedf211e588..b96437b6e82b 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -32,6 +32,9 @@ gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size) return 0; nla_put_failure: + kfree(d->xstats); + d->xstats = NULL; + d->xstats_len = 0; spin_unlock_bh(d->lock); return -1; } @@ -205,7 +208,9 @@ int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) { if (d->compat_xstats) { - d->xstats = st; + d->xstats = kmemdup(st, len, GFP_ATOMIC); + if (!d->xstats) + goto err_out; d->xstats_len = len; } @@ -213,6 +218,11 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) return gnet_stats_copy(d, TCA_STATS_APP, st, len); return 0; + +err_out: + d->xstats_len = 0; + spin_unlock_bh(d->lock); + return -1; } EXPORT_SYMBOL(gnet_stats_copy_app); @@ -245,6 +255,9 @@ gnet_stats_finish_copy(struct gnet_dump *d) return -1; } + kfree(d->xstats); + d->xstats = NULL; + d->xstats_len = 0; spin_unlock_bh(d->lock); return 0; } diff --git a/net/core/iovec.c b/net/core/iovec.c index de178e462682..1117a26a8548 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -39,7 +39,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a { int size, ct, err; - if (m->msg_namelen) { + if (m->msg_name && m->msg_namelen) { if (mode == VERIFY_READ) { void __user *namep; namep = (void __user __force *) m->msg_name; @@ -51,6 +51,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a m->msg_name = address; } else { m->msg_name = NULL; + m->msg_namelen = 0; } size = m->msg_iovlen * sizeof(struct iovec); @@ -106,6 +107,10 @@ EXPORT_SYMBOL(memcpy_toiovecend); int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, int offset, int len) { + /* No data? Done! */ + if (len == 0) + return 0; + /* Skip over the finished iovecs */ while (offset >= iov->iov_len) { offset -= iov->iov_len; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5c56b217b999..b49e8bafab17 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -231,7 +231,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) we must kill timers etc. and move it to safe state. */ - skb_queue_purge(&n->arp_queue); + __skb_queue_purge(&n->arp_queue); n->arp_queue_len_bytes = 0; n->output = neigh_blackhole; if (n->nud_state & NUD_VALID) @@ -286,7 +286,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device if (!n) goto out_entries; - skb_queue_head_init(&n->arp_queue); + __skb_queue_head_init(&n->arp_queue); rwlock_init(&n->lock); seqlock_init(&n->ha_lock); n->updated = n->used = now; @@ -708,7 +708,9 @@ void neigh_destroy(struct neighbour *neigh) if (neigh_del_timer(neigh)) pr_warn("Impossible event\n"); - skb_queue_purge(&neigh->arp_queue); + write_lock_bh(&neigh->lock); + __skb_queue_purge(&neigh->arp_queue); + write_unlock_bh(&neigh->lock); neigh->arp_queue_len_bytes = 0; if (dev->netdev_ops->ndo_neigh_destroy) @@ -762,9 +764,6 @@ static void neigh_periodic_work(struct work_struct *work) nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - if (atomic_read(&tbl->entries) < tbl->gc_thresh1) - goto out; - /* * periodically recompute ReachableTime from random function */ @@ -777,6 +776,9 @@ static void neigh_periodic_work(struct work_struct *work) neigh_rand_reach_time(p->base_reachable_time); } + if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + goto out; + for (i = 0 ; i < (1 << nht->hash_shift); i++) { np = &nht->hash_buckets[i]; @@ -858,7 +860,7 @@ static void neigh_invalidate(struct neighbour *neigh) neigh->ops->error_report(neigh, skb); write_lock(&neigh->lock); } - skb_queue_purge(&neigh->arp_queue); + __skb_queue_purge(&neigh->arp_queue); neigh->arp_queue_len_bytes = 0; } @@ -1210,7 +1212,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, write_lock_bh(&neigh->lock); } - skb_queue_purge(&neigh->arp_queue); + __skb_queue_purge(&neigh->arp_queue); neigh->arp_queue_len_bytes = 0; } out: @@ -1272,7 +1274,7 @@ int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb) if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL, skb->len) < 0 && - dev->header_ops->rebuild(skb)) + dev_rebuild_header(skb)) return 0; return dev_queue_xmit(skb); @@ -1443,16 +1445,18 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, atomic_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(p->base_reachable_time); + dev_hold(dev); + p->dev = dev; + write_pnet(&p->net, hold_net(net)); + p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { + release_net(net); + dev_put(dev); kfree(p); return NULL; } - dev_hold(dev); - p->dev = dev; - write_pnet(&p->net, hold_net(net)); - p->sysctl_table = NULL; write_lock_bh(&tbl->lock); p->next = tbl->parms.next; tbl->parms.next = p; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index cec074be8c43..e861438d5454 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -386,8 +386,14 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, !vlan_hw_offload_capable(netif_skb_features(skb), skb->vlan_proto)) { skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb)); - if (unlikely(!skb)) - break; + if (unlikely(!skb)) { + /* This is actually a packet drop, but we + * don't want the code at the end of this + * function to try and re-queue a NULL skb. + */ + status = NETDEV_TX_OK; + goto unlock_txq; + } skb->vlan_tci = 0; } @@ -395,6 +401,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, if (status == NETDEV_TX_OK) txq_trans_update(txq); } + unlock_txq: __netif_tx_unlock(txq); if (status == NETDEV_TX_OK) @@ -550,7 +557,7 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo return; proto = ntohs(eth_hdr(skb)->h_proto); - if (proto == ETH_P_IP) { + if (proto == ETH_P_ARP) { struct arphdr *arp; unsigned char *arp_ptr; /* No arp on this interface */ @@ -738,7 +745,7 @@ static bool pkt_is_ns(struct sk_buff *skb) struct nd_msg *msg; struct ipv6hdr *hdr; - if (skb->protocol != htons(ETH_P_ARP)) + if (skb->protocol != htons(ETH_P_IPV6)) return false; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg))) return false; @@ -941,6 +948,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) { char *cur=opt, *delim; int ipv6; + bool ipversion_set = false; if (*cur != '@') { if ((delim = strchr(cur, '@')) == NULL) @@ -953,6 +961,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) cur++; if (*cur != '/') { + ipversion_set = true; if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; @@ -995,7 +1004,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); if (ipv6 < 0) goto parse_failed; - else if (np->ipv6 != (bool)ipv6) + else if (ipversion_set && np->ipv6 != (bool)ipv6) goto parse_failed; else np->ipv6 = (bool)ipv6; @@ -1289,15 +1298,14 @@ EXPORT_SYMBOL_GPL(__netpoll_free_async); void netpoll_cleanup(struct netpoll *np) { - if (!np->dev) - return; - rtnl_lock(); + if (!np->dev) + goto out; __netpoll_cleanup(np); - rtnl_unlock(); - dev_put(np->dev); np->dev = NULL; +out: + rtnl_unlock(); } EXPORT_SYMBOL(netpoll_cleanup); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 11f2704c3810..ebbea5371967 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2515,6 +2515,8 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, if (x) { int ret; __u8 *eth; + struct iphdr *iph; + nhead = x->props.header_len - skb_headroom(skb); if (nhead > 0) { ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC); @@ -2536,6 +2538,11 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, eth = (__u8 *) skb_push(skb, ETH_HLEN); memcpy(eth, pkt_dev->hh, 12); *(u16 *) ð[12] = protocol; + + /* Update IPv4 header len as well as checksum value */ + iph = ip_hdr(skb); + iph->tot_len = htons(skb->len - ETH_HLEN); + ip_send_check(iph); } } return 1; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a08bd2b7fe3f..a67310e00b3f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -714,7 +714,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, return 0; } -static size_t rtnl_port_size(const struct net_device *dev) +static size_t rtnl_port_size(const struct net_device *dev, + u32 ext_filter_mask) { size_t port_size = nla_total_size(4) /* PORT_VF */ + nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */ @@ -730,7 +731,8 @@ static size_t rtnl_port_size(const struct net_device *dev) size_t port_self_size = nla_total_size(sizeof(struct nlattr)) + port_size; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; if (dev_num_vf(dev->dev.parent)) return port_self_size + vf_ports_size + @@ -765,7 +767,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(ext_filter_mask & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ - + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */ } @@ -826,11 +828,13 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev) return 0; } -static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) +static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev, + u32 ext_filter_mask) { int err; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; err = rtnl_port_self_fill(skb, dev); @@ -985,7 +989,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_nest_end(skb, vfinfo); } - if (rtnl_port_fill(skb, dev)) + if (rtnl_port_fill(skb, dev, ext_filter_mask)) goto nla_put_failure; if (dev->rtnl_link_ops) { @@ -1039,6 +1043,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_head *head; struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; + int err; + int hdrlen; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -1046,8 +1052,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); cb->seq = net->dev_base_seq; - if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, - ifla_policy) >= 0) { + /* A hack to preserve kernel<->userspace interface. + * The correct header is ifinfomsg. It is consistent with rtnl_getlink. + * However, before Linux v3.9 the code here assumed rtgenmsg and that's + * what iproute2 < v3.9.0 used. + * We can detect the old iproute2. Even including the IFLA_EXT_MASK + * attribute, its netlink message is shorter than struct ifinfomsg. + */ + hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); + + if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); @@ -1059,11 +1074,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; - if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI, - ext_filter_mask) <= 0) + err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI, + ext_filter_mask); + /* If we ran out of room on the first message, + * we're in trouble + */ + WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); + + if (err <= 0) goto out; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -1117,14 +1138,10 @@ static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = { }; static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { - [IFLA_VF_MAC] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_mac) }, - [IFLA_VF_VLAN] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_vlan) }, - [IFLA_VF_TX_RATE] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_tx_rate) }, - [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_spoofchk) }, + [IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) }, + [IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) }, + [IFLA_VF_TX_RATE] = { .len = sizeof(struct ifla_vf_tx_rate) }, + [IFLA_VF_SPOOFCHK] = { .len = sizeof(struct ifla_vf_spoofchk) }, }; static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { @@ -1283,7 +1300,8 @@ static int do_set_master(struct net_device *dev, int ifindex) return 0; } -static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, +static int do_setlink(const struct sk_buff *skb, + struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { const struct net_device_ops *ops = dev->netdev_ops; @@ -1295,7 +1313,8 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, err = PTR_ERR(net); goto errout; } - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); err = -EPERM; goto errout; } @@ -1549,7 +1568,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) if (err < 0) goto errout; - err = do_setlink(dev, ifm, tb, ifname, 0); + err = do_setlink(skb, dev, ifm, tb, ifname, 0); errout: return err; } @@ -1589,7 +1608,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) ops->dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); - list_del(&list_kill); return 0; } @@ -1667,7 +1685,8 @@ err: } EXPORT_SYMBOL(rtnl_create_link); -static int rtnl_group_changelink(struct net *net, int group, +static int rtnl_group_changelink(const struct sk_buff *skb, + struct net *net, int group, struct ifinfomsg *ifm, struct nlattr **tb) { @@ -1676,7 +1695,7 @@ static int rtnl_group_changelink(struct net *net, int group, for_each_netdev(net, dev) { if (dev->group == group) { - err = do_setlink(dev, ifm, tb, NULL, 0); + err = do_setlink(skb, dev, ifm, tb, NULL, 0); if (err < 0) return err; } @@ -1778,12 +1797,12 @@ replay: modified = 1; } - return do_setlink(dev, ifm, tb, ifname, modified); + return do_setlink(skb, dev, ifm, tb, ifname, modified); } if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) - return rtnl_group_changelink(net, + return rtnl_group_changelink(skb, net, nla_get_u32(tb[IFLA_GROUP]), ifm, tb); return -ENODEV; @@ -1832,8 +1851,16 @@ replay: goto out; err = rtnl_configure_link(dev, ifm); - if (err < 0) - unregister_netdevice(dev); + if (err < 0) { + if (ops->newlink) { + LIST_HEAD(list_kill); + + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + } else { + unregister_netdevice(dev); + } + } out: put_net(dest_net); return err; @@ -1895,9 +1922,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; u16 min_ifinfo_dump_size = 0; + int hdrlen; + + /* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */ + hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); - if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, - ifla_policy) >= 0) { + if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); } @@ -1973,12 +2004,13 @@ EXPORT_SYMBOL(rtmsg_ifinfo); static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, u8 *addr, u32 pid, u32 seq, - int type, unsigned int flags) + int type, unsigned int flags, + int nlflags) { struct nlmsghdr *nlh; struct ndmsg *ndm; - nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), nlflags); if (!nlh) return -EMSGSIZE; @@ -2016,7 +2048,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type) if (!skb) goto errout; - err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF); + err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0); if (err < 0) { kfree_skb(skb); goto errout; @@ -2142,7 +2174,7 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, /* If aging addresses are supported device will need to * implement its own handler for this. */ - if (ndm->ndm_state & NUD_PERMANENT) { + if (!(ndm->ndm_state & NUD_PERMANENT)) { pr_info("%s: FDB only supports static addresses\n", dev->name); return -EINVAL; } @@ -2167,7 +2199,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) int err = -EINVAL; __u8 *addr; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); @@ -2249,7 +2281,8 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, portid, seq, - RTM_NEWNEIGH, NTF_SELF); + RTM_NEWNEIGH, NTF_SELF, + NLM_F_MULTI); if (err < 0) return err; skip: @@ -2374,7 +2407,7 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) struct nlattr *extfilt; u32 filter_mask = 0; - extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct rtgenmsg), + extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg), IFLA_EXT_MASK); if (extfilt) filter_mask = nla_get_u32(extfilt); @@ -2448,12 +2481,16 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags) goto errout; } + if (!skb->len) + goto errout; + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0; errout: WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - rtnl_set_sk_err(net, RTNLGRP_LINK, err); + if (err) + rtnl_set_sk_err(net, RTNLGRP_LINK, err); return err; } @@ -2622,7 +2659,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sz_idx = type>>2; kind = type&3; - if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { diff --git a/net/core/scm.c b/net/core/scm.c index 03795d0147f2..b4da80b1cc07 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -54,7 +54,7 @@ static __inline__ int scm_check_creds(struct ucred *creds) return -EINVAL; if ((creds->pid == task_tgid_vnr(current) || - ns_capable(current->nsproxy->pid_ns->user_ns, CAP_SYS_ADMIN)) && + ns_capable(task_active_pid_ns(current)->user_ns, CAP_SYS_ADMIN)) && ((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) || uid_eq(uid, cred->suid)) || nsown_capable(CAP_SETUID)) && ((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) || diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 6a2f13cee86a..d0afc322b961 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -10,12 +10,27 @@ #include <net/secure_seq.h> -static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned; +#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET) +#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4) -void net_secret_init(void) +static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned; + +static void net_secret_init(void) { - get_random_bytes(net_secret, sizeof(net_secret)); + u32 tmp; + int i; + + if (likely(net_secret[0])) + return; + + for (i = NET_SECRET_SIZE; i > 0;) { + do { + get_random_bytes(&tmp, sizeof(tmp)); + } while (!tmp); + cmpxchg(&net_secret[--i], 0, tmp); + } } +#endif #ifdef CONFIG_INET static u32 seq_scale(u32 seq) @@ -42,6 +57,7 @@ __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, u32 hash[MD5_DIGEST_WORDS]; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + (__force u32)daddr[i]; @@ -63,6 +79,7 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, u32 hash[MD5_DIGEST_WORDS]; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + (__force u32) daddr[i]; @@ -78,35 +95,13 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -__u32 secure_ip_id(__be32 daddr) -{ - u32 hash[MD5_DIGEST_WORDS]; - - hash[0] = (__force __u32) daddr; - hash[1] = net_secret[13]; - hash[2] = net_secret[14]; - hash[3] = net_secret[15]; - - md5_transform(hash, net_secret); - - return hash[0]; -} - -__u32 secure_ipv6_id(const __be32 daddr[4]) -{ - __u32 hash[4]; - - memcpy(hash, daddr, 16); - md5_transform(hash, net_secret); - - return hash[0]; -} __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport) { u32 hash[MD5_DIGEST_WORDS]; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = ((__force u16)sport << 16) + (__force u16)dport; @@ -121,6 +116,7 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { u32 hash[MD5_DIGEST_WORDS]; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = (__force u32)dport ^ net_secret[14]; @@ -140,6 +136,7 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, u32 hash[MD5_DIGEST_WORDS]; u64 seq; + net_secret_init(); hash[0] = (__force u32)saddr; hash[1] = (__force u32)daddr; hash[2] = ((__force u16)sport << 16) + (__force u16)dport; @@ -164,6 +161,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, u64 seq; u32 i; + net_secret_init(); memcpy(hash, saddr, 16); for (i = 0; i < 4; i++) secret[i] = net_secret[i] + daddr[i]; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1c1738cc4538..6148716884ae 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -47,6 +47,8 @@ #include <linux/in.h> #include <linux/inet.h> #include <linux/slab.h> +#include <linux/tcp.h> +#include <linux/udp.h> #include <linux/netdevice.h> #ifdef CONFIG_NET_CLS_ACT #include <net/pkt_sched.h> @@ -74,36 +76,6 @@ struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; -static void sock_pipe_buf_release(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) -{ - put_page(buf->page); -} - -static void sock_pipe_buf_get(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) -{ - get_page(buf->page); -} - -static int sock_pipe_buf_steal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) -{ - return 1; -} - - -/* Pipe buffer operations for a socket. */ -static const struct pipe_buf_operations sock_pipe_buf_ops = { - .can_merge = 0, - .map = generic_pipe_buf_map, - .unmap = generic_pipe_buf_unmap, - .confirm = generic_pipe_buf_confirm, - .release = sock_pipe_buf_release, - .steal = sock_pipe_buf_steal, - .get = sock_pipe_buf_get, -}; - /** * skb_panic - private function for out-of-line support * @skb: buffer @@ -585,9 +557,6 @@ static void skb_release_head_state(struct sk_buff *skb) #if IS_ENABLED(CONFIG_NF_CONNTRACK) nf_conntrack_put(skb->nfct); #endif -#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED - nf_conntrack_put_reasm(skb->nfct_reasm); -#endif #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(skb->nf_bridge); #endif @@ -1814,7 +1783,7 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, .partial = partial, .nr_pages_max = MAX_SKB_FRAGS, .flags = flags, - .ops = &sock_pipe_buf_ops, + .ops = &nosteal_pipe_buf_ops, .spd_release = sock_spd_release, }; struct sk_buff *frag_iter; @@ -2841,7 +2810,6 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) tail = nskb; __copy_skb_header(nskb, skb); - nskb->mac_len = skb->mac_len; /* nskb and skb might have different headroom */ if (nskb->ip_summed == CHECKSUM_PARTIAL) @@ -2851,13 +2819,14 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_set_network_header(nskb, skb->mac_len); nskb->transport_header = (nskb->network_header + skb_network_header_len(skb)); + skb_reset_mac_len(nskb); skb_copy_from_linear_data_offset(skb, -tnl_hlen, nskb->data - tnl_hlen, doffset + tnl_hlen); if (fskb != skb_shinfo(skb)->frag_list) - continue; + goto perform_csum_check; if (!sg) { nskb->ip_summed = CHECKSUM_NONE; @@ -2875,6 +2844,8 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; while (pos < offset + len && i < nfrags) { + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + goto err; *frag = skb_shinfo(skb)->frags[i]; __skb_frag_ref(frag); size = skb_frag_size(frag); @@ -2921,6 +2892,7 @@ skip_fraglist: nskb->len += nskb->data_len; nskb->truesize += nskb->data_len; +perform_csum_check: if (!csum) { nskb->csum = skb_checksum(nskb, doffset, nskb->len - doffset, 0); @@ -3503,3 +3475,28 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, return true; } EXPORT_SYMBOL(skb_try_coalesce); + +/** + * skb_gso_transport_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_transport_seglen is used to determine the real size of the + * individual segments, including Layer4 headers (TCP/UDP). + * + * The MAC/L2 or network (IP, IPv6) headers are not accounted for. + */ +unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + return tcp_hdrlen(skb) + shinfo->gso_size; + + /* UFO sets gso_size to the size of the fragmentation + * payload, i.e. the size of the L4 (UDP) header is already + * accounted for. + */ + return shinfo->gso_size; +} +EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); diff --git a/net/core/sock.c b/net/core/sock.c index d6d024cfaaaf..af65d17517b8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -142,6 +142,55 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); +/** + * sk_ns_capable - General socket capability test + * @sk: Socket to use a capability on or through + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in the user + * namespace @user_ns. + */ +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap) +{ + return file_ns_capable(sk->sk_socket->file, user_ns, cap) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(sk_ns_capable); + +/** + * sk_capable - Socket global capability test + * @sk: Socket to use a capability on or through + * @cap: The global capbility to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in all user + * namespaces. + */ +bool sk_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, &init_user_ns, cap); +} +EXPORT_SYMBOL(sk_capable); + +/** + * sk_net_capable - Network namespace socket capability test + * @sk: Socket to use a capability on or through + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socke was created + * and the current process has the capability @cap over the network namespace + * the socket is a member of. + */ +bool sk_net_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); +} +EXPORT_SYMBOL(sk_net_capable); + + #ifdef CONFIG_MEMCG_KMEM int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { @@ -885,7 +934,7 @@ set_rcvbuf: case SO_PEEK_OFF: if (sock->ops->set_peek_off) - sock->ops->set_peek_off(sk, val); + ret = sock->ops->set_peek_off(sk, val); else ret = -EOPNOTSUPP; break; @@ -1814,7 +1863,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) gfp_t gfp = sk->sk_allocation; if (order) - gfp |= __GFP_COMP | __GFP_NOWARN; + gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; pfrag->page = alloc_pages(gfp, order); if (likely(pfrag->page)) { pfrag->offset = 0; @@ -2271,6 +2320,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_stamp = ktime_set(-1L, 0); + sk->sk_pacing_rate = ~0U; /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) @@ -2308,10 +2358,13 @@ void release_sock(struct sock *sk) if (sk->sk_backlog.tail) __release_sock(sk); + /* Warning : release_cb() might need to release sk ownership, + * ie call sock_release_ownership(sk) before us. + */ if (sk->sk_prot->release_cb) sk->sk_prot->release_cb(sk); - sk->sk_lock.owned = 0; + sock_release_ownership(sk); if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); spin_unlock_bh(&sk->sk_lock.slock); diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index a0e9cf6379de..c38e7a2b5a8e 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); -int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct nlattr *attr; @@ -57,7 +57,7 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, unsigned int len; int err = 0; - if (!ns_capable(user_ns, CAP_NET_ADMIN)) { + if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index cfdb46ab3a7f..0a327b66a344 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -20,7 +20,11 @@ #include <net/sock.h> #include <net/net_ratelimit.h> +static int zero = 0; static int one = 1; +static int ushort_max = USHRT_MAX; +static int min_sndbuf = SOCK_MIN_SNDBUF; +static int min_rcvbuf = SOCK_MIN_RCVBUF; #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(ctl_table *table, int write, @@ -95,7 +99,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_max", @@ -103,7 +107,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "wmem_default", @@ -111,7 +115,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_default", @@ -119,7 +123,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "dev_weight", @@ -204,7 +208,9 @@ static struct ctl_table netns_core_table[] = { .data = &init_net.core.sysctl_somaxconn, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .extra1 = &zero, + .extra2 = &ushort_max, + .proc_handler = proc_dointvec_minmax }, { } }; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 40d5829ed36a..1074ffb6d533 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1670,7 +1670,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlmsghdr *reply_nlh = NULL; const struct reply_func *fn; - if ((nlh->nlmsg_type == RTM_SETDCB) && !capable(CAP_NET_ADMIN)) + if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9c61f9c02fdb..6cf9f7782ad4 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -135,6 +135,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (dst) dst->ops->redirect(dst, sk, skb); + goto out; } if (type == ICMPV6_PKT_TOOBIG) { diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 7d9197063ebb..b5e52100a89a 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -573,7 +573,7 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) struct dn_ifaddr __rcu **ifap; int err = -EINVAL; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) @@ -617,7 +617,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) struct dn_ifaddr *ifa; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 57dc159245ec..d332aefb0846 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -505,7 +505,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *attrs[RTA_MAX+1]; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) @@ -530,7 +530,7 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *attrs[RTA_MAX+1]; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index 2a7efe388344..f3dc69a41d63 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -107,7 +107,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb) if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) return; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) RCV_SKB_FAIL(-EPERM); /* Eventually we might send routing messages too */ diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c index c32be292c7e3..2022b46ab38f 100644 --- a/net/dns_resolver/dns_query.c +++ b/net/dns_resolver/dns_query.c @@ -150,7 +150,9 @@ int dns_query(const char *type, const char *name, size_t namelen, if (!*_result) goto put; - memcpy(*_result, upayload->data, len + 1); + memcpy(*_result, upayload->data, len); + (*_result)[len] = '\0'; + if (_expiry) *_expiry = rkey->expiry; diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index 55e1fd5b3e56..ca118e8cb141 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -862,7 +862,7 @@ lowpan_process_data(struct sk_buff *skb) * Traffic class carried in-line * ECN + DSCP (1 byte), Flow Label is elided */ - case 1: /* 10b */ + case 2: /* 10b */ if (lowpan_fetch_skb_u8(skb, &tmp)) goto drop; @@ -875,7 +875,7 @@ lowpan_process_data(struct sk_buff *skb) * Flow Label carried in-line * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided */ - case 2: /* 01b */ + case 1: /* 01b */ if (lowpan_fetch_skb_u8(skb, &tmp)) goto drop; @@ -1173,7 +1173,27 @@ static struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; +static struct lock_class_key lowpan_tx_busylock; +static struct lock_class_key lowpan_netdev_xmit_lock_key; + +static void lowpan_set_lockdep_class_one(struct net_device *dev, + struct netdev_queue *txq, + void *_unused) +{ + lockdep_set_class(&txq->_xmit_lock, + &lowpan_netdev_xmit_lock_key); +} + + +static int lowpan_dev_init(struct net_device *dev) +{ + netdev_for_each_tx_queue(dev, lowpan_set_lockdep_class_one, NULL); + dev->qdisc_tx_busylock = &lowpan_tx_busylock; + return 0; +} + static const struct net_device_ops lowpan_netdev_ops = { + .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_set_mac_address = lowpan_set_address, }; diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 581a59504bd5..1865fdf5a5a5 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -315,9 +315,8 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk, if (saddr) { saddr->family = AF_IEEE802154; saddr->addr = mac_cb(skb)->sa; - } - if (addr_len) *addr_len = sizeof(*saddr); + } if (flags & MSG_TRUNC) copied = skb->len; diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index 22b1a7058fd3..4efd2375d7e1 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -224,8 +224,10 @@ static int ieee802154_add_iface(struct sk_buff *skb, if (info->attrs[IEEE802154_ATTR_DEV_TYPE]) { type = nla_get_u8(info->attrs[IEEE802154_ATTR_DEV_TYPE]); - if (type >= __IEEE802154_DEV_MAX) - return -EINVAL; + if (type >= __IEEE802154_DEV_MAX) { + rc = -EINVAL; + goto nla_put_failure; + } } dev = phy->add_iface(phy, devname, type); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index d01be2a3ae53..c4adc319cc2e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -263,10 +263,8 @@ void build_ehash_secret(void) get_random_bytes(&rnd, sizeof(rnd)); } while (rnd == 0); - if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) { + if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); - net_secret_init(); - } } EXPORT_SYMBOL(build_ehash_secret); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index b28e863fe0a7..5f3dc1df04bf 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -57,7 +57,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) - IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); goto out; } @@ -86,18 +86,26 @@ out: } EXPORT_SYMBOL(ip4_datagram_connect); +/* Because UDP xmit path can manipulate sk_dst_cache without holding + * socket lock, we need to use sk_dst_set() here, + * even if we own the socket lock. + */ void ip4_datagram_release_cb(struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; + struct dst_entry *dst; struct flowi4 fl4; struct rtable *rt; - if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0)) - return; - rcu_read_lock(); + + dst = __sk_dst_get(sk); + if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) { + rcu_read_unlock(); + return; + } inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; @@ -105,8 +113,10 @@ void ip4_datagram_release_cb(struct sock *sk) inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); - if (!IS_ERR(rt)) - __sk_dst_set(sk, &rt->dst); + + dst = !IS_ERR(rt) ? &rt->dst : NULL; + sk_dst_set(sk, dst); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ip4_datagram_release_cb); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index dfc39d4d48b7..e40eef4ac697 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -771,7 +771,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, ci = nla_data(tb[IFA_CACHEINFO]); if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { err = -EINVAL; - goto errout; + goto errout_free; } *pvalid_lft = ci->ifa_valid; *pprefered_lft = ci->ifa_prefered; @@ -779,6 +779,8 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, return ifa; +errout_free: + inet_free_ifa(ifa); errout: return ERR_PTR(err); } @@ -1431,7 +1433,8 @@ static size_t inet_nlmsg_size(void) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ - + nla_total_size(IFNAMSIZ); /* IFA_LABEL */ + + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } static inline u32 cstamp_delta(unsigned long cstamp) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c7629a209f9d..4556cd25acde 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1049,6 +1049,8 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo } in_dev = __in_dev_get_rtnl(dev); + if (!in_dev) + return NOTIFY_DONE; switch (event) { case NETDEV_UP: diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 26aa65d1fce4..c5c8b248d8f6 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -62,6 +62,10 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res) else res->tclassid = 0; #endif + + if (err == -ESRCH) + err = -ENETUNREACH; + return err; } EXPORT_SYMBOL_GPL(__fib_lookup); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 8f6cb7a87cd6..bc773a10dca6 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -533,7 +533,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) return 1; attrlen = rtnh_attrlen(rtnh); - if (attrlen < 0) { + if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); @@ -818,13 +818,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); if (fi == NULL) goto failure; + fib_info_cnt++; if (cfg->fc_mx) { fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); if (!fi->fib_metrics) goto failure; } else fi->fib_metrics = (u32 *) dst_default_metrics; - fib_info_cnt++; fi->fib_net = hold_net(net); fi->fib_protocol = cfg->fc_protocol; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 49616fed9340..6e8a13da6cbd 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -71,7 +71,6 @@ #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> -#include <linux/prefetch.h> #include <linux/export.h> #include <net/net_namespace.h> #include <net/ip.h> @@ -1761,10 +1760,8 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct rt_trie_node *c) if (!c) continue; - if (IS_LEAF(c)) { - prefetch(rcu_dereference_rtnl(p->child[idx])); + if (IS_LEAF(c)) return (struct leaf *) c; - } /* Rescan start scanning in new node */ p = (struct tnode *) c; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 76e10b47e053..ea78ef5ac352 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -697,8 +697,6 @@ static void icmp_unreach(struct sk_buff *skb) &iph->daddr); } else { info = ntohs(icmph->un.frag.mtu); - if (!info) - goto out; } break; case ICMP_SR_FAILED: diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d8c232794bcb..155adf8729c2 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -343,7 +343,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(pip, &rt->dst, NULL); + ip_select_ident(skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -687,7 +687,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; @@ -709,7 +709,7 @@ static void igmp_gq_timer_expire(unsigned long data) in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); - __in_dev_put(in_dev); + in_dev_put(in_dev); } static void igmp_ifc_timer_expire(unsigned long data) @@ -721,7 +721,7 @@ static void igmp_ifc_timer_expire(unsigned long data) in_dev->mr_ifc_count--; igmp_ifc_start_timer(in_dev, IGMP_Unsolicited_Report_Interval); } - __in_dev_put(in_dev); + in_dev_put(in_dev); } static void igmp_ifc_event(struct in_device *in_dev) @@ -1874,6 +1874,10 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) rtnl_lock(); in_dev = ip_mc_find_dev(net, imr); + if (!in_dev) { + ret = -ENODEV; + goto out; + } ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = rtnl_dereference(*imlp)) != NULL; @@ -1891,16 +1895,14 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) *imlp = iml->next_rcu; - if (in_dev) - ip_mc_dec_group(in_dev, group); + ip_mc_dec_group(in_dev, group); rtnl_unlock(); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); return 0; } - if (!in_dev) - ret = -ENODEV; +out: rtnl_unlock(); return ret; } diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 5f648751fce2..14a1ed611b05 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -71,6 +71,20 @@ static inline void inet_diag_unlock_handler( mutex_unlock(&inet_diag_table_mutex); } +static size_t inet_sk_attr_size(void) +{ + return nla_total_size(sizeof(struct tcp_info)) + + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ + + nla_total_size(1) /* INET_DIAG_TOS */ + + nla_total_size(1) /* INET_DIAG_TCLASS */ + + nla_total_size(sizeof(struct inet_diag_meminfo)) + + nla_total_size(sizeof(struct inet_diag_msg)) + + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + + nla_total_size(TCP_CA_NAME_MAX) + + nla_total_size(sizeof(struct tcpvegas_info)) + + 64; +} + int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, struct inet_diag_req_v2 *req, struct user_namespace *user_ns, @@ -106,6 +120,10 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->id.idiag_sport = inet->inet_sport; r->id.idiag_dport = inet->inet_dport; + + memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); + memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); + r->id.idiag_src[0] = inet->inet_rcv_saddr; r->id.idiag_dst[0] = inet->inet_daddr; @@ -240,12 +258,19 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, r->idiag_family = tw->tw_family; r->idiag_retrans = 0; + r->id.idiag_if = tw->tw_bound_dev_if; sock_diag_save_cookie(tw, r->id.idiag_cookie); + r->id.idiag_sport = tw->tw_sport; r->id.idiag_dport = tw->tw_dport; + + memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); + memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); + r->id.idiag_src[0] = tw->tw_rcv_saddr; r->id.idiag_dst[0] = tw->tw_daddr; + r->idiag_state = tw->tw_substate; r->idiag_timer = 3; r->idiag_expires = DIV_ROUND_UP(tmo * 1000, HZ); @@ -315,9 +340,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s if (err) goto out; - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + - sizeof(struct tcp_info) + 64, GFP_KERNEL); + rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL); if (!rep) { err = -ENOMEM; goto out; @@ -732,8 +755,13 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->id.idiag_sport = inet->inet_sport; r->id.idiag_dport = ireq->rmt_port; + + memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); + memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); + r->id.idiag_src[0] = ireq->loc_addr; r->id.idiag_dst[0] = ireq->rmt_addr; + r->idiag_expires = jiffies_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; @@ -945,7 +973,7 @@ next_normal: ++num; } - if (r->idiag_states & TCPF_TIME_WAIT) { + if (r->idiag_states & (TCPF_TIME_WAIT | TCPF_FIN_WAIT2)) { struct inet_timewait_sock *tw; inet_twsk_for_each(tw, node, @@ -955,6 +983,8 @@ next_normal: if (num < s_num) goto next_dying; + if (!(r->idiag_states & (1 << tw->tw_substate))) + goto next_dying; if (r->sdiag_family != AF_UNSPEC && tw->tw_family != r->sdiag_family) goto next_dying; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 7e06641e36ae..af02a39175e3 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -211,7 +211,7 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force) } work = frag_mem_limit(nf) - nf->low_thresh; - while (work > 0) { + while (work > 0 || force) { spin_lock(&nf->lru_lock); if (list_empty(&nf->lru_list)) { @@ -283,9 +283,10 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, atomic_inc(&qp->refcnt); hlist_add_head(&qp->list, &hb->chain); + inet_frag_lru_add(nf, qp); spin_unlock(&hb->chain_lock); read_unlock(&f->lock); - inet_frag_lru_add(nf, qp); + return qp; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 6af375afeeef..c95848d00039 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -287,7 +287,7 @@ begintw: if (unlikely(!INET_TW_MATCH(sk, net, acookie, saddr, daddr, ports, dif))) { - sock_put(sk); + inet_twsk_put(inet_twsk(sk)); goto begintw; } goto out; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 000e3d239d64..67140efc15fd 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -26,20 +26,7 @@ * Theory of operations. * We keep one entry for each peer IP address. The nodes contains long-living * information about the peer which doesn't depend on routes. - * At this moment this information consists only of ID field for the next - * outgoing IP packet. This field is incremented with each packet as encoded - * in inet_getid() function (include/net/inetpeer.h). - * At the moment of writing this notes identifier of IP packets is generated - * to be unpredictable using this code only for packets subjected - * (actually or potentially) to defragmentation. I.e. DF packets less than - * PMTU in size uses a constant ID and do not use this code (see - * ip_select_ident() in include/net/ip.h). * - * Route cache entries hold references to our nodes. - * New cache entries get references via lookup by destination IP address in - * the avl tree. The reference is grabbed only when it's needed i.e. only - * when we try to output IP packet which needs an unpredictable ID (see - * __ip_select_ident() in net/ipv4/route.c). * Nodes are removed only when reference counter goes to 0. * When it's happened the node may be removed when a sufficient amount of * time has been passed since its last use. The less-recently-used entry can @@ -62,7 +49,6 @@ * refcnt: atomically against modifications on other CPU; * usually under some other lock to prevent node disappearing * daddr: unchangeable - * ip_id_count: atomic value (no lock needed) */ static struct kmem_cache *peer_cachep __read_mostly; @@ -504,10 +490,6 @@ relookup: p->daddr = *daddr; atomic_set(&p->refcnt, 1); atomic_set(&p->rid, 0); - atomic_set(&p->ip_id_count, - (daddr->family == AF_INET) ? - secure_ip_id(daddr->addr.a4) : - secure_ipv6_id(daddr->addr.a6)); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; /* 60*HZ is arbitrary, but chosen enough high so that the first diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 694de3b7aebf..479e8a63125a 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -39,6 +39,71 @@ #include <net/route.h> #include <net/xfrm.h> +static bool ip_may_fragment(const struct sk_buff *skb) +{ + return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) || + skb->local_df; +} + +static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu) + return false; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + +static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb) +{ + unsigned int mtu; + + if (skb->local_df || !skb_is_gso(skb)) + return false; + + mtu = dst_mtu(skb_dst(skb)); + + /* if seglen > mtu, do software segmentation for IP fragmentation on + * output. DF bit cannot be set since ip_forward would have sent + * icmp error. + */ + return skb_gso_network_seglen(skb) > mtu; +} + +/* called if GSO skb needs to be fragmented on forward */ +static int ip_forward_finish_gso(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + netdev_features_t features; + struct sk_buff *segs; + int ret = 0; + + features = netif_skb_dev_features(skb, dst->dev); + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR(segs)) { + kfree_skb(skb); + return -ENOMEM; + } + + consume_skb(skb); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = dst_output(segs); + + if (err && ret == 0) + ret = err; + segs = nskb; + } while (segs); + + return ret; +} + static int ip_forward_finish(struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); @@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb) if (unlikely(opt->optlen)) ip_forward_options(skb); + if (ip_gso_exceeds_dst_mtu(skb)) + return ip_forward_finish_gso(skb); + return dst_output(skb); } @@ -58,6 +126,9 @@ int ip_forward(struct sk_buff *skb) struct rtable *rt; /* Route we use */ struct ip_options *opt = &(IPCB(skb)->opt); + if (unlikely(skb->sk)) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -88,8 +159,7 @@ int ip_forward(struct sk_buff *skb) if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; - if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && - (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { + if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, dst_mtu(&rt->dst))) { IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(dst_mtu(&rt->dst))); @@ -108,7 +178,8 @@ int ip_forward(struct sk_buff *skb) * We now generate an ICMP HOST REDIRECT giving the route * we calculated. */ - if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb)) + if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr && + !skb_sec_path(skb)) ip_rt_send_redirect(skb); skb->priority = rt_tos2priority(iph->tos); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b66910aaef4d..4c1884fed548 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -678,27 +678,30 @@ EXPORT_SYMBOL(ip_defrag); struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) { struct iphdr iph; + int netoff; u32 len; if (skb->protocol != htons(ETH_P_IP)) return skb; - if (!skb_copy_bits(skb, 0, &iph, sizeof(iph))) + netoff = skb_network_offset(skb); + + if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0) return skb; if (iph.ihl < 5 || iph.version != 4) return skb; len = ntohs(iph.tot_len); - if (skb->len < len || len < (iph.ihl * 4)) + if (skb->len < netoff + len || len < (iph.ihl * 4)) return skb; if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { - if (!pskb_may_pull(skb, iph.ihl*4)) + if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) return skb; - if (pskb_trim_rcsum(skb, len)) + if (pskb_trim_rcsum(skb, netoff + len)) return skb; memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(skb, user)) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 2a83591492dd..fae5a8459538 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -335,7 +335,8 @@ static int ipgre_rcv(struct sk_buff *skb) iph->saddr, iph->daddr, tpi.key); if (tunnel) { - ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); + skb_pop_mac_header(skb); + ip_tunnel_rcv(tunnel, skb, &tpi, hdr_len, log_ecn_error); return 0; } icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); @@ -503,10 +504,11 @@ static int ipgre_tunnel_ioctl(struct net_device *dev, if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) return -EFAULT; - if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE || - p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) || - ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING))) { - return -EINVAL; + if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { + if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE || + p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) || + ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING))) + return -EINVAL; } p.i_flags = gre_flags_to_tnl_flags(p.i_flags); p.o_flags = gre_flags_to_tnl_flags(p.o_flags); @@ -571,7 +573,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, if (daddr) memcpy(&iph->daddr, daddr, 4); if (iph->daddr) - return t->hlen; + return t->hlen + sizeof(*iph); return -(t->hlen + sizeof(*iph)); } @@ -650,6 +652,7 @@ static const struct net_device_ops ipgre_netdev_ops = { static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; + dev->type = ARPHRD_IPGRE; ip_tunnel_setup(dev, ipgre_net_id); } @@ -688,7 +691,6 @@ static int ipgre_tunnel_init(struct net_device *dev) memcpy(dev->dev_addr, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); - dev->type = ARPHRD_IPGRE; dev->flags = IFF_NOARP; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->addr_len = 4; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 3da817b89e9b..0a22bb0ce1a8 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -190,10 +190,7 @@ static int ip_local_deliver_finish(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); - __skb_pull(skb, ip_hdrlen(skb)); - - /* Point into the IP datagram, just past the header. */ - skb_reset_transport_header(skb); + __skb_pull(skb, skb_network_header_len(skb)); rcu_read_lock(); { @@ -316,7 +313,7 @@ static int ip_rcv_finish(struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; - if (sysctl_ip_early_demux && !skb_dst(skb)) { + if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { const struct net_protocol *ipprot; int protocol = iph->protocol; @@ -437,6 +434,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, goto drop; } + skb->transport_header = skb->network_header + iph->ihl*4; + /* Remove any debris in the socket control block */ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ec7264514a82..089ed81d1878 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -288,6 +288,10 @@ int ip_options_compile(struct net *net, optptr++; continue; } + if (unlikely(l < 2)) { + pp_ptr = optptr; + goto error; + } optlen = optptr[1]; if (optlen<2 || optlen>l) { pp_ptr = optptr; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 4bcabf3ab4ca..57e745086302 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(iph, &rt->dst, sk); + ip_select_ident(skb, sk); if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -394,8 +394,7 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_more(iph, &rt->dst, sk, - (skb_shinfo(skb)->gso_segs ?: 1) - 1); + ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -844,9 +843,10 @@ static int __ip_append_data(struct sock *sk, csummode = CHECKSUM_PARTIAL; cork->length += length; - if (((length > mtu) || (skb && skb_is_gso(skb))) && + if (((length > mtu) || (skb && skb_has_frags(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) { + (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && + (sk->sk_type == SOCK_DGRAM)) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, maxfraglen, flags); @@ -1324,7 +1324,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, else ttl = ip_select_ttl(inet, &rt->dst); - iph = (struct iphdr *)skb->data; + iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = inet->tos; @@ -1332,7 +1332,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); - ip_select_ident(iph, &rt->dst, sk); + ip_select_ident(skb, sk); if (opt) { iph->ihl += opt->optlen>>2; @@ -1455,23 +1455,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, /* * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. - * - * Use a fake percpu inet socket to avoid false sharing and contention. */ -static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = { - .sk = { - .__sk_common = { - .skc_refcnt = ATOMIC_INIT(1), - }, - .sk_wmem_alloc = ATOMIC_INIT(1), - .sk_allocation = GFP_ATOMIC, - .sk_flags = (1UL << SOCK_USE_WRITE_QUEUE), - }, - .pmtudisc = IP_PMTUDISC_WANT, - .uc_ttl = -1, -}; - -void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, +void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len) { @@ -1479,9 +1464,9 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); + struct net *net = sock_net(sk); struct sk_buff *nskb; - struct sock *sk; - struct inet_sock *inet; + int err; if (ip_options_echo(&replyopts.opt.opt, skb)) return; @@ -1508,18 +1493,19 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, if (IS_ERR(rt)) return; - inet = &get_cpu_var(unicast_sock); + inet_sk(sk)->tos = arg->tos; - inet->tos = arg->tos; - sk = &inet->sk; sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; - sock_net_set(sk, net); - __skb_queue_head_init(&sk->sk_write_queue); sk->sk_sndbuf = sysctl_wmem_default; - ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, - &ipc, &rt, MSG_DONTWAIT); + err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, + len, 0, &ipc, &rt, MSG_DONTWAIT); + if (unlikely(err)) { + ip_flush_pending_frames(sk); + goto out; + } + nskb = skb_peek(&sk->sk_write_queue); if (nskb) { if (arg->csumoffset >= 0) @@ -1527,13 +1513,10 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; - skb_orphan(nskb); skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb)); ip_push_pending_frames(sk, &fl4); } - - put_cpu_var(unicast_sock); - +out: ip_rt_put(rt); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index d9c4f113d709..f6603142cb33 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -368,7 +368,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf /* * Handle MSG_ERRQUEUE */ -int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct sock_exterr_skb *serr; struct sk_buff *skb, *skb2; @@ -405,19 +405,16 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) serr->addr_offset); sin->sin_port = serr->port; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; - sin->sin_family = AF_UNSPEC; + memset(sin, 0, sizeof(*sin)); if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { - struct inet_sock *inet = inet_sk(sk); - sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; - sin->sin_port = 0; - memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); - if (inet->cmsg_flags) + if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 7fa8f08fa7ae..84aa69caee59 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -166,6 +166,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, hlist_for_each_entry_rcu(t, head, hash_node) { if (remote != t->parms.iph.daddr || + t->parms.iph.saddr != 0 || !(t->dev->flags & IFF_UP)) continue; @@ -182,10 +183,11 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { - if ((local != t->parms.iph.saddr && - (local != t->parms.iph.daddr || - !ipv4_is_multicast(local))) || - !(t->dev->flags & IFF_UP)) + if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) && + (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) + continue; + + if (!(t->dev->flags & IFF_UP)) continue; if (!ip_tunnel_key_match(&t->parms, flags, key)) @@ -202,6 +204,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, hlist_for_each_entry_rcu(t, head, hash_node) { if (t->parms.i_key != key || + t->parms.iph.saddr != 0 || + t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) continue; @@ -402,7 +406,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, } int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, - const struct tnl_ptk_info *tpi, bool log_ecn_error) + const struct tnl_ptk_info *tpi, int hdr_len, bool log_ecn_error) { struct pcpu_tstats *tstats; const struct iphdr *iph = ip_hdr(skb); @@ -413,7 +417,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, skb->protocol = tpi->proto; skb->mac_header = skb->network_header; - __pskb_pull(skb, tunnel->hlen); + __pskb_pull(skb, hdr_len); skb_postpull_rcsum(skb, skb_transport_header(skb), tunnel->hlen); #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { @@ -486,6 +490,53 @@ drop: } EXPORT_SYMBOL_GPL(ip_tunnel_rcv); +static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, + struct rtable *rt, __be16 df) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len; + int mtu; + + if (df) + mtu = dst_mtu(&rt->dst) - dev->hard_header_len + - sizeof(struct iphdr) - tunnel->hlen; + else + mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + + if (skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); + + if (skb->protocol == htons(ETH_P_IP)) { + if (!skb_is_gso(skb) && + (df & htons(IP_DF)) && mtu < pkt_size) { + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); + return -E2BIG; + } + } +#if IS_ENABLED(CONFIG_IPV6) + else if (skb->protocol == htons(ETH_P_IPV6)) { + struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); + + if (rt6 && mtu < dst_mtu(skb_dst(skb)) && + mtu >= IPV6_MIN_MTU) { + if ((tunnel->parms.iph.daddr && + !ipv4_is_multicast(tunnel->parms.iph.daddr)) || + rt6->rt6i_dst.plen == 128) { + rt6->rt6i_flags |= RTF_MODIFIED; + dst_metric_set(skb_dst(skb), RTAX_MTU, mtu); + } + } + + if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU && + mtu < pkt_size) { + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + return -E2BIG; + } + } +#endif + return 0; +} + void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params) { @@ -499,7 +550,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, struct net_device *tdev; /* Device to other host */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst; - int mtu; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); @@ -579,56 +629,18 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } - df = tnl_params->frag_off; - - if (df) - mtu = dst_mtu(&rt->dst) - dev->hard_header_len - - sizeof(struct iphdr); - else - mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; - - if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); - - if (skb->protocol == htons(ETH_P_IP)) { - df |= (inner_iph->frag_off&htons(IP_DF)); - - if (!skb_is_gso(skb) && - (inner_iph->frag_off&htons(IP_DF)) && - mtu < ntohs(inner_iph->tot_len)) { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); - ip_rt_put(rt); - goto tx_error; - } - } -#if IS_ENABLED(CONFIG_IPV6) - else if (skb->protocol == htons(ETH_P_IPV6)) { - struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); - - if (rt6 && mtu < dst_mtu(skb_dst(skb)) && - mtu >= IPV6_MIN_MTU) { - if ((tunnel->parms.iph.daddr && - !ipv4_is_multicast(tunnel->parms.iph.daddr)) || - rt6->rt6i_dst.plen == 128) { - rt6->rt6i_flags |= RTF_MODIFIED; - dst_metric_set(skb_dst(skb), RTAX_MTU, mtu); - } - } - if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU && - mtu < skb->len) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); - ip_rt_put(rt); - goto tx_error; - } + if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) { + ip_rt_put(rt); + goto tx_error; } -#endif if (tunnel->err_count > 0) { if (time_before(jiffies, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); dst_link_failure(skb); } else tunnel->err_count = 0; @@ -646,15 +658,19 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ttl = ip4_dst_hoplimit(&rt->dst); } + df = tnl_params->frag_off; + if (skb->protocol == htons(ETH_P_IP)) + df |= (inner_iph->frag_off&htons(IP_DF)); + max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr) + rt->dst.header_len; - if (max_headroom > dev->needed_headroom) { + if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; - if (skb_cow_head(skb, dev->needed_headroom)) { - dev->stats.tx_dropped++; - dev_kfree_skb(skb); - return; - } + + if (skb_cow_head(skb, dev->needed_headroom)) { + dev->stats.tx_dropped++; + dev_kfree_skb(skb); + return; } skb_dst_drop(skb); @@ -675,7 +691,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, iph->daddr = fl4.daddr; iph->saddr = fl4.saddr; iph->ttl = ttl; - tunnel_ip_select_ident(skb, inner_iph, &rt->dst); + __ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1); iptunnel_xmit(skb, dev); return; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index c118f6b576bb..4ec34275160b 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -285,8 +285,17 @@ static int vti_rcv(struct sk_buff *skb) tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr); if (tunnel != NULL) { struct pcpu_tstats *tstats; + u32 oldmark = skb->mark; + int ret; - if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + + /* temporarily mark the skb with the tunnel o_key, to + * only match policies with this mark. + */ + skb->mark = be32_to_cpu(tunnel->parms.o_key); + ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb); + skb->mark = oldmark; + if (!ret) return -1; tstats = this_cpu_ptr(tunnel->dev->tstats); @@ -295,7 +304,6 @@ static int vti_rcv(struct sk_buff *skb) tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); - skb->mark = 0; secpath_reset(skb); skb->dev = tunnel->dev; return 1; @@ -327,7 +335,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&fl4, 0, sizeof(fl4)); flowi4_init_output(&fl4, tunnel->parms.link, - be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos), + be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPIP, 0, dst, tiph->saddr, 0, 0); @@ -342,6 +350,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (!rt->dst.xfrm || rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) { dev->stats.tx_carrier_errors++; + ip_rt_put(rt); goto tx_error_icmp; } tdev = rt->dst.dev; @@ -570,9 +579,9 @@ static void vti_dev_free(struct net_device *dev) static void vti_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &vti_netdev_ops; + dev->type = ARPHRD_TUNNEL; dev->destructor = vti_dev_free; - dev->type = ARPHRD_TUNNEL; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); dev->mtu = ETH_DATA_LEN; dev->flags = IFF_NOARP; @@ -606,17 +615,10 @@ static int __net_init vti_fb_tunnel_init(struct net_device *dev) struct iphdr *iph = &tunnel->parms.iph; struct vti_net *ipn = net_generic(dev_net(dev), vti_net_id); - tunnel->dev = dev; - strcpy(tunnel->parms.name, dev->name); - iph->version = 4; iph->protocol = IPPROTO_IPIP; iph->ihl = 5; - dev->tstats = alloc_percpu(struct pcpu_tstats); - if (!dev->tstats) - return -ENOMEM; - dev_hold(dev); rcu_assign_pointer(ipn->tunnels_wc[0], tunnel); return 0; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 77bfcce64fe5..897b784e9c05 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -149,13 +149,13 @@ static int ipip_err(struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, - t->dev->ifindex, 0, IPPROTO_IPIP, 0); + t->parms.link, 0, IPPROTO_IPIP, 0); err = 0; goto out; } if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, IPPROTO_IPIP, 0); err = 0; goto out; @@ -195,7 +195,7 @@ static int ipip_rcv(struct sk_buff *skb) if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; - return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); + return ip_tunnel_rcv(tunnel, skb, &tpi, 0, log_ecn_error); } return -1; @@ -240,11 +240,13 @@ ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) return -EFAULT; - if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP || - p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF))) - return -EINVAL; - if (p.i_key || p.o_key || p.i_flags || p.o_flags) - return -EINVAL; + if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { + if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP || + p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF))) + return -EINVAL; + } + + p.i_key = p.o_key = p.i_flags = p.o_flags = 0; if (p.iph.ttl) p.iph.frag_off |= htons(IP_DF); @@ -481,4 +483,5 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ipip"); MODULE_ALIAS_NETDEV("tunl0"); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9d9610ae7855..56d079b63ad3 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -157,9 +157,12 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id) static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { - struct ipmr_result res; - struct fib_lookup_arg arg = { .result = &res, }; int err; + struct ipmr_result res; + struct fib_lookup_arg arg = { + .result = &res, + .flags = FIB_LOOKUP_NOREF, + }; err = fib_rules_lookup(net->ipv4.mr_rules_ops, flowi4_to_flowi(flp4), 0, &arg); @@ -1658,7 +1661,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(iph, skb_dst(skb), NULL); + ip_select_ident(skb, NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); @@ -2252,13 +2255,14 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, } static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc_cache *c, int cmd) + u32 portid, u32 seq, struct mfc_cache *c, int cmd, + int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; - nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -2326,7 +2330,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, if (skb == NULL) goto errout; - err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; @@ -2365,7 +2369,8 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ipmr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) goto done; next_entry: e++; @@ -2379,7 +2384,8 @@ next_entry: if (ipmr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) { + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) { spin_unlock_bh(&mfc_unres_lock); goto done; } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 85a4f21aac1a..c8abe31961ed 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1039,8 +1039,10 @@ static int __do_replace(struct net *net, const char *name, xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, - sizeof(struct xt_counters) * num_counters) != 0) - ret = -EFAULT; + sizeof(struct xt_counters) * num_counters) != 0) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("arptables: counters copy to user failed while replacing table\n"); + } vfree(counters); xt_table_unlock(t); return ret; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index d23118d95ff9..651c10774d58 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1226,8 +1226,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, - sizeof(struct xt_counters) * num_counters) != 0) - ret = -EFAULT; + sizeof(struct xt_counters) * num_counters) != 0) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n"); + } vfree(counters); xt_table_unlock(t); return ret; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 32b0e978c8e0..f8629c04f35b 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -220,6 +220,7 @@ static void ipt_ulog_packet(struct net *net, ub->qlen++; pm = nlmsg_data(nlh); + memset(pm, 0, sizeof(*pm)); /* We might not have a timestamp, get one */ if (skb->tstamp.tv64 == 0) @@ -238,8 +239,6 @@ static void ipt_ulog_packet(struct net *net, } else if (loginfo->prefix[0] != '\0') strncpy(pm->prefix, loginfo->prefix, sizeof(pm->prefix)); - else - *(pm->prefix) = '\0'; if (in && in->hard_header_len > 0 && skb->mac_header != skb->network_header && @@ -251,13 +250,9 @@ static void ipt_ulog_packet(struct net *net, if (in) strncpy(pm->indev_name, in->name, sizeof(pm->indev_name)); - else - pm->indev_name[0] = '\0'; if (out) strncpy(pm->outdev_name, out->name, sizeof(pm->outdev_name)); - else - pm->outdev_name[0] = '\0'; /* copy_len <= skb->len, so can't fail. */ if (skb_copy_bits(skb, 0, pm->payload, copy_len) < 0) diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 742815518b0f..4cfb3bd1677c 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -22,7 +22,6 @@ #endif #include <net/netfilter/nf_conntrack_zones.h> -/* Returns new sk_buff, or NULL */ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) { int err; @@ -33,8 +32,10 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) err = ip_defrag(skb, user); local_bh_enable(); - if (!err) + if (!err) { ip_send_check(ip_hdr(skb)); + skb->local_df = 1; + } return err; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 7d93d62cd5fd..459b957104a8 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -139,6 +139,7 @@ static void ping_v4_unhash(struct sock *sk) if (sk_hashed(sk)) { write_lock_bh(&ping_table.lock); hlist_nulls_del(&sk->sk_nulls_node); + sk_nulls_node_init(&sk->sk_nulls_node); sock_put(sk); isk->inet_num = 0; isk->inet_sport = 0; @@ -204,26 +205,33 @@ static int ping_init_sock(struct sock *sk) { struct net *net = sock_net(sk); kgid_t group = current_egid(); - struct group_info *group_info = get_current_groups(); - int i, j, count = group_info->ngroups; + struct group_info *group_info; + int i, j, count; kgid_t low, high; + int ret = 0; inet_get_ping_group_range_net(net, &low, &high); if (gid_lte(low, group) && gid_lte(group, high)) return 0; + group_info = get_current_groups(); + count = group_info->ngroups; for (i = 0; i < group_info->nblocks; i++) { int cp_count = min_t(int, NGROUPS_PER_BLOCK, count); for (j = 0; j < cp_count; j++) { kgid_t gid = group_info->blocks[i][j]; if (gid_lte(low, gid) && gid_lte(gid, high)) - return 0; + goto out_release_group; } count -= cp_count; } - return -EACCES; + ret = -EACCES; + +out_release_group: + put_group_info(group_info); + return ret; } static void ping_close(struct sock *sk, long timeout) @@ -570,7 +578,7 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } @@ -626,7 +634,6 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct inet_sock *isk = inet_sk(sk); - struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; struct sk_buff *skb; int copied, err; @@ -636,11 +643,8 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_OOB) goto out; - if (addr_len) - *addr_len = sizeof(*sin); - if (flags & MSG_ERRQUEUE) - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) @@ -660,11 +664,14 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sock_recv_timestamp(msg, sk, skb); /* Copy the address. */ - if (sin) { + if (msg->msg_name) { + struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; + sin->sin_family = AF_INET; sin->sin_port = 0 /* skb->h.uh->source */; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } if (isk->cmsg_flags) ip_cmsg_recv(msg, skb); @@ -714,8 +721,11 @@ void ping_rcv(struct sk_buff *skb) sk = ping_v4_lookup(net, saddr, daddr, ntohs(icmph->un.echo.id), skb->dev->ifindex); if (sk != NULL) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + pr_debug("rcv on socket %p\n", sk); - ping_queue_rcv_skb(sk, skb_get(skb)); + if (skb2) + ping_queue_rcv_skb(sk, skb2); sock_put(sk); return; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index dd44e0ab600c..b4a1c42a627f 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -387,7 +387,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } @@ -571,7 +571,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, - inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP, + inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP | + (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0); if (!inet->hdrincl) { @@ -691,11 +692,8 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_OOB) goto out; - if (addr_len) - *addr_len = sizeof(*sin); - if (flags & MSG_ERRQUEUE) { - err = ip_recv_error(sk, msg, len); + err = ip_recv_error(sk, msg, len, addr_len); goto out; } @@ -721,6 +719,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sin->sin_addr.s_addr = ip_hdr(skb)->saddr; sin->sin_port = 0; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d35bbf0cf404..e23c5f64286b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -89,6 +89,7 @@ #include <linux/rcupdate.h> #include <linux/times.h> #include <linux/slab.h> +#include <linux/jhash.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -464,39 +465,53 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, return neigh_create(&arp_tbl, pkey, dev); } -/* - * Peer allocation may fail only in serious out-of-memory conditions. However - * we still can generate some output. - * Random ID selection looks a bit dangerous because we have no chances to - * select ID being unique in a reasonable period of time. - * But broken packet identifier may be better than no packet at all. +#define IP_IDENTS_SZ 2048u +struct ip_ident_bucket { + atomic_t id; + u32 stamp32; +}; + +static struct ip_ident_bucket *ip_idents __read_mostly; + +/* In order to protect privacy, we add a perturbation to identifiers + * if one generator is seldom used. This makes hard for an attacker + * to infer how many packets were sent between two points in time. */ -static void ip_select_fb_ident(struct iphdr *iph) +u32 ip_idents_reserve(u32 hash, int segs) { - static DEFINE_SPINLOCK(ip_fb_id_lock); - static u32 ip_fallback_id; - u32 salt; + struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ; + u32 old = ACCESS_ONCE(bucket->stamp32); + u32 now = (u32)jiffies; + u32 delta = 0; + + if (old != now && cmpxchg(&bucket->stamp32, old, now) == old) { + u64 x = prandom_u32(); + + x *= (now - old); + delta = (u32)(x >> 32); + } - spin_lock_bh(&ip_fb_id_lock); - salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr); - iph->id = htons(salt & 0xFFFF); - ip_fallback_id = salt; - spin_unlock_bh(&ip_fb_id_lock); + return atomic_add_return(segs + delta, &bucket->id) - segs; } +EXPORT_SYMBOL(ip_idents_reserve); -void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) +void __ip_select_ident(struct iphdr *iph, int segs) { - struct net *net = dev_net(dst->dev); - struct inet_peer *peer; + static u32 ip_idents_hashrnd __read_mostly; + static bool hashrnd_initialized = false; + u32 hash, id; - peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1); - if (peer) { - iph->id = htons(inet_getid(peer, more)); - inet_putpeer(peer); - return; + if (unlikely(!hashrnd_initialized)) { + hashrnd_initialized = true; + get_random_bytes(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd)); } - ip_select_fb_ident(iph); + hash = jhash_3words((__force u32)iph->daddr, + (__force u32)iph->saddr, + iph->protocol, + ip_idents_hashrnd); + id = ip_idents_reserve(hash, segs); + iph->id = htons(id); } EXPORT_SYMBOL(__ip_select_ident); @@ -985,20 +1000,21 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; struct rtable *rt; - struct dst_entry *dst; + struct dst_entry *odst = NULL; bool new = false; bh_lock_sock(sk); - rt = (struct rtable *) __sk_dst_get(sk); + odst = sk_dst_get(sk); - if (sock_owned_by_user(sk) || !rt) { + if (sock_owned_by_user(sk) || !odst) { __ipv4_sk_update_pmtu(skb, sk, mtu); goto out; } __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); - if (!__sk_dst_check(sk, 0)) { + rt = (struct rtable *)odst; + if (odst->obsolete && odst->ops->check(odst, 0) == NULL) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; @@ -1008,8 +1024,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu); - dst = dst_check(&rt->dst, 0); - if (!dst) { + if (!dst_check(&rt->dst, 0)) { if (new) dst_release(&rt->dst); @@ -1021,10 +1036,11 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) } if (new) - __sk_dst_set(sk, &rt->dst); + sk_dst_set(sk, &rt->dst); out: bh_unlock_sock(sk); + dst_release(odst); } EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); @@ -1478,7 +1494,7 @@ static int __mkroute_input(struct sk_buff *skb, struct in_device *out_dev; unsigned int flags = 0; bool do_cache; - u32 itag; + u32 itag = 0; /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res)); @@ -1498,11 +1514,10 @@ static int __mkroute_input(struct sk_buff *skb, do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && + skb->protocol == htons(ETH_P_IP) && (IN_DEV_SHARED_MEDIA(out_dev) || - inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) { - flags |= RTCF_DOREDIRECT; - do_cache = false; - } + inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) + IPCB(skb)->flags |= IPSKB_DOREDIRECT; if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is @@ -1544,6 +1559,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rth->dst.output = ip_output; @@ -1645,8 +1661,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (err != 0) goto no_route; - RT_CACHE_STAT_INC(in_slow_tot); - if (res.type == RTN_BROADCAST) goto brd_input; @@ -1715,13 +1729,18 @@ local_input: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } - if (do_cache) - rt_cache_route(&FIB_RES_NH(res), rth); + if (do_cache) { + if (unlikely(!rt_cache_route(&FIB_RES_NH(res), rth))) { + rth->dst.flags |= DST_NOCACHE; + rt_add_uncached_list(rth); + } + } skb_dst_set(skb, &rth->dst); err = 0; goto out; @@ -2020,7 +2039,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) RT_SCOPE_LINK); goto make_route; } - if (fl4->saddr) { + if (!fl4->saddr) { if (ipv4_is_multicast(fl4->daddr)) fl4->saddr = inet_select_addr(dev_out, 0, fl4->flowi4_scope); @@ -2235,6 +2254,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; + if (IPCB(skb)->flags & IPSKB_DOREDIRECT) + r->rtm_flags |= RTCF_DOREDIRECT; if (nla_put_be32(skb, RTA_DST, dst)) goto nla_put_failure; @@ -2302,7 +2323,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, } } else #endif - if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) + if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex)) goto nla_put_failure; } @@ -2651,6 +2672,12 @@ int __init ip_rt_init(void) { int rc = 0; + ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL); + if (!ip_idents) + panic("IP: failed to allocate ip_idents\n"); + + prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents)); + #ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index fa2f63fc453b..90b26beb84d4 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -29,6 +29,7 @@ static int zero; static int one = 1; static int four = 4; +static int gso_max_segs = GSO_MAX_SEGS; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; @@ -36,6 +37,8 @@ static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; static int ip_ttl_min = 1; static int ip_ttl_max = 255; +static int tcp_syn_retries_min = 1; +static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; @@ -331,7 +334,9 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_syn_retries, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_syn_retries_min, + .extra2 = &tcp_syn_retries_max }, { .procname = "tcp_synack_retries", @@ -749,6 +754,15 @@ static struct ctl_table ipv4_table[] = { .extra2 = &four, }, { + .procname = "tcp_min_tso_segs", + .data = &sysctl_tcp_min_tso_segs, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &gso_max_segs, + }, + { .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ab450c099aa4..5d4bd6ca3ab1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -282,6 +282,8 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; +int sysctl_tcp_min_tso_segs __read_mostly = 2; + struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); @@ -786,14 +788,24 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, xmit_size_goal = mss_now; if (large_allowed && sk_can_gso(sk)) { - xmit_size_goal = ((sk->sk_gso_max_size - 1) - - inet_csk(sk)->icsk_af_ops->net_header_len - - inet_csk(sk)->icsk_ext_hdr_len - - tp->tcp_header_len); + u32 gso_size, hlen; + + /* Maybe we should/could use sk->sk_prot->max_header here ? */ + hlen = inet_csk(sk)->icsk_af_ops->net_header_len + + inet_csk(sk)->icsk_ext_hdr_len + + tp->tcp_header_len; + + /* Goal is to send at least one packet per ms, + * not one big TSO packet every 100 ms. + * This preserves ACK clocking and is consistent + * with tcp_tso_should_defer() heuristic. + */ + gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC); + gso_size = max_t(u32, gso_size, + sysctl_tcp_min_tso_segs * mss_now); - /* TSQ : try to have two TSO segments in flight */ - xmit_size_goal = min_t(u32, xmit_size_goal, - sysctl_tcp_limit_output_bytes >> 1); + xmit_size_goal = min_t(u32, gso_size, + sk->sk_gso_max_size - 1 - hlen); xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal); @@ -989,7 +1001,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp) } } -static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) +static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, + int *copied, size_t size) { struct tcp_sock *tp = tcp_sk(sk); int err, flags; @@ -1004,11 +1017,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) if (unlikely(tp->fastopen_req == NULL)) return -ENOBUFS; tp->fastopen_req->data = msg; + tp->fastopen_req->size = size; flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, flags); - *size = tp->fastopen_req->copied; + *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); return err; } @@ -1028,7 +1042,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flags = msg->msg_flags; if (flags & MSG_FASTOPEN) { - err = tcp_sendmsg_fastopen(sk, msg, &copied_syn); + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) @@ -1051,7 +1065,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { copied = tcp_send_rcvq(sk, msg, size); - goto out; + goto out_nopush; } err = -EINVAL; @@ -1118,6 +1132,13 @@ new_segment: goto wait_for_memory; /* + * All packets are restored as if they have + * already been sent. + */ + if (tp->repair) + TCP_SKB_CB(skb)->when = tcp_time_stamp; + + /* * Check whether we can use HW checksum. */ if (sk->sk_route_caps & NETIF_F_ALL_CSUM) @@ -1217,6 +1238,7 @@ wait_for_memory: out: if (copied) tcp_push(sk, flags, mss_now, tp->nonagle); +out_nopush: release_sock(sk); return copied + copied_syn; @@ -2440,10 +2462,11 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_THIN_DUPACK: if (val < 0 || val > 1) err = -EINVAL; - else + else { tp->thin_dupack = val; if (tp->thin_dupack) tcp_disable_early_retrans(tp); + } break; case TCP_REPAIR: @@ -2879,6 +2902,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int sum_truesize = 0; struct tcphdr *th; unsigned int thlen; unsigned int seq; @@ -2962,13 +2986,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, if (copy_destructor) { skb->destructor = gso_skb->destructor; skb->sk = gso_skb->sk; - /* {tcp|sock}_wfree() use exact truesize accounting : - * sum(skb->truesize) MUST be exactly be gso_skb->truesize - * So we account mss bytes of 'true size' for each segment. - * The last segment will contain the remaining. - */ - skb->truesize = mss; - gso_skb->truesize -= mss; + sum_truesize += skb->truesize; } skb = skb->next; th = tcp_hdr(skb); @@ -2985,7 +3003,9 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, if (copy_destructor) { swap(gso_skb->sk, skb->sk); swap(gso_skb->destructor, skb->destructor); - swap(gso_skb->truesize, skb->truesize); + sum_truesize += skb->truesize; + atomic_add(sum_truesize - gso_skb->truesize, + &skb->sk->sk_wmem_alloc); } delta = htonl(oldlen + (skb->tail - skb->transport_header) + diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index a9077f441cb2..894b7cea5d7b 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -206,8 +206,8 @@ static u32 cubic_root(u64 a) */ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) { - u64 offs; - u32 delta, t, bic_target, max_cnt; + u32 delta, bic_target, max_cnt; + u64 offs, t; ca->ack_cnt++; /* count the number of ACKs */ @@ -250,9 +250,11 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) * if the cwnd < 1 million packets !!! */ + t = (s32)(tcp_time_stamp - ca->epoch_start); + t += msecs_to_jiffies(ca->delay_min >> 3); /* change the unit from HZ to bictcp_HZ */ - t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3) - - ca->epoch_start) << BICTCP_HZ) / HZ; + t <<= BICTCP_HZ; + do_div(t, HZ); if (t < ca->bic_K) /* t - K */ offs = ca->bic_K - t; @@ -406,7 +408,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT; ratio += cnt; - ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT); + ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT); } /* Some calls are for duplicates without timetamps */ @@ -414,7 +416,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) return; /* Discard delay samples right after fast recovery */ - if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ) + if (ca->epoch_start && (s32)(tcp_time_stamp - ca->epoch_start) < HZ) return; delay = (rtt_us << 3) / USEC_PER_MSEC; diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 834857f3c871..86183c4e4fd5 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -23,7 +23,6 @@ #define ALPHA_MIN ((3*ALPHA_SCALE)/10) /* ~0.3 */ #define ALPHA_MAX (10*ALPHA_SCALE) /* 10.0 */ #define ALPHA_BASE ALPHA_SCALE /* 1.0 */ -#define U32_MAX ((u32)~0U) #define RTT_MAX (U32_MAX / ALPHA_MAX) /* 3.3 secs */ #define BETA_SHIFT 6 diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9c6225780bd5..a8be45e4d34f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -699,6 +699,34 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) } } +/* Set the sk_pacing_rate to allow proper sizing of TSO packets. + * Note: TCP stack does not yet implement pacing. + * FQ packet scheduler can be used to implement cheap but effective + * TCP pacing, to smooth the burst on large writes when packets + * in flight is significantly lower than cwnd (or rwin) + */ +static void tcp_update_pacing_rate(struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + u64 rate; + + /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */ + rate = (u64)tp->mss_cache * 2 * (HZ << 3); + + rate *= max(tp->snd_cwnd, tp->packets_out); + + /* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3), + * be conservative and assume srtt = 1 (125 us instead of 1.25 ms) + * We probably need usec resolution in the future. + * Note: This also takes care of possible srtt=0 case, + * when tcp_rtt_estimator() was not yet called. + */ + if (tp->srtt > 8 + 2) + do_div(rate, tp->srtt); + + sk->sk_pacing_rate = min_t(u64, rate, ~0U); +} + /* Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ @@ -1047,7 +1075,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, } /* D-SACK for already forgotten data... Do dumb counting. */ - if (dup_sack && tp->undo_marker && tp->undo_retrans && + if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 && !after(end_seq_0, prior_snd_una) && after(end_seq_0, tp->undo_marker)) tp->undo_retrans--; @@ -1102,7 +1130,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, unsigned int new_len = (pkt_len / mss) * mss; if (!in_sack && new_len < pkt_len) { new_len += mss; - if (new_len > skb->len) + if (new_len >= skb->len) return 0; } pkt_len = new_len; @@ -1126,7 +1154,7 @@ static u8 tcp_sacktag_one(struct sock *sk, /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { - if (tp->undo_marker && tp->undo_retrans && + if (tp->undo_marker && tp->undo_retrans > 0 && after(end_seq, tp->undo_marker)) tp->undo_retrans--; if (sacked & TCPCB_SACKED_ACKED) @@ -1264,7 +1292,10 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tp->lost_cnt_hint -= tcp_skb_pcount(prev); } - TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags; + TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + TCP_SKB_CB(prev)->end_seq++; + if (skb == tcp_highest_sack(sk)) tcp_advance_highest_sack(sk, skb); @@ -1819,7 +1850,7 @@ static void tcp_clear_retrans_partial(struct tcp_sock *tp) tp->lost_out = 0; tp->undo_marker = 0; - tp->undo_retrans = 0; + tp->undo_retrans = -1; } void tcp_clear_retrans(struct tcp_sock *tp) @@ -2669,7 +2700,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) tp->prior_ssthresh = 0; tp->undo_marker = tp->snd_una; - tp->undo_retrans = tp->retrans_out; + tp->undo_retrans = tp->retrans_out ? : -1; if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { if (!ece_ack) @@ -2689,13 +2720,12 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) bool recovered = !before(tp->snd_una, tp->high_seq); if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ - if (flag & FLAG_ORIG_SACK_ACKED) { - /* Step 3.b. A timeout is spurious if not all data are - * lost, i.e., never-retransmitted data are (s)acked. - */ - tcp_try_undo_loss(sk, true); + /* Step 3.b. A timeout is spurious if not all data are + * lost, i.e., never-retransmitted data are (s)acked. + */ + if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED)) return; - } + if (after(tp->snd_nxt, tp->high_seq) && (flag & FLAG_DATA_SACKED || is_dupack)) { tp->frto = 0; /* Loss was real: 2nd part of step 3.a */ @@ -3046,10 +3076,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (seq_rtt < 0) { seq_rtt = ca_seq_rtt; } - if (!(sacked & TCPCB_SACKED_ACKED)) + if (!(sacked & TCPCB_SACKED_ACKED)) { reord = min(pkts_acked, reord); - if (!after(scb->end_seq, tp->high_seq)) - flag |= FLAG_ORIG_SACK_ACKED; + if (!after(scb->end_seq, tp->high_seq)) + flag |= FLAG_ORIG_SACK_ACKED; + } } if (sacked & TCPCB_SACKED_ACKED) @@ -3314,7 +3345,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) tcp_init_cwnd_reduction(sk, true); tcp_set_ca_state(sk, TCP_CA_CWR); tcp_end_cwnd_reduction(sk); - tcp_set_ca_state(sk, TCP_CA_Open); + tcp_try_keep_open(sk); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBERECOVERY); } @@ -3330,7 +3361,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; - u32 prior_in_flight; + u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt; u32 prior_fackets; int prior_packets = tp->packets_out; int prior_sacked = tp->sacked_out; @@ -3438,6 +3469,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (icsk->icsk_pending == ICSK_TIME_RETRANS) tcp_schedule_loss_probe(sk); + if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd) + tcp_update_pacing_rate(sk); return 1; no_queue: @@ -3598,7 +3631,10 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr ++ptr; tp->rx_opt.rcv_tsval = ntohl(*ptr); ++ptr; - tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset; + if (*ptr) + tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset; + else + tp->rx_opt.rcv_tsecr = 0; return true; } return false; @@ -3623,7 +3659,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, } tcp_parse_options(skb, &tp->rx_opt, 1, NULL); - if (tp->rx_opt.saw_tstamp) + if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; return true; @@ -5376,7 +5412,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, int saved_clamp = tp->rx_opt.mss_clamp; tcp_parse_options(skb, &tp->rx_opt, 0, &foc); - if (tp->rx_opt.saw_tstamp) + if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; if (th->ack) { @@ -5733,6 +5769,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } else tcp_init_metrics(sk); + tcp_update_pacing_rate(sk); + /* Prevent spurious tcp_cwnd_restart() on * first data packet. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7999fc55c83b..7c3eec386a4b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -176,7 +176,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) - IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); return err; } @@ -268,7 +268,7 @@ EXPORT_SYMBOL(tcp_v4_connect); * It can be called through tcp_release_cb() if socket was owned by user * at the time tcp_v4_err() was called to handle ICMP message. */ -static void tcp_v4_mtu_reduced(struct sock *sk) +void tcp_v4_mtu_reduced(struct sock *sk) { struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); @@ -298,6 +298,7 @@ static void tcp_v4_mtu_reduced(struct sock *sk) tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ } +EXPORT_SYMBOL(tcp_v4_mtu_reduced); static void do_redirect(struct sk_buff *skb, struct sock *sk) { @@ -706,7 +707,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) net = dev_net(skb_dst(skb)->dev); arg.tos = ip_hdr(skb)->tos; - ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -789,7 +791,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, if (oif) arg.bound_dev_if = oif; arg.tos = tos; - ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -1898,7 +1901,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); @@ -2142,6 +2145,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = { .compat_setsockopt = compat_ip_setsockopt, .compat_getsockopt = compat_ip_getsockopt, #endif + .mtu_reduced = tcp_v4_mtu_reduced, }; EXPORT_SYMBOL(ipv4_specific); @@ -2867,7 +2871,6 @@ struct proto tcp_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, - .mtu_reduced = tcp_v4_mtu_reduced, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, @@ -2897,14 +2900,39 @@ struct proto tcp_prot = { }; EXPORT_SYMBOL(tcp_prot); +static void __net_exit tcp_sk_exit(struct net *net) +{ + int cpu; + + for_each_possible_cpu(cpu) + inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); + free_percpu(net->ipv4.tcp_sk); +} + static int __net_init tcp_sk_init(struct net *net) { + int res, cpu; + + net->ipv4.tcp_sk = alloc_percpu(struct sock *); + if (!net->ipv4.tcp_sk) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct sock *sk; + + res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, + IPPROTO_TCP, net); + if (res) + goto fail; + *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; + } net->ipv4.sysctl_tcp_ecn = 2; return 0; -} -static void __net_exit tcp_sk_exit(struct net *net) -{ +fail: + tcp_sk_exit(net); + + return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index f6a005c485a9..b500d2ddc476 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -22,6 +22,9 @@ int sysctl_tcp_nometrics_save __read_mostly; +static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr, + struct net *net, unsigned int hash); + struct tcp_fastopen_metrics { u16 mss; u16 syn_loss:10; /* Recurring Fast Open SYN losses */ @@ -130,16 +133,41 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst, } } +#define TCP_METRICS_TIMEOUT (60 * 60 * HZ) + +static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst) +{ + if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT))) + tcpm_suck_dst(tm, dst, false); +} + +#define TCP_METRICS_RECLAIM_DEPTH 5 +#define TCP_METRICS_RECLAIM_PTR (struct tcp_metrics_block *) 0x1UL + static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, struct inetpeer_addr *addr, - unsigned int hash, - bool reclaim) + unsigned int hash) { struct tcp_metrics_block *tm; struct net *net; + bool reclaim = false; spin_lock_bh(&tcp_metrics_lock); net = dev_net(dst->dev); + + /* While waiting for the spin-lock the cache might have been populated + * with this entry and so we have to check again. + */ + tm = __tcp_get_metrics(addr, net, hash); + if (tm == TCP_METRICS_RECLAIM_PTR) { + reclaim = true; + tm = NULL; + } + if (tm) { + tcpm_check_stamp(tm, dst); + goto out_unlock; + } + if (unlikely(reclaim)) { struct tcp_metrics_block *oldest; @@ -169,17 +197,6 @@ out_unlock: return tm; } -#define TCP_METRICS_TIMEOUT (60 * 60 * HZ) - -static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst) -{ - if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT))) - tcpm_suck_dst(tm, dst, false); -} - -#define TCP_METRICS_RECLAIM_DEPTH 5 -#define TCP_METRICS_RECLAIM_PTR (struct tcp_metrics_block *) 0x1UL - static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, int depth) { if (tm) @@ -280,7 +297,6 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, struct inetpeer_addr addr; unsigned int hash; struct net *net; - bool reclaim; addr.family = sk->sk_family; switch (addr.family) { @@ -300,13 +316,10 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); tm = __tcp_get_metrics(&addr, net, hash); - reclaim = false; - if (tm == TCP_METRICS_RECLAIM_PTR) { - reclaim = true; + if (tm == TCP_METRICS_RECLAIM_PTR) tm = NULL; - } if (!tm && create) - tm = tcpm_new(dst, &addr, hash, reclaim); + tm = tcpm_new(dst, &addr, hash); else tcpm_check_stamp(tm, dst); @@ -665,10 +678,13 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_cookie *cookie, bool syn_lost) { + struct dst_entry *dst = __sk_dst_get(sk); struct tcp_metrics_block *tm; + if (!dst) + return; rcu_read_lock(); - tm = tcp_get_metrics(sk, __sk_dst_get(sk), true); + tm = tcp_get_metrics(sk, dst, true); if (tm) { struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index ec335fabd5cc..76c80b59e80f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -686,7 +686,8 @@ static void tcp_tsq_handler(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) - tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC); + tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle, + 0, GFP_ATOMIC); } /* * One tasklest per cpu tries to send more skbs. @@ -754,6 +755,17 @@ void tcp_release_cb(struct sock *sk) if (flags & (1UL << TCP_TSQ_DEFERRED)) tcp_tsq_handler(sk); + /* Here begins the tricky part : + * We are called from release_sock() with : + * 1) BH disabled + * 2) sk_lock.slock spinlock held + * 3) socket owned by us (sk->sk_lock.owned == 1) + * + * But following code is meant to be called from BH handlers, + * so we should keep BH disabled, but early release socket ownership + */ + sock_release_ownership(sk); + if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) { tcp_write_timer_handler(sk); __sock_put(sk); @@ -763,7 +775,7 @@ void tcp_release_cb(struct sock *sk) __sock_put(sk); } if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) { - sk->sk_prot->mtu_reduced(sk); + inet_csk(sk)->icsk_af_ops->mtu_reduced(sk); __sock_put(sk); } } @@ -887,8 +899,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_orphan(skb); skb->sk = sk; - skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ? - tcp_wfree : sock_wfree; + skb->destructor = tcp_wfree; atomic_add(skb->truesize, &sk->sk_wmem_alloc); /* Build TCP header and checksum it. */ @@ -977,6 +988,9 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { + /* Make sure we own this skb before messing gso_size/gso_segs */ + WARN_ON_ONCE(skb_cloned(skb)); + if (skb->len <= mss_now || !sk_can_gso(sk) || skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal @@ -1058,9 +1072,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, if (nsize < 0) nsize = 0; - if (skb_cloned(skb) && - skb_is_nonlinear(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; /* Get a new skb... force flag on. */ @@ -1623,7 +1635,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) /* If a full-sized TSO skb can be sent, do it. */ if (limit >= min_t(unsigned int, sk->sk_gso_max_size, - sk->sk_gso_max_segs * tp->mss_cache)) + tp->xmit_size_goal_segs * tp->mss_cache)) goto send_now; /* Middle in queue won't get any more data, full sendable already? */ @@ -1832,7 +1844,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, while ((skb = tcp_send_head(sk))) { unsigned int limit; - tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); @@ -1851,7 +1862,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) break; - if (tso_segs == 1) { + if (tso_segs == 1 || !sk->sk_gso_max_segs) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? nonagle : TCP_NAGLE_PUSH)))) @@ -1861,15 +1872,34 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, break; } - /* TSQ : sk_wmem_alloc accounts skb truesize, - * including skb overhead. But thats OK. + /* TCP Small Queues : + * Control number of packets in qdisc/devices to two packets / or ~1 ms. + * This allows for : + * - better RTT estimation and ACK scheduling + * - faster recovery + * - high rates + * Alas, some drivers / subsystems require a fair amount + * of queued bytes to ensure line rate. + * One example is wifi aggregation (802.11 AMPDU) */ - if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) { + limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes, + sk->sk_pacing_rate >> 10); + + if (atomic_read(&sk->sk_wmem_alloc) > limit) { set_bit(TSQ_THROTTLED, &tp->tsq_flags); - break; + /* It is possible TX completion already happened + * before we set TSQ_THROTTLED, so we must + * test again the condition. + * We abuse smp_mb__after_clear_bit() because + * there is no smp_mb__after_set_bit() yet + */ + smp_mb__after_clear_bit(); + if (atomic_read(&sk->sk_wmem_alloc) > limit) + break; } + limit = mss_now; - if (tso_segs > 1 && !tcp_urg_mode(tp)) + if (tso_segs > 1 && sk->sk_gso_max_segs && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, min_t(unsigned int, cwnd_quota, @@ -2006,9 +2036,7 @@ void tcp_send_loss_probe(struct sock *sk) if (WARN_ON(!skb || !tcp_skb_pcount(skb))) goto rearm_timer; - /* Probe with zero data doesn't trigger fast recovery. */ - if (skb->len > 0) - err = __tcp_retransmit_skb(sk, skb); + err = __tcp_retransmit_skb(sk, skb); /* Record snd_nxt for loss detection. */ if (likely(!err)) @@ -2329,6 +2357,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) int oldpcount = tcp_skb_pcount(skb); if (unlikely(oldpcount > 1)) { + if (skb_unclone(skb, GFP_ATOMIC)) + return -ENOMEM; tcp_init_tso_segs(sk, skb, cur_mss); tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb)); } @@ -2396,13 +2426,15 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (!tp->retrans_stamp) tp->retrans_stamp = TCP_SKB_CB(skb)->when; - tp->undo_retrans += tcp_skb_pcount(skb); - /* snd_nxt is stored to detect loss of retransmitted segment, * see tcp_input.c tcp_sacktag_write_queue(). */ TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt; } + + if (tp->undo_retrans < 0) + tp->undo_retrans = 0; + tp->undo_retrans += tcp_skb_pcount(skb); return err; } @@ -2539,43 +2571,65 @@ begin_fwd: } } -/* Send a fin. The caller locks the socket for us. This cannot be - * allowed to fail queueing a FIN frame under any circumstances. +/* We allow to exceed memory limits for FIN packets to expedite + * connection tear down and (memory) recovery. + * Otherwise tcp_send_fin() could be tempted to either delay FIN + * or even be forced to close flow without any FIN. + */ +static void sk_forced_wmem_schedule(struct sock *sk, int size) +{ + int amt, status; + + if (size <= sk->sk_forward_alloc) + return; + amt = sk_mem_pages(size); + sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; + sk_memory_allocated_add(sk, amt, &status); +} + +/* Send a FIN. The caller locks the socket for us. + * We should try to send a FIN packet really hard, but eventually give up. */ void tcp_send_fin(struct sock *sk) { + struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = tcp_write_queue_tail(sk); - int mss_now; - /* Optimization, tack on the FIN if we have a queue of - * unsent frames. But be careful about outgoing SACKS - * and IP options. + /* Optimization, tack on the FIN if we have one skb in write queue and + * this skb was not yet sent, or we are under memory pressure. + * Note: in the latter case, FIN packet will be sent after a timeout, + * as TCP stack thinks it has already been transmitted. */ - mss_now = tcp_current_mss(sk); - - if (tcp_send_head(sk) != NULL) { - TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN; - TCP_SKB_CB(skb)->end_seq++; + if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) { +coalesce: + TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; + TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; + if (!tcp_send_head(sk)) { + /* This means tskb was already sent. + * Pretend we included the FIN on previous transmit. + * We need to set tp->snd_nxt to the value it would have + * if FIN had been sent. This is because retransmit path + * does not change tp->snd_nxt. + */ + tp->snd_nxt++; + return; + } } else { - /* Socket is locked, keep trying until memory is available. */ - for (;;) { - skb = alloc_skb_fclone(MAX_TCP_HEADER, - sk->sk_allocation); - if (skb) - break; - yield(); + skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + if (unlikely(!skb)) { + if (tskb) + goto coalesce; + return; } - - /* Reserve space for headers and prepare control bits. */ skb_reserve(skb, MAX_TCP_HEADER); + sk_forced_wmem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } - __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF); + __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); } /* We get here when a process closes a file descriptor (either due to @@ -2664,7 +2718,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, int tcp_header_size; int mss; - skb = alloc_skb(MAX_TCP_HEADER + 15, sk_gfp_atomic(sk, GFP_ATOMIC)); + skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC); if (unlikely(!skb)) { dst_release(dst); return NULL; @@ -2744,6 +2798,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, } #endif + /* Do not fool tcpdump (if any), clean our debris */ + skb->tstamp.tv64 = 0; return skb; } EXPORT_SYMBOL(tcp_make_synack); @@ -2808,6 +2864,8 @@ void tcp_connect_init(struct sock *sk) if (likely(!tp->repair)) tp->rcv_nxt = 0; + else + tp->rcv_tstamp = tcp_time_stamp; tp->rcv_wup = tp->rcv_nxt; tp->copied_seq = tp->rcv_nxt; @@ -2841,9 +2899,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; - int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen; - struct sk_buff *syn_data = NULL, *data; + int syn_loss = 0, space, err = 0; unsigned long last_syn_loss = 0; + struct sk_buff *syn_data; tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie, @@ -2869,42 +2927,44 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; - syn_data = skb_copy_expand(syn, skb_headroom(syn), space, - sk->sk_allocation); - if (syn_data == NULL) - goto fallback; - - for (i = 0; i < iovlen && syn_data->len < space; ++i) { - struct iovec *iov = &fo->data->msg_iov[i]; - unsigned char __user *from = iov->iov_base; - int len = iov->iov_len; + space = min_t(size_t, space, fo->size); - if (syn_data->len + len > space) - len = space - syn_data->len; - else if (i + 1 == iovlen) - /* No more data pending in inet_wait_for_connect() */ - fo->data = NULL; + /* limit to order-0 allocations */ + space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); - if (skb_add_data(syn_data, from, len)) - goto fallback; + syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation); + if (!syn_data) + goto fallback; + syn_data->ip_summed = CHECKSUM_PARTIAL; + memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); + skb_shinfo(syn_data)->gso_segs = 1; + if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space), + fo->data->msg_iov, 0, space))) { + kfree_skb(syn_data); + goto fallback; } - /* Queue a data-only packet after the regular SYN for retransmission */ - data = pskb_copy(syn_data, sk->sk_allocation); - if (data == NULL) - goto fallback; - TCP_SKB_CB(data)->seq++; - TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN; - TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH); - tcp_connect_queue_skb(sk, data); - fo->copied = data->len; + /* No more data pending in inet_wait_for_connect() */ + if (space == fo->size) + fo->data = NULL; + fo->copied = space; + + tcp_connect_queue_skb(sk, syn_data); + + err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); - if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { + /* Now full SYN+DATA was cloned and sent (or not), + * remove the SYN from the original skb (syn_data) + * we keep in write queue in case of a retransmit, as we + * also have the SYN packet (with no data) in the same queue. + */ + TCP_SKB_CB(syn_data)->seq++; + TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; + if (!err) { tp->syn_data = (fo->copied > 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); goto done; } - syn_data = NULL; fallback: /* Send a regular SYN with Fast Open cookie request option */ @@ -2913,7 +2973,6 @@ fallback: err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation); if (err) tp->syn_fastopen = 0; - kfree_skb(syn_data); done: fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */ return err; @@ -2933,13 +2992,10 @@ int tcp_connect(struct sock *sk) return 0; } - buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation); - if (unlikely(buff == NULL)) + buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); + if (unlikely(!buff)) return -ENOBUFS; - /* Reserve space for headers. */ - skb_reserve(buff, MAX_TCP_HEADER); - tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp; tcp_connect_queue_skb(sk, buff); @@ -3088,7 +3144,6 @@ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; - tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq; tcp_xmit_probe_skb(sk, 0); } } diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 80fa2bfd7ede..c042e529a11e 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -218,7 +218,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) * This is: * (actual rate in segments) * baseRTT */ - target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt; + target_cwnd = (u64)tp->snd_cwnd * vegas->baseRTT; + do_div(target_cwnd, rtt); /* Calculate the difference between the window we had, * and the window we would like to have. This quantity diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index ac43cd747bce..b4d1858be550 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -144,7 +144,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) rtt = veno->minrtt; - target_cwnd = (tp->snd_cwnd * veno->basertt); + target_cwnd = (u64)tp->snd_cwnd * veno->basertt; target_cwnd <<= V_PARAM_SHIFT; do_div(target_cwnd, rtt); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0bf5d399a03c..c3075b552248 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -799,7 +799,7 @@ send: /* * Push out all pending data as one UDP datagram. Socket is locked. */ -static int udp_push_pending_frames(struct sock *sk) +int udp_push_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); @@ -818,6 +818,7 @@ out: up->pending = 0; return err; } +EXPORT_SYMBOL(udp_push_pending_frames); int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) @@ -970,7 +971,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } @@ -1069,6 +1070,9 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, struct udp_sock *up = udp_sk(sk); int ret; + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + if (!up->pending) { struct msghdr msg = { .msg_flags = flags|MSG_MORE }; @@ -1206,14 +1210,8 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, int is_udplite = IS_UDPLITE(sk); bool slow; - /* - * Check any passed addresses - */ - if (addr_len) - *addr_len = sizeof(*sin); - if (flags & MSG_ERRQUEUE) - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), @@ -1273,6 +1271,7 @@ try_again: sin->sin_port = udp_hdr(skb)->source; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 7927db0a9279..4a000f1dd757 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -99,11 +99,13 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin s_slot = cb->args[0]; num = s_num = cb->args[1]; - for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) { + for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) { struct sock *sk; struct hlist_nulls_node *node; struct udp_hslot *hslot = &table->hash[slot]; + num = 0; + if (hlist_nulls_empty(&hslot->head)) continue; diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index eb1dd4d643f2..e3f64831bc36 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -117,12 +117,12 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); - ip_select_ident(top_iph, dst->child, NULL); top_iph->ttl = ip4_dst_hoplimit(dst->child); top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; + ip_select_ident(skb, NULL); return 0; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4ab4c38958c6..d0912acd9522 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1111,8 +1111,11 @@ retry: * Lifetime is greater than REGEN_ADVANCE time units. In particular, * an implementation must not create a temporary address with a zero * Preferred Lifetime. + * Use age calculation as in addrconf_verify to avoid unnecessary + * temporary addresses being generated. */ - if (tmp_prefered_lft <= regen_advance) { + age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + if (tmp_prefered_lft <= regen_advance + age) { in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; @@ -1124,12 +1127,10 @@ retry: if (ifp->flags & IFA_F_OPTIMISTIC) addr_flags |= IFA_F_OPTIMISTIC; - ift = !max_addresses || - ipv6_count_addresses(idev) < max_addresses ? - ipv6_add_addr(idev, &addr, tmp_plen, - ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK, - addr_flags) : NULL; - if (IS_ERR_OR_NULL(ift)) { + ift = ipv6_add_addr(idev, &addr, tmp_plen, + ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK, + addr_flags); + if (IS_ERR(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); pr_info("%s: retry temporary address regeneration\n", __func__); @@ -1448,6 +1449,23 @@ try_nextdev: } EXPORT_SYMBOL(ipv6_dev_get_saddr); +int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, + unsigned char banned_flags) +{ + struct inet6_ifaddr *ifp; + int err = -EADDRNOTAVAIL; + + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if (ifp->scope == IFA_LINK && + !(ifp->flags & banned_flags)) { + *addr = ifp->addr; + err = 0; + break; + } + } + return err; +} + int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, unsigned char banned_flags) { @@ -1457,17 +1475,8 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - struct inet6_ifaddr *ifp; - read_lock_bh(&idev->lock); - list_for_each_entry(ifp, &idev->addr_list, if_list) { - if (ifp->scope == IFA_LINK && - !(ifp->flags & banned_flags)) { - *addr = ifp->addr; - err = 0; - break; - } - } + err = __ipv6_get_lladdr(idev, addr, banned_flags); read_unlock_bh(&idev->lock); } rcu_read_unlock(); @@ -1527,6 +1536,33 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, return false; } +/* Compares an address/prefix_len with addresses on device @dev. + * If one is found it returns true. + */ +bool ipv6_chk_custom_prefix(const struct in6_addr *addr, + const unsigned int prefix_len, struct net_device *dev) +{ + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + bool ret = false; + + rcu_read_lock(); + idev = __in6_dev_get(dev); + if (idev) { + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); + if (ret) + break; + } + read_unlock_bh(&idev->lock); + } + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(ipv6_chk_custom_prefix); + int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { struct inet6_dev *idev; @@ -2655,8 +2691,18 @@ static void init_loopback(struct net_device *dev) if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE)) continue; - if (sp_ifa->rt) - continue; + if (sp_ifa->rt) { + /* This dst has been added to garbage list when + * lo device down, release this obsolete dst and + * reallocate a new router for ifa. + */ + if (sp_ifa->rt->dst.obsolete > 0) { + ip6_rt_put(sp_ifa->rt); + sp_ifa->rt = NULL; + } else { + continue; + } + } sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, 0); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index f083a583a05c..b30ad3741b46 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -251,38 +251,36 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, /* add a label */ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) { + struct hlist_node *n; + struct ip6addrlbl_entry *last = NULL, *p = NULL; int ret = 0; - ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", - __func__, - newp, replace); + ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp, + replace); - if (hlist_empty(&ip6addrlbl_table.head)) { - hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head); - } else { - struct hlist_node *n; - struct ip6addrlbl_entry *p = NULL; - hlist_for_each_entry_safe(p, n, - &ip6addrlbl_table.head, list) { - if (p->prefixlen == newp->prefixlen && - net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) && - p->ifindex == newp->ifindex && - ipv6_addr_equal(&p->prefix, &newp->prefix)) { - if (!replace) { - ret = -EEXIST; - goto out; - } - hlist_replace_rcu(&p->list, &newp->list); - ip6addrlbl_put(p); - goto out; - } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) || - (p->prefixlen < newp->prefixlen)) { - hlist_add_before_rcu(&newp->list, &p->list); + hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { + if (p->prefixlen == newp->prefixlen && + net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) && + p->ifindex == newp->ifindex && + ipv6_addr_equal(&p->prefix, &newp->prefix)) { + if (!replace) { + ret = -EEXIST; goto out; } + hlist_replace_rcu(&p->list, &newp->list); + ip6addrlbl_put(p); + goto out; + } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) || + (p->prefixlen < newp->prefixlen)) { + hlist_add_before_rcu(&newp->list, &p->list); + goto out; } - hlist_add_after_rcu(&p->list, &newp->list); + last = p; } + if (last) + hlist_add_after_rcu(&last->list, &newp->list); + else + hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head); out: if (!ret) ip6addrlbl_table.seq++; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 4b56cbbc7890..ce17d3da9b2b 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -318,7 +318,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) /* * Handle MSG_ERRQUEUE */ -int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; @@ -369,14 +369,15 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) &sin->sin6_addr); sin->sin6_scope_id = 0; } + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; - sin->sin6_family = AF_UNSPEC; + memset(sin, 0, sizeof(*sin)); + if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { sin->sin6_family = AF_INET6; - sin->sin6_flowinfo = 0; if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) @@ -385,12 +386,9 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); } else { - struct inet_sock *inet = inet_sk(sk); - ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin->sin6_addr); - sin->sin6_scope_id = 0; - if (inet->cmsg_flags) + if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } } @@ -423,7 +421,8 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error); /* * Handle IPV6_RECVPATHMTU */ -int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; @@ -457,6 +456,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) sin->sin6_port = 0; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; + *addr_len = sizeof(*sin); } put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 07a7d65a7cb6..8d67900aa003 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -162,12 +162,6 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb) off += optlen; len -= optlen; } - /* This case will not be caught by above check since its padding - * length is smaller than 7: - * 1 byte NH + 1 byte Length + 6 bytes Padding - */ - if ((padlen == 6) && ((off - skb_network_header_len(skb)) == 8)) - goto bad; if (len == 0) return true; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index c5e83fae4df4..51af9d0d019a 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -212,7 +212,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, found = (nexthdr == target); if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { - if (target < 0) + if (target < 0 || found) break; return -ENOENT; } diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c index cf77f3abfd06..447a7fbd1bb6 100644 --- a/net/ipv6/exthdrs_offload.c +++ b/net/ipv6/exthdrs_offload.c @@ -25,11 +25,11 @@ int __init ipv6_exthdrs_offload_init(void) int ret; ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING); - if (!ret) + if (ret) goto out; ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS); - if (!ret) + if (ret) goto out_rt; out: diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index b4ff0a42b8c7..2dee1d9d7305 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -508,7 +508,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) np->tclass, NULL, &fl6, (struct rt6_info *)dst, MSG_DONTWAIT, np->dontfrag); if (err) { - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, @@ -931,6 +931,14 @@ static const struct icmp6_err { .err = ECONNREFUSED, .fatal = 1, }, + { /* POLICY_FAIL */ + .err = EACCES, + .fatal = 1, + }, + { /* REJECT_ROUTE */ + .err = EACCES, + .fatal = 1, + }, }; int icmpv6_err_convert(u8 type, u8 code, int *err) @@ -942,7 +950,7 @@ int icmpv6_err_convert(u8 type, u8 code, int *err) switch (type) { case ICMPV6_DEST_UNREACH: fatal = 1; - if (code <= ICMPV6_PORT_UNREACH) { + if (code < ARRAY_SIZE(tab_unreach)) { *err = tab_unreach[code].err; fatal = tab_unreach[code].fatal; } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 32b4a1675d82..066640e0ba8e 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -116,7 +116,7 @@ begintw: } if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr, ports, dif))) { - sock_put(sk); + inet_twsk_put(inet_twsk(sk)); goto begintw; } goto out; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 192dd1a0e188..ceeb9458bb60 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -632,6 +632,35 @@ insert_above: return ln; } +static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt) +{ + return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == + RTF_GATEWAY; +} + +static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, + struct net *net) +{ + if (atomic_read(&rt->rt6i_ref) != 1) { + /* This route is used as dummy address holder in some split + * nodes. It is not leaked, but it still holds other resources, + * which must be released in time. So, scan ascendant nodes + * and replace dummy references to this route with references + * to still alive ones. + */ + while (fn) { + if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { + fn->leaf = fib6_find_prefix(net, fn); + atomic_inc(&fn->leaf->rt6i_ref); + rt6_release(rt); + } + fn = fn->parent; + } + /* No more references are possible at this point. */ + BUG_ON(atomic_read(&rt->rt6i_ref) != 1); + } +} + /* * Insert routing information in a node. */ @@ -646,6 +675,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; + bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); ins = &fn->leaf; @@ -691,9 +721,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, * To avoid long list, we only had siblings if the * route have a gateway. */ - if (rt->rt6i_flags & RTF_GATEWAY && - !(rt->rt6i_flags & RTF_EXPIRES) && - !(iter->rt6i_flags & RTF_EXPIRES)) + if (rt_can_ecmp && + rt6_qualify_for_ecmp(iter)) rt->rt6i_nsiblings++; } @@ -715,7 +744,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, /* Find the first route that have the same metric */ sibling = fn->leaf; while (sibling) { - if (sibling->rt6i_metric == rt->rt6i_metric) { + if (sibling->rt6i_metric == rt->rt6i_metric && + rt6_qualify_for_ecmp(sibling)) { list_add_tail(&rt->rt6i_siblings, &sibling->rt6i_siblings); break; @@ -768,11 +798,12 @@ add: rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); inet6_rt_notify(RTM_NEWROUTE, rt, info); - rt6_release(iter); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + fib6_purge_rt(iter, fn, info->nl_net); + rt6_release(iter); } return 0; @@ -818,9 +849,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr), rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, replace_required); - if (IS_ERR(fn)) { err = PTR_ERR(fn); + fn = NULL; goto out; } @@ -986,14 +1017,22 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES - if (fn->subtree) - fn = fib6_lookup_1(fn->subtree, args + 1); + if (fn->subtree) { + struct fib6_node *sfn; + sfn = fib6_lookup_1(fn->subtree, + args + 1); + if (!sfn) + goto backtrack; + fn = sfn; + } #endif - if (!fn || fn->fn_flags & RTN_RTINFO) + if (fn->fn_flags & RTN_RTINFO) return fn; } } - +#ifdef CONFIG_IPV6_SUBTREES +backtrack: +#endif if (fn->fn_flags & RTN_ROOT) break; @@ -1269,24 +1308,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, fn = fib6_repair_tree(net, fn); } - if (atomic_read(&rt->rt6i_ref) != 1) { - /* This route is used as dummy address holder in some split - * nodes. It is not leaked, but it still holds other resources, - * which must be released in time. So, scan ascendant nodes - * and replace dummy references to this route with references - * to still alive ones. - */ - while (fn) { - if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { - fn->leaf = fib6_find_prefix(net, fn); - atomic_inc(&fn->leaf->rt6i_ref); - rt6_release(rt); - } - fn = fn->parent; - } - /* No more references are possible at this point. */ - BUG_ON(atomic_read(&rt->rt6i_ref) != 1); - } + fib6_purge_rt(rt, fn, net); inet6_rt_notify(RTM_DELROUTE, rt, info); rt6_release(rt); @@ -1403,7 +1425,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w) if (w->skip) { w->skip--; - continue; + goto skip; } err = w->func(w); @@ -1413,6 +1435,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w) w->count++; continue; } +skip: w->state = FWS_U; case FWS_U: if (fn == w->root) diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 46e88433ec7d..f0ccdb787100 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -453,8 +453,10 @@ static int mem_check(struct sock *sk) if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK) return 0; + rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) count++; + rcu_read_unlock_bh(); if (room <= 0 || ((count >= FL_MAX_PER_SOCK || diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index ecd60733e5e2..65156a73b3f3 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -512,11 +512,11 @@ static int ip6gre_rcv(struct sk_buff *skb) skb->protocol = gre_proto; /* WCCP version 1 and 2 protocol decoding. - * - Change protocol to IP + * - Change protocol to IPv6 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) { - skb->protocol = htons(ETH_P_IP); + skb->protocol = htons(ETH_P_IPV6); if ((*(h + offset) & 0xF0) != 0x40) offset += 4; } @@ -620,7 +620,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, struct ip6_tnl *tunnel = netdev_priv(dev); struct net_device *tdev; /* Device to other host */ struct ipv6hdr *ipv6h; /* Our new IP header */ - unsigned int max_headroom; /* The extra header space needed */ + unsigned int max_headroom = 0; /* The extra header space needed */ int gre_hlen; struct ipv6_tel_txoption opt; int mtu; @@ -693,7 +693,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, tunnel->err_count = 0; } - max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; + max_headroom += LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len; if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { @@ -787,7 +787,7 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_IPIP; + fl6.flowi6_proto = IPPROTO_GRE; dsfield = ipv4_get_dsfield(iph); @@ -837,7 +837,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_IPV6; + fl6.flowi6_proto = IPPROTO_GRE; dsfield = ipv6_get_dsfield(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) @@ -962,8 +962,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) else dev->flags &= ~IFF_POINTOPOINT; - dev->iflink = p->link; - /* Precalculate GRE options length */ if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) { if (t->parms.o_flags&GRE_CSUM) @@ -1267,6 +1265,8 @@ static int ip6gre_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; + dev->iflink = tunnel->parms.link; + return 0; } @@ -1282,7 +1282,6 @@ static void ip6gre_fb_tunnel_init(struct net_device *dev) dev_hold(dev); } - static struct inet6_protocol ip6gre_protocol __read_mostly = { .handler = ip6gre_rcv, .err_handler = ip6gre_err, @@ -1458,6 +1457,8 @@ static int ip6gre_tap_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; + dev->iflink = tunnel->parms.link; + return 0; } @@ -1549,6 +1550,15 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], return 0; } +static void ip6gre_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + if (dev != ign->fb_tunnel_dev) + unregister_netdevice_queue(dev, head); +} + static size_t ip6gre_get_size(const struct net_device *dev) { return @@ -1626,6 +1636,7 @@ static struct rtnl_link_ops ip6gre_link_ops __read_mostly = { .validate = ip6gre_tunnel_validate, .newlink = ip6gre_newlink, .changelink = ip6gre_changelink, + .dellink = ip6gre_dellink, .get_size = ip6gre_get_size, .fill_info = ip6gre_fill_info, }; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 2bab2aa59745..774b09cb2920 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -49,7 +49,7 @@ int ip6_rcv_finish(struct sk_buff *skb) { - if (sysctl_ip_early_demux && !skb_dst(skb)) { + if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { const struct inet6_protocol *ipprot; ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d5d20cde8d92..1ce7ea1f40b7 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -130,7 +130,7 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_lock_bh(); - nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + nexthop = rt6_nexthop((struct rt6_info *)dst); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); @@ -141,8 +141,8 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_unlock_bh(); - IP6_INC_STATS_BH(dev_net(dst->dev), - ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } @@ -150,7 +150,8 @@ static int ip6_finish_output2(struct sk_buff *skb) static int ip6_finish_output(struct sk_buff *skb) { if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || - dst_allfrag(skb_dst(skb))) + dst_allfrag(skb_dst(skb)) || + (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(skb, ip6_finish_output2); else return ip6_finish_output2(skb); @@ -344,6 +345,24 @@ static inline int ip6_forward_finish(struct sk_buff *skb) return dst_output(skb); } +static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu) + return false; + + /* ipv6 conntrack defrag sets max_frag_size + local_df */ + if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) + return true; + + if (skb->local_df) + return false; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -466,8 +485,7 @@ int ip6_forward(struct sk_buff *skb) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) || - (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) { + if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); @@ -522,6 +540,23 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } +static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +{ + static u32 ip6_idents_hashrnd __read_mostly; + static bool hashrnd_initialized = false; + u32 hash, id; + + if (unlikely(!hashrnd_initialized)) { + hashrnd_initialized = true; + get_random_bytes(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); + } + hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd); + hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash); + + id = ip_idents_reserve(hash, 1); + fhdr->identification = htonl(id); +} + int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; @@ -898,7 +933,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, */ rt = (struct rt6_info *) *dst; rcu_read_lock_bh(); - n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt)); err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock_bh(); @@ -1039,6 +1074,8 @@ static inline int ip6_ufo_append_data(struct sock *sk, * udp datagram */ if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) { + struct frag_hdr fhdr; + skb = sock_alloc_send_skb(sk, hh_len + fragheaderlen + transhdrlen + 20, (flags & MSG_DONTWAIT), &err); @@ -1059,12 +1096,6 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - } - - err = skb_append_datato_frags(sk,skb, getfrag, from, - (length - transhdrlen)); - if (!err) { - struct frag_hdr fhdr; /* Specify the length of each IPv6 datagram fragment. * It has to be a multiple of 8. @@ -1075,15 +1106,10 @@ static inline int ip6_ufo_append_data(struct sock *sk, ipv6_select_ident(&fhdr, rt); skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); - - return 0; } - /* There is not enough support do UPD LSO, - * so follow normal path - */ - kfree_skb(skb); - return err; + return skb_append_datato_frags(sk, skb, getfrag, from, + (length - transhdrlen)); } static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, @@ -1098,23 +1124,24 @@ 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, +static void ip6_append_data_mtu(unsigned int *mtu, int *maxfraglen, unsigned int fragheaderlen, struct sk_buff *skb, - struct rt6_info *rt) + struct rt6_info *rt, + unsigned int orig_mtu) { if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { if (skb == NULL) { /* first fragment, reserve header_len */ - *mtu = *mtu - rt->dst.header_len; + *mtu = orig_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); + *mtu = orig_mtu; } *maxfraglen = ((*mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); @@ -1131,11 +1158,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, struct ipv6_pinfo *np = inet6_sk(sk); struct inet_cork *cork; struct sk_buff *skb, *skb_prev = NULL; - unsigned int maxfraglen, fragheaderlen; + unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu; int exthdrlen; int dst_exthdrlen; int hh_len; - int mtu; int copy; int err; int offset = 0; @@ -1214,6 +1240,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, dst_exthdrlen = 0; mtu = cork->fragsize; } + orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1248,27 +1275,28 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, * --yoshfuji */ - cork->length += length; - if (length > mtu) { - int proto = sk->sk_protocol; - if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){ - ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); - return -EMSGSIZE; - } - - if (proto == IPPROTO_UDP && - (rt->dst.dev->features & NETIF_F_UFO)) { + if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_RAW)) { + ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen); + return -EMSGSIZE; + } - err = ip6_ufo_append_data(sk, getfrag, from, length, - hh_len, fragheaderlen, - transhdrlen, mtu, flags, rt); - if (err) - goto error; - return 0; - } + skb = skb_peek_tail(&sk->sk_write_queue); + cork->length += length; + if (((length > mtu) || + (skb && skb_has_frags(skb))) && + (sk->sk_protocol == IPPROTO_UDP) && + (rt->dst.dev->features & NETIF_F_UFO) && + (sk->sk_type == SOCK_DGRAM)) { + err = ip6_ufo_append_data(sk, getfrag, from, length, + hh_len, fragheaderlen, + transhdrlen, mtu, flags, rt); + if (err) + goto error; + return 0; } - if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) + if (!skb) goto alloc_new_skb; while (length > 0) { @@ -1292,7 +1320,8 @@ alloc_new_skb: /* update mtu and maxfraglen if necessary */ if (skb == NULL || skb_prev == NULL) ip6_append_data_mtu(&mtu, &maxfraglen, - fragheaderlen, skb, rt); + fragheaderlen, skb, rt, + orig_mtu); skb_prev = skb; @@ -1547,8 +1576,8 @@ int ip6_push_pending_frames(struct sock *sk) if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type); - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); + ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } err = ip6_local_out(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 1e55866cead7..14f46af17704 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -61,6 +61,7 @@ MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("ip6tnl"); MODULE_ALIAS_NETDEV("ip6tnl0"); #ifdef IP6_TNL_DEBUG @@ -264,9 +265,6 @@ static int ip6_tnl_create2(struct net_device *dev) int err; t = netdev_priv(dev); - err = ip6_tnl_dev_init(dev); - if (err < 0) - goto out; err = register_netdevice(dev); if (err < 0) @@ -1432,6 +1430,7 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) static const struct net_device_ops ip6_tnl_netdev_ops = { + .ndo_init = ip6_tnl_dev_init, .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_xmit, .ndo_do_ioctl = ip6_tnl_ioctl, @@ -1513,16 +1512,10 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - int err = ip6_tnl_dev_init_gen(dev); - - if (err) - return err; t->parms.proto = IPPROTO_IPV6; dev_hold(dev); - ip6_tnl_link_config(t); - rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } @@ -1531,7 +1524,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) { u8 proto; - if (!data) + if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); @@ -1617,6 +1610,15 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], return ip6_tnl_update(t, &p); } +static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + + if (dev != ip6n->fb_tnl_dev) + unregister_netdevice_queue(dev, head); +} + static size_t ip6_tnl_get_size(const struct net_device *dev) { return @@ -1646,9 +1648,9 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr), - &parm->raddr) || - nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), &parm->laddr) || + nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr), + &parm->raddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || @@ -1681,6 +1683,7 @@ static struct rtnl_link_ops ip6_link_ops __read_mostly = { .validate = ip6_tnl_validate, .newlink = ip6_tnl_newlink, .changelink = ip6_tnl_changelink, + .dellink = ip6_tnl_dellink, .get_size = ip6_tnl_get_size, .fill_info = ip6_tnl_fill_info, }; @@ -1732,6 +1735,7 @@ static int __net_init ip6_tnl_init_net(struct net *net) if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); + ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops; err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 241fb8ad9fcf..2c84072b1da7 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -141,9 +141,12 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, struct mr6_table **mrt) { - struct ip6mr_result res; - struct fib_lookup_arg arg = { .result = &res, }; int err; + struct ip6mr_result res; + struct fib_lookup_arg arg = { + .result = &res, + .flags = FIB_LOOKUP_NOREF, + }; err = fib_rules_lookup(net->ipv6.mr6_rules_ops, flowi6_to_flowi(flp6), 0, &arg); @@ -259,10 +262,12 @@ static void __net_exit ip6mr_rules_exit(struct net *net) { struct mr6_table *mrt, *next; + rtnl_lock(); list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) { list_del(&mrt->list); ip6mr_free_table(mrt); } + rtnl_unlock(); fib_rules_unregister(net->ipv6.mr6_rules_ops); } #else @@ -289,7 +294,10 @@ static int __net_init ip6mr_rules_init(struct net *net) static void __net_exit ip6mr_rules_exit(struct net *net) { + rtnl_lock(); ip6mr_free_table(net->ipv6.mrt6); + net->ipv6.mrt6 = NULL; + rtnl_unlock(); } #endif @@ -2343,13 +2351,14 @@ int ip6mr_get_route(struct net *net, } static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - u32 portid, u32 seq, struct mfc6_cache *c, int cmd) + u32 portid, u32 seq, struct mfc6_cache *c, int cmd, + int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; - nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -2417,7 +2426,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, if (skb == NULL) goto errout; - err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd); + err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; @@ -2456,7 +2465,8 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (ip6mr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) goto done; next_entry: e++; @@ -2470,7 +2480,8 @@ next_entry: if (ip6mr_fill_mroute(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE) < 0) { + mfc, RTM_NEWROUTE, + NLM_F_MULTI) < 0) { spin_unlock_bh(&mfc_unres_lock); goto done; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index bfa6cc36ef2a..734aec059ffd 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1343,8 +1343,9 @@ static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb, hdr->daddr = *daddr; } -static struct sk_buff *mld_newpack(struct net_device *dev, int size) +static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size) { + struct net_device *dev = idev->dev; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.igmp_sk; struct sk_buff *skb; @@ -1369,7 +1370,7 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size) skb_reserve(skb, hlen); - if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { + if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. @@ -1438,11 +1439,12 @@ static void mld_sendpack(struct sk_buff *skb) dst_output); out: if (!err) { - ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT); - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); - IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); - } else - IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS); + ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); + } else { + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + } rcu_read_unlock(); return; @@ -1465,7 +1467,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, struct mld2_grec *pgr; if (!skb) - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(pmc->idev, dev->mtu); if (!skb) return NULL; pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec)); @@ -1485,7 +1487,8 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) { - struct net_device *dev = pmc->idev->dev; + struct inet6_dev *idev = pmc->idev; + struct net_device *dev = idev->dev; struct mld2_report *pmr; struct mld2_grec *pgr = NULL; struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list; @@ -1514,7 +1517,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(idev, dev->mtu); } } first = 1; @@ -1541,7 +1544,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); - skb = mld_newpack(dev, dev->mtu); + skb = mld_newpack(idev, dev->mtu); first = 1; scount = 0; } @@ -1596,8 +1599,8 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) struct sk_buff *skb = NULL; int type; + read_lock_bh(&idev->lock); if (!pmc) { - read_lock_bh(&idev->lock); for (pmc=idev->mc_list; pmc; pmc=pmc->next) { if (pmc->mca_flags & MAF_NOREPORT) continue; @@ -1609,7 +1612,6 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->mca_lock); } - read_unlock_bh(&idev->lock); } else { spin_lock_bh(&pmc->mca_lock); if (pmc->mca_sfcount[MCAST_EXCLUDE]) @@ -1619,6 +1621,7 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->mca_lock); } + read_unlock_bh(&idev->lock); if (skb) mld_sendpack(skb); } @@ -2156,7 +2159,7 @@ static void mld_gq_timer_expire(unsigned long data) idev->mc_gq_running = 0; mld_send_report(idev, NULL); - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_timer_expire(unsigned long data) @@ -2169,7 +2172,7 @@ static void mld_ifc_timer_expire(unsigned long data) if (idev->mc_ifc_count) mld_ifc_start_timer(idev, idev->mc_maxdelay); } - __in6_dev_put(idev); + in6_dev_put(idev); } static void mld_ifc_event(struct inet6_dev *idev) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index ca4ffcc287f1..05f361338c2e 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -372,14 +372,11 @@ static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, int tlen = dev->needed_tailroom; struct sock *sk = dev_net(dev)->ipv6.ndisc_sk; struct sk_buff *skb; - int err; - skb = sock_alloc_send_skb(sk, - hlen + sizeof(struct ipv6hdr) + len + tlen, - 1, &err); + skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC); if (!skb) { - ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb, err=%d\n", - __func__, err); + ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n", + __func__); return NULL; } @@ -389,6 +386,11 @@ static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, skb_reserve(skb, hlen + sizeof(struct ipv6hdr)); skb_reset_transport_header(skb); + /* Manually assign socket ownership as we avoid calling + * sock_alloc_send_pskb() to bypass wmem buffer limits + */ + skb_set_owner_w(skb, sk); + return skb; } @@ -1191,7 +1193,14 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt) rt6_set_expires(rt, jiffies + (HZ * lifetime)); if (ra_msg->icmph.icmp6_hop_limit) { - in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + /* Only set hop_limit on the interface if it is higher than + * the current hop_limit. + */ + if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) { + in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + } else { + ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n"); + } if (rt) dst_metric_set(&rt->dst, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 95f3f1da0d7f..d38e6a8d8b9f 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -30,13 +30,15 @@ int ip6_route_me_harder(struct sk_buff *skb) .daddr = iph->daddr, .saddr = iph->saddr, }; + int err; dst = ip6_route_output(net, skb->sk, &fl6); - if (dst->error) { + err = dst->error; + if (err) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n"); dst_release(dst); - return dst->error; + return err; } /* Drop old route. */ diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 44400c216dc6..89a4e4ddd8bb 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1236,8 +1236,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, - sizeof(struct xt_counters) * num_counters) != 0) - ret = -EFAULT; + sizeof(struct xt_counters) * num_counters) != 0) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); + } vfree(counters); xt_table_unlock(t); return ret; diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index c9b6a6e6a1e8..97cd7507c1a4 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -172,63 +172,13 @@ out: return nf_conntrack_confirm(skb); } -static unsigned int __ipv6_conntrack_in(struct net *net, - unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct sk_buff *reasm = skb->nfct_reasm; - const struct nf_conn_help *help; - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - - /* This packet is fragmented and has reassembled packet. */ - if (reasm) { - /* Reassembled packet isn't parsed yet ? */ - if (!reasm->nfct) { - unsigned int ret; - - ret = nf_conntrack_in(net, PF_INET6, hooknum, reasm); - if (ret != NF_ACCEPT) - return ret; - } - - /* Conntrack helpers need the entire reassembled packet in the - * POST_ROUTING hook. In case of unconfirmed connections NAT - * might reassign a helper, so the entire packet is also - * required. - */ - ct = nf_ct_get(reasm, &ctinfo); - if (ct != NULL && !nf_ct_is_untracked(ct)) { - help = nfct_help(ct); - if ((help && help->helper) || !nf_ct_is_confirmed(ct)) { - nf_conntrack_get_reasm(reasm); - NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm, - (struct net_device *)in, - (struct net_device *)out, - okfn, NF_IP6_PRI_CONNTRACK + 1); - return NF_DROP_ERR(-ECANCELED); - } - } - - nf_conntrack_get(reasm->nfct); - skb->nfct = reasm->nfct; - skb->nfctinfo = reasm->nfctinfo; - return NF_ACCEPT; - } - - return nf_conntrack_in(net, PF_INET6, hooknum, skb); -} - static unsigned int ipv6_conntrack_in(unsigned int hooknum, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn); + return nf_conntrack_in(dev_net(in), PF_INET6, hooknum, skb); } static unsigned int ipv6_conntrack_local(unsigned int hooknum, @@ -242,7 +192,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum, net_notice_ratelimited("ipv6_conntrack_local: packet too short\n"); return NF_ACCEPT; } - return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn); + return nf_conntrack_in(dev_net(out), PF_INET6, hooknum, skb); } static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index dffdc1a389c5..253566a8d55b 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -621,31 +621,16 @@ ret_orig: return skb; } -void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, - struct net_device *in, struct net_device *out, - int (*okfn)(struct sk_buff *)) +void nf_ct_frag6_consume_orig(struct sk_buff *skb) { struct sk_buff *s, *s2; - unsigned int ret = 0; for (s = NFCT_FRAG6_CB(skb)->orig; s;) { - nf_conntrack_put_reasm(s->nfct_reasm); - nf_conntrack_get_reasm(skb); - s->nfct_reasm = skb; - s2 = s->next; s->next = NULL; - - if (ret != -ECANCELED) - ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s, - in, out, okfn, - NF_IP6_PRI_CONNTRACK_DEFRAG + 1); - else - kfree_skb(s); - + consume_skb(s); s = s2; } - nf_conntrack_put_reasm(skb); } static int nf_ct_net_init(struct net *net) diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index aacd121fe8c5..581dd9ede0de 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -75,8 +75,11 @@ static unsigned int ipv6_defrag(unsigned int hooknum, if (reasm == skb) return NF_ACCEPT; - nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in, - (struct net_device *)out, okfn); + nf_ct_frag6_consume_orig(reasm); + + NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm, + (struct net_device *) in, (struct net_device *) out, + okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1); return NF_STOLEN; } diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index c2e73e647e44..a5d465105b69 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -6,34 +6,6 @@ #include <net/ipv6.h> #include <net/ip6_fib.h> -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) -{ - static atomic_t ipv6_fragmentation_id; - int old, new; - -#if IS_ENABLED(CONFIG_IPV6) - if (rt && !(rt->dst.flags & DST_NOPEER)) { - struct inet_peer *peer; - struct net *net; - - net = dev_net(rt->dst.dev); - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); - if (peer) { - fhdr->identification = htonl(inet_getid(peer, 0)); - inet_putpeer(peer); - return; - } - } -#endif - do { - old = atomic_read(&ipv6_fragmentation_id); - new = old + 1; - if (!new) - new = 1; - } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); - fhdr->identification = htonl(new); -} -EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index eedff8ccded5..464b1c9c08e4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -459,14 +459,11 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, if (flags & MSG_OOB) return -EOPNOTSUPP; - if (addr_len) - *addr_len=sizeof(*sin6); - if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) @@ -500,6 +497,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, IP6CB(skb)->iif); + *addr_len = sizeof(*sin6); } sock_recv_ts_and_drops(msg, sk, skb); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 790d9f4b8b0b..1aeb473b2cc6 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -490,6 +490,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, ipv6_hdr(head)->payload_len = htons(payload_len); ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); IP6CB(head)->nhoff = nhoff; + IP6CB(head)->flags |= IP6SKB_FRAGMENTED; /* Yes, and fold redundant checksum back. 8) */ if (head->ip_summed == CHECKSUM_COMPLETE) @@ -524,6 +525,9 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct net *net = dev_net(skb_dst(skb)->dev); int evicted; + if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) + goto fail_hdr; + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS); /* Jumbo payload inhibits frag. header */ @@ -544,6 +548,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS); IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb); + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; return 1; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ad0aa6b0b86a..d94d224f7e68 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -65,6 +65,12 @@ #include <linux/sysctl.h> #endif +enum rt6_nud_state { + RT6_NUD_FAIL_HARD = -2, + RT6_NUD_FAIL_SOFT = -1, + RT6_NUD_SUCCEED = 1 +}; + static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, const struct in6_addr *dest); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); @@ -78,6 +84,8 @@ static int ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct sk_buff *skb); +static int ip6_pkt_prohibit(struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); @@ -101,7 +109,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) u32 *p = NULL; if (!(rt->dst.flags & DST_HOST)) - return NULL; + return dst_cow_metrics_generic(dst, old); peer = rt6_get_peer_create(rt); if (peer) { @@ -227,9 +235,6 @@ static const struct rt6_info ip6_null_entry_template = { #ifdef CONFIG_IPV6_MULTIPLE_TABLES -static int ip6_pkt_prohibit(struct sk_buff *skb); -static int ip6_pkt_prohibit_out(struct sk_buff *skb); - static const struct rt6_info ip6_prohibit_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), @@ -467,6 +472,24 @@ out: } #ifdef CONFIG_IPV6_ROUTER_PREF +struct __rt6_probe_work { + struct work_struct work; + struct in6_addr target; + struct net_device *dev; +}; + +static void rt6_probe_deferred(struct work_struct *w) +{ + struct in6_addr mcaddr; + struct __rt6_probe_work *work = + container_of(w, struct __rt6_probe_work, work); + + addrconf_addr_solict_mult(&work->target, &mcaddr); + ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL); + dev_put(work->dev); + kfree(w); +} + static void rt6_probe(struct rt6_info *rt) { struct neighbour *neigh; @@ -490,17 +513,23 @@ static void rt6_probe(struct rt6_info *rt) if (!neigh || time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { - struct in6_addr mcaddr; - struct in6_addr *target; + struct __rt6_probe_work *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (neigh) { + if (neigh && work) neigh->updated = jiffies; + + if (neigh) write_unlock(&neigh->lock); - } - target = (struct in6_addr *)&rt->rt6i_gateway; - addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } } else { out: write_unlock(&neigh->lock); @@ -527,26 +556,29 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif) return 0; } -static inline bool rt6_check_neigh(struct rt6_info *rt) +static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt) { struct neighbour *neigh; - bool ret = false; + enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) - return true; + return RT6_NUD_SUCCEED; rcu_read_lock_bh(); neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (neigh) { read_lock(&neigh->lock); if (neigh->nud_state & NUD_VALID) - ret = true; + ret = RT6_NUD_SUCCEED; #ifdef CONFIG_IPV6_ROUTER_PREF else if (!(neigh->nud_state & NUD_FAILED)) - ret = true; + ret = RT6_NUD_SUCCEED; #endif read_unlock(&neigh->lock); + } else { + ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? + RT6_NUD_SUCCEED : RT6_NUD_FAIL_SOFT; } rcu_read_unlock_bh(); @@ -560,43 +592,52 @@ static int rt6_score_route(struct rt6_info *rt, int oif, m = rt6_check_dev(rt, oif); if (!m && (strict & RT6_LOOKUP_F_IFACE)) - return -1; + return RT6_NUD_FAIL_HARD; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; #endif - if (!rt6_check_neigh(rt) && (strict & RT6_LOOKUP_F_REACHABLE)) - return -1; + if (strict & RT6_LOOKUP_F_REACHABLE) { + int n = rt6_check_neigh(rt); + if (n < 0) + return n; + } return m; } static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, - int *mpri, struct rt6_info *match) + int *mpri, struct rt6_info *match, + bool *do_rr) { int m; + bool match_do_rr = false; if (rt6_check_expired(rt)) goto out; m = rt6_score_route(rt, oif, strict); - if (m < 0) + if (m == RT6_NUD_FAIL_SOFT && !IS_ENABLED(CONFIG_IPV6_ROUTER_PREF)) { + match_do_rr = true; + m = 0; /* lowest valid score */ + } else if (m < 0) { goto out; + } + + if (strict & RT6_LOOKUP_F_REACHABLE) + rt6_probe(rt); if (m > *mpri) { - if (strict & RT6_LOOKUP_F_REACHABLE) - rt6_probe(match); + *do_rr = match_do_rr; *mpri = m; match = rt; - } else if (strict & RT6_LOOKUP_F_REACHABLE) { - rt6_probe(rt); } - out: return match; } static struct rt6_info *find_rr_leaf(struct fib6_node *fn, struct rt6_info *rr_head, - u32 metric, int oif, int strict) + u32 metric, int oif, int strict, + bool *do_rr) { struct rt6_info *rt, *match; int mpri = -1; @@ -604,10 +645,10 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = NULL; for (rt = rr_head; rt && rt->rt6i_metric == metric; rt = rt->dst.rt6_next) - match = find_match(rt, oif, strict, &mpri, match); + match = find_match(rt, oif, strict, &mpri, match, do_rr); for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric; rt = rt->dst.rt6_next) - match = find_match(rt, oif, strict, &mpri, match); + match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; } @@ -616,15 +657,16 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) { struct rt6_info *match, *rt0; struct net *net; + bool do_rr = false; rt0 = fn->rr_ptr; if (!rt0) fn->rr_ptr = rt0 = fn->leaf; - match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict); + match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict, + &do_rr); - if (!match && - (strict & RT6_LOOKUP_F_REACHABLE)) { + if (do_rr) { struct rt6_info *next = rt0->dst.rt6_next; /* no entries matched; do round-robin */ @@ -685,8 +727,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, prefix = &prefix_buf; } - rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, - dev->ifindex); + if (rinfo->prefix_len == 0) + rt = rt6_get_dflt_router(gwaddr, dev); + else + rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, + gwaddr, dev->ifindex); if (rt && !lifetime) { ip6_del_rt(rt); @@ -829,7 +874,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; - rt->rt6i_gateway = *daddr; } rt->rt6i_flags |= RTF_CACHE; @@ -1042,10 +1086,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev))) return NULL; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) - return dst; + if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) + return NULL; - return NULL; + if (rt6_check_expired(rt)) + return NULL; + + return dst; } static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) @@ -1074,10 +1121,13 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { - if (rt->rt6i_flags & RTF_CACHE) - rt6_update_expires(rt, 0); - else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) + if (rt->rt6i_flags & RTF_CACHE) { + dst_hold(&rt->dst); + if (ip6_del_rt(rt)) + dst_free(&rt->dst); + } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { rt->rt6i_node->fn_sernum = -1; + } } } @@ -1091,12 +1141,9 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct net *net = dev_net(dst->dev); rt6->rt6i_flags |= RTF_MODIFIED; - if (mtu < IPV6_MIN_MTU) { - u32 features = dst_metric(dst, RTAX_FEATURES); + if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - features |= RTAX_FEATURE_ALLFRAG; - dst_metric_set(dst, RTAX_FEATURES, features); - } + dst_metric_set(dst, RTAX_MTU, mtu); rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires); } @@ -1186,7 +1233,7 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; mtu = IPV6_MIN_MTU; @@ -1196,7 +1243,8 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) mtu = idev->cnf.mtu6; rcu_read_unlock(); - return mtu; +out: + return min_t(unsigned int, mtu, IP6_MAX_MTU); } static struct dst_entry *icmp6_dst_gc_list; @@ -1223,6 +1271,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; atomic_set(&rt->dst.__refcnt, 1); + rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; @@ -1377,7 +1426,7 @@ int ip6_route_add(struct fib6_config *cfg) if (!table) goto out; - rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table); + rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table); if (!rt) { err = -ENOMEM; @@ -1446,21 +1495,24 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } } - rt->dst.output = ip6_pkt_discard_out; - rt->dst.input = ip6_pkt_discard; rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP; switch (cfg->fc_type) { case RTN_BLACKHOLE: rt->dst.error = -EINVAL; + rt->dst.output = dst_discard; + rt->dst.input = dst_discard; break; case RTN_PROHIBIT: rt->dst.error = -EACCES; + rt->dst.output = ip6_pkt_prohibit_out; + rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: - rt->dst.error = -EAGAIN; - break; default: - rt->dst.error = -ENETUNREACH; + rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN + : -ENETUNREACH; + rt->dst.output = ip6_pkt_discard_out; + rt->dst.input = ip6_pkt_discard; break; } goto install_route; @@ -1779,11 +1831,12 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, in6_dev_hold(rt->rt6i_idev); rt->dst.lastuse = jiffies; - rt->rt6i_gateway = ort->rt6i_gateway; + if (ort->rt6i_flags & RTF_GATEWAY) + rt->rt6i_gateway = ort->rt6i_gateway; + else + rt->rt6i_gateway = *dest; rt->rt6i_flags = ort->rt6i_flags; - if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == - (RTF_DEFAULT | RTF_ADDRCONF)) - rt6_set_from(rt, ort); + rt6_set_from(rt, ort); rt->rt6i_metric = 0; #ifdef CONFIG_IPV6_SUBTREES @@ -2022,8 +2075,6 @@ static int ip6_pkt_discard_out(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } -#ifdef CONFIG_IPV6_MULTIPLE_TABLES - static int ip6_pkt_prohibit(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); @@ -2035,8 +2086,6 @@ static int ip6_pkt_prohibit_out(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } -#endif - /* * Allocate a dst for local (unicast / anycast) address. */ @@ -2046,12 +2095,10 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, bool anycast) { struct net *net = dev_net(idev->dev); - struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL); - - if (!rt) { - net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n"); + struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, + DST_NOCOUNT, NULL); + if (!rt) return ERR_PTR(-ENOMEM); - } in6_dev_hold(idev); @@ -2066,6 +2113,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, else rt->rt6i_flags |= RTF_LOCAL; + rt->rt6i_gateway = *addr; rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 335363478bbf..4ddf67c6355b 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -101,19 +101,19 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && - (!dev || !t->parms.link || dev->iflink == t->parms.link) && + (!dev || !t->parms.link || dev->ifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } @@ -530,12 +530,12 @@ static int ipip6_err(struct sk_buff *skb, u32 info) if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, - t->dev->ifindex, 0, IPPROTO_IPV6, 0); + t->parms.link, 0, IPPROTO_IPV6, 0); err = 0; goto out; } if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0, + ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, IPPROTO_IPV6, 0); err = 0; goto out; @@ -566,6 +566,70 @@ static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, return false; } +/* Checks if an address matches an address on the tunnel interface. + * Used to detect the NAT of proto 41 packets and let them pass spoofing test. + * Long story: + * This function is called after we considered the packet as spoofed + * in is_spoofed_6rd. + * We may have a router that is doing NAT for proto 41 packets + * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb + * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd + * function will return true, dropping the packet. + * But, we can still check if is spoofed against the IP + * addresses associated with the interface. + */ +static bool only_dnatted(const struct ip_tunnel *tunnel, + const struct in6_addr *v6dst) +{ + int prefix_len; + +#ifdef CONFIG_IPV6_SIT_6RD + prefix_len = tunnel->ip6rd.prefixlen + 32 + - tunnel->ip6rd.relay_prefixlen; +#else + prefix_len = 48; +#endif + return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev); +} + +/* Returns true if a packet is spoofed */ +static bool packet_is_spoofed(struct sk_buff *skb, + const struct iphdr *iph, + struct ip_tunnel *tunnel) +{ + const struct ipv6hdr *ipv6h; + + if (tunnel->dev->priv_flags & IFF_ISATAP) { + if (!isatap_chksrc(skb, iph, tunnel)) + return true; + + return false; + } + + if (tunnel->dev->flags & IFF_POINTOPOINT) + return false; + + ipv6h = ipv6_hdr(skb); + + if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) { + net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; + } + + if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr))) + return false; + + if (only_dnatted(tunnel, &ipv6h->daddr)) + return false; + + net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n", + &iph->saddr, &ipv6h->saddr, + &iph->daddr, &ipv6h->daddr); + return true; +} + static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); @@ -584,19 +648,9 @@ static int ipip6_rcv(struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); skb->pkt_type = PACKET_HOST; - if (tunnel->dev->priv_flags & IFF_ISATAP) { - if (!isatap_chksrc(skb, iph, tunnel)) { - tunnel->dev->stats.rx_errors++; - goto out; - } - } else { - if (is_spoofed_6rd(tunnel, iph->saddr, - &ipv6_hdr(skb)->saddr) || - is_spoofed_6rd(tunnel, iph->daddr, - &ipv6_hdr(skb)->daddr)) { - tunnel->dev->stats.rx_errors++; - goto out; - } + if (packet_is_spoofed(skb, iph, tunnel)) { + tunnel->dev->stats.rx_errors++; + goto out; } __skb_tunnel_rx(skb, tunnel->dev); @@ -713,7 +767,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - net_dbg_ratelimited("sit: nexthop == NULL\n"); + net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -742,7 +796,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { - net_dbg_ratelimited("sit: nexthop == NULL\n"); + net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } @@ -865,7 +919,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, iph->ttl = iph6->hop_limit; skb->ip_summed = CHECKSUM_NONE; - ip_select_ident(iph, skb_dst(skb), NULL); + ip_select_ident(skb, NULL); iptunnel_xmit(skb, dev); return NETDEV_TX_OK; @@ -1453,6 +1507,15 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { #endif }; +static void ipip6_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct sit_net *sitn = net_generic(net, sit_net_id); + + if (dev != sitn->fb_tunnel_dev) + unregister_netdevice_queue(dev, head); +} + static struct rtnl_link_ops sit_link_ops __read_mostly = { .kind = "sit", .maxtype = IFLA_IPTUN_MAX, @@ -1463,6 +1526,7 @@ static struct rtnl_link_ops sit_link_ops __read_mostly = { .changelink = ipip6_changelink, .get_size = ipip6_get_size, .fill_info = ipip6_fill_info, + .dellink = ipip6_dellink, }; static struct xfrm_tunnel sit_handler __read_mostly = { @@ -1507,6 +1571,7 @@ static int __net_init sit_init_net(struct net *net) goto err_alloc_dev; } dev_net_set(sitn->fb_tunnel_dev, net); + sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops; err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); if (err) @@ -1589,4 +1654,5 @@ xfrm_tunnel_failed: module_init(sit_init); module_exit(sit_cleanup); MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0a17ed9eaf39..4659b8ab55d9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1426,7 +1426,7 @@ ipv6_pktoptions: if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; if (np->rxopt.bits.rxtclass) - np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb)) { skb_set_owner_r(opt_skb, sk); opt_skb = xchg(&np->pktoptions, opt_skb); @@ -1616,7 +1616,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); @@ -1651,6 +1651,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif + .mtu_reduced = tcp_v6_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG @@ -1682,6 +1683,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, #endif + .mtu_reduced = tcp_v4_mtu_reduced, }; #ifdef CONFIG_TCP_MD5SIG @@ -1919,7 +1921,6 @@ struct proto tcpv6_prot = { .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, - .mtu_reduced = tcp_v6_mtu_reduced, .hash = tcp_v6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 42923b14dfa6..6b298dc614e3 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -373,14 +373,11 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, int is_udp4; bool slow; - if (addr_len) - *addr_len = sizeof(struct sockaddr_in6); - if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), @@ -461,7 +458,7 @@ try_again: ipv6_iface_scope_id(&sin6->sin6_addr, IP6CB(skb)->iif); } - + *addr_len = sizeof(*sin6); } if (is_udp4) { if (inet->cmsg_flags) @@ -955,11 +952,16 @@ static int udp_v6_push_pending_frames(struct sock *sk) struct udphdr *uh; struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); - struct flowi6 *fl6 = &inet->cork.fl.u.ip6; + struct flowi6 *fl6; int err = 0; int is_udplite = IS_UDPLITE(sk); __wsum csum = 0; + if (up->pending == AF_INET) + return udp_push_pending_frames(sk); + + fl6 = &inet->cork.fl.u.ip6; + /* Grab the skbuff where UDP header space exists. */ if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) goto out; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index d3cfaf9c7a08..2f65b022627b 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -85,7 +85,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, /* Check if there is enough headroom to insert fragment header. */ tnl_hlen = skb_tnl_header_len(skb); - if (skb_headroom(skb) < (tnl_hlen + frag_hdr_sz)) { + if (skb_mac_header(skb) < skb->head + tnl_hlen + frag_hdr_sz) { if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) goto out; } @@ -108,7 +108,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; - ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); + fptr->identification = skb_shinfo(skb)->ip6_frag_id; /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index f547a47d381c..2665bf4b8d05 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1778,6 +1778,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, struct ipxhdr *ipx = NULL; struct sk_buff *skb; int copied, rc; + bool locked = true; lock_sock(sk); /* put the autobinding in */ @@ -1804,6 +1805,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, if (sock_flag(sk, SOCK_ZAPPED)) goto out; + release_sock(sk); + locked = false; skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &rc); if (!skb) @@ -1823,8 +1826,6 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, if (skb->tstamp.tv64) sk->sk_stamp = skb->tstamp; - msg->msg_namelen = sizeof(*sipx); - if (sipx) { sipx->sipx_family = AF_IPX; sipx->sipx_port = ipx->ipx_source.sock; @@ -1832,13 +1833,15 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, sipx->sipx_network = IPX_SKB_CB(skb)->ipx_source_net; sipx->sipx_type = ipx->ipx_type; sipx->sipx_zero = 0; + msg->msg_namelen = sizeof(*sipx); } rc = copied; out_free: skb_free_datagram(sk, skb); out: - release_sock(sk); + if (locked) + release_sock(sk); return rc; } diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 0578d4fa00a9..a5e62ef57155 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1385,8 +1385,6 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock, IRDA_DEBUG(4, "%s()\n", __func__); - msg->msg_namelen = 0; - skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &err); if (!skb) @@ -1451,8 +1449,6 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock, target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, noblock); - msg->msg_namelen = 0; - do { int chunk; struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue); diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 41ac7938268b..2ee29ed13bd4 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -820,7 +820,9 @@ static void ircomm_tty_wait_until_sent(struct tty_struct *tty, int timeout) orig_jiffies = jiffies; /* Set poll time to 200 ms */ - poll_time = IRDA_MIN(timeout, msecs_to_jiffies(200)); + poll_time = msecs_to_jiffies(200); + if (timeout) + poll_time = min_t(unsigned long, timeout, poll_time); spin_lock_irqsave(&self->spinlock, flags); while (self->tx_skb && self->tx_skb->len) { diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index ae691651b721..215e9b008db6 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1324,8 +1324,6 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, int err = 0; u32 offset; - msg->msg_namelen = 0; - if ((sk->sk_state == IUCV_DISCONN) && skb_queue_empty(&iucv->backlog_skb_q) && skb_queue_empty(&sk->sk_receive_queue) && @@ -1831,7 +1829,7 @@ static void iucv_callback_txdone(struct iucv_path *path, spin_lock_irqsave(&list->lock, flags); while (list_skb != (struct sk_buff *)list) { - if (msg->tag != IUCV_SKB_CB(list_skb)->tag) { + if (msg->tag == IUCV_SKB_CB(list_skb)->tag) { this = list_skb; break; } diff --git a/net/key/af_key.c b/net/key/af_key.c index 9da862070dd8..66f51c5a8a3a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2081,6 +2081,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * pol->sadb_x_policy_type = IPSEC_POLICY_NONE; } pol->sadb_x_policy_dir = dir+1; + pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; pol->sadb_x_policy_priority = xp->priority; @@ -3137,7 +3138,9 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = XFRM_POLICY_OUT + 1; + pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; + pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ if (x->id.proto == IPPROTO_AH) @@ -3525,6 +3528,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = dir + 1; + pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = 0; pol->sadb_x_policy_priority = 0; @@ -3619,7 +3623,6 @@ static int pfkey_recvmsg(struct kiocb *kiocb, if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT)) goto out; - msg->msg_namelen = 0; skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 6984c3a353cd..8c27de2b4d5a 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -115,6 +115,11 @@ struct l2tp_net { static void l2tp_session_set_header_len(struct l2tp_session *session, int version); static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); +static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) +{ + return sk->sk_user_data; +} + static inline struct l2tp_net *l2tp_pernet(struct net *net) { BUG_ON(!net); @@ -507,7 +512,7 @@ static inline int l2tp_verify_udp_checksum(struct sock *sk, return 0; #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) { + if (sk->sk_family == PF_INET6 && !l2tp_tunnel(sk)->v4mapped) { if (!uh->check) { LIMIT_NETDEBUG(KERN_INFO "L2TP: IPv6: checksum is 0\n"); return 1; @@ -1071,7 +1076,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->local_df = 1; #if IS_ENABLED(CONFIG_IPV6) - if (skb->sk->sk_family == PF_INET6) + if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped) error = inet6_csk_xmit(skb, NULL); else #endif @@ -1198,7 +1203,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) + if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) l2tp_xmit_ipv6_csum(sk, skb, udp_len); else #endif @@ -1247,10 +1252,9 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); */ static void l2tp_tunnel_destruct(struct sock *sk) { - struct l2tp_tunnel *tunnel; + struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); struct l2tp_net *pn; - tunnel = sk->sk_user_data; if (tunnel == NULL) goto end; @@ -1618,7 +1622,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 } /* Check if this socket has already been prepped */ - tunnel = (struct l2tp_tunnel *)sk->sk_user_data; + tunnel = l2tp_tunnel(sk); if (tunnel != NULL) { /* This socket has already been prepped */ err = -EBUSY; @@ -1647,6 +1651,24 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 if (cfg != NULL) tunnel->debug = cfg->debug; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == PF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + + if (ipv6_addr_v4mapped(&np->saddr) && + ipv6_addr_v4mapped(&np->daddr)) { + struct inet_sock *inet = inet_sk(sk); + + tunnel->v4mapped = true; + inet->inet_saddr = np->saddr.s6_addr32[3]; + inet->inet_rcv_saddr = np->rcv_saddr.s6_addr32[3]; + inet->inet_daddr = np->daddr.s6_addr32[3]; + } else { + tunnel->v4mapped = false; + } + } +#endif + /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */ tunnel->encap = encap; if (encap == L2TP_ENCAPTYPE_UDP) { @@ -1655,7 +1677,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv; udp_sk(sk)->encap_destroy = l2tp_udp_encap_destroy; #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) + if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) udpv6_encap_enable(); else #endif diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 485a490fd990..2f89d43877d7 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -189,6 +189,9 @@ struct l2tp_tunnel { struct sock *sock; /* Parent socket */ int fd; /* Parent fd, if tunnel socket * was created by userspace */ +#if IS_ENABLED(CONFIG_IPV6) + bool v4mapped; +#endif struct work_struct del_work; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 571db8dd2292..da1a1cee1a08 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -518,9 +518,6 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m if (flags & MSG_OOB) goto out; - if (addr_len) - *addr_len = sizeof(*sin); - skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; @@ -543,6 +540,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m sin->sin_addr.s_addr = ip_hdr(skb)->saddr; sin->sin_port = 0; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index b8a6039314e8..e6e8408c9e36 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -665,7 +665,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, *addr_len = sizeof(*lsa); if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 8dec6876dc50..c3ae2411650c 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -197,8 +197,6 @@ static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock, if (sk->sk_state & PPPOX_BOUND) goto end; - msg->msg_namelen = 0; - err = 0; skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &err); @@ -353,7 +351,9 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh goto error_put_sess_tun; } + local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); + local_bh_enable(); sock_put(ps->tunnel_sock); sock_put(sk); @@ -422,7 +422,9 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) skb->data[0] = ppph[0]; skb->data[1] = ppph[1]; + local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); + local_bh_enable(); sock_put(sk_tun); sock_put(sk); @@ -752,9 +754,10 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, session->deref = pppol2tp_session_sock_put; /* If PMTU discovery was enabled, use the MTU that was discovered */ - dst = sk_dst_get(sk); + dst = sk_dst_get(tunnel->sock); if (dst != NULL) { - u32 pmtu = dst_mtu(__sk_dst_get(sk)); + u32 pmtu = dst_mtu(dst); + if (pmtu != 0) session->mtu = session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD; @@ -1363,7 +1366,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, int err; if (level != SOL_PPPOL2TP) - return udp_prot.setsockopt(sk, level, optname, optval, optlen); + return -EINVAL; if (optlen < sizeof(int)) return -EINVAL; @@ -1489,7 +1492,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, struct pppol2tp_session *ps; if (level != SOL_PPPOL2TP) - return udp_prot.getsockopt(sk, level, optname, optval, optlen); + return -EINVAL; if (get_user(len, optlen)) return -EFAULT; @@ -1793,7 +1796,8 @@ static const struct proto_ops pppol2tp_ops = { static const struct pppox_proto pppol2tp_proto = { .create = pppol2tp_create, - .ioctl = pppol2tp_ioctl + .ioctl = pppol2tp_ioctl, + .owner = THIS_MODULE, }; #ifdef CONFIG_L2TP_V3 diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 48aaa89253e0..c3ee80547066 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -715,13 +715,11 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, unsigned long cpu_flags; size_t copied = 0; u32 peek_seq = 0; - u32 *seq; + u32 *seq, skb_len; unsigned long used; int target; /* Read at least this many bytes */ long timeo; - msg->msg_namelen = 0; - lock_sock(sk); copied = -ENOTCONN; if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN)) @@ -814,6 +812,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, } continue; found_ok_skb: + skb_len = skb->len; /* Ok so how much can we use? */ used = skb->len - offset; if (len < used) @@ -846,7 +845,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, } /* Partial read */ - if (used + offset < skb->len) + if (used + offset < skb_len) continue; } while (len > 0); diff --git a/net/llc/sysctl_net_llc.c b/net/llc/sysctl_net_llc.c index 612a5ddaf93b..799bafc2af39 100644 --- a/net/llc/sysctl_net_llc.c +++ b/net/llc/sysctl_net_llc.c @@ -18,28 +18,28 @@ static struct ctl_table llc2_timeout_table[] = { { .procname = "ack", .data = &sysctl_llc2_ack_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_ack_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "busy", .data = &sysctl_llc2_busy_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_busy_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "p", .data = &sysctl_llc2_p_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_p_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "rej", .data = &sysctl_llc2_rej_timeout, - .maxlen = sizeof(long), + .maxlen = sizeof(sysctl_llc2_rej_timeout), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 4fdb306e42e0..e922bf3f422c 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -652,6 +652,8 @@ static void ieee80211_get_et_stats(struct wiphy *wiphy, if (sta->sdata->dev != dev) continue; + sinfo.filled = 0; + sta_set_sinfo(sta, &sinfo); i = 0; ADD_STA_STATS(sta); } @@ -973,8 +975,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, IEEE80211_P2P_OPPPS_ENABLE_BIT; err = ieee80211_assign_beacon(sdata, ¶ms->beacon); - if (err < 0) + if (err < 0) { + ieee80211_vif_release_channel(sdata); return err; + } changed |= err; err = drv_start_ap(sdata->local, sdata); @@ -983,6 +987,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (old) kfree_rcu(old, rcu_head); RCU_INIT_POINTER(sdata->u.ap.beacon, NULL); + ieee80211_vif_release_channel(sdata); return err; } @@ -2354,8 +2359,7 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - if (sdata->vif.type != NL80211_IFTYPE_STATION && - sdata->vif.type != NL80211_IFTYPE_MESH_POINT) + if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS)) @@ -2475,6 +2479,24 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, INIT_DELAYED_WORK(&roc->work, ieee80211_sw_roc_work); INIT_LIST_HEAD(&roc->dependents); + /* + * cookie is either the roc cookie (for normal roc) + * or the SKB (for mgmt TX) + */ + if (!txskb) { + /* local->mtx protects this */ + local->roc_cookie_counter++; + roc->cookie = local->roc_cookie_counter; + /* wow, you wrapped 64 bits ... more likely a bug */ + if (WARN_ON(roc->cookie == 0)) { + roc->cookie = 1; + local->roc_cookie_counter++; + } + *cookie = roc->cookie; + } else { + *cookie = (unsigned long)txskb; + } + /* if there's one pending or we're scanning, queue this one */ if (!list_empty(&local->roc_list) || local->scanning || local->radar_detect_enabled) @@ -2609,24 +2631,6 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, if (!queued) list_add_tail(&roc->list, &local->roc_list); - /* - * cookie is either the roc cookie (for normal roc) - * or the SKB (for mgmt TX) - */ - if (!txskb) { - /* local->mtx protects this */ - local->roc_cookie_counter++; - roc->cookie = local->roc_cookie_counter; - /* wow, you wrapped 64 bits ... more likely a bug */ - if (WARN_ON(roc->cookie == 0)) { - roc->cookie = 1; - local->roc_cookie_counter++; - } - *cookie = roc->cookie; - } else { - *cookie = (unsigned long)txskb; - } - return 0; } @@ -3313,7 +3317,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, return -EINVAL; } band = chanctx_conf->def.chan->band; - sta = sta_info_get(sdata, peer); + sta = sta_info_get_bss(sdata, peer); if (sta) { qos = test_sta_flag(sta, WLAN_STA_WME); } else { diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 14abcf44f974..2d5b4f65c519 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -34,8 +34,7 @@ static ssize_t ieee80211_if_read( ssize_t ret = -EINVAL; read_lock(&dev_base_lock); - if (sdata->dev->reg_state == NETREG_REGISTERED) - ret = (*format)(sdata, buf, sizeof(buf)); + ret = (*format)(sdata, buf, sizeof(buf)); read_unlock(&dev_base_lock); if (ret >= 0) @@ -62,8 +61,7 @@ static ssize_t ieee80211_if_write( ret = -ENODEV; rtnl_lock(); - if (sdata->dev->reg_state == NETREG_REGISTERED) - ret = (*write)(sdata, buf, count); + ret = (*write)(sdata, buf, count); rtnl_unlock(); return ret; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 170f9a7fa319..3052672e37f7 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1166,6 +1166,7 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED | BSS_CHANGED_IBSS); + ieee80211_vif_release_channel(sdata); synchronize_rcu(); kfree(presp); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 9ca8e3278cc0..9f0ea9d8be73 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -60,13 +60,24 @@ struct ieee80211_local; #define IEEE80211_UNSET_POWER_LEVEL INT_MIN /* - * Some APs experience problems when working with U-APSD. Decrease the - * probability of that happening by using legacy mode for all ACs but VO. - * The AP that caused us trouble was a Cisco 4410N. It ignores our - * setting, and always treats non-VO ACs as legacy. + * Some APs experience problems when working with U-APSD. Decreasing the + * probability of that happening by using legacy mode for all ACs but VO isn't + * enough. + * + * Cisco 4410N originally forced us to enable VO by default only because it + * treated non-VO ACs as legacy. + * + * However some APs (notably Netgear R7000) silently reclassify packets to + * different ACs. Since u-APSD ACs require trigger frames for frame retrieval + * clients would never see some frames (e.g. ARP responses) or would fetch them + * accidentally after a long time. + * + * It makes little sense to enable u-APSD queues by default because it needs + * userspace applications to be aware of it to actually take advantage of the + * possible additional powersavings. Implicitly depending on driver autotrigger + * frame support doesn't make much sense. */ -#define IEEE80211_DEFAULT_UAPSD_QUEUES \ - IEEE80211_WMM_IE_STA_QOSINFO_AC_VO +#define IEEE80211_DEFAULT_UAPSD_QUEUES 0 #define IEEE80211_DEFAULT_MAX_SP_LEN \ IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL @@ -311,6 +322,7 @@ struct ieee80211_roc_work { bool started, abort, hw_begun, notified; bool to_be_freed; + bool on_channel; unsigned long hw_start_time; @@ -842,6 +854,8 @@ struct tpt_led_trigger { * that the scan completed. * @SCAN_ABORTED: Set for our scan work function when the driver reported * a scan complete for an aborted scan. + * @SCAN_HW_CANCELLED: Set for our scan work function when the scan is being + * cancelled. */ enum { SCAN_SW_SCANNING, @@ -849,6 +863,7 @@ enum { SCAN_ONCHANNEL_SCANNING, SCAN_COMPLETED, SCAN_ABORTED, + SCAN_HW_CANCELLED, }; /** @@ -1267,6 +1282,7 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata); void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata); void ieee80211_mgd_conn_tx_status(struct ieee80211_sub_if_data *sdata, __le16 fc, bool acked); +void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata); /* IBSS code */ diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 98d20c0f6fed..2c64ab27b515 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1726,6 +1726,15 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) dev_close(sdata->dev); + /* + * Close all AP_VLAN interfaces first, as otherwise they + * might be closed while the AP interface they belong to + * is closed, causing unregister_netdevice_many() to crash. + */ + list_for_each_entry(sdata, &local->interfaces, list) + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + dev_close(sdata->dev); + mutex_lock(&local->iflist_mtx); list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del(&sdata->list); @@ -1737,7 +1746,6 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) } mutex_unlock(&local->iflist_mtx); unregister_netdevice_many(&unreg_list); - list_del(&unreg_list); list_for_each_entry_safe(sdata, tmp, &wdev_list, list) { list_del(&sdata->list); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 67059b88fea5..635d0972b688 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -607,7 +607,7 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local, int i; mutex_lock(&local->key_mtx); - for (i = 0; i < NUM_DEFAULT_KEYS; i++) { + for (i = 0; i < ARRAY_SIZE(sta->gtk); i++) { key = key_mtx_dereference(local, sta->gtk[i]); if (!key) continue; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 8a7bfc47d577..6658c5809353 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -157,6 +157,8 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local) list_for_each_entry_rcu(sdata, &local->interfaces, list) { if (!rcu_access_pointer(sdata->vif.chanctx_conf)) continue; + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + continue; power = min(power, sdata->vif.bss_conf.txpower); } rcu_read_unlock(); diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c index 3b7bfc01ee36..ddda201832b3 100644 --- a/net/mac80211/mesh_ps.c +++ b/net/mac80211/mesh_ps.c @@ -36,6 +36,7 @@ static struct sk_buff *mps_qos_null_get(struct sta_info *sta) sdata->vif.addr); nullfunc->frame_control = fc; nullfunc->duration_id = 0; + nullfunc->seq_ctrl = 0; /* no address resolution for this frame -> set addr 1 immediately */ memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); memset(skb_put(skb, 2), 0, 2); /* append QoS control field */ diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 741448b30825..e606e4a113e1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -31,10 +31,12 @@ #include "led.h" #define IEEE80211_AUTH_TIMEOUT (HZ / 5) +#define IEEE80211_AUTH_TIMEOUT_LONG (HZ / 2) #define IEEE80211_AUTH_TIMEOUT_SHORT (HZ / 10) #define IEEE80211_AUTH_MAX_TRIES 3 #define IEEE80211_AUTH_WAIT_ASSOC (HZ * 5) #define IEEE80211_ASSOC_TIMEOUT (HZ / 5) +#define IEEE80211_ASSOC_TIMEOUT_LONG (HZ / 2) #define IEEE80211_ASSOC_TIMEOUT_SHORT (HZ / 10) #define IEEE80211_ASSOC_MAX_TRIES 3 @@ -237,8 +239,9 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *channel, const struct ieee80211_ht_operation *ht_oper, const struct ieee80211_vht_operation *vht_oper, - struct cfg80211_chan_def *chandef, bool verbose) + struct cfg80211_chan_def *chandef, bool tracking) { + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct cfg80211_chan_def vht_chandef; u32 ht_cfreq, ret; @@ -257,7 +260,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan, channel->band); /* check that channel matches the right operating channel */ - if (channel->center_freq != ht_cfreq) { + if (!tracking && channel->center_freq != ht_cfreq) { /* * It's possible that some APs are confused here; * Netgear WNDR3700 sometimes reports 4 higher than @@ -265,11 +268,10 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, * since we look at probe response/beacon data here * it should be OK. */ - if (verbose) - sdata_info(sdata, - "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n", - channel->center_freq, ht_cfreq, - ht_oper->primary_chan, channel->band); + sdata_info(sdata, + "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n", + channel->center_freq, ht_cfreq, + ht_oper->primary_chan, channel->band); ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; goto out; } @@ -308,6 +310,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, switch (vht_oper->chan_width) { case IEEE80211_VHT_CHANWIDTH_USE_HT: vht_chandef.width = chandef->width; + vht_chandef.center_freq1 = chandef->center_freq1; break; case IEEE80211_VHT_CHANWIDTH_80MHZ: vht_chandef.width = NL80211_CHAN_WIDTH_80; @@ -323,7 +326,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, channel->band); break; default: - if (verbose) + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) sdata_info(sdata, "AP VHT operation IE has invalid channel width (%d), disable VHT\n", vht_oper->chan_width); @@ -332,7 +335,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, } if (!cfg80211_chandef_valid(&vht_chandef)) { - if (verbose) + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) sdata_info(sdata, "AP VHT information is invalid, disable VHT\n"); ret = IEEE80211_STA_DISABLE_VHT; @@ -345,7 +348,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, } if (!cfg80211_chandef_compatible(chandef, &vht_chandef)) { - if (verbose) + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) sdata_info(sdata, "AP VHT information doesn't match HT, disable VHT\n"); ret = IEEE80211_STA_DISABLE_VHT; @@ -357,22 +360,53 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, ret = 0; out: + /* + * When tracking the current AP, don't do any further checks if the + * new chandef is identical to the one we're currently using for the + * connection. This keeps us from playing ping-pong with regulatory, + * without it the following can happen (for example): + * - connect to an AP with 80 MHz, world regdom allows 80 MHz + * - AP advertises regdom US + * - CRDA loads regdom US with 80 MHz prohibited (old database) + * - the code below detects an unsupported channel, downgrades, and + * we disconnect from the AP in the caller + * - disconnect causes CRDA to reload world regdomain and the game + * starts anew. + * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881) + * + * It seems possible that there are still scenarios with CSA or real + * bandwidth changes where a this could happen, but those cases are + * less common and wouldn't completely prevent using the AP. + */ + if (tracking && + cfg80211_chandef_identical(chandef, &sdata->vif.bss_conf.chandef)) + return ret; + /* don't print the message below for VHT mismatch if VHT is disabled */ if (ret & IEEE80211_STA_DISABLE_VHT) vht_chandef = *chandef; + /* + * Ignore the DISABLED flag when we're already connected and only + * tracking the APs beacon for bandwidth changes - otherwise we + * might get disconnected here if we connect to an AP, update our + * regulatory information based on the AP's country IE and the + * information we have is wrong/outdated and disables the channel + * that we're actually using for the connection to the AP. + */ while (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef, - IEEE80211_CHAN_DISABLED)) { + tracking ? 0 : + IEEE80211_CHAN_DISABLED)) { if (WARN_ON(chandef->width == NL80211_CHAN_WIDTH_20_NOHT)) { ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; - goto out; + break; } ret |= chandef_downgrade(chandef); } - if (chandef->width != vht_chandef.width && verbose) + if (chandef->width != vht_chandef.width && !tracking) sdata_info(sdata, "capabilities/regulatory prevented using AP HT/VHT configuration, downgraded\n"); @@ -412,7 +446,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, /* calculate new channel (type) based on HT/VHT operation IEs */ flags = ieee80211_determine_chantype(sdata, sband, chan, ht_oper, - vht_oper, &chandef, false); + vht_oper, &chandef, true); /* * Downgrade the new channel if we associated with restricted @@ -3461,10 +3495,13 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata) if (tx_flags == 0) { auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT; - ifmgd->auth_data->timeout_started = true; + auth_data->timeout_started = true; run_again(ifmgd, auth_data->timeout); } else { - auth_data->timeout_started = false; + auth_data->timeout = + round_jiffies_up(jiffies + IEEE80211_AUTH_TIMEOUT_LONG); + auth_data->timeout_started = true; + run_again(ifmgd, auth_data->timeout); } return 0; @@ -3501,7 +3538,11 @@ static int ieee80211_do_assoc(struct ieee80211_sub_if_data *sdata) assoc_data->timeout_started = true; run_again(&sdata->u.mgd, assoc_data->timeout); } else { - assoc_data->timeout_started = false; + assoc_data->timeout = + round_jiffies_up(jiffies + + IEEE80211_ASSOC_TIMEOUT_LONG); + assoc_data->timeout_started = true; + run_again(&sdata->u.mgd, assoc_data->timeout); } return 0; @@ -3713,6 +3754,32 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) } #ifdef CONFIG_PM +void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + + mutex_lock(&ifmgd->mtx); + + if (ifmgd->auth_data) { + /* + * If we are trying to authenticate while suspending, cfg80211 + * won't know and won't actually abort those attempts, thus we + * need to do that ourselves. + */ + ieee80211_send_deauth_disassoc(sdata, + ifmgd->auth_data->bss->bssid, + IEEE80211_STYPE_DEAUTH, + WLAN_REASON_DEAUTH_LEAVING, + false, frame_buf); + ieee80211_destroy_auth_data(sdata, false); + cfg80211_send_deauth(sdata->dev, frame_buf, + IEEE80211_DEAUTH_FRAME_LEN); + } + + mutex_unlock(&ifmgd->mtx); +} + void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -3906,7 +3973,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= ieee80211_determine_chantype(sdata, sband, cbss->channel, ht_oper, vht_oper, - &chandef, true); + &chandef, false); sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss), local->rx_chains); @@ -4328,8 +4395,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); if (bss->wmm_used && bss->uapsd_supported && - (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD) && - sdata->wmm_acm != 0xff) { + (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) { assoc_data->uapsd = true; ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED; } else { diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index acd1f71adc03..0427a58b4397 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -333,7 +333,7 @@ void ieee80211_sw_roc_work(struct work_struct *work) container_of(work, struct ieee80211_roc_work, work.work); struct ieee80211_sub_if_data *sdata = roc->sdata; struct ieee80211_local *local = sdata->local; - bool started; + bool started, on_channel; mutex_lock(&local->mtx); @@ -354,13 +354,24 @@ void ieee80211_sw_roc_work(struct work_struct *work) if (!roc->started) { struct ieee80211_roc_work *dep; - /* start this ROC */ + WARN_ON(local->use_chanctx); + + /* If actually operating on the desired channel (with at least + * 20 MHz channel width) don't stop all the operations but still + * treat it as though the ROC operation started properly, so + * other ROC operations won't interfere with this one. + */ + roc->on_channel = roc->chan == local->_oper_chandef.chan; - /* switch channel etc */ + /* start this ROC */ ieee80211_recalc_idle(local); - local->tmp_channel = roc->chan; - ieee80211_hw_config(local, 0); + if (!roc->on_channel) { + ieee80211_offchannel_stop_vifs(local); + + local->tmp_channel = roc->chan; + ieee80211_hw_config(local, 0); + } /* tell userspace or send frame */ ieee80211_handle_roc_started(roc); @@ -379,9 +390,10 @@ void ieee80211_sw_roc_work(struct work_struct *work) finish: list_del(&roc->list); started = roc->started; + on_channel = roc->on_channel; ieee80211_roc_notify_destroy(roc, !roc->abort); - if (started) { + if (started && !on_channel) { ieee80211_flush_queues(local, NULL); local->tmp_channel = NULL; diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 7fc5d0d8149a..efb510e6f206 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -99,10 +99,21 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) } mutex_unlock(&local->sta_mtx); - /* remove all interfaces */ + /* remove all interfaces that were created in the driver */ list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_MONITOR: + continue; + case NL80211_IFTYPE_STATION: + ieee80211_mgd_quiesce(sdata); + break; + default: + break; + } + drv_remove_interface(local, sdata); } diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index a02bef35b134..d68d6cfac3b5 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -448,7 +448,7 @@ static void rate_fixup_ratelist(struct ieee80211_vif *vif, */ if (!(rates[0].flags & IEEE80211_TX_RC_MCS)) { u32 basic_rates = vif->bss_conf.basic_rates; - s8 baserate = basic_rates ? ffs(basic_rates - 1) : 0; + s8 baserate = basic_rates ? ffs(basic_rates) - 1 : 0; rate = &sband->bitrates[rates[0].idx]; diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index ac7ef5414bde..e6512e2ffd20 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -290,7 +290,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, struct minstrel_rate *msr, *mr; unsigned int ndx; bool mrr_capable; - bool prev_sample = mi->prev_sample; + bool prev_sample; int delta; int sampling_ratio; @@ -314,6 +314,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, (mi->sample_count + mi->sample_deferred / 2); /* delta < 0: no sampling required */ + prev_sample = mi->prev_sample; mi->prev_sample = false; if (delta < 0 || (!mrr_capable && prev_sample)) return; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 5b2d3012b983..f3bbea1eb9e7 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -804,10 +804,18 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, sample_group = &minstrel_mcs_groups[sample_idx / MCS_GROUP_RATES]; info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; + rate->count = 1; + + if (sample_idx / MCS_GROUP_RATES == MINSTREL_CCK_GROUP) { + int idx = sample_idx % ARRAY_SIZE(mp->cck_rates); + rate->idx = mp->cck_rates[idx]; + rate->flags = 0; + return; + } + rate->idx = sample_idx % MCS_GROUP_RATES + (sample_group->streams - 1) * MCS_GROUP_RATES; rate->flags = IEEE80211_TX_RC_MCS | sample_group->flags; - rate->count = 1; } static void @@ -820,6 +828,9 @@ minstrel_ht_update_cck(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, if (sband->band != IEEE80211_BAND_2GHZ) return; + if (!(mp->hw->flags & IEEE80211_HW_SUPPORTS_HT_CCK_RATES)) + return; + mi->cck_supported = 0; mi->cck_supported_short = 0; for (i = 0; i < 4; i++) { diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 8e2952620256..cd60be8d9aba 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -864,7 +864,8 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, u16 sc; u8 tid, ack_policy; - if (!ieee80211_is_data_qos(hdr->frame_control)) + if (!ieee80211_is_data_qos(hdr->frame_control) || + is_multicast_ether_addr(hdr->addr1)) goto dont_reorder; /* @@ -932,8 +933,14 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx) struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); - /* Drop duplicate 802.11 retransmissions (IEEE 802.11 Chap. 9.2.9) */ - if (rx->sta && !is_multicast_ether_addr(hdr->addr1)) { + /* + * Drop duplicate 802.11 retransmissions + * (IEEE 802.11-2012: 9.3.2.10 "Duplicate detection and recovery") + */ + if (rx->skb->len >= 24 && rx->sta && + !ieee80211_is_ctl(hdr->frame_control) && + !ieee80211_is_qos_nullfunc(hdr->frame_control) && + !is_multicast_ether_addr(hdr->addr1)) { if (unlikely(ieee80211_has_retry(hdr->frame_control) && rx->sta->last_seq_ctrl[rx->seqno_idx] == hdr->seq_ctrl)) { @@ -1578,11 +1585,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG; - if (likely((!ieee80211_has_morefrags(fc) && frag == 0) || - is_multicast_ether_addr(hdr->addr1))) { - /* not fragmented */ - goto out; + if (is_multicast_ether_addr(hdr->addr1)) { + rx->local->dot11MulticastReceivedFrameCount++; + goto out_no_led; } + + if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) + goto out; + I802_DEBUG_INC(rx->local->rx_handlers_fragments); if (skb_linearize(rx->skb)) @@ -1673,12 +1683,10 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) status->rx_flags |= IEEE80211_RX_FRAGMENTED; out: + ieee80211_led_rx(rx->local); + out_no_led: if (rx->sta) rx->sta->rx_packets++; - if (is_multicast_ether_addr(hdr->addr1)) - rx->local->dot11MulticastReceivedFrameCount++; - else - ieee80211_led_rx(rx->local); return RX_CONTINUE; } @@ -2015,6 +2023,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) hdr = (struct ieee80211_hdr *) skb->data; mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + if (ieee80211_drop_unencrypted(rx, hdr->frame_control)) + return RX_DROP_MONITOR; + /* frame is in RMC, don't forward */ if (ieee80211_is_data(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1) && @@ -2996,6 +3007,9 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, case NL80211_IFTYPE_ADHOC: if (!bssid) return 0; + if (ether_addr_equal(sdata->vif.addr, hdr->addr2) || + ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2)) + return 0; if (ieee80211_is_beacon(hdr->frame_control)) { return 1; } else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) { diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 99b103921a4b..eb03337b6545 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -202,6 +202,9 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) enum ieee80211_band band; int i, ielen, n_chans; + if (test_bit(SCAN_HW_CANCELLED, &local->scanning)) + return false; + do { if (local->hw_scan_band == IEEE80211_NUM_BANDS) return false; @@ -878,7 +881,23 @@ void ieee80211_scan_cancel(struct ieee80211_local *local) if (!local->scan_req) goto out; + /* + * We have a scan running and the driver already reported completion, + * but the worker hasn't run yet or is stuck on the mutex - mark it as + * cancelled. + */ + if (test_bit(SCAN_HW_SCANNING, &local->scanning) && + test_bit(SCAN_COMPLETED, &local->scanning)) { + set_bit(SCAN_HW_CANCELLED, &local->scanning); + goto out; + } + if (test_bit(SCAN_HW_SCANNING, &local->scanning)) { + /* + * Make sure that __ieee80211_scan_completed doesn't trigger a + * scan on another band. + */ + set_bit(SCAN_HW_CANCELLED, &local->scanning); if (local->ops->cancel_hw_scan) drv_cancel_hw_scan(local, rcu_dereference_protected(local->scan_sdata, diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 11216bc13b27..557a5760f9f6 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -270,6 +270,7 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr); + kfree(rcu_dereference_raw(sta->sta.rates)); kfree(sta); } @@ -339,6 +340,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, return NULL; spin_lock_init(&sta->lock); + spin_lock_init(&sta->ps_lock); INIT_WORK(&sta->drv_unblock_wk, sta_unblock); INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work); mutex_init(&sta->ampdu_mlme.mtx); @@ -1045,6 +1047,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) skb_queue_head_init(&pending); + /* sync with ieee80211_tx_h_unicast_ps_buf */ + spin_lock(&sta->ps_lock); /* Send all buffered frames to the station */ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { int count = skb_queue_len(&pending), tmp; @@ -1064,6 +1068,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) } ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta); + spin_unlock(&sta->ps_lock); local->total_ps_buffered -= buffered; @@ -1110,6 +1115,7 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN); memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN); + nullfunc->seq_ctrl = 0; skb->priority = tid; skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index adc30045f99e..3184b2b2853c 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -244,6 +244,7 @@ struct sta_ampdu_mlme { * @drv_unblock_wk: used for driver PS unblocking * @listen_interval: listen interval of this station, when we're acting as AP * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly + * @ps_lock: used for powersave (when mac80211 is the AP) related locking * @ps_tx_buf: buffers (per AC) of frames to transmit to this station * when it leaves power saving state or polls * @tx_filtered: buffers (per AC) of frames we already tried to @@ -324,10 +325,8 @@ struct sta_info { /* use the accessors defined below */ unsigned long _flags; - /* - * STA powersave frame queues, no more than the internal - * locking required. - */ + /* STA powersave lock and frame queues */ + spinlock_t ps_lock; struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS]; struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS]; unsigned long driver_buffered_tids; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 43439203f4e4..9e78206bd9bb 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -180,6 +180,9 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; + if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) + sta->last_rx = jiffies; + if (ieee80211_is_data_qos(mgmt->frame_control)) { struct ieee80211_hdr *hdr = (void *) skb->data; u8 *qc = ieee80211_get_qos_ctl(hdr); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 9972e07a2f96..10eea2326022 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -398,6 +398,9 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) if (ieee80211_has_order(hdr->frame_control)) return TX_CONTINUE; + if (ieee80211_is_probe_req(hdr->frame_control)) + return TX_CONTINUE; + /* no stations in PS mode */ if (!atomic_read(&ps->num_sta_ps)) return TX_CONTINUE; @@ -471,6 +474,20 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) sta->sta.addr, sta->sta.aid, ac); if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER) purge_old_ps_buffers(tx->local); + + /* sync with ieee80211_sta_ps_deliver_wakeup */ + spin_lock(&sta->ps_lock); + /* + * STA woke up the meantime and all the frames on ps_tx_buf have + * been queued to pending queue. No reordering can happen, go + * ahead and Tx the packet. + */ + if (!test_sta_flag(sta, WLAN_STA_PS_STA) && + !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) { + spin_unlock(&sta->ps_lock); + return TX_CONTINUE; + } + if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) { struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]); ps_dbg(tx->sdata, @@ -484,6 +501,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) info->control.vif = &tx->sdata->vif; info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb); + spin_unlock(&sta->ps_lock); if (!timer_pending(&local->sta_cleanup)) mod_timer(&local->sta_cleanup, @@ -511,7 +529,6 @@ ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx) { if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED)) return TX_CONTINUE; - if (tx->flags & IEEE80211_TX_UNICAST) return ieee80211_tx_h_unicast_ps_buf(tx); else @@ -851,7 +868,7 @@ static int ieee80211_fragment(struct ieee80211_tx_data *tx, } /* adjust first fragment's length */ - skb->len = hdrlen + per_fragm; + skb_trim(skb, hdrlen + per_fragm); return 0; } @@ -1100,7 +1117,8 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, tx->sta = rcu_dereference(sdata->u.vlan.sta); if (!tx->sta && sdata->dev->ieee80211_ptr->use_4addr) return TX_DROP; - } else if (info->flags & IEEE80211_TX_CTL_INJECTED || + } else if (info->flags & (IEEE80211_TX_CTL_INJECTED | + IEEE80211_TX_INTFL_NL80211_FRAME_TX) || tx->sdata->control_port_protocol == tx->skb->protocol) { tx->sta = sta_info_get_bss(sdata, hdr->addr1); } @@ -2692,7 +2710,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, cpu_to_le16(IEEE80211_FCTL_MOREDATA); } - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + if (sdata->vif.type == NL80211_IFTYPE_AP) sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev); if (!ieee80211_tx_prepare(sdata, &tx, skb)) break; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 72e6292955bb..5db8eb5d56cf 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2174,6 +2174,10 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, } rate = cfg80211_calculate_bitrate(&ri); + if (WARN_ONCE(!rate, + "Invalid bitrate: flags=0x%x, idx=%d, vht_nss=%d\n", + status->flag, status->rate_idx, status->vht_nss)) + return 0; /* rewind from end of MPDU */ if (status->flag & RX_FLAG_MACTIME_END) diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index afba19cb6f87..a282fddf8b00 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -153,6 +153,11 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, return IEEE80211_AC_BE; } + if (skb->protocol == sdata->control_port_protocol) { + skb->priority = 7; + return ieee80211_downgrade_queue(sdata, skb); + } + /* use the data classifier to determine what 802.1d tag the * data frame has */ skb->priority = cfg80211_classify8021d(skb); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index f77139007983..3b04dfd34554 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1754,6 +1754,12 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) if (*op < IP_SET_OP_VERSION) { /* Check the version at the beginning of operations */ struct ip_set_req_version *req_version = data; + + if (*len < sizeof(struct ip_set_req_version)) { + ret = -EINVAL; + goto done; + } + if (req_version->version != IPSET_PROTOCOL) { ret = -EPROTO; goto done; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 57beb1762b2d..707bc520d629 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -325,18 +325,22 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length) static void mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length) { - u8 i, j; - - for (i = 0; i < nets_length - 1 && h->nets[i].cidr != cidr; i++) - ; - h->nets[i].nets--; - - if (h->nets[i].nets != 0) - return; - - for (j = i; j < nets_length - 1 && h->nets[j].nets; j++) { - h->nets[j].cidr = h->nets[j + 1].cidr; - h->nets[j].nets = h->nets[j + 1].nets; + u8 i, j, net_end = nets_length - 1; + + for (i = 0; i < nets_length; i++) { + if (h->nets[i].cidr != cidr) + continue; + if (h->nets[i].nets > 1 || i == net_end || + h->nets[i + 1].nets == 0) { + h->nets[i].nets--; + return; + } + for (j = i; j < net_end && h->nets[j].nets; j++) { + h->nets[j].cidr = h->nets[j + 1].cidr; + h->nets[j].nets = h->nets[j + 1].nets; + } + h->nets[j].nets = 0; + return; } } #endif diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index a083bda322b6..90e756cf6e52 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -797,7 +797,6 @@ static void ip_vs_conn_expire(unsigned long data) ip_vs_control_del(cp); if (cp->flags & IP_VS_CONN_F_NFCT) { - ip_vs_conn_drop_conntrack(cp); /* Do not access conntracks during subsys cleanup * because nf_conntrack_find_get can not be used after * conntrack cleanup for the net. diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 23b8eb53a569..1c6a71c41e62 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -650,16 +650,24 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user) return err; } -static int ip_vs_route_me_harder(int af, struct sk_buff *skb) +static int ip_vs_route_me_harder(int af, struct sk_buff *skb, + unsigned int hooknum) { + if (!sysctl_snat_reroute(skb)) + return 0; + /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */ + if (NF_INET_LOCAL_IN == hooknum) + return 0; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0) + struct dst_entry *dst = skb_dst(skb); + + if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && + ip6_route_me_harder(skb) != 0) return 1; } else #endif - if ((sysctl_snat_reroute(skb) || - skb_rtable(skb)->rt_flags & RTCF_LOCAL) && + if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(skb, RTN_LOCAL) != 0) return 1; @@ -782,7 +790,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, __u8 protocol, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, - unsigned int offset, unsigned int ihl) + unsigned int offset, unsigned int ihl, + unsigned int hooknum) { unsigned int verdict = NF_DROP; @@ -812,7 +821,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, #endif ip_vs_nat_icmp(skb, pp, cp, 1); - if (ip_vs_route_me_harder(af, skb)) + if (ip_vs_route_me_harder(af, skb, hooknum)) goto out; /* do the statistics and put it back */ @@ -907,7 +916,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, - pp, ciph.len, ihl); + pp, ciph.len, ihl, hooknum); } #ifdef CONFIG_IP_VS_IPV6 @@ -972,7 +981,8 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, snet.in6 = ciph.saddr.in6; writable = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, - pp, writable, sizeof(struct ipv6hdr)); + pp, writable, sizeof(struct ipv6hdr), + hooknum); } #endif @@ -1031,7 +1041,8 @@ static inline bool is_new_conn(const struct sk_buff *skb, */ static unsigned int handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, - struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph, + unsigned int hooknum) { struct ip_vs_protocol *pp = pd->pp; @@ -1069,7 +1080,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, * if it came from this machine itself. So re-compute * the routing information. */ - if (ip_vs_route_me_harder(af, skb)) + if (ip_vs_route_me_harder(af, skb, hooknum)) goto drop; IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT"); @@ -1131,12 +1142,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iph_skb(af, skb, &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (!iph.fragoffs && skb_nfct_reasm(skb)) { - struct sk_buff *reasm = skb_nfct_reasm(skb); - /* Save fw mark for coming frags */ - reasm->ipvs_property = 1; - reasm->mark = skb->mark; - } if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_out_icmp_v6(skb, &related, @@ -1178,7 +1183,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) cp = pp->conn_out_get(af, skb, &iph, 0); if (likely(cp)) - return handle_response(af, skb, pd, cp, &iph); + return handle_response(af, skb, pd, cp, &iph, hooknum); if (sysctl_nat_icmp_send(net) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || @@ -1390,15 +1395,19 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) if (ipip) { __be32 info = ic->un.gateway; + __u8 type = ic->type; + __u8 code = ic->code; /* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { struct ip_vs_dest *dest = cp->dest; u32 mtu = ntohs(ic->un.frag.mtu); + __be16 frag_off = cih->frag_off; /* Strip outer IP and ICMP, go to IPIP header */ - __skb_pull(skb, ihl + sizeof(_icmph)); + if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL) + goto ignore_ipip; offset2 -= ihl + sizeof(_icmph); skb_reset_network_header(skb); IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n", @@ -1406,7 +1415,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) ipv4_update_pmtu(skb, dev_net(skb->dev), mtu, 0, 0, 0, 0); /* Client uses PMTUD? */ - if (!(cih->frag_off & htons(IP_DF))) + if (!(frag_off & htons(IP_DF))) goto ignore_ipip; /* Prefer the resulting PMTU */ if (dest) { @@ -1425,12 +1434,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) /* Strip outer IP, ICMP and IPIP, go to IP header of * original request. */ - __skb_pull(skb, offset2); + if (pskb_pull(skb, offset2) == NULL) + goto ignore_ipip; skb_reset_network_header(skb); IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, - ic->type, ic->code, ntohl(info)); - icmp_send(skb, ic->type, ic->code, info); + type, code, ntohl(info)); + icmp_send(skb, type, code, info); /* ICMP can be shorter but anyways, account it */ ip_vs_out_stats(cp, skb); @@ -1606,12 +1616,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (!iph.fragoffs && skb_nfct_reasm(skb)) { - struct sk_buff *reasm = skb_nfct_reasm(skb); - /* Save fw mark for coming frags. */ - reasm->ipvs_property = 1; - reasm->mark = skb->mark; - } if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum, @@ -1663,9 +1667,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, 0, "ip_vs_in: packet continues traversal as normal"); - if (iph.fragoffs && !skb_nfct_reasm(skb)) { + if (iph.fragoffs) { /* Fragment that couldn't be mapped to a conn entry - * and don't have any pointer to a reasm skb * is missing module nf_defrag_ipv6 */ IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); @@ -1748,38 +1751,6 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb, #ifdef CONFIG_IP_VS_IPV6 /* - * AF_INET6 fragment handling - * Copy info from first fragment, to the rest of them. - */ -static unsigned int -ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct sk_buff *reasm = skb_nfct_reasm(skb); - struct net *net; - - /* Skip if not a "replay" from nf_ct_frag6_output or first fragment. - * ipvs_property is set when checking first fragment - * in ip_vs_in() and ip_vs_out(). - */ - if (reasm) - IP_VS_DBG(2, "Fragment recv prop:%d\n", reasm->ipvs_property); - if (!reasm || !reasm->ipvs_property) - return NF_ACCEPT; - - net = skb_net(skb); - if (!net_ipvs(net)->enable) - return NF_ACCEPT; - - /* Copy stored fw mark, saved in ip_vs_{in,out} */ - skb->mark = reasm->mark; - - return NF_ACCEPT; -} - -/* * AF_INET6 handler in NF_INET_LOCAL_IN chain * Schedule and forward packets from remote clients */ @@ -1916,14 +1887,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .priority = 100, }, #ifdef CONFIG_IP_VS_IPV6 - /* After mangle & nat fetch 2:nd fragment and following */ - { - .hook = ip_vs_preroute_frag6, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_NAT_DST + 1, - }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, @@ -1946,7 +1909,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { { .hook = ip_vs_local_reply6, .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, + .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 77c173282f38..4a662f15eaee 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -183,6 +183,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, struct nf_conn *ct; struct net *net; + *diff = 0; + #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, * so turn this into a no-op for IPv6 packets @@ -191,8 +193,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; #endif - *diff = 0; - /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; @@ -321,6 +321,9 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, struct ip_vs_conn *n_cp; struct net *net; + /* no diff required for incoming packets */ + *diff = 0; + #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, * so turn this into a no-op for IPv6 packets @@ -329,9 +332,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; #endif - /* no diff required for incoming packets */ - *diff = 0; - /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index 9ef22bdce9f1..bed5f7042529 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -65,7 +65,6 @@ static int get_callid(const char *dptr, unsigned int dataoff, static int ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) { - struct sk_buff *reasm = skb_nfct_reasm(skb); struct ip_vs_iphdr iph; unsigned int dataoff, datalen, matchoff, matchlen; const char *dptr; @@ -79,15 +78,10 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) /* todo: IPv6 fragments: * I think this only should be done for the first fragment. /HS */ - if (reasm) { - skb = reasm; - dataoff = iph.thoff_reasm + sizeof(struct udphdr); - } else - dataoff = iph.len + sizeof(struct udphdr); + dataoff = iph.len + sizeof(struct udphdr); if (dataoff >= skb->len) return -EINVAL; - /* todo: Check if this will mess-up the reasm skb !!! /HS */ retc = skb_linearize(skb); if (retc < 0) return retc; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index f6046d9af8d3..e476cc7dc801 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -878,6 +878,8 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, IP_VS_DBG(2, "BACKUP, add new conn. failed\n"); return; } + if (!(flags & IP_VS_CONN_F_TEMPLATE)) + kfree(param->pe_data); } if (opt) @@ -1151,6 +1153,7 @@ static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end) (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) ); #endif + ip_vs_pe_put(param.pe); return 0; /* Error exit */ out: diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b75ff6429a04..1692e7534759 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -883,7 +883,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = old_iph->ttl; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -967,8 +967,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, iph->nexthdr = IPPROTO_IPV6; iph->payload_len = old_iph->payload_len; be16_add_cpu(&iph->payload_len, sizeof(*old_iph)); - iph->priority = old_iph->priority; memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl)); + ipv6_change_dsfield(iph, 0, ipv6_get_dsfield(old_iph)); iph->daddr = cp->daddr.in6; iph->saddr = saddr; iph->hop_limit = old_iph->hop_limit; diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index bdebd03bc8cd..70866d192efc 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -778,8 +778,8 @@ static int callforward_do_filter(const union nf_inet_addr *src, flowi6_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, flowi6_to_flowi(&fl2), false)) { - if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, - sizeof(rt1->rt6i_gateway)) && + if (ipv6_addr_equal(rt6_nexthop(rt1), + rt6_nexthop(rt2)) && rt1->dst.dev == rt2->dst.dev) ret = 1; dst_release(&rt2->dst); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index a99b6c3427b0..59359bec328a 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -428,7 +428,7 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, const char *msg; u_int8_t state; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh); + dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); BUG_ON(dh == NULL); state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE]; @@ -486,7 +486,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, u_int8_t type, old_state, new_state; enum ct_dccp_roles role; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh); + dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); BUG_ON(dh == NULL); type = dh->dccph_type; @@ -577,7 +577,7 @@ static int dccp_error(struct net *net, struct nf_conn *tmpl, unsigned int cscov; const char *msg; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh); + dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); if (dh == NULL) { msg = "nf_ct_dccp: short packet "; goto out_invalid; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index d25f29377648..957c1db66652 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -14,6 +14,30 @@ static unsigned int nf_ct_generic_timeout __read_mostly = 600*HZ; +static bool nf_generic_should_process(u8 proto) +{ + switch (proto) { +#ifdef CONFIG_NF_CT_PROTO_SCTP_MODULE + case IPPROTO_SCTP: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_DCCP_MODULE + case IPPROTO_DCCP: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE_MODULE + case IPPROTO_GRE: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE_MODULE + case IPPROTO_UDPLITE: + return false; +#endif + default: + return true; + } +} + static inline struct nf_generic_net *generic_pernet(struct net *net) { return &net->ct.nf_ct_proto.generic; @@ -67,7 +91,7 @@ static int generic_packet(struct nf_conn *ct, static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, unsigned int *timeouts) { - return true; + return nf_generic_should_process(nf_ct_protonum(ct)); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 4d4d8f1d01fc..7dcc376eea5f 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1043,6 +1043,12 @@ static int tcp_packet(struct nf_conn *ct, nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } + /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection + * pickup with loose=1. Avoid large ESTABLISHED timeout. + */ + if (new_state == TCP_CONNTRACK_ESTABLISHED && + timeout > timeouts[TCP_CONNTRACK_UNACK]) + timeout = timeouts[TCP_CONNTRACK_UNACK]; } else if (!test_bit(IPS_ASSURED_BIT, &ct->status) && (old_state == TCP_CONNTRACK_SYN_RECV || old_state == TCP_CONNTRACK_ESTABLISHED) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 038eee5c8f85..2bb801e3ee8c 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -487,6 +487,39 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data) return i->status & IPS_NAT_MASK ? 1 : 0; } +static int nf_nat_proto_clean(struct nf_conn *ct, void *data) +{ + struct nf_conn_nat *nat = nfct_nat(ct); + + if (nf_nat_proto_remove(ct, data)) + return 1; + + if (!nat || !nat->ct) + return 0; + + /* This netns is being destroyed, and conntrack has nat null binding. + * Remove it from bysource hash, as the table will be freed soon. + * + * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack() + * will delete entry from already-freed table. + */ + if (!del_timer(&ct->timeout)) + return 1; + + spin_lock_bh(&nf_nat_lock); + hlist_del_rcu(&nat->bysource); + ct->status &= ~IPS_NAT_DONE_MASK; + nat->ct = NULL; + spin_unlock_bh(&nf_nat_lock); + + add_timer(&ct->timeout); + + /* don't delete conntrack. Although that would make things a lot + * simpler, we'd end up flushing all conntracks on nat rmmod. + */ + return 0; +} + static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) { struct nf_nat_proto_clean clean = { @@ -749,7 +782,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) { struct nf_nat_proto_clean clean = {}; - nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); synchronize_rcu(); nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size); } diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c index f02b3605823e..1fb2258c3535 100644 --- a/net/netfilter/nf_nat_irc.c +++ b/net/netfilter/nf_nat_irc.c @@ -34,10 +34,14 @@ static unsigned int help(struct sk_buff *skb, struct nf_conntrack_expect *exp) { char buffer[sizeof("4294967296 65635")]; + struct nf_conn *ct = exp->master; + union nf_inet_addr newaddr; u_int16_t port; unsigned int ret; /* Reply comes from server. */ + newaddr = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3; + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; exp->dir = IP_CT_DIR_REPLY; exp->expectfn = nf_nat_follow_master; @@ -57,17 +61,35 @@ static unsigned int help(struct sk_buff *skb, } if (port == 0) { - nf_ct_helper_log(skb, exp->master, "all ports in use"); + nf_ct_helper_log(skb, ct, "all ports in use"); return NF_DROP; } - ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo, - protoff, matchoff, matchlen, buffer, - strlen(buffer)); + /* strlen("\1DCC CHAT chat AAAAAAAA P\1\n")=27 + * strlen("\1DCC SCHAT chat AAAAAAAA P\1\n")=28 + * strlen("\1DCC SEND F AAAAAAAA P S\1\n")=26 + * strlen("\1DCC MOVE F AAAAAAAA P S\1\n")=26 + * strlen("\1DCC TSEND F AAAAAAAA P S\1\n")=27 + * + * AAAAAAAAA: bound addr (1.0.0.0==16777216, min 8 digits, + * 255.255.255.255==4294967296, 10 digits) + * P: bound port (min 1 d, max 5d (65635)) + * F: filename (min 1 d ) + * S: size (min 1 d ) + * 0x01, \n: terminators + */ + /* AAA = "us", ie. where server normally talks to. */ + snprintf(buffer, sizeof(buffer), "%u %u", ntohl(newaddr.ip), port); + pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n", + buffer, &newaddr.ip, port); + + ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff, + matchlen, buffer, strlen(buffer)); if (ret != NF_ACCEPT) { - nf_ct_helper_log(skb, exp->master, "cannot mangle packet"); + nf_ct_helper_log(skb, ct, "cannot mangle packet"); nf_ct_unexpect_related(exp); } + return ret; } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 572d87dc116f..0a03662bfbef 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -147,7 +147,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) const struct nfnetlink_subsystem *ss; int type, err; - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (!netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; /* All the messages must at least contain nfgenmsg */ diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 962e9792e317..216261dd32ae 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -45,7 +45,8 @@ #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ -#define NFULNL_COPY_RANGE_MAX 0xFFFF /* max packet size is limited by 16-bit struct nfattr nfa_len field */ +/* max packet size is limited by 16-bit struct nfattr nfa_len field */ +#define NFULNL_COPY_RANGE_MAX (0xFFFF - NLA_HDRLEN) #define PRINTR(x, args...) do { if (net_ratelimit()) \ printk(x, ## args); } while (0); @@ -255,6 +256,8 @@ nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode, case NFULNL_COPY_PACKET: inst->copy_mode = mode; + if (range == 0) + range = NFULNL_COPY_RANGE_MAX; inst->copy_range = min_t(unsigned int, range, NFULNL_COPY_RANGE_MAX); break; @@ -345,26 +348,25 @@ nfulnl_alloc_skb(u32 peer_portid, unsigned int inst_size, unsigned int pkt_size) return skb; } -static int +static void __nfulnl_send(struct nfulnl_instance *inst) { - int status = -1; - if (inst->qlen > 1) { struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0, NLMSG_DONE, sizeof(struct nfgenmsg), 0); - if (!nlh) + if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n", + inst->skb->len, skb_tailroom(inst->skb))) { + kfree_skb(inst->skb); goto out; + } } - status = nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid, - MSG_DONTWAIT); - + nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid, + MSG_DONTWAIT); +out: inst->qlen = 0; inst->skb = NULL; -out: - return status; } static void @@ -647,7 +649,8 @@ nfulnl_log_packet(struct net *net, + nla_total_size(sizeof(u_int32_t)) /* gid */ + nla_total_size(plen) /* prefix */ + nla_total_size(sizeof(struct nfulnl_msg_packet_hw)) - + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)); + + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)) + + nla_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */ if (in && skb_mac_header_was_set(skb)) { size += nla_total_size(skb->dev->hard_header_len) @@ -676,8 +679,7 @@ nfulnl_log_packet(struct net *net, break; case NFULNL_COPY_PACKET: - if (inst->copy_range == 0 - || inst->copy_range > skb->len) + if (inst->copy_range > skb->len) data_len = skb->len; else data_len = inst->copy_range; @@ -690,8 +692,7 @@ nfulnl_log_packet(struct net *net, goto unlock_and_release; } - if (inst->skb && - size > skb_tailroom(inst->skb) - sizeof(struct nfgenmsg)) { + if (inst->skb && size > skb_tailroom(inst->skb)) { /* either the queue len is too high or we don't have * enough room in the skb left. flush to userspace. */ __nfulnl_flush(inst); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 5352b2d2d5bf..5497f50af2f0 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -227,22 +227,23 @@ nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data) spin_unlock_bh(&queue->lock); } -static void -nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen) +static int +nfqnl_zcopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) { int i, j = 0; int plen = 0; /* length of skb->head fragment */ + int ret; struct page *page; unsigned int offset; /* dont bother with small payloads */ - if (len <= skb_tailroom(to)) { - skb_copy_bits(from, 0, skb_put(to, len), len); - return; - } + if (len <= skb_tailroom(to)) + return skb_copy_bits(from, 0, skb_put(to, len), len); if (hlen) { - skb_copy_bits(from, 0, skb_put(to, hlen), hlen); + ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen); + if (unlikely(ret)) + return ret; len -= hlen; } else { plen = min_t(int, skb_headlen(from), len); @@ -260,6 +261,11 @@ nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen) to->len += len + plen; to->data_len += len + plen; + if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) { + skb_tx_error(from); + return -ENOMEM; + } + for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { if (!len) break; @@ -270,6 +276,8 @@ nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen) j++; } skb_shinfo(to)->nr_frags = j; + + return 0; } static int nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet) @@ -355,13 +363,16 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, skb = nfnetlink_alloc_skb(&init_net, size, queue->peer_portid, GFP_ATOMIC); - if (!skb) + if (!skb) { + skb_tx_error(entskb); return NULL; + } nlh = nlmsg_put(skb, 0, 0, NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET, sizeof(struct nfgenmsg), 0); if (!nlh) { + skb_tx_error(entskb); kfree_skb(skb); return NULL; } @@ -481,13 +492,15 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, nla->nla_type = NFQA_PAYLOAD; nla->nla_len = nla_attr_size(data_len); - nfqnl_zcopy(skb, entskb, data_len, hlen); + if (nfqnl_zcopy(skb, entskb, data_len, hlen)) + goto nla_put_failure; } nlh->nlmsg_len = skb->len; return skb; nla_put_failure: + skb_tx_error(entskb); kfree_skb(skb); net_err_ratelimited("nf_queue: error creating packet message\n"); return NULL; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 57ee84d21470..f7ad5c630b65 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -374,14 +374,14 @@ out: return err; } -static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr) +static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len) { #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 struct page *p_start, *p_end; /* First page is flushed through netlink_{get,set}_status */ p_start = pgvec_to_page(hdr + PAGE_SIZE); - p_end = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + hdr->nm_len - 1); + p_end = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1); while (p_start <= p_end) { flush_dcache_page(p_start); p_start++; @@ -399,9 +399,9 @@ static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr) static void netlink_set_status(struct nl_mmap_hdr *hdr, enum nl_mmap_status status) { + smp_mb(); hdr->nm_status = status; flush_dcache_page(pgvec_to_page(hdr)); - smp_wmb(); } static struct nl_mmap_hdr * @@ -500,7 +500,7 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock, while (nlk->cb != NULL && netlink_dump_space(nlk)) { err = netlink_dump(sk); if (err < 0) { - sk->sk_err = err; + sk->sk_err = -err; sk->sk_error_report(sk); break; } @@ -563,24 +563,16 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg, struct nl_mmap_hdr *hdr; struct sk_buff *skb; unsigned int maxlen; - bool excl = true; int err = 0, len = 0; - /* Netlink messages are validated by the receiver before processing. - * In order to avoid userspace changing the contents of the message - * after validation, the socket and the ring may only be used by a - * single process, otherwise we fall back to copying. - */ - if (atomic_long_read(&sk->sk_socket->file->f_count) > 2 || - atomic_read(&nlk->mapped) > 1) - excl = false; - mutex_lock(&nlk->pg_vec_lock); ring = &nlk->tx_ring; maxlen = ring->frame_size - NL_MMAP_HDRLEN; do { + unsigned int nm_len; + hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID); if (hdr == NULL) { if (!(msg->msg_flags & MSG_DONTWAIT) && @@ -588,35 +580,23 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg, schedule(); continue; } - if (hdr->nm_len > maxlen) { + + nm_len = ACCESS_ONCE(hdr->nm_len); + if (nm_len > maxlen) { err = -EINVAL; goto out; } - netlink_frame_flush_dcache(hdr); + netlink_frame_flush_dcache(hdr, nm_len); - if (likely(dst_portid == 0 && dst_group == 0 && excl)) { - skb = alloc_skb_head(GFP_KERNEL); - if (skb == NULL) { - err = -ENOBUFS; - goto out; - } - sock_hold(sk); - netlink_ring_setup_skb(skb, sk, ring, hdr); - NETLINK_CB(skb).flags |= NETLINK_SKB_TX; - __skb_put(skb, hdr->nm_len); - netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED); - atomic_inc(&ring->pending); - } else { - skb = alloc_skb(hdr->nm_len, GFP_KERNEL); - if (skb == NULL) { - err = -ENOBUFS; - goto out; - } - __skb_put(skb, hdr->nm_len); - memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, hdr->nm_len); - netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED); + skb = alloc_skb(nm_len, GFP_KERNEL); + if (skb == NULL) { + err = -ENOBUFS; + goto out; } + __skb_put(skb, nm_len); + memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len); + netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED); netlink_increment_head(ring); @@ -662,7 +642,7 @@ static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb) hdr->nm_pid = NETLINK_CB(skb).creds.pid; hdr->nm_uid = from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid); hdr->nm_gid = from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid); - netlink_frame_flush_dcache(hdr); + netlink_frame_flush_dcache(hdr, hdr->nm_len); netlink_set_status(hdr, NL_MMAP_STATUS_VALID); NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED; @@ -1219,7 +1199,74 @@ retry: return err; } -static inline int netlink_capable(const struct socket *sock, unsigned int flag) +/** + * __netlink_ns_capable - General netlink message capability test + * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace. + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in the user namespace @user_ns. + */ +bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, + struct user_namespace *user_ns, int cap) +{ + return ((nsp->flags & NETLINK_SKB_DST) || + file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(__netlink_ns_capable); + +/** + * netlink_ns_capable - General netlink message capability test + * @skb: socket buffer holding a netlink command from userspace + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in the user namespace @user_ns. + */ +bool netlink_ns_capable(const struct sk_buff *skb, + struct user_namespace *user_ns, int cap) +{ + return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap); +} +EXPORT_SYMBOL(netlink_ns_capable); + +/** + * netlink_capable - Netlink global message capability test + * @skb: socket buffer holding a netlink command from userspace + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in all user namespaces. + */ +bool netlink_capable(const struct sk_buff *skb, int cap) +{ + return netlink_ns_capable(skb, &init_user_ns, cap); +} +EXPORT_SYMBOL(netlink_capable); + +/** + * netlink_net_capable - Netlink network namespace message capability test + * @skb: socket buffer holding a netlink command from userspace + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap over the network namespace of + * the socket we received the message from. + */ +bool netlink_net_capable(const struct sk_buff *skb, int cap) +{ + return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap); +} +EXPORT_SYMBOL(netlink_net_capable); + +static inline int netlink_allowed(const struct socket *sock, unsigned int flag) { return (nl_table[sock->sk->sk_protocol].flags & flag) || ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN); @@ -1287,7 +1334,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, /* Only superuser is allowed to listen multicasts */ if (nladdr->nl_groups) { - if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV)) + if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) @@ -1349,7 +1396,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, return -EINVAL; /* Only superuser is allowed to send multicasts */ - if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) + if (nladdr->nl_groups && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; if (!nlk->portid) @@ -1921,7 +1968,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, break; case NETLINK_ADD_MEMBERSHIP: case NETLINK_DROP_MEMBERSHIP: { - if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV)) + if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) @@ -2053,6 +2100,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, struct sk_buff *skb; int err; struct scm_cookie scm; + u32 netlink_skb_flags = 0; if (msg->msg_flags&MSG_OOB) return -EOPNOTSUPP; @@ -2072,8 +2120,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, dst_group = ffs(addr->nl_groups); err = -EPERM; if ((dst_group || dst_portid) && - !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) + !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) goto out; + netlink_skb_flags |= NETLINK_SKB_DST; } else { dst_portid = nlk->dst_portid; dst_group = nlk->dst_group; @@ -2103,6 +2152,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, NETLINK_CB(skb).portid = nlk->portid; NETLINK_CB(skb).dst_group = dst_group; NETLINK_CB(skb).creds = siocb->scm->creds; + NETLINK_CB(skb).flags = netlink_skb_flags; err = -EFAULT; if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) { @@ -2168,8 +2218,6 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, } #endif - msg->msg_namelen = 0; - copied = data_skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; @@ -2204,7 +2252,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk); if (ret) { - sk->sk_err = ret; + sk->sk_err = -ret; sk->sk_error_report(sk); } } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 2fd6dbea327a..ade434b8abd8 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -364,7 +364,7 @@ int genl_unregister_ops(struct genl_family *family, struct genl_ops *ops) EXPORT_SYMBOL(genl_unregister_ops); /** - * genl_register_family - register a generic netlink family + * __genl_register_family - register a generic netlink family * @family: generic netlink family * * Registers the specified family after validating it first. Only one @@ -374,7 +374,7 @@ EXPORT_SYMBOL(genl_unregister_ops); * * Return 0 on success or a negative error code. */ -int genl_register_family(struct genl_family *family) +int __genl_register_family(struct genl_family *family) { int err = -EINVAL; @@ -430,10 +430,10 @@ errout_locked: errout: return err; } -EXPORT_SYMBOL(genl_register_family); +EXPORT_SYMBOL(__genl_register_family); /** - * genl_register_family_with_ops - register a generic netlink family + * __genl_register_family_with_ops - register a generic netlink family * @family: generic netlink family * @ops: operations to be registered * @n_ops: number of elements to register @@ -457,12 +457,12 @@ EXPORT_SYMBOL(genl_register_family); * * Return 0 on success or a negative error code. */ -int genl_register_family_with_ops(struct genl_family *family, +int __genl_register_family_with_ops(struct genl_family *family, struct genl_ops *ops, size_t n_ops) { int err, i; - err = genl_register_family(family); + err = __genl_register_family(family); if (err) return err; @@ -476,7 +476,7 @@ err_out: genl_unregister_family(family); return err; } -EXPORT_SYMBOL(genl_register_family_with_ops); +EXPORT_SYMBOL(__genl_register_family_with_ops); /** * genl_unregister_family - unregister generic netlink family @@ -544,6 +544,30 @@ void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, } EXPORT_SYMBOL(genlmsg_put); +static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct genl_ops *ops = cb->data; + int rc; + + genl_lock(); + rc = ops->dumpit(skb, cb); + genl_unlock(); + return rc; +} + +static int genl_lock_done(struct netlink_callback *cb) +{ + struct genl_ops *ops = cb->data; + int rc = 0; + + if (ops->done) { + genl_lock(); + rc = ops->done(cb); + genl_unlock(); + } + return rc; +} + static int genl_family_rcv_msg(struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh) @@ -568,19 +592,38 @@ static int genl_family_rcv_msg(struct genl_family *family, return -EOPNOTSUPP; if ((ops->flags & GENL_ADMIN_PERM) && - !capable(CAP_NET_ADMIN)) + !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlh->nlmsg_flags & NLM_F_DUMP) { - struct netlink_dump_control c = { - .dump = ops->dumpit, - .done = ops->done, - }; + int rc; if (ops->dumpit == NULL) return -EOPNOTSUPP; - return netlink_dump_start(net->genl_sock, skb, nlh, &c); + if (!family->parallel_ops) { + struct netlink_dump_control c = { + .module = family->module, + .data = ops, + .dump = genl_lock_dumpit, + .done = genl_lock_done, + }; + + genl_unlock(); + rc = __netlink_dump_start(net->genl_sock, skb, nlh, &c); + genl_lock(); + + } else { + struct netlink_dump_control c = { + .module = family->module, + .dump = ops->dumpit, + .done = ops->done, + }; + + rc = __netlink_dump_start(net->genl_sock, skb, nlh, &c); + } + + return rc; } if (ops->doit == NULL) @@ -877,8 +920,10 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) #ifdef CONFIG_MODULES if (res == NULL) { genl_unlock(); + up_read(&cb_lock); request_module("net-pf-%d-proto-%d-family-%s", PF_NETLINK, NETLINK_GENERIC, name); + down_read(&cb_lock); genl_lock(); res = genl_family_find_byname(name); } diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ec0c80fde69f..13b92982a506 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1179,10 +1179,9 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock, sax->sax25_family = AF_NETROM; skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call, AX25_ADDR_LEN); + msg->msg_namelen = sizeof(*sax); } - msg->msg_namelen = sizeof(*sax); - skb_free_datagram(sk, skb); release_sock(sk); diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h index ff8c434f7df8..f924dd209b31 100644 --- a/net/nfc/llcp.h +++ b/net/nfc/llcp.h @@ -19,6 +19,7 @@ enum llcp_state { LLCP_CONNECTED = 1, /* wait_for_packet() wants that */ + LLCP_CONNECTING, LLCP_CLOSED, LLCP_BOUND, LLCP_LISTEN, diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 380253eccb74..86470cf54cee 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -571,7 +571,7 @@ static unsigned int llcp_sock_poll(struct file *file, struct socket *sock, if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= POLLHUP; - if (sock_writeable(sk)) + if (sock_writeable(sk) && sk->sk_state == LLCP_CONNECTED) mask |= POLLOUT | POLLWRNORM | POLLWRBAND; else set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); @@ -722,14 +722,16 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, if (ret) goto sock_unlink; + sk->sk_state = LLCP_CONNECTING; + ret = sock_wait_state(sk, LLCP_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); - if (ret) + if (ret && ret != -EINPROGRESS) goto sock_unlink; release_sock(sk); - return 0; + return ret; sock_unlink: nfc_llcp_put_ssap(local, llcp_sock->ssap); @@ -798,8 +800,6 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock, pr_debug("%p %zu\n", sk, len); - msg->msg_namelen = 0; - lock_sock(sk); if (sk->sk_state == LLCP_CLOSED && diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 313bf1bc848a..5d11f4ac3ecb 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -241,8 +241,6 @@ static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return rc; - msg->msg_namelen = 0; - copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 894b6cbdd929..c4779ca59032 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -40,6 +40,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, static int make_writable(struct sk_buff *skb, int write_len) { + if (!pskb_may_pull(skb, write_len)) + return -ENOMEM; + if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; @@ -68,6 +71,8 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci) vlan_set_encap_proto(skb, vhdr); skb->mac_header += VLAN_HLEN; + if (skb_network_offset(skb) < ETH_HLEN) + skb_set_network_header(skb, ETH_HLEN); skb_reset_mac_len(skb); return 0; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 20a1bd0e6549..81b4b816f131 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -237,6 +237,30 @@ struct packet_skb_cb { static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); +static struct net_device *packet_cached_dev_get(struct packet_sock *po) +{ + struct net_device *dev; + + rcu_read_lock(); + dev = rcu_dereference(po->cached_dev); + if (likely(dev)) + dev_hold(dev); + rcu_read_unlock(); + + return dev; +} + +static void packet_cached_dev_assign(struct packet_sock *po, + struct net_device *dev) +{ + rcu_assign_pointer(po->cached_dev, dev); +} + +static void packet_cached_dev_reset(struct packet_sock *po) +{ + RCU_INIT_POINTER(po->cached_dev, NULL); +} + /* register_prot_hook must be invoked with the po->bind_lock held, * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). @@ -244,11 +268,13 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po); static void register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); + if (!po->running) { if (po->fanout) __fanout_link(sk, po); else dev_add_pack(&po->prot_hook); + sock_hold(sk); po->running = 1; } @@ -266,10 +292,12 @@ static void __unregister_prot_hook(struct sock *sk, bool sync) struct packet_sock *po = pkt_sk(sk); po->running = 0; + if (po->fanout) __fanout_unlink(sk, po); else __dev_remove_pack(&po->prot_hook); + __sock_put(sk); if (sync) { @@ -432,9 +460,9 @@ static void prb_shutdown_retire_blk_timer(struct packet_sock *po, pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc; - spin_lock(&rb_queue->lock); + spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; - spin_unlock(&rb_queue->lock); + spin_unlock_bh(&rb_queue->lock); prb_del_retire_blk_timer(pkc); } @@ -537,6 +565,7 @@ static void init_prb_bdqc(struct packet_sock *po, p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; + p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); prb_setup_retire_blk_timer(po, tx_ring); prb_open_block(p1, pbd); @@ -1775,6 +1804,18 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if ((int)snaplen < 0) snaplen = 0; } + } else if (unlikely(macoff + snaplen > + GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { + u32 nval; + + nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff; + pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n", + snaplen, nval, macoff); + snaplen = nval; + if (unlikely((int)snaplen < 0)) { + snaplen = 0; + macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; + } } spin_lock(&sk->sk_receive_queue.lock); h.raw = packet_current_rx_frame(po, skb, @@ -2046,7 +2087,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) struct sk_buff *skb; struct net_device *dev; __be16 proto; - bool need_rls_dev = false; int err, reserve = 0; void *ph; struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; @@ -2058,8 +2098,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) mutex_lock(&po->pg_vec_lock); - if (saddr == NULL) { - dev = po->prot_hook.dev; + if (likely(saddr == NULL)) { + dev = packet_cached_dev_get(po); proto = po->num; addr = NULL; } else { @@ -2073,19 +2113,17 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) proto = saddr->sll_protocol; addr = saddr->sll_addr; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); - need_rls_dev = true; } err = -ENXIO; if (unlikely(dev == NULL)) goto out; - - reserve = dev->hard_header_len; - err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; + reserve = dev->hard_header_len; + size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); @@ -2162,8 +2200,7 @@ out_status: __packet_set_status(po, ph, status); kfree_skb(skb); out_put: - if (need_rls_dev) - dev_put(dev); + dev_put(dev); out: mutex_unlock(&po->pg_vec_lock); return err; @@ -2201,7 +2238,6 @@ static int packet_snd(struct socket *sock, struct sk_buff *skb; struct net_device *dev; __be16 proto; - bool need_rls_dev = false; unsigned char *addr; int err, reserve = 0; struct virtio_net_hdr vnet_hdr = { 0 }; @@ -2216,8 +2252,8 @@ static int packet_snd(struct socket *sock, * Get and verify the address. */ - if (saddr == NULL) { - dev = po->prot_hook.dev; + if (likely(saddr == NULL)) { + dev = packet_cached_dev_get(po); proto = po->num; addr = NULL; } else { @@ -2229,19 +2265,17 @@ static int packet_snd(struct socket *sock, proto = saddr->sll_protocol; addr = saddr->sll_addr; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); - need_rls_dev = true; } err = -ENXIO; - if (dev == NULL) + if (unlikely(dev == NULL)) goto out_unlock; - if (sock->type == SOCK_RAW) - reserve = dev->hard_header_len; - err = -ENETDOWN; - if (!(dev->flags & IFF_UP)) + if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; + if (sock->type == SOCK_RAW) + reserve = dev->hard_header_len; if (po->has_vnet_hdr) { vnet_hdr_len = sizeof(vnet_hdr); @@ -2375,15 +2409,14 @@ static int packet_snd(struct socket *sock, if (err > 0 && (err = net_xmit_errno(err)) != 0) goto out_unlock; - if (need_rls_dev) - dev_put(dev); + dev_put(dev); return len; out_free: kfree_skb(skb); out_unlock: - if (dev && need_rls_dev) + if (dev) dev_put(dev); out: return err; @@ -2428,6 +2461,8 @@ static int packet_release(struct socket *sock) spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); + packet_cached_dev_reset(po); + if (po->prot_hook.dev) { dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; @@ -2483,14 +2518,17 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc spin_lock(&po->bind_lock); unregister_prot_hook(sk, true); + po->num = protocol; po->prot_hook.type = protocol; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); - po->prot_hook.dev = dev; + po->prot_hook.dev = dev; po->ifindex = dev ? dev->ifindex : 0; + packet_cached_dev_assign(po, dev); + if (protocol == 0) goto out_unlock; @@ -2604,6 +2642,8 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, sk->sk_family = PF_PACKET; po->num = proto; + packet_cached_dev_reset(po); + sk->sk_destruct = packet_sock_destruct; sk_refcnt_debug_inc(sk); @@ -2694,7 +2734,6 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; - struct sockaddr_ll *sll; int vnet_hdr_len = 0; err = -EINVAL; @@ -2777,22 +2816,10 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, goto out_free; } - /* - * If the address length field is there to be filled in, we fill - * it in now. - */ - - sll = &PACKET_SKB_CB(skb)->sa.ll; - if (sock->type == SOCK_PACKET) - msg->msg_namelen = sizeof(struct sockaddr_pkt); - else - msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); - - /* - * You lose any data beyond the buffer you gave. If it worries a - * user program they can ask the device for its MTU anyway. + /* You lose any data beyond the buffer you gave. If it worries + * a user program they can ask the device for its MTU + * anyway. */ - copied = skb->len; if (copied > len) { copied = len; @@ -2805,9 +2832,20 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, sock_recv_ts_and_drops(msg, sk, skb); - if (msg->msg_name) + if (msg->msg_name) { + /* If the address length field is there to be filled + * in, we fill it in now. + */ + if (sock->type == SOCK_PACKET) { + msg->msg_namelen = sizeof(struct sockaddr_pkt); + } else { + struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; + msg->msg_namelen = sll->sll_halen + + offsetof(struct sockaddr_ll, sll_addr); + } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, msg->msg_namelen); + } if (pkt_sk(sk)->auxdata) { struct tpacket_auxdata aux; @@ -3259,9 +3297,11 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, if (po->tp_version == TPACKET_V3) { lv = sizeof(struct tpacket_stats_v3); + st.stats3.tp_packets += st.stats3.tp_drops; data = &st.stats3; } else { lv = sizeof(struct tpacket_stats); + st.stats1.tp_packets += st.stats1.tp_drops; data = &st.stats1; } @@ -3356,6 +3396,7 @@ static int packet_notifier(struct notifier_block *this, unsigned long msg, void sk->sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { + packet_cached_dev_reset(po); po->ifindex = -1; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); @@ -3614,6 +3655,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; if (unlikely(req->tp_block_size & (PAGE_SIZE - 1))) goto out; + if (po->tp_version >= TPACKET_V3 && + (int)(req->tp_block_size - + BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0) + goto out; if (unlikely(req->tp_frame_size < po->tp_hdrlen + po->tp_reserve)) goto out; diff --git a/net/packet/diag.c b/net/packet/diag.c index a9584a2f6d69..674b0a65df6c 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -127,6 +127,7 @@ static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb) static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag_req *req, + bool may_report_filterinfo, struct user_namespace *user_ns, u32 portid, u32 seq, u32 flags, int sk_ino) { @@ -171,7 +172,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, goto out_nlmsg_trim; if ((req->pdiag_show & PACKET_SHOW_FILTER) && - sock_diag_put_filterinfo(user_ns, sk, skb, PACKET_DIAG_FILTER)) + sock_diag_put_filterinfo(may_report_filterinfo, sk, skb, + PACKET_DIAG_FILTER)) goto out_nlmsg_trim; return nlmsg_end(skb, nlh); @@ -187,9 +189,11 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) struct packet_diag_req *req; struct net *net; struct sock *sk; + bool may_report_filterinfo; net = sock_net(skb->sk); req = nlmsg_data(cb->nlh); + may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN); mutex_lock(&net->packet.sklist_lock); sk_for_each(sk, &net->packet.sklist) { @@ -199,6 +203,7 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) goto next; if (sk_diag_fill(sk, skb, req, + may_report_filterinfo, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, diff --git a/net/packet/internal.h b/net/packet/internal.h index c4e4b4561207..ca086c0c2c08 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -29,6 +29,7 @@ struct tpacket_kbdq_core { char *pkblk_start; char *pkblk_end; int kblk_size; + unsigned int max_frame_len; unsigned int knum_blocks; uint64_t knxt_seq_num; char *prev; @@ -113,6 +114,7 @@ struct packet_sock { unsigned int tp_loss:1; unsigned int tp_tx_has_off:1; unsigned int tp_tstamp; + struct net_device __rcu *cached_dev; struct packet_type prot_hook ____cacheline_aligned_in_smp; }; diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 12c30f3e643e..38946b26e471 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -139,9 +139,6 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk, MSG_CMSG_COMPAT)) goto out_nofree; - if (addr_len) - *addr_len = sizeof(sa); - skb = skb_recv_datagram(sk, flags, noblock, &rval); if (skb == NULL) goto out_nofree; @@ -162,8 +159,10 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk, rval = (flags & MSG_TRUNC) ? skb->len : copylen; - if (msg->msg_name != NULL) - memcpy(msg->msg_name, &sa, sizeof(struct sockaddr_pn)); + if (msg->msg_name != NULL) { + memcpy(msg->msg_name, &sa, sizeof(sa)); + *addr_len = sizeof(sa); + } out: skb_free_datagram(sk, skb); diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index dc15f4300808..b64151ade6b3 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -70,10 +70,10 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh) int err; u8 pnaddr; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; - if (!capable(CAP_SYS_ADMIN)) + if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; ASSERT_RTNL(); @@ -233,10 +233,10 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh) int err; u8 dst; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; - if (!capable(CAP_SYS_ADMIN)) + if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; ASSERT_RTNL(); diff --git a/net/rds/ib.c b/net/rds/ib.c index b4c8b0022fee..ba2dffeff608 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -338,7 +338,8 @@ static int rds_ib_laddr_check(__be32 addr) ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin); /* due to this, we will claim to support iWARP devices unless we check node_type. */ - if (ret || cm_id->device->node_type != RDMA_NODE_IB_CA) + if (ret || !cm_id->device || + cm_id->device->node_type != RDMA_NODE_IB_CA) ret = -EADDRNOTAVAIL; rdsdebug("addr %pI4 ret %d node type %d\n", diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 8eb9501e3d60..b7ebe23cdedf 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -421,8 +421,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item, struct rds_ib_refill_cache *cache) { unsigned long flags; - struct list_head *old; - struct list_head __percpu *chpfirst; + struct list_head *old, *chpfirst; local_irq_save(flags); @@ -432,7 +431,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item, else /* put on front */ list_add_tail(new_item, chpfirst); - __this_cpu_write(chpfirst, new_item); + __this_cpu_write(cache->percpu->first, new_item); __this_cpu_inc(cache->percpu->count); if (__this_cpu_read(cache->percpu->count) < RDS_IB_RECYCLE_BATCH_COUNT) @@ -452,7 +451,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item, } while (old); - __this_cpu_write(chpfirst, NULL); + __this_cpu_write(cache->percpu->first, NULL); __this_cpu_write(cache->percpu->count, 0); end: local_irq_restore(flags); diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index e59094981175..37be6e226d1b 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -552,9 +552,8 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, && rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) { rds_cong_map_updated(conn->c_fcong, ~(u64) 0); scat = &rm->data.op_sg[sg]; - ret = sizeof(struct rds_header) + RDS_CONG_MAP_BYTES; - ret = min_t(int, ret, scat->length - conn->c_xmit_data_off); - return ret; + ret = max_t(int, RDS_CONG_MAP_BYTES, scat->length); + return sizeof(struct rds_header) + ret; } /* FIXME we may overallocate here */ diff --git a/net/rds/iw.c b/net/rds/iw.c index 7826d46baa70..589935661d66 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 addr) ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin); /* due to this, we will claim to support IB devices unless we check node_type. */ - if (ret || cm_id->device->node_type != RDMA_NODE_RNIC) + if (ret || !cm_id->device || + cm_id->device->node_type != RDMA_NODE_RNIC) ret = -EADDRNOTAVAIL; rdsdebug("addr %pI4 ret %d node type %d\n", diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index a817705ce2d0..dba8d0864f18 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -88,7 +88,9 @@ static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool, int *unpinned); static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr); -static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id) +static int rds_iw_get_device(struct sockaddr_in *src, struct sockaddr_in *dst, + struct rds_iw_device **rds_iwdev, + struct rdma_cm_id **cm_id) { struct rds_iw_device *iwdev; struct rds_iw_cm_id *i_cm_id; @@ -112,15 +114,15 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd src_addr->sin_port, dst_addr->sin_addr.s_addr, dst_addr->sin_port, - rs->rs_bound_addr, - rs->rs_bound_port, - rs->rs_conn_addr, - rs->rs_conn_port); + src->sin_addr.s_addr, + src->sin_port, + dst->sin_addr.s_addr, + dst->sin_port); #ifdef WORKING_TUPLE_DETECTION - if (src_addr->sin_addr.s_addr == rs->rs_bound_addr && - src_addr->sin_port == rs->rs_bound_port && - dst_addr->sin_addr.s_addr == rs->rs_conn_addr && - dst_addr->sin_port == rs->rs_conn_port) { + if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr && + src_addr->sin_port == src->sin_port && + dst_addr->sin_addr.s_addr == dst->sin_addr.s_addr && + dst_addr->sin_port == dst->sin_port) { #else /* FIXME - needs to compare the local and remote * ipaddr/port tuple, but the ipaddr is the only @@ -128,7 +130,7 @@ static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwd * zero'ed. It doesn't appear to be properly populated * during connection setup... */ - if (src_addr->sin_addr.s_addr == rs->rs_bound_addr) { + if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr) { #endif spin_unlock_irq(&iwdev->spinlock); *rds_iwdev = iwdev; @@ -180,19 +182,13 @@ int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_i { struct sockaddr_in *src_addr, *dst_addr; struct rds_iw_device *rds_iwdev_old; - struct rds_sock rs; struct rdma_cm_id *pcm_id; int rc; src_addr = (struct sockaddr_in *)&cm_id->route.addr.src_addr; dst_addr = (struct sockaddr_in *)&cm_id->route.addr.dst_addr; - rs.rs_bound_addr = src_addr->sin_addr.s_addr; - rs.rs_bound_port = src_addr->sin_port; - rs.rs_conn_addr = dst_addr->sin_addr.s_addr; - rs.rs_conn_port = dst_addr->sin_port; - - rc = rds_iw_get_device(&rs, &rds_iwdev_old, &pcm_id); + rc = rds_iw_get_device(src_addr, dst_addr, &rds_iwdev_old, &pcm_id); if (rc) rds_iw_remove_cm_id(rds_iwdev, cm_id); @@ -598,9 +594,17 @@ void *rds_iw_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_iw_device *rds_iwdev; struct rds_iw_mr *ibmr = NULL; struct rdma_cm_id *cm_id; + struct sockaddr_in src = { + .sin_addr.s_addr = rs->rs_bound_addr, + .sin_port = rs->rs_bound_port, + }; + struct sockaddr_in dst = { + .sin_addr.s_addr = rs->rs_conn_addr, + .sin_port = rs->rs_conn_port, + }; int ret; - ret = rds_iw_get_device(rs, &rds_iwdev, &cm_id); + ret = rds_iw_get_device(&src, &dst, &rds_iwdev, &cm_id); if (ret || !cm_id) { ret = -ENODEV; goto out; diff --git a/net/rds/recv.c b/net/rds/recv.c index 9f0f17cf6bf9..de339b24ca14 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -410,8 +410,6 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo); - msg->msg_namelen = 0; - if (msg_flags & MSG_OOB) goto out; diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c index 907214b4c4d0..fc6cbe827856 100644 --- a/net/rds/sysctl.c +++ b/net/rds/sysctl.c @@ -71,14 +71,14 @@ static ctl_table rds_sysctl_rds_table[] = { { .procname = "max_unacked_packets", .data = &rds_sysctl_max_unacked_packets, - .maxlen = sizeof(unsigned long), + .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_unacked_bytes", .data = &rds_sysctl_max_unacked_bytes, - .maxlen = sizeof(unsigned long), + .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 9c8347451597..27e6896705e6 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1216,7 +1216,6 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); - struct sockaddr_rose *srose = (struct sockaddr_rose *)msg->msg_name; size_t copied; unsigned char *asmptr; struct sk_buff *skb; @@ -1252,24 +1251,19 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock, skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); - if (srose != NULL) { - memset(srose, 0, msg->msg_namelen); + if (msg->msg_name) { + struct sockaddr_rose *srose; + struct full_sockaddr_rose *full_srose = msg->msg_name; + + memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose)); + srose = msg->msg_name; srose->srose_family = AF_ROSE; srose->srose_addr = rose->dest_addr; srose->srose_call = rose->dest_call; srose->srose_ndigis = rose->dest_ndigis; - if (msg->msg_namelen >= sizeof(struct full_sockaddr_rose)) { - struct full_sockaddr_rose *full_srose = (struct full_sockaddr_rose *)msg->msg_name; - for (n = 0 ; n < rose->dest_ndigis ; n++) - full_srose->srose_digis[n] = rose->dest_digis[n]; - msg->msg_namelen = sizeof(struct full_sockaddr_rose); - } else { - if (rose->dest_ndigis >= 1) { - srose->srose_ndigis = 1; - srose->srose_digi = rose->dest_digis[0]; - } - msg->msg_namelen = sizeof(struct sockaddr_rose); - } + for (n = 0 ; n < rose->dest_ndigis ; n++) + full_srose->srose_digis[n] = rose->dest_digis[n]; + msg->msg_namelen = sizeof(struct full_sockaddr_rose); } skb_free_datagram(sk, skb); diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 4b48687c3890..5cc2da5d295d 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -87,7 +87,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) { /* nothing remains on the queue */ if (copied && - (msg->msg_flags & MSG_PEEK || timeo == 0)) + (flags & MSG_PEEK || timeo == 0)) goto out; /* wait for a message to turn up */ @@ -143,10 +143,13 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, /* copy the peer address and timestamp */ if (!continue_call) { - if (msg->msg_name && msg->msg_namelen > 0) + if (msg->msg_name) { + size_t len = + sizeof(call->conn->trans->peer->srx); memcpy(msg->msg_name, - &call->conn->trans->peer->srx, - sizeof(call->conn->trans->peer->srx)); + &call->conn->trans->peer->srx, len); + msg->msg_namelen = len; + } sock_recv_ts_and_drops(msg, &rx->sk, skb); } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index fd7072827a40..15d46b9166de 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -989,7 +989,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n) u32 portid = skb ? NETLINK_CB(skb).portid : 0; int ret = 0, ovr = 0; - if ((n->nlmsg_type != RTM_GETACTION) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8e118af90973..2ea40d1877a6 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -138,7 +138,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n) int err; int tp_created = 0; - if ((n->nlmsg_type != RTM_GETTFILTER) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETTFILTER) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; replay: diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 3a633debb6df..a2abc449ce8f 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -227,6 +227,7 @@ static int tcf_em_validate(struct tcf_proto *tp, * to replay the request. */ module_put(em->ops->owner); + em->ops = NULL; err = -EAGAIN; } #endif diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 281c1bded1f6..2d2f07945c85 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -285,6 +285,45 @@ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind) return q; } +/* The linklayer setting were not transferred from iproute2, in older + * versions, and the rate tables lookup systems have been dropped in + * the kernel. To keep backward compatible with older iproute2 tc + * utils, we detect the linklayer setting by detecting if the rate + * table were modified. + * + * For linklayer ATM table entries, the rate table will be aligned to + * 48 bytes, thus some table entries will contain the same value. The + * mpu (min packet unit) is also encoded into the old rate table, thus + * starting from the mpu, we find low and high table entries for + * mapping this cell. If these entries contain the same value, when + * the rate tables have been modified for linklayer ATM. + * + * This is done by rounding mpu to the nearest 48 bytes cell/entry, + * and then roundup to the next cell, calc the table entry one below, + * and compare. + */ +static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab) +{ + int low = roundup(r->mpu, 48); + int high = roundup(low+1, 48); + int cell_low = low >> r->cell_log; + int cell_high = (high >> r->cell_log) - 1; + + /* rtab is too inaccurate at rates > 100Mbit/s */ + if ((r->rate > (100000000/8)) || (rtab[0] == 0)) { + pr_debug("TC linklayer: Giving up ATM detection\n"); + return TC_LINKLAYER_ETHERNET; + } + + if ((cell_high > cell_low) && (cell_high < 256) + && (rtab[cell_low] == rtab[cell_high])) { + pr_debug("TC linklayer: Detected ATM, low(%d)=high(%d)=%u\n", + cell_low, cell_high, rtab[cell_high]); + return TC_LINKLAYER_ATM; + } + return TC_LINKLAYER_ETHERNET; +} + static struct qdisc_rate_table *qdisc_rtab_list; struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab) @@ -308,6 +347,8 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *ta rtab->rate = *r; rtab->refcnt = 1; memcpy(rtab->data, nla_data(tab), 1024); + if (r->linklayer == TC_LINKLAYER_UNAWARE) + r->linklayer = __detect_linklayer(r, rtab->data); rtab->next = qdisc_rtab_list; qdisc_rtab_list = rtab; } @@ -983,7 +1024,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n) struct Qdisc *p = NULL; int err; - if ((n->nlmsg_type != RTM_GETQDISC) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -1050,7 +1091,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n) struct Qdisc *q, *p; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; replay: @@ -1390,7 +1431,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n) u32 qid; int err; - if ((n->nlmsg_type != RTM_GETTCLASS) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index ca8e0a57d945..1f9c31411f19 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -605,6 +605,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, struct sockaddr_atmpvc pvc; int state; + memset(&pvc, 0, sizeof(pvc)); pvc.sap_family = AF_ATMPVC; pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; pvc.sap_addr.vpi = flow->vcc->vpi; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 1bc210ffcba2..8ec15988b5f3 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1465,6 +1465,7 @@ static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_wrropt opt; + memset(&opt, 0, sizeof(opt)); opt.flags = 0; opt.allot = cl->allot; opt.priority = cl->priority + 1; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 20224086cc28..a7f838b45dc8 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -908,6 +908,7 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r, memset(r, 0, sizeof(*r)); r->overhead = conf->overhead; r->rate_bps = (u64)conf->rate << 3; + r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK); r->mult = 1; /* * Calibrate mult, shift so that token counting is accurate diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index adaedd79389c..e09b074bb8a7 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -87,7 +87,7 @@ struct htb_class { unsigned int children; struct htb_class *parent; /* parent class */ - int prio; /* these two are used only by leaves... */ + u32 prio; /* these two are used only by leaves... */ int quantum; /* but stored for parent-to-leaf return */ union { @@ -1312,6 +1312,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)*arg, *parent; struct nlattr *opt = tca[TCA_OPTIONS]; + struct qdisc_rate_table *rtab = NULL, *ctab = NULL; struct nlattr *tb[TCA_HTB_MAX + 1]; struct tc_htb_opt *hopt; @@ -1333,6 +1334,18 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!hopt->rate.rate || !hopt->ceil.rate) goto failure; + /* Keeping backward compatible with rate_table based iproute2 tc */ + if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) { + rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]); + if (rtab) + qdisc_put_rtab(rtab); + } + if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE) { + ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]); + if (ctab) + qdisc_put_rtab(ctab); + } + if (!cl) { /* new class */ struct Qdisc *new_q; int prio; @@ -1463,7 +1476,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, psched_ratecfg_precompute(&cl->ceil, &hopt->ceil); cl->buffer = PSCHED_TICKS2NS(hopt->buffer); - cl->cbuffer = PSCHED_TICKS2NS(hopt->buffer); + cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer); sch_tree_unlock(sch); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index d51852bba01c..57922524f0c7 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -113,7 +113,6 @@ #define FRAC_BITS 30 /* fixed point arithmetic */ #define ONE_FP (1UL << FRAC_BITS) -#define IWSUM (ONE_FP/QFQ_MAX_WSUM) #define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */ #define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */ @@ -189,6 +188,7 @@ struct qfq_sched { struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */ u32 num_active_agg; /* Num. of active aggregates */ u32 wsum; /* weight sum */ + u32 iwsum; /* inverse weight sum */ unsigned long bitmaps[QFQ_MAX_STATE]; /* Group bitmaps. */ struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */ @@ -314,6 +314,7 @@ static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg, q->wsum += (int) agg->class_weight * (new_num_classes - agg->num_classes); + q->iwsum = ONE_FP / q->wsum; agg->num_classes = new_num_classes; } @@ -340,6 +341,10 @@ static void qfq_destroy_agg(struct qfq_sched *q, struct qfq_aggregate *agg) { if (!hlist_unhashed(&agg->nonfull_next)) hlist_del_init(&agg->nonfull_next); + q->wsum -= agg->class_weight; + if (q->wsum != 0) + q->iwsum = ONE_FP / q->wsum; + if (q->in_serv_agg == agg) q->in_serv_agg = qfq_choose_next_agg(q); kfree(agg); @@ -827,38 +832,60 @@ static void qfq_make_eligible(struct qfq_sched *q) } } - /* - * The index of the slot in which the aggregate is to be inserted must - * not be higher than QFQ_MAX_SLOTS-2. There is a '-2' and not a '-1' - * because the start time of the group may be moved backward by one - * slot after the aggregate has been inserted, and this would cause - * non-empty slots to be right-shifted by one position. + * The index of the slot in which the input aggregate agg is to be + * inserted must not be higher than QFQ_MAX_SLOTS-2. There is a '-2' + * and not a '-1' because the start time of the group may be moved + * backward by one slot after the aggregate has been inserted, and + * this would cause non-empty slots to be right-shifted by one + * position. + * + * QFQ+ fully satisfies this bound to the slot index if the parameters + * of the classes are not changed dynamically, and if QFQ+ never + * happens to postpone the service of agg unjustly, i.e., it never + * happens that the aggregate becomes backlogged and eligible, or just + * eligible, while an aggregate with a higher approximated finish time + * is being served. In particular, in this case QFQ+ guarantees that + * the timestamps of agg are low enough that the slot index is never + * higher than 2. Unfortunately, QFQ+ cannot provide the same + * guarantee if it happens to unjustly postpone the service of agg, or + * if the parameters of some class are changed. + * + * As for the first event, i.e., an out-of-order service, the + * upper bound to the slot index guaranteed by QFQ+ grows to + * 2 + + * QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) * + * (current_max_weight/current_wsum) <= 2 + 8 * 128 * 1. * - * If the weight and lmax (max_pkt_size) of the classes do not change, - * then QFQ+ does meet the above contraint according to the current - * values of its parameters. In fact, if the weight and lmax of the - * classes do not change, then, from the theory, QFQ+ guarantees that - * the slot index is never higher than - * 2 + QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) * - * (QFQ_MAX_WEIGHT/QFQ_MAX_WSUM) = 2 + 8 * 128 * (1 / 64) = 18 + * The following function deals with this problem by backward-shifting + * the timestamps of agg, if needed, so as to guarantee that the slot + * index is never higher than QFQ_MAX_SLOTS-2. This backward-shift may + * cause the service of other aggregates to be postponed, yet the + * worst-case guarantees of these aggregates are not violated. In + * fact, in case of no out-of-order service, the timestamps of agg + * would have been even lower than they are after the backward shift, + * because QFQ+ would have guaranteed a maximum value equal to 2 for + * the slot index, and 2 < QFQ_MAX_SLOTS-2. Hence the aggregates whose + * service is postponed because of the backward-shift would have + * however waited for the service of agg before being served. * - * When the weight of a class is increased or the lmax of the class is - * decreased, a new aggregate with smaller slot size than the original - * parent aggregate of the class may happen to be activated. The - * activation of this aggregate should be properly delayed to when the - * service of the class has finished in the ideal system tracked by - * QFQ+. If the activation of the aggregate is not delayed to this - * reference time instant, then this aggregate may be unjustly served - * before other aggregates waiting for service. This may cause the - * above bound to the slot index to be violated for some of these - * unlucky aggregates. + * The other event that may cause the slot index to be higher than 2 + * for agg is a recent change of the parameters of some class. If the + * weight of a class is increased or the lmax (max_pkt_size) of the + * class is decreased, then a new aggregate with smaller slot size + * than the original parent aggregate of the class may happen to be + * activated. The activation of this aggregate should be properly + * delayed to when the service of the class has finished in the ideal + * system tracked by QFQ+. If the activation of the aggregate is not + * delayed to this reference time instant, then this aggregate may be + * unjustly served before other aggregates waiting for service. This + * may cause the above bound to the slot index to be violated for some + * of these unlucky aggregates. * * Instead of delaying the activation of the new aggregate, which is - * quite complex, the following inaccurate but simple solution is used: - * if the slot index is higher than QFQ_MAX_SLOTS-2, then the - * timestamps of the aggregate are shifted backward so as to let the - * slot index become equal to QFQ_MAX_SLOTS-2. + * quite complex, the above-discussed capping of the slot index is + * used to handle also the consequences of a change of the parameters + * of a class. */ static void qfq_slot_insert(struct qfq_group *grp, struct qfq_aggregate *agg, u64 roundedS) @@ -1077,7 +1104,7 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) else in_serv_agg->budget -= len; - q->V += (u64)len * IWSUM; + q->V += (u64)len * q->iwsum; pr_debug("qfq dequeue: len %u F %lld now %lld\n", len, (unsigned long long) in_serv_agg->F, (unsigned long long) q->V); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 91cfd8f94a19..6360a14edeab 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -387,7 +387,7 @@ void sctp_association_free(struct sctp_association *asoc) /* Only real associations count against the endpoint, so * don't bother for if this is a temporary association. */ - if (!asoc->temp) { + if (!list_empty(&asoc->asocs)) { list_del(&asoc->asocs); /* Decrement the backlog value for a TCP-style listening @@ -1213,6 +1213,7 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->c = new->c; asoc->peer.rwnd = new->peer.rwnd; asoc->peer.sack_needed = new->peer.sack_needed; + asoc->peer.auth_capable = new->peer.auth_capable; asoc->peer.i = new->peer.i; sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, asoc->peer.i.initial_tsn, GFP_ATOMIC); @@ -1296,7 +1297,6 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->peer.peer_hmacs = new->peer.peer_hmacs; new->peer.peer_hmacs = NULL; - sctp_auth_key_put(asoc->asoc_shared_key); sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); } @@ -1658,6 +1658,8 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack( * ack chunk whose serial number matches that of the request. */ list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) { + if (sctp_chunk_pending(ack)) + continue; if (ack->subh.addip_hdr->serial == serial) { sctp_chunk_hold(ack); return ack; diff --git a/net/sctp/auth.c b/net/sctp/auth.c index ba1dfc3f8def..bc2fae7e67be 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -393,14 +393,13 @@ nomem: */ int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp) { - struct net *net = sock_net(asoc->base.sk); struct sctp_auth_bytes *secret; struct sctp_shared_key *ep_key; /* If we don't support AUTH, or peer is not capable * we don't need to do anything. */ - if (!net->sctp.auth_enable || !asoc->peer.auth_capable) + if (!asoc->ep->auth_enable || !asoc->peer.auth_capable) return 0; /* If the key_id is non-zero and we couldn't find an @@ -447,16 +446,16 @@ struct sctp_shared_key *sctp_auth_get_shkey( */ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp) { - struct net *net = sock_net(ep->base.sk); struct crypto_hash *tfm = NULL; __u16 id; - /* if the transforms are already allocted, we are done */ - if (!net->sctp.auth_enable) { + /* If AUTH extension is disabled, we are done */ + if (!ep->auth_enable) { ep->auth_hmacs = NULL; return 0; } + /* If the transforms are already allocated, we are done */ if (ep->auth_hmacs) return 0; @@ -677,12 +676,10 @@ static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param) /* Check if peer requested that this chunk is authenticated */ int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc) { - struct net *net; if (!asoc) return 0; - net = sock_net(asoc->base.sk); - if (!net->sctp.auth_enable || !asoc->peer.auth_capable) + if (!asoc->ep->auth_enable || !asoc->peer.auth_capable) return 0; return __sctp_auth_cid(chunk, asoc->peer.peer_chunks); @@ -691,12 +688,10 @@ int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc) /* Check if we requested that peer authenticate this chunk. */ int sctp_auth_recv_cid(sctp_cid_t chunk, const struct sctp_association *asoc) { - struct net *net; if (!asoc) return 0; - net = sock_net(asoc->base.sk); - if (!net->sctp.auth_enable) + if (!asoc->ep->auth_enable) return 0; return __sctp_auth_cid(chunk, @@ -879,8 +874,6 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, list_add(&cur_key->key_list, sh_keys); cur_key->key = key; - sctp_auth_key_hold(key); - return 0; nomem: if (!replace) diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 5fbd7bc6bb11..e09f906514db 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -75,7 +75,8 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, if (!ep->digest) return NULL; - if (net->sctp.auth_enable) { + ep->auth_enable = net->sctp.auth_enable; + if (ep->auth_enable) { /* Allocate space for HMACS and CHUNKS authentication * variables. There are arrays that we encode directly * into parameters to make the rest of the operations easier. diff --git a/net/sctp/input.c b/net/sctp/input.c index 4b2c83146aa7..bd4fb459c63b 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -648,8 +648,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) break; case ICMP_REDIRECT: sctp_icmp_redirect(sk, transport, skb); - err = 0; - break; + /* Fall through to out_unlock. */ default: goto out_unlock; } diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 3221d073448c..49c58eadbfa2 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -147,18 +147,9 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) } else { /* Nothing to do. Next chunk in the packet, please. */ ch = (sctp_chunkhdr_t *) chunk->chunk_end; - /* Force chunk->skb->data to chunk->chunk_end. */ - skb_pull(chunk->skb, - chunk->chunk_end - chunk->skb->data); - - /* Verify that we have at least chunk headers - * worth of buffer left. - */ - if (skb_headlen(chunk->skb) < sizeof(sctp_chunkhdr_t)) { - sctp_chunk_free(chunk); - chunk = queue->in_progress = NULL; - } + skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data); + /* We are guaranteed to pull a SCTP header. */ } } @@ -194,24 +185,14 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - if (chunk->chunk_end < skb_tail_pointer(chunk->skb)) { + if (chunk->chunk_end + sizeof(sctp_chunkhdr_t) < + skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { - /* RFC 2960, Section 6.10 Bundling - * - * Partial chunks MUST NOT be placed in an SCTP packet. - * If the receiver detects a partial chunk, it MUST drop - * the chunk. - * - * Since the end of the chunk is past the end of our buffer - * (which contains the whole packet, we can freely discard - * the whole packet. - */ - sctp_chunk_free(chunk); - chunk = queue->in_progress = NULL; - - return NULL; + /* Discard inside state machine. */ + chunk->pdiscard = 1; + chunk->chunk_end = skb_tail_pointer(chunk->skb); } else { /* We are at the end of the packet, so mark the chunk * in case we need to send a SACK. diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 391a245d5203..422d8bdacc0d 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -189,7 +189,7 @@ SCTP_STATIC void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, break; case NDISC_REDIRECT: sctp_icmp_redirect(sk, transport, skb); - break; + goto out_unlock; default: break; } @@ -210,45 +210,24 @@ out: in6_dev_put(idev); } -/* Based on tcp_v6_xmit() in tcp_ipv6.c. */ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) { struct sock *sk = skb->sk; struct ipv6_pinfo *np = inet6_sk(sk); - struct flowi6 fl6; - - memset(&fl6, 0, sizeof(fl6)); - - fl6.flowi6_proto = sk->sk_protocol; - - /* Fill in the dest address from the route entry passed with the skb - * and the source address from the transport. - */ - fl6.daddr = transport->ipaddr.v6.sin6_addr; - fl6.saddr = transport->saddr.v6.sin6_addr; - - fl6.flowlabel = np->flow_label; - IP6_ECN_flow_xmit(sk, fl6.flowlabel); - if (ipv6_addr_type(&fl6.saddr) & IPV6_ADDR_LINKLOCAL) - fl6.flowi6_oif = transport->saddr.v6.sin6_scope_id; - else - fl6.flowi6_oif = sk->sk_bound_dev_if; - - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt; - fl6.daddr = *rt0->addr; - } + struct flowi6 *fl6 = &transport->fl.u.ip6; SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb, skb->len, - &fl6.saddr, &fl6.daddr); + &fl6->saddr, &fl6->daddr); - SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); + IP6_ECN_flow_xmit(sk, fl6->flowlabel); if (!(transport->param_flags & SPP_PMTUD_ENABLE)) skb->local_df = 1; - return ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); + SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); + + return ip6_xmit(sk, skb, fl6, np->opt, np->tclass); } /* Returns the dst cache entry for the given source and destination ip @@ -261,10 +240,12 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, struct dst_entry *dst = NULL; struct flowi6 *fl6 = &fl->u.ip6; struct sctp_bind_addr *bp; + struct ipv6_pinfo *np = inet6_sk(sk); struct sctp_sockaddr_entry *laddr; union sctp_addr *baddr = NULL; union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; + struct in6_addr *final_p, final; __u8 matchlen = 0; __u8 bmatchlen; sctp_scope_t scope; @@ -287,7 +268,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, SCTP_DEBUG_PRINTK("SRC=%pI6 - ", &fl6->saddr); } - dst = ip6_dst_lookup_flow(sk, fl6, NULL, false); + final_p = fl6_update_dst(fl6, np->opt, &final); + dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); if (!asoc || saddr) goto out; @@ -339,10 +321,12 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, } } rcu_read_unlock(); + if (baddr) { fl6->saddr = baddr->v6.sin6_addr; fl6->fl6_sport = baddr->v6.sin6_port; - dst = ip6_dst_lookup_flow(sk, fl6, NULL, false); + final_p = fl6_update_dst(fl6, np->opt, &final); + dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); } out: diff --git a/net/sctp/output.c b/net/sctp/output.c index bbef4a7a9b56..73b8ca51ba14 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -413,12 +413,12 @@ int sctp_packet_transmit(struct sctp_packet *packet) sk = chunk->skb->sk; /* Allocate the new skb. */ - nskb = alloc_skb(packet->size + LL_MAX_HEADER, GFP_ATOMIC); + nskb = alloc_skb(packet->size + MAX_HEADER, GFP_ATOMIC); if (!nskb) goto nomem; /* Make sure the outbound skb has enough header room reserved. */ - skb_reserve(nskb, packet->overhead + LL_MAX_HEADER); + skb_reserve(nskb, packet->overhead + MAX_HEADER); /* Set the owning socket so that we know where to get the * destination IP address. @@ -547,7 +547,8 @@ int sctp_packet_transmit(struct sctp_packet *packet) * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>. */ if (!sctp_checksum_disable) { - if (!(dst->dev->features & NETIF_F_SCTP_CSUM)) { + if (!(dst->dev->features & NETIF_F_SCTP_CSUM) || + (dst_xfrm(dst) != NULL) || packet->ipfragok) { __u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len); /* 3) Put the resultant value into the checksum field in the @@ -617,7 +618,7 @@ out: return err; no_route: kfree_skb(nskb); - IP_INC_STATS_BH(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); /* FIXME: Returning the 'err' will effect all the associations * associated with a socket, although only one of the paths of the diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index eaee00c61139..5a3c1c0a84a1 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -498,8 +498,13 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, continue; if ((laddr->state == SCTP_ADDR_SRC) && (AF_INET == laddr->a.sa.sa_family)) { - fl4->saddr = laddr->a.v4.sin_addr.s_addr; fl4->fl4_sport = laddr->a.v4.sin_port; + flowi4_update_output(fl4, + asoc->base.sk->sk_bound_dev_if, + RT_CONN_FLAGS(asoc->base.sk), + daddr->v4.sin_addr.s_addr, + laddr->a.v4.sin_addr.s_addr); + rt = ip_route_output_key(sock_net(sk), fl4); if (!IS_ERR(rt)) { dst = &rt->dst; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index cf579e71cff0..beedadf62f6c 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -199,6 +199,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, gfp_t gfp, int vparam_len) { struct net *net = sock_net(asoc->base.sk); + struct sctp_endpoint *ep = asoc->ep; sctp_inithdr_t init; union sctp_params addrs; size_t chunksize; @@ -258,7 +259,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, chunksize += vparam_len; /* Account for AUTH related parameters */ - if (net->sctp.auth_enable) { + if (ep->auth_enable) { /* Add random parameter length*/ chunksize += sizeof(asoc->c.auth_random); @@ -343,7 +344,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, } /* Add SCTP-AUTH chunks to the parameter list */ - if (net->sctp.auth_enable) { + if (ep->auth_enable) { sctp_addto_chunk(retval, sizeof(asoc->c.auth_random), asoc->c.auth_random); if (auth_hmacs) @@ -1403,8 +1404,8 @@ static void sctp_chunk_destroy(struct sctp_chunk *chunk) BUG_ON(!list_empty(&chunk->list)); list_del_init(&chunk->transmitted_list); - /* Free the chunk skb data and the SCTP_chunk stub itself. */ - dev_kfree_skb(chunk->skb); + consume_skb(chunk->skb); + consume_skb(chunk->auth_chunk); SCTP_DBG_OBJCNT_DEC(chunk); kmem_cache_free(sctp_chunk_cachep, chunk); @@ -1995,7 +1996,7 @@ static void sctp_process_ext_param(struct sctp_association *asoc, /* if the peer reports AUTH, assume that he * supports AUTH. */ - if (net->sctp.auth_enable) + if (asoc->ep->auth_enable) asoc->peer.auth_capable = 1; break; case SCTP_CID_ASCONF: @@ -2087,6 +2088,7 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc, * SCTP_IERROR_NO_ERROR - continue with the chunk */ static sctp_ierror_t sctp_verify_param(struct net *net, + const struct sctp_endpoint *ep, const struct sctp_association *asoc, union sctp_params param, sctp_cid_t cid, @@ -2137,7 +2139,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, goto fallthrough; case SCTP_PARAM_RANDOM: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fallthrough; /* SCTP-AUTH: Secion 6.1 @@ -2154,7 +2156,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, break; case SCTP_PARAM_CHUNKS: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fallthrough; /* SCTP-AUTH: Section 3.2 @@ -2170,7 +2172,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, break; case SCTP_PARAM_HMAC_ALGO: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fallthrough; hmacs = (struct sctp_hmac_algo_param *)param.p; @@ -2204,10 +2206,9 @@ fallthrough: } /* Verify the INIT packet before we process it. */ -int sctp_verify_init(struct net *net, const struct sctp_association *asoc, - sctp_cid_t cid, - sctp_init_chunk_t *peer_init, - struct sctp_chunk *chunk, +int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, sctp_cid_t cid, + sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk, struct sctp_chunk **errp) { union sctp_params param; @@ -2250,8 +2251,8 @@ int sctp_verify_init(struct net *net, const struct sctp_association *asoc, /* Verify all the variable length parameters */ sctp_walk_params(param, peer_init, init_hdr.params) { - - result = sctp_verify_param(net, asoc, param, cid, chunk, errp); + result = sctp_verify_param(net, ep, asoc, param, cid, + chunk, errp); switch (result) { case SCTP_IERROR_ABORT: case SCTP_IERROR_NOMEM: @@ -2483,6 +2484,7 @@ static int sctp_process_param(struct sctp_association *asoc, struct sctp_af *af; union sctp_addr_param *addr_param; struct sctp_transport *t; + struct sctp_endpoint *ep = asoc->ep; /* We maintain all INIT parameters in network byte order all the * time. This allows us to not worry about whether the parameters @@ -2593,7 +2595,10 @@ do_addr_param: addr_param = param.v + sizeof(sctp_addip_param_t); - af = sctp_get_af_specific(param_type2af(param.p->type)); + af = sctp_get_af_specific(param_type2af(addr_param->p.type)); + if (af == NULL) + break; + af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0); @@ -2623,7 +2628,7 @@ do_addr_param: goto fall_through; case SCTP_PARAM_RANDOM: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fall_through; /* Save peer's random parameter */ @@ -2636,7 +2641,7 @@ do_addr_param: break; case SCTP_PARAM_HMAC_ALGO: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fall_through; /* Save peer's HMAC list */ @@ -2652,7 +2657,7 @@ do_addr_param: break; case SCTP_PARAM_CHUNKS: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fall_through; asoc->peer.peer_chunks = kmemdup(param.p, @@ -3092,50 +3097,63 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, return SCTP_ERROR_NO_ERROR; } -/* Verify the ASCONF packet before we process it. */ -int sctp_verify_asconf(const struct sctp_association *asoc, - struct sctp_paramhdr *param_hdr, void *chunk_end, - struct sctp_paramhdr **errp) { - sctp_addip_param_t *asconf_param; +/* Verify the ASCONF packet before we process it. */ +bool sctp_verify_asconf(const struct sctp_association *asoc, + struct sctp_chunk *chunk, bool addr_param_needed, + struct sctp_paramhdr **errp) +{ + sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) chunk->chunk_hdr; union sctp_params param; - int length, plen; - - param.v = (sctp_paramhdr_t *) param_hdr; - while (param.v <= chunk_end - sizeof(sctp_paramhdr_t)) { - length = ntohs(param.p->length); - *errp = param.p; + bool addr_param_seen = false; - if (param.v > chunk_end - length || - length < sizeof(sctp_paramhdr_t)) - return 0; + sctp_walk_params(param, addip, addip_hdr.params) { + size_t length = ntohs(param.p->length); + *errp = param.p; switch (param.p->type) { + case SCTP_PARAM_ERR_CAUSE: + break; + case SCTP_PARAM_IPV4_ADDRESS: + if (length != sizeof(sctp_ipv4addr_param_t)) + return false; + addr_param_seen = true; + break; + case SCTP_PARAM_IPV6_ADDRESS: + if (length != sizeof(sctp_ipv6addr_param_t)) + return false; + addr_param_seen = true; + break; case SCTP_PARAM_ADD_IP: case SCTP_PARAM_DEL_IP: case SCTP_PARAM_SET_PRIMARY: - asconf_param = (sctp_addip_param_t *)param.v; - plen = ntohs(asconf_param->param_hdr.length); - if (plen < sizeof(sctp_addip_param_t) + - sizeof(sctp_paramhdr_t)) - return 0; + /* In ASCONF chunks, these need to be first. */ + if (addr_param_needed && !addr_param_seen) + return false; + length = ntohs(param.addip->param_hdr.length); + if (length < sizeof(sctp_addip_param_t) + + sizeof(sctp_paramhdr_t)) + return false; break; case SCTP_PARAM_SUCCESS_REPORT: case SCTP_PARAM_ADAPTATION_LAYER_IND: if (length != sizeof(sctp_addip_param_t)) - return 0; - + return false; break; default: - break; + /* This is unkown to us, reject! */ + return false; } - - param.v += WORD_ROUND(length); } - if (param.v != chunk_end) - return 0; + /* Remaining sanity checks. */ + if (addr_param_needed && !addr_param_seen) + return false; + if (!addr_param_needed && addr_param_seen) + return false; + if (param.v != chunk->chunk_end) + return false; - return 1; + return true; } /* Process an incoming ASCONF chunk with the next expected serial no. and @@ -3144,16 +3162,17 @@ int sctp_verify_asconf(const struct sctp_association *asoc, struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, struct sctp_chunk *asconf) { + sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) asconf->chunk_hdr; + bool all_param_pass = true; + union sctp_params param; sctp_addiphdr_t *hdr; union sctp_addr_param *addr_param; sctp_addip_param_t *asconf_param; struct sctp_chunk *asconf_ack; - __be16 err_code; int length = 0; int chunk_len; __u32 serial; - int all_param_pass = 1; chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); hdr = (sctp_addiphdr_t *)asconf->skb->data; @@ -3181,9 +3200,14 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, goto done; /* Process the TLVs contained within the ASCONF chunk. */ - while (chunk_len > 0) { + sctp_walk_params(param, addip, addip_hdr.params) { + /* Skip preceeding address parameters. */ + if (param.p->type == SCTP_PARAM_IPV4_ADDRESS || + param.p->type == SCTP_PARAM_IPV6_ADDRESS) + continue; + err_code = sctp_process_asconf_param(asoc, asconf, - asconf_param); + param.addip); /* ADDIP 4.1 A7) * If an error response is received for a TLV parameter, * all TLVs with no response before the failed TLV are @@ -3191,28 +3215,20 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, * the failed response are considered unsuccessful unless * a specific success indication is present for the parameter. */ - if (SCTP_ERROR_NO_ERROR != err_code) - all_param_pass = 0; - + if (err_code != SCTP_ERROR_NO_ERROR) + all_param_pass = false; if (!all_param_pass) - sctp_add_asconf_response(asconf_ack, - asconf_param->crr_id, err_code, - asconf_param); + sctp_add_asconf_response(asconf_ack, param.addip->crr_id, + err_code, param.addip); /* ADDIP 4.3 D11) When an endpoint receiving an ASCONF to add * an IP address sends an 'Out of Resource' in its response, it * MUST also fail any subsequent add or delete requests bundled * in the ASCONF. */ - if (SCTP_ERROR_RSRC_LOW == err_code) + if (err_code == SCTP_ERROR_RSRC_LOW) goto done; - - /* Move to the next ASCONF param. */ - length = ntohs(asconf_param->param_hdr.length); - asconf_param = (void *)asconf_param + length; - chunk_len -= length; } - done: asoc->peer.addip_serial++; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index de1a0138317f..c52763a26297 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -177,6 +177,9 @@ sctp_chunk_length_valid(struct sctp_chunk *chunk, { __u16 chunk_length = ntohs(chunk->chunk_hdr->length); + /* Previously already marked? */ + if (unlikely(chunk->pdiscard)) + return 0; if (unlikely(chunk_length < required_length)) return 0; @@ -364,7 +367,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, /* Verify the INIT chunk before processing it. */ err_chunk = NULL; - if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type, + if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. @@ -531,7 +534,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, /* Verify the INIT chunk before processing it. */ err_chunk = NULL; - if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type, + if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, &err_chunk)) { @@ -765,6 +768,12 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, struct sctp_chunk auth; sctp_ierror_t ret; + /* Make sure that we and the peer are AUTH capable */ + if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + /* set-up our fake chunk so that we can process it */ auth.skb = chunk->auth_chunk; auth.asoc = chunk->asoc; @@ -775,10 +784,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, auth.transport = chunk->transport; ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth); - - /* We can now safely free the auth_chunk clone */ - kfree_skb(chunk->auth_chunk); - if (ret != SCTP_IERROR_NO_ERROR) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -1435,7 +1440,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( /* Verify the INIT chunk before processing it. */ err_chunk = NULL; - if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type, + if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. @@ -1780,9 +1785,22 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net, /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); - sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, - SCTP_STATE(SCTP_STATE_ESTABLISHED)); - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + if (sctp_state(asoc, SHUTDOWN_PENDING) && + (sctp_sstate(asoc->base.sk, CLOSING) || + sock_flag(asoc->base.sk, SOCK_DEAD))) { + /* if were currently in SHUTDOWN_PENDING, but the socket + * has been closed by user, don't transition to ESTABLISHED. + * Instead trigger SHUTDOWN bundled with COOKIE_ACK. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + return sctp_sf_do_9_2_start_shutdown(net, ep, asoc, + SCTP_ST_CHUNK(0), NULL, + commands); + } else { + sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, + SCTP_STATE(SCTP_STATE_ESTABLISHED)); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + } return SCTP_DISPOSITION_CONSUME; nomem_ev: @@ -3578,9 +3596,7 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net, struct sctp_chunk *asconf_ack = NULL; struct sctp_paramhdr *err_param = NULL; sctp_addiphdr_t *hdr; - union sctp_addr_param *addr_param; __u32 serial; - int length; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, @@ -3605,17 +3621,8 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net, hdr = (sctp_addiphdr_t *)chunk->skb->data; serial = ntohl(hdr->serial); - addr_param = (union sctp_addr_param *)hdr->params; - length = ntohs(addr_param->p.length); - if (length < sizeof(sctp_paramhdr_t)) - return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, - (void *)addr_param, commands); - /* Verify the ASCONF chunk before processing it. */ - if (!sctp_verify_asconf(asoc, - (sctp_paramhdr_t *)((void *)addr_param + length), - (void *)chunk->chunk_end, - &err_param)) + if (!sctp_verify_asconf(asoc, chunk, true, &err_param)) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err_param, commands); @@ -3733,10 +3740,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, rcvd_serial = ntohl(addip_hdr->serial); /* Verify the ASCONF-ACK chunk before processing it. */ - if (!sctp_verify_asconf(asoc, - (sctp_paramhdr_t *)addip_hdr->params, - (void *)asconf_ack->chunk_end, - &err_param)) + if (!sctp_verify_asconf(asoc, asconf_ack, false, &err_param)) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, (void *)err_param, commands); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6abb1caf9836..dfb9b133e662 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -71,6 +71,7 @@ #include <linux/crypto.h> #include <linux/slab.h> #include <linux/file.h> +#include <linux/compat.h> #include <net/ip.h> #include <net/icmp.h> @@ -820,6 +821,9 @@ static int sctp_send_asconf_del_ip(struct sock *sk, goto skip_mkasconf; } + if (laddr == NULL) + return -EINVAL; + /* We do not need RCU protection throughout this loop * because this is done under a socket lock from the * setsockopt call. @@ -1381,11 +1385,19 @@ SCTP_STATIC int sctp_setsockopt_connectx(struct sock* sk, /* * New (hopefully final) interface for the API. * We use the sctp_getaddrs_old structure so that use-space library - * can avoid any unnecessary allocations. The only defferent part + * can avoid any unnecessary allocations. The only different part * is that we store the actual length of the address buffer into the - * addrs_num structure member. That way we can re-use the existing + * addrs_num structure member. That way we can re-use the existing * code. */ +#ifdef CONFIG_COMPAT +struct compat_sctp_getaddrs_old { + sctp_assoc_t assoc_id; + s32 addr_num; + compat_uptr_t addrs; /* struct sockaddr * */ +}; +#endif + SCTP_STATIC int sctp_getsockopt_connectx3(struct sock* sk, int len, char __user *optval, int __user *optlen) @@ -1394,16 +1406,30 @@ SCTP_STATIC int sctp_getsockopt_connectx3(struct sock* sk, int len, sctp_assoc_t assoc_id = 0; int err = 0; - if (len < sizeof(param)) - return -EINVAL; +#ifdef CONFIG_COMPAT + if (is_compat_task()) { + struct compat_sctp_getaddrs_old param32; - if (copy_from_user(¶m, optval, sizeof(param))) - return -EFAULT; + if (len < sizeof(param32)) + return -EINVAL; + if (copy_from_user(¶m32, optval, sizeof(param32))) + return -EFAULT; - err = __sctp_setsockopt_connectx(sk, - (struct sockaddr __user *)param.addrs, - param.addr_num, &assoc_id); + param.assoc_id = param32.assoc_id; + param.addr_num = param32.addr_num; + param.addrs = compat_ptr(param32.addrs); + } else +#endif + { + if (len < sizeof(param)) + return -EINVAL; + if (copy_from_user(¶m, optval, sizeof(param))) + return -EFAULT; + } + err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *) + param.addrs, param.addr_num, + &assoc_id); if (err == 0 || err == -EINPROGRESS) { if (copy_to_user(optval, &assoc_id, sizeof(assoc_id))) return -EFAULT; @@ -3292,10 +3318,10 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authchunk val; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen != sizeof(struct sctp_authchunk)) @@ -3312,7 +3338,7 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, } /* add this chunk id to the endpoint */ - return sctp_auth_ep_add_chunkid(sctp_sk(sk)->ep, val.sauth_chunk); + return sctp_auth_ep_add_chunkid(ep, val.sauth_chunk); } /* @@ -3325,12 +3351,12 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_hmacalgo *hmacs; u32 idents; int err; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen < sizeof(struct sctp_hmacalgo)) @@ -3347,7 +3373,7 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk, goto out; } - err = sctp_auth_ep_set_hmacs(sctp_sk(sk)->ep, hmacs); + err = sctp_auth_ep_set_hmacs(ep, hmacs); out: kfree(hmacs); return err; @@ -3363,12 +3389,12 @@ static int sctp_setsockopt_auth_key(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkey *authkey; struct sctp_association *asoc; int ret; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen <= sizeof(struct sctp_authkey)) @@ -3389,7 +3415,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk, goto out; } - ret = sctp_auth_set_key(sctp_sk(sk)->ep, asoc, authkey); + ret = sctp_auth_set_key(ep, asoc, authkey); out: kzfree(authkey); return ret; @@ -3405,11 +3431,11 @@ static int sctp_setsockopt_active_key(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkeyid val; struct sctp_association *asoc; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen != sizeof(struct sctp_authkeyid)) @@ -3421,8 +3447,7 @@ static int sctp_setsockopt_active_key(struct sock *sk, if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_set_active_key(sctp_sk(sk)->ep, asoc, - val.scact_keynumber); + return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber); } /* @@ -3434,11 +3459,11 @@ static int sctp_setsockopt_del_key(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkeyid val; struct sctp_association *asoc; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen != sizeof(struct sctp_authkeyid)) @@ -3450,8 +3475,7 @@ static int sctp_setsockopt_del_key(struct sock *sk, if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_del_key_id(sctp_sk(sk)->ep, asoc, - val.scact_keynumber); + return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber); } @@ -5342,16 +5366,16 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_hmacalgo __user *p = (void __user *)optval; struct sctp_hmac_algo_param *hmacs; __u16 data_len = 0; u32 num_idents; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; - hmacs = sctp_sk(sk)->ep->auth_hmacs_list; + hmacs = ep->auth_hmacs_list; data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t); if (len < sizeof(struct sctp_hmacalgo) + data_len) @@ -5372,11 +5396,11 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, static int sctp_getsockopt_active_key(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkeyid val; struct sctp_association *asoc; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (len < sizeof(struct sctp_authkeyid)) @@ -5391,7 +5415,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len, if (asoc) val.scact_keynumber = asoc->active_key_id; else - val.scact_keynumber = sctp_sk(sk)->ep->active_key_id; + val.scact_keynumber = ep->active_key_id; len = sizeof(struct sctp_authkeyid); if (put_user(len, optlen)) @@ -5405,7 +5429,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len, static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; @@ -5413,7 +5437,7 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, u32 num_chunks = 0; char __user *to; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (len < sizeof(struct sctp_authchunks)) @@ -5449,7 +5473,7 @@ num: static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; @@ -5457,7 +5481,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, u32 num_chunks = 0; char __user *to; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (len < sizeof(struct sctp_authchunks)) @@ -5474,7 +5498,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, if (asoc) ch = (struct sctp_chunks_param*)asoc->c.auth_chunks; else - ch = sctp_sk(sk)->ep->auth_chunk_list; + ch = ep->auth_chunk_list; if (!ch) goto num; @@ -6193,7 +6217,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Is there any exceptional events? */ if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) mask |= POLLERR | - sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0; + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) @@ -6556,6 +6580,46 @@ static void __sctp_write_space(struct sctp_association *asoc) } } +static void sctp_wake_up_waiters(struct sock *sk, + struct sctp_association *asoc) +{ + struct sctp_association *tmp = asoc; + + /* We do accounting for the sndbuf space per association, + * so we only need to wake our own association. + */ + if (asoc->ep->sndbuf_policy) + return __sctp_write_space(asoc); + + /* If association goes down and is just flushing its + * outq, then just normally notify others. + */ + if (asoc->base.dead) + return sctp_write_space(sk); + + /* Accounting for the sndbuf space is per socket, so we + * need to wake up others, try to be fair and in case of + * other associations, let them have a go first instead + * of just doing a sctp_write_space() call. + * + * Note that we reach sctp_wake_up_waiters() only when + * associations free up queued chunks, thus we are under + * lock and the list of associations on a socket is + * guaranteed not to change. + */ + for (tmp = list_next_entry(tmp, asocs); 1; + tmp = list_next_entry(tmp, asocs)) { + /* Manually skip the head element. */ + if (&tmp->asocs == &((sctp_sk(sk))->ep->asocs)) + continue; + /* Wake up association. */ + __sctp_write_space(tmp); + /* We've reached the end. */ + if (tmp == asoc) + break; + } +} + /* Do accounting for the sndbuf space. * Decrement the used sndbuf space of the corresponding association by the * data size which was just transmitted(freed). @@ -6583,7 +6647,7 @@ static void sctp_wfree(struct sk_buff *skb) sk_mem_uncharge(sk, skb->truesize); sock_wfree(skb); - __sctp_write_space(asoc); + sctp_wake_up_waiters(sk, asoc); sctp_association_put(asoc); } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index bf3c6e8fc401..29299dcabfbb 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -65,8 +65,11 @@ extern int sysctl_sctp_wmem[3]; static int proc_sctp_do_hmac_alg(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, - loff_t *ppos); +static int proc_sctp_do_auth(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); + static ctl_table sctp_table[] = { { .procname = "sctp_mem", @@ -267,7 +270,7 @@ static ctl_table sctp_net_table[] = { .data = &init_net.sctp.auth_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_sctp_do_auth, }, { .procname = "addr_scope_policy", @@ -348,6 +351,36 @@ static int proc_sctp_do_hmac_alg(ctl_table *ctl, return ret; } +static int proc_sctp_do_auth(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + struct ctl_table tbl; + int new_value, ret; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.auth_enable; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { + struct sock *sk = net->sctp.ctl_sock; + + net->sctp.auth_enable = new_value; + /* Update the value in the control socket */ + lock_sock(sk); + sctp_sk(sk)->ep->auth_enable = new_value; + release_sock(sk); + } + + return ret; +} + int sctp_sysctl_net_register(struct net *net) { struct ctl_table *table; diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 10c018a5b9fe..ca907f2f5e5a 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -373,9 +373,10 @@ fail: * specification [SCTP] and any extensions for a list of possible * error formats. */ -struct sctp_ulpevent *sctp_ulpevent_make_remote_error( - const struct sctp_association *asoc, struct sctp_chunk *chunk, - __u16 flags, gfp_t gfp) +struct sctp_ulpevent * +sctp_ulpevent_make_remote_error(const struct sctp_association *asoc, + struct sctp_chunk *chunk, __u16 flags, + gfp_t gfp) { struct sctp_ulpevent *event; struct sctp_remote_error *sre; @@ -394,8 +395,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error( /* Copy the skb to a new skb with room for us to prepend * notification with. */ - skb = skb_copy_expand(chunk->skb, sizeof(struct sctp_remote_error), - 0, gfp); + skb = skb_copy_expand(chunk->skb, sizeof(*sre), 0, gfp); /* Pull off the rest of the cause TLV from the chunk. */ skb_pull(chunk->skb, elen); @@ -406,62 +406,21 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error( event = sctp_skb2event(skb); sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize); - sre = (struct sctp_remote_error *) - skb_push(skb, sizeof(struct sctp_remote_error)); + sre = (struct sctp_remote_error *) skb_push(skb, sizeof(*sre)); /* Trim the buffer to the right length. */ - skb_trim(skb, sizeof(struct sctp_remote_error) + elen); + skb_trim(skb, sizeof(*sre) + elen); - /* Socket Extensions for SCTP - * 5.3.1.3 SCTP_REMOTE_ERROR - * - * sre_type: - * It should be SCTP_REMOTE_ERROR. - */ + /* RFC6458, Section 6.1.3. SCTP_REMOTE_ERROR */ + memset(sre, 0, sizeof(*sre)); sre->sre_type = SCTP_REMOTE_ERROR; - - /* - * Socket Extensions for SCTP - * 5.3.1.3 SCTP_REMOTE_ERROR - * - * sre_flags: 16 bits (unsigned integer) - * Currently unused. - */ sre->sre_flags = 0; - - /* Socket Extensions for SCTP - * 5.3.1.3 SCTP_REMOTE_ERROR - * - * sre_length: sizeof (__u32) - * - * This field is the total length of the notification data, - * including the notification header. - */ sre->sre_length = skb->len; - - /* Socket Extensions for SCTP - * 5.3.1.3 SCTP_REMOTE_ERROR - * - * sre_error: 16 bits (unsigned integer) - * This value represents one of the Operational Error causes defined in - * the SCTP specification, in network byte order. - */ sre->sre_error = cause; - - /* Socket Extensions for SCTP - * 5.3.1.3 SCTP_REMOTE_ERROR - * - * sre_assoc_id: sizeof (sctp_assoc_t) - * - * The association id field, holds the identifier for the association. - * All notifications for a given association have the same association - * identifier. For TCP style socket, this field is ignored. - */ sctp_ulpevent_set_owner(event, asoc); sre->sre_assoc_id = sctp_assoc2id(asoc); return event; - fail: return NULL; } @@ -906,7 +865,9 @@ __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event) return notification->sn_header.sn_type; } -/* Copy out the sndrcvinfo into a msghdr. */ +/* RFC6458, Section 5.3.2. SCTP Header Information Structure + * (SCTP_SNDRCV, DEPRECATED) + */ void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event, struct msghdr *msghdr) { @@ -915,74 +876,21 @@ void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event, if (sctp_ulpevent_is_notification(event)) return; - /* Sockets API Extensions for SCTP - * Section 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV) - * - * sinfo_stream: 16 bits (unsigned integer) - * - * For recvmsg() the SCTP stack places the message's stream number in - * this value. - */ + memset(&sinfo, 0, sizeof(sinfo)); sinfo.sinfo_stream = event->stream; - /* sinfo_ssn: 16 bits (unsigned integer) - * - * For recvmsg() this value contains the stream sequence number that - * the remote endpoint placed in the DATA chunk. For fragmented - * messages this is the same number for all deliveries of the message - * (if more than one recvmsg() is needed to read the message). - */ sinfo.sinfo_ssn = event->ssn; - /* sinfo_ppid: 32 bits (unsigned integer) - * - * In recvmsg() this value is - * the same information that was passed by the upper layer in the peer - * application. Please note that byte order issues are NOT accounted - * for and this information is passed opaquely by the SCTP stack from - * one end to the other. - */ sinfo.sinfo_ppid = event->ppid; - /* sinfo_flags: 16 bits (unsigned integer) - * - * This field may contain any of the following flags and is composed of - * a bitwise OR of these values. - * - * recvmsg() flags: - * - * SCTP_UNORDERED - This flag is present when the message was sent - * non-ordered. - */ sinfo.sinfo_flags = event->flags; - /* sinfo_tsn: 32 bit (unsigned integer) - * - * For the receiving side, this field holds a TSN that was - * assigned to one of the SCTP Data Chunks. - */ sinfo.sinfo_tsn = event->tsn; - /* sinfo_cumtsn: 32 bit (unsigned integer) - * - * This field will hold the current cumulative TSN as - * known by the underlying SCTP layer. Note this field is - * ignored when sending and only valid for a receive - * operation when sinfo_flags are set to SCTP_UNORDERED. - */ sinfo.sinfo_cumtsn = event->cumtsn; - /* sinfo_assoc_id: sizeof (sctp_assoc_t) - * - * The association handle field, sinfo_assoc_id, holds the identifier - * for the association announced in the COMMUNICATION_UP notification. - * All notifications for a given association have the same identifier. - * Ignored for one-to-one style sockets. - */ sinfo.sinfo_assoc_id = sctp_assoc2id(event->asoc); - - /* context value that is set via SCTP_CONTEXT socket option. */ + /* Context value that is set via SCTP_CONTEXT socket option. */ sinfo.sinfo_context = event->asoc->default_rcv_context; - /* These fields are not used while receiving. */ sinfo.sinfo_timetolive = 0; put_cmsg(msghdr, IPPROTO_SCTP, SCTP_SNDRCV, - sizeof(struct sctp_sndrcvinfo), (void *)&sinfo); + sizeof(sinfo), &sinfo); } /* Do accounting for bytes received and hold a reference to the association diff --git a/net/socket.c b/net/socket.c index 4ca1526db756..fc90b4f0da3c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -215,12 +215,13 @@ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen, int err; int len; + BUG_ON(klen > sizeof(struct sockaddr_storage)); err = get_user(len, ulen); if (err) return err; if (len > klen) len = klen; - if (len < 0 || len > sizeof(struct sockaddr_storage)) + if (len < 0) return -EINVAL; if (len) { if (audit_sockaddr(klen, kaddr)) @@ -1832,8 +1833,10 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, msg.msg_iov = &iov; iov.iov_len = size; iov.iov_base = ubuf; - msg.msg_name = (struct sockaddr *)&address; - msg.msg_namelen = sizeof(address); + /* Save some cycles and don't copy the address if not needed */ + msg.msg_name = addr ? (struct sockaddr *)&address : NULL; + /* We assume all kernel code knows the size of sockaddr_storage */ + msg.msg_namelen = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, size, flags); @@ -1956,6 +1959,20 @@ struct used_address { unsigned int name_len; }; +static int copy_msghdr_from_user(struct msghdr *kmsg, + struct msghdr __user *umsg) +{ + if (copy_from_user(kmsg, umsg, sizeof(struct msghdr))) + return -EFAULT; + + if (kmsg->msg_namelen < 0) + return -EINVAL; + + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) + kmsg->msg_namelen = sizeof(struct sockaddr_storage); + return 0; +} + static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address) @@ -1974,8 +1991,11 @@ static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg, if (MSG_CMSG_COMPAT & flags) { if (get_compat_msghdr(msg_sys, msg_compat)) return -EFAULT; - } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) - return -EFAULT; + } else { + err = copy_msghdr_from_user(msg_sys, msg); + if (err) + return err; + } if (msg_sys->msg_iovlen > UIO_FASTIOV) { err = -EMSGSIZE; @@ -2183,8 +2203,11 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, if (MSG_CMSG_COMPAT & flags) { if (get_compat_msghdr(msg_sys, msg_compat)) return -EFAULT; - } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) - return -EFAULT; + } else { + err = copy_msghdr_from_user(msg_sys, msg); + if (err) + return err; + } if (msg_sys->msg_iovlen > UIO_FASTIOV) { err = -EMSGSIZE; @@ -2197,16 +2220,14 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, goto out; } - /* - * Save the user-mode address (verify_iovec will change the - * kernel msghdr to use the kernel address space) + /* Save the user-mode address (verify_iovec will change the + * kernel msghdr to use the kernel address space) */ - uaddr = (__force void __user *)msg_sys->msg_name; uaddr_len = COMPAT_NAMELEN(msg); - if (MSG_CMSG_COMPAT & flags) { + if (MSG_CMSG_COMPAT & flags) err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE); - } else + else err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE); if (err < 0) goto out_freeiov; @@ -2215,6 +2236,9 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, cmsg_ptr = (unsigned long)msg_sys->msg_control; msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); + /* We assume all kernel code knows the size of sockaddr_storage */ + msg_sys->msg_namelen = 0; + if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys, diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index d304f41260f2..f1eb0d16666c 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -120,7 +120,7 @@ static int gssp_rpc_create(struct net *net, struct rpc_clnt **_clnt) if (IS_ERR(clnt)) { dprintk("RPC: failed to create AF_LOCAL gssproxy " "client (errno %ld).\n", PTR_ERR(clnt)); - result = -PTR_ERR(clnt); + result = PTR_ERR(clnt); *_clnt = NULL; goto out; } @@ -213,6 +213,26 @@ static int gssp_call(struct net *net, struct rpc_message *msg) return status; } +static void gssp_free_receive_pages(struct gssx_arg_accept_sec_context *arg) +{ + int i; + + for (i = 0; i < arg->npages && arg->pages[i]; i++) + __free_page(arg->pages[i]); +} + +static int gssp_alloc_receive_pages(struct gssx_arg_accept_sec_context *arg) +{ + arg->npages = DIV_ROUND_UP(NGROUPS_MAX * 4, PAGE_SIZE); + arg->pages = kzalloc(arg->npages * sizeof(struct page *), GFP_KERNEL); + /* + * XXX: actual pages are allocated by xdr layer in + * xdr_partial_copy_from_skb. + */ + if (!arg->pages) + return -ENOMEM; + return 0; +} /* * Public functions @@ -261,10 +281,16 @@ int gssp_accept_sec_context_upcall(struct net *net, arg.context_handle = &ctxh; res.output_token->len = GSSX_max_output_token_sz; + ret = gssp_alloc_receive_pages(&arg); + if (ret) + return ret; + /* use nfs/ for targ_name ? */ ret = gssp_call(net, &msg); + gssp_free_receive_pages(&arg); + /* we need to fetch all data even in case of error so * that we can free special strctures is they have been allocated */ data->major_status = res.status.major_status; @@ -328,7 +354,6 @@ void gssp_free_upcall_data(struct gssp_upcall_data *data) kfree(data->in_handle.data); kfree(data->out_handle.data); kfree(data->out_token.data); - kfree(data->mech_oid.data); free_svc_cred(&data->creds); } diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 357f613df7ff..f0f78c5f1c7d 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -166,14 +166,15 @@ static int dummy_dec_opt_array(struct xdr_stream *xdr, return 0; } -static int get_s32(void **p, void *max, s32 *res) +static int get_host_u32(struct xdr_stream *xdr, u32 *res) { - void *base = *p; - void *next = (void *)((char *)base + sizeof(s32)); - if (unlikely(next > max || next < base)) + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (!p) return -EINVAL; - memcpy(res, base, sizeof(s32)); - *p = next; + /* Contents of linux creds are all host-endian: */ + memcpy(res, p, sizeof(u32)); return 0; } @@ -182,9 +183,9 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr, { u32 length; __be32 *p; - void *q, *end; - s32 tmp; - int N, i, err; + u32 tmp; + u32 N; + int i, err; p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) @@ -192,33 +193,28 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr, length = be32_to_cpup(p); - /* FIXME: we do not want to use the scratch buffer for this one - * may need to use functions that allows us to access an io vector - * directly */ - p = xdr_inline_decode(xdr, length); - if (unlikely(p == NULL)) + if (length > (3 + NGROUPS_MAX) * sizeof(u32)) return -ENOSPC; - q = p; - end = q + length; - /* uid */ - err = get_s32(&q, end, &tmp); + err = get_host_u32(xdr, &tmp); if (err) return err; creds->cr_uid = make_kuid(&init_user_ns, tmp); /* gid */ - err = get_s32(&q, end, &tmp); + err = get_host_u32(xdr, &tmp); if (err) return err; creds->cr_gid = make_kgid(&init_user_ns, tmp); /* number of additional gid's */ - err = get_s32(&q, end, &tmp); + err = get_host_u32(xdr, &tmp); if (err) return err; N = tmp; + if ((3 + N) * sizeof(u32) != length) + return -EINVAL; creds->cr_group_info = groups_alloc(N); if (creds->cr_group_info == NULL) return -ENOMEM; @@ -226,7 +222,7 @@ static int gssx_dec_linux_creds(struct xdr_stream *xdr, /* gid's */ for (i = 0; i < N; i++) { kgid_t kgid; - err = get_s32(&q, end, &tmp); + err = get_host_u32(xdr, &tmp); if (err) goto out_free_groups; err = -EINVAL; @@ -430,7 +426,7 @@ static int dummy_enc_nameattr_array(struct xdr_stream *xdr, static int dummy_dec_nameattr_array(struct xdr_stream *xdr, struct gssx_name_attr_array *naa) { - struct gssx_name_attr dummy; + struct gssx_name_attr dummy = { .attr = {.len = 0} }; u32 count, i; __be32 *p; @@ -493,12 +489,13 @@ static int gssx_enc_name(struct xdr_stream *xdr, return err; } + static int gssx_dec_name(struct xdr_stream *xdr, struct gssx_name *name) { - struct xdr_netobj dummy_netobj; - struct gssx_name_attr_array dummy_name_attr_array; - struct gssx_option_array dummy_option_array; + struct xdr_netobj dummy_netobj = { .len = 0 }; + struct gssx_name_attr_array dummy_name_attr_array = { .count = 0 }; + struct gssx_option_array dummy_option_array = { .count = 0 }; int err; /* name->display_name */ @@ -783,6 +780,9 @@ void gssx_enc_accept_sec_context(struct rpc_rqst *req, /* arg->options */ err = dummy_enc_opt_array(xdr, &arg->options); + xdr_inline_pages(&req->rq_rcv_buf, + PAGE_SIZE/2 /* pretty arbitrary */, + arg->pages, 0 /* page base */, arg->npages * PAGE_SIZE); done: if (err) dprintk("RPC: gssx_enc_accept_sec_context: %d\n", err); diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h index 1c98b27d870c..685a688f3d8a 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.h +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h @@ -147,6 +147,8 @@ struct gssx_arg_accept_sec_context { struct gssx_cb *input_cb; u32 ret_deleg_cred; struct gssx_option_array options; + struct page **pages; + unsigned int npages; }; struct gssx_res_accept_sec_context { @@ -240,7 +242,8 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, 2 * GSSX_max_princ_sz + \ 8 + 8 + 4 + 4 + 4) #define GSSX_max_output_token_sz 1024 -#define GSSX_max_creds_sz (4 + 4 + 4 + NGROUPS_MAX * 4) +/* grouplist not included; we allocate separate pages for that: */ +#define GSSX_max_creds_sz (4 + 4 + 4 /* + NGROUPS_MAX*4 */) #define GSSX_RES_accept_sec_context_sz (GSSX_default_status_sz + \ GSSX_default_ctx_sz + \ GSSX_max_output_token_sz + \ diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 80fe5c86efd1..231b71944c52 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -930,7 +930,7 @@ static unsigned int cache_poll(struct file *filp, poll_table *wait, poll_wait(filp, &queue_wait, wait); /* alway allow write */ - mask = POLL_OUT | POLLWRNORM; + mask = POLLOUT | POLLWRNORM; if (!rp) return mask; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 5a750b9c3640..3524a8b50046 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1402,14 +1402,18 @@ call_refreshresult(struct rpc_task *task) task->tk_action = call_refresh; switch (status) { case 0: - if (rpcauth_uptodatecred(task)) + if (rpcauth_uptodatecred(task)) { task->tk_action = call_allocate; - return; + return; + } + /* Use rate-limiting and a max number of retries if refresh + * had status 0 but failed to update the cred. + */ case -ETIMEDOUT: rpc_delay(task, 3*HZ); - case -EKEYEXPIRED: case -EAGAIN: status = -EACCES; + case -EKEYEXPIRED: if (!task->tk_cred_retry) break; task->tk_cred_retry--; @@ -1644,6 +1648,10 @@ call_connect(struct rpc_task *task) task->tk_action = call_connect_status; if (task->tk_status < 0) return; + if (task->tk_flags & RPC_TASK_NOCONNECT) { + rpc_exit(task, -ENOTCONN); + return; + } xprt_connect(task); } } diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h index 74d948f5d5a1..779742cfc1ff 100644 --- a/net/sunrpc/netns.h +++ b/net/sunrpc/netns.h @@ -23,6 +23,7 @@ struct sunrpc_net { struct rpc_clnt *rpcb_local_clnt4; spinlock_t rpcb_clnt_lock; unsigned int rpcb_users; + unsigned int rpcb_is_af_local : 1; struct mutex gssp_lock; wait_queue_head_t gssp_wq; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 3df764dc330c..1891a1022c17 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -204,13 +204,15 @@ void rpcb_put_local(struct net *net) } static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt, - struct rpc_clnt *clnt4) + struct rpc_clnt *clnt4, + bool is_af_local) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); /* Protected by rpcb_create_local_mutex */ sn->rpcb_local_clnt = clnt; sn->rpcb_local_clnt4 = clnt4; + sn->rpcb_is_af_local = is_af_local ? 1 : 0; smp_wmb(); sn->rpcb_users = 1; dprintk("RPC: created new rpcb local clients (rpcb_local_clnt: " @@ -238,6 +240,14 @@ static int rpcb_create_local_unix(struct net *net) .program = &rpcb_program, .version = RPCBVERS_2, .authflavor = RPC_AUTH_NULL, + /* + * We turn off the idle timeout to prevent the kernel + * from automatically disconnecting the socket. + * Otherwise, we'd have to cache the mount namespace + * of the caller and somehow pass that to the socket + * reconnect code. + */ + .flags = RPC_CLNT_CREATE_NO_IDLE_TIMEOUT, }; struct rpc_clnt *clnt, *clnt4; int result = 0; @@ -263,7 +273,7 @@ static int rpcb_create_local_unix(struct net *net) clnt4 = NULL; } - rpcb_set_local(net, clnt, clnt4); + rpcb_set_local(net, clnt, clnt4, true); out: return result; @@ -315,7 +325,7 @@ static int rpcb_create_local_net(struct net *net) clnt4 = NULL; } - rpcb_set_local(net, clnt, clnt4); + rpcb_set_local(net, clnt, clnt4, false); out: return result; @@ -376,13 +386,16 @@ static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname, return rpc_create(&args); } -static int rpcb_register_call(struct rpc_clnt *clnt, struct rpc_message *msg) +static int rpcb_register_call(struct sunrpc_net *sn, struct rpc_clnt *clnt, struct rpc_message *msg, bool is_set) { - int result, error = 0; + int flags = RPC_TASK_NOCONNECT; + int error, result = 0; + if (is_set || !sn->rpcb_is_af_local) + flags = RPC_TASK_SOFTCONN; msg->rpc_resp = &result; - error = rpc_call_sync(clnt, msg, RPC_TASK_SOFTCONN); + error = rpc_call_sync(clnt, msg, flags); if (error < 0) { dprintk("RPC: failed to contact local rpcbind " "server (errno %d).\n", -error); @@ -439,16 +452,19 @@ int rpcb_register(struct net *net, u32 prog, u32 vers, int prot, unsigned short .rpc_argp = &map, }; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + bool is_set = false; dprintk("RPC: %sregistering (%u, %u, %d, %u) with local " "rpcbind\n", (port ? "" : "un"), prog, vers, prot, port); msg.rpc_proc = &rpcb_procedures2[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg.rpc_proc = &rpcb_procedures2[RPCBPROC_SET]; + is_set = true; + } - return rpcb_register_call(sn->rpcb_local_clnt, &msg); + return rpcb_register_call(sn, sn->rpcb_local_clnt, &msg, is_set); } /* @@ -461,6 +477,7 @@ static int rpcb_register_inet4(struct sunrpc_net *sn, const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin->sin_port); + bool is_set = false; int result; map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); @@ -471,10 +488,12 @@ static int rpcb_register_inet4(struct sunrpc_net *sn, map->r_addr, map->r_netid); msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; + is_set = true; + } - result = rpcb_register_call(sn->rpcb_local_clnt4, msg); + result = rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, is_set); kfree(map->r_addr); return result; } @@ -489,6 +508,7 @@ static int rpcb_register_inet6(struct sunrpc_net *sn, const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin6->sin6_port); + bool is_set = false; int result; map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); @@ -499,10 +519,12 @@ static int rpcb_register_inet6(struct sunrpc_net *sn, map->r_addr, map->r_netid); msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; + is_set = true; + } - result = rpcb_register_call(sn->rpcb_local_clnt4, msg); + result = rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, is_set); kfree(map->r_addr); return result; } @@ -519,7 +541,7 @@ static int rpcb_unregister_all_protofamilies(struct sunrpc_net *sn, map->r_addr = ""; msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - return rpcb_register_call(sn->rpcb_local_clnt4, msg); + return rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, false); } /** diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 80a6640f329b..b9aad4723a9d 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -730,6 +730,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) newxpt = xprt->xpt_ops->xpo_accept(xprt); if (newxpt) svc_add_new_temp_xprt(serv, newxpt); + else + module_put(xprt->xpt_class->xcl_owner); } else if (xprt->xpt_ops->xpo_has_wspace(xprt)) { /* XPT_DATA|XPT_DEFERRED case: */ dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n", diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 06bdf5a1082c..1583c8a4eb7f 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -493,8 +493,6 @@ static int unix_gid_parse(struct cache_detail *cd, if (rv) return -EINVAL; uid = make_kuid(&init_user_ns, id); - if (!uid_valid(uid)) - return -EINVAL; ug.uid = uid; expiry = get_expiry(&mesg); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 0f679df7d072..5c62c5e89b46 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -683,6 +683,7 @@ static struct svc_xprt_class svc_udp_class = { .xcl_owner = THIS_MODULE, .xcl_ops = &svc_udp_ops, .xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP, + .xcl_ident = XPRT_TRANSPORT_UDP, }; static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) @@ -917,7 +918,10 @@ static void svc_tcp_clear_pages(struct svc_sock *svsk) len = svsk->sk_datalen; npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < npages; i++) { - BUG_ON(svsk->sk_pages[i] == NULL); + if (svsk->sk_pages[i] == NULL) { + WARN_ON_ONCE(1); + continue; + } put_page(svsk->sk_pages[i]); svsk->sk_pages[i] = NULL; } @@ -1092,8 +1096,10 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) goto err_noclose; } - if (svc_sock_reclen(svsk) < 8) + if (svsk->sk_datalen < 8) { + svsk->sk_datalen = 0; goto err_delete; /* client is nuts. */ + } rqstp->rq_arg.len = svsk->sk_datalen; rqstp->rq_arg.page_base = 0; @@ -1270,6 +1276,7 @@ static struct svc_xprt_class svc_tcp_class = { .xcl_owner = THIS_MODULE, .xcl_ops = &svc_tcp_ops, .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, + .xcl_ident = XPRT_TRANSPORT_TCP, }; void svc_init_xprt_sock(void) @@ -1388,6 +1395,22 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, return svsk; } +bool svc_alien_sock(struct net *net, int fd) +{ + int err; + struct socket *sock = sockfd_lookup(fd, &err); + bool ret = false; + + if (!sock) + goto out; + if (sock_net(sock->sk) != net) + ret = true; + sockfd_put(sock); +out: + return ret; +} +EXPORT_SYMBOL_GPL(svc_alien_sock); + /** * svc_addsock - add a listener socket to an RPC service * @serv: pointer to RPC service to which to add a new listener diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 75edcfad6e26..1504bb11e4f3 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -207,10 +207,13 @@ _shift_data_right_pages(struct page **pages, size_t pgto_base, pgfrom_base -= copy; vto = kmap_atomic(*pgto); - vfrom = kmap_atomic(*pgfrom); - memmove(vto + pgto_base, vfrom + pgfrom_base, copy); + if (*pgto != *pgfrom) { + vfrom = kmap_atomic(*pgfrom); + memcpy(vto + pgto_base, vfrom + pgfrom_base, copy); + kunmap_atomic(vfrom); + } else + memmove(vto + pgto_base, vto + pgfrom_base, copy); flush_dcache_page(*pgto); - kunmap_atomic(vfrom); kunmap_atomic(vto); } while ((len -= copy) != 0); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 095363eee764..42ce6bfc729d 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1290,7 +1290,7 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) } } spin_unlock(&xprt_list_lock); - printk(KERN_ERR "RPC: transport (%d) not supported\n", args->ident); + dprintk("RPC: transport (%d) not supported\n", args->ident); return ERR_PTR(-EIO); found: diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c index 8d2edddf48cf..65b146297f5a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c +++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c @@ -98,6 +98,7 @@ void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch, */ static u32 *decode_write_list(u32 *va, u32 *vaend) { + unsigned long start, end; int nchunks; struct rpcrdma_write_array *ary = @@ -113,9 +114,12 @@ static u32 *decode_write_list(u32 *va, u32 *vaend) return NULL; } nchunks = ntohl(ary->wc_nchunks); - if (((unsigned long)&ary->wc_array[0] + - (sizeof(struct rpcrdma_write_chunk) * nchunks)) > - (unsigned long)vaend) { + + start = (unsigned long)&ary->wc_array[0]; + end = (unsigned long)vaend; + if (nchunks < 0 || + nchunks > (SIZE_MAX - start) / sizeof(struct rpcrdma_write_chunk) || + (start + (sizeof(struct rpcrdma_write_chunk) * nchunks)) > end) { dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n", ary, nchunks, vaend); return NULL; @@ -129,6 +133,7 @@ static u32 *decode_write_list(u32 *va, u32 *vaend) static u32 *decode_reply_array(u32 *va, u32 *vaend) { + unsigned long start, end; int nchunks; struct rpcrdma_write_array *ary = (struct rpcrdma_write_array *)va; @@ -143,9 +148,12 @@ static u32 *decode_reply_array(u32 *va, u32 *vaend) return NULL; } nchunks = ntohl(ary->wc_nchunks); - if (((unsigned long)&ary->wc_array[0] + - (sizeof(struct rpcrdma_write_chunk) * nchunks)) > - (unsigned long)vaend) { + + start = (unsigned long)&ary->wc_array[0]; + end = (unsigned long)vaend; + if (nchunks < 0 || + nchunks > (SIZE_MAX - start) / sizeof(struct rpcrdma_write_chunk) || + (start + (sizeof(struct rpcrdma_write_chunk) * nchunks)) > end) { dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n", ary, nchunks, vaend); return NULL; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 62e4f9bcc387..ed36cb52cd86 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -89,6 +89,7 @@ struct svc_xprt_class svc_rdma_class = { .xcl_owner = THIS_MODULE, .xcl_ops = &svc_rdma_ops, .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, + .xcl_ident = XPRT_TRANSPORT_RDMA, }; struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ffd50348a509..fc47165dc254 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -391,8 +391,10 @@ static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen, return kernel_sendmsg(sock, &msg, NULL, 0, 0); } -static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more) +static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy) { + ssize_t (*do_sendpage)(struct socket *sock, struct page *page, + int offset, size_t size, int flags); struct page **ppage; unsigned int remainder; int err, sent = 0; @@ -401,6 +403,9 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i base += xdr->page_base; ppage = xdr->pages + (base >> PAGE_SHIFT); base &= ~PAGE_MASK; + do_sendpage = sock->ops->sendpage; + if (!zerocopy) + do_sendpage = sock_no_sendpage; for(;;) { unsigned int len = min_t(unsigned int, PAGE_SIZE - base, remainder); int flags = XS_SENDMSG_FLAGS; @@ -408,7 +413,7 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i remainder -= len; if (remainder != 0 || more) flags |= MSG_MORE; - err = sock->ops->sendpage(sock, *ppage, base, len, flags); + err = do_sendpage(sock, *ppage, base, len, flags); if (remainder == 0 || err != len) break; sent += err; @@ -429,9 +434,10 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i * @addrlen: UDP only -- length of destination address * @xdr: buffer containing this request * @base: starting position in the buffer + * @zerocopy: true if it is safe to use sendpage() * */ -static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base) +static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy) { unsigned int remainder = xdr->len - base; int err, sent = 0; @@ -459,7 +465,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, if (base < xdr->page_len) { unsigned int len = xdr->page_len - base; remainder -= len; - err = xs_send_pagedata(sock, xdr, base, remainder != 0); + err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy); if (remainder == 0 || err != len) goto out; sent += err; @@ -496,6 +502,7 @@ static int xs_nospace(struct rpc_task *task) struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + struct sock *sk = transport->inet; int ret = -EAGAIN; dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", @@ -513,7 +520,7 @@ static int xs_nospace(struct rpc_task *task) * window size */ set_bit(SOCK_NOSPACE, &transport->sock->flags); - transport->inet->sk_write_pending++; + sk->sk_write_pending++; /* ...and wait for more buffer space */ xprt_wait_for_buffer_space(task, xs_nospace_callback); } @@ -523,6 +530,9 @@ static int xs_nospace(struct rpc_task *task) } spin_unlock_bh(&xprt->transport_lock); + + /* Race breaker in case memory is freed before above code is called */ + sk->sk_write_space(sk); return ret; } @@ -562,7 +572,7 @@ static int xs_local_send_request(struct rpc_task *task) req->rq_svec->iov_base, req->rq_svec->iov_len); status = xs_sendpages(transport->sock, NULL, 0, - xdr, req->rq_bytes_sent); + xdr, req->rq_bytes_sent, true); dprintk("RPC: %s(%u) = %d\n", __func__, xdr->len - req->rq_bytes_sent, status); if (likely(status >= 0)) { @@ -618,7 +628,7 @@ static int xs_udp_send_request(struct rpc_task *task) status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen, xdr, - req->rq_bytes_sent); + req->rq_bytes_sent, true); dprintk("RPC: xs_udp_send_request(%u) = %d\n", xdr->len - req->rq_bytes_sent, status); @@ -689,6 +699,7 @@ static int xs_tcp_send_request(struct rpc_task *task) struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct xdr_buf *xdr = &req->rq_snd_buf; + bool zerocopy = true; int status; xs_encode_stream_record_marker(&req->rq_snd_buf); @@ -696,13 +707,20 @@ static int xs_tcp_send_request(struct rpc_task *task) xs_pktdump("packet data:", req->rq_svec->iov_base, req->rq_svec->iov_len); + /* Don't use zero copy if this is a resend. If the RPC call + * completes while the socket holds a reference to the pages, + * then we may end up resending corrupted data. + */ + if (task->tk_flags & RPC_TASK_SENT) + zerocopy = false; /* Continue transmitting the packet/record. We must be careful * to cope with writespace callbacks arriving _after_ we have * called sendmsg(). */ while (1) { status = xs_sendpages(transport->sock, - NULL, 0, xdr, req->rq_bytes_sent); + NULL, 0, xdr, req->rq_bytes_sent, + zerocopy); dprintk("RPC: xs_tcp_send_request(%u) = %d\n", xdr->len - req->rq_bytes_sent, status); diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 9bc6db04be3e..e7000be321b0 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -47,12 +47,12 @@ static int net_ctl_permissions(struct ctl_table_header *head, /* Allow network administrator to have same access as root. */ if (ns_capable(net->user_ns, CAP_NET_ADMIN) || - uid_eq(root_uid, current_uid())) { + uid_eq(root_uid, current_euid())) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } /* Allow netns root group to have the same access as the root group */ - if (gid_eq(root_gid, current_gid())) { + if (in_egroup_p(root_gid)) { int mode = (table->mode >> 3) & 7; return (mode << 3) | mode; } diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index e5f3da507823..bf2755419ec6 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -531,6 +531,7 @@ receive: buf = node->bclink.deferred_head; node->bclink.deferred_head = buf->next; + buf->next = NULL; node->bclink.deferred_size--; goto receive; } diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 8bcd4985d0fb..1e6081fb6078 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -47,7 +47,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info) int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN); u16 cmd; - if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN))) + if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN))) cmd = TIPC_CMD_NOT_NET_ADMIN; else cmd = req_userhdr->cmd; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 515ce38e4f4c..2b1d7c2d677d 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -905,9 +905,6 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock, goto exit; } - /* will be updated in set_orig_addr() if needed */ - m->msg_namelen = 0; - timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); restart: @@ -1017,9 +1014,6 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock, goto exit; } - /* will be updated in set_orig_addr() if needed */ - m->msg_namelen = 0; - target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len); timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); @@ -1179,7 +1173,7 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) /* Accept only ACK or NACK message */ if (unlikely(msg_errcode(msg))) { sock->state = SS_DISCONNECTING; - sk->sk_err = -ECONNREFUSED; + sk->sk_err = ECONNREFUSED; retval = TIPC_OK; break; } @@ -1190,7 +1184,7 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) res = auto_connect(sock, msg); if (res) { sock->state = SS_DISCONNECTING; - sk->sk_err = res; + sk->sk_err = -res; retval = TIPC_OK; break; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 826e09938bff..75e198d029d2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -160,9 +160,8 @@ static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb) static inline unsigned int unix_hash_fold(__wsum n) { - unsigned int hash = (__force unsigned int)n; + unsigned int hash = (__force unsigned int)csum_fold(n); - hash ^= hash>>16; hash ^= hash>>8; return hash&(UNIX_HASH_SIZE-1); } @@ -529,13 +528,17 @@ static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *, static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, int); -static void unix_set_peek_off(struct sock *sk, int val) +static int unix_set_peek_off(struct sock *sk, int val) { struct unix_sock *u = unix_sk(sk); - mutex_lock(&u->readlock); + if (mutex_lock_interruptible(&u->readlock)) + return -EINTR; + sk->sk_peek_off = val; mutex_unlock(&u->readlock); + + return 0; } @@ -713,7 +716,9 @@ static int unix_autobind(struct socket *sock) int err; unsigned int retries = 0; - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) + return err; err = 0; if (u->addr) @@ -872,7 +877,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) + goto out; err = -EINVAL; if (u->addr) @@ -1245,6 +1252,15 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb) return 0; } +static void unix_sock_inherit_flags(const struct socket *old, + struct socket *new) +{ + if (test_bit(SOCK_PASSCRED, &old->flags)) + set_bit(SOCK_PASSCRED, &new->flags); + if (test_bit(SOCK_PASSSEC, &old->flags)) + set_bit(SOCK_PASSSEC, &new->flags); +} + static int unix_accept(struct socket *sock, struct socket *newsock, int flags) { struct sock *sk = sock->sk; @@ -1279,6 +1295,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags) /* attach accepted sock to socket */ unix_state_lock(tsk); newsock->state = SS_CONNECTED; + unix_sock_inherit_flags(sock, newsock); sock_graft(tsk, newsock); unix_state_unlock(tsk); return 0; @@ -1751,7 +1768,6 @@ static void unix_copy_addr(struct msghdr *msg, struct sock *sk) { struct unix_sock *u = unix_sk(sk); - msg->msg_namelen = 0; if (u->addr) { msg->msg_namelen = u->addr->len; memcpy(msg->msg_name, u->addr->name, u->addr->len); @@ -1775,11 +1791,12 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags&MSG_OOB) goto out; - msg->msg_namelen = 0; - err = mutex_lock_interruptible(&u->readlock); - if (err) { - err = sock_intr_errno(sock_rcvtimeo(sk, noblock)); + if (unlikely(err)) { + /* recvmsg() in non blocking mode is supposed to return -EAGAIN + * sk_rcvtimeo is not honored by mutex_lock_interruptible() + */ + err = noblock ? -EAGAIN : -ERESTARTSYS; goto out; } @@ -1899,6 +1916,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = msg->msg_name; int copied = 0; + int noblock = flags & MSG_DONTWAIT; int check_creds = 0; int target; int err = 0; @@ -1914,9 +1932,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, goto out; target = sock_rcvlowat(sk, flags&MSG_WAITALL, size); - timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT); - - msg->msg_namelen = 0; + timeo = sock_rcvtimeo(sk, noblock); /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg @@ -1928,8 +1944,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, } err = mutex_lock_interruptible(&u->readlock); - if (err) { - err = sock_intr_errno(timeo); + if (unlikely(err)) { + /* recvmsg() in non blocking mode is supposed to return -EAGAIN + * sk_rcvtimeo is not honored by mutex_lock_interruptible() + */ + err = noblock ? -EAGAIN : -ERESTARTSYS; goto out; } diff --git a/net/unix/diag.c b/net/unix/diag.c index d591091603bf..86fa0f3b2caf 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -124,6 +124,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r rep->udiag_family = AF_UNIX; rep->udiag_type = sk->sk_type; rep->udiag_state = sk->sk_state; + rep->pad = 0; rep->udiag_ino = sk_ino; sock_diag_save_cookie(sk, rep->udiag_cookie); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 3f77f42a3b58..9b88693bcc99 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1670,8 +1670,6 @@ vsock_stream_recvmsg(struct kiocb *kiocb, vsk = vsock_sk(sk); err = 0; - msg->msg_namelen = 0; - lock_sock(sk); if (sk->sk_state != SS_CONNECTED) { diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index daff75200e25..62bbf7d73980 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1746,8 +1746,6 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb, if (flags & MSG_OOB || flags & MSG_ERRQUEUE) return -EOPNOTSUPP; - msg->msg_namelen = 0; - /* Retrieve the head sk_buff from the socket's receive queue. */ err = 0; skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err); diff --git a/net/wireless/chan.c b/net/wireless/chan.c index fd556ac05fdb..e69a17da1e84 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -338,7 +338,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, { struct ieee80211_sta_ht_cap *ht_cap; struct ieee80211_sta_vht_cap *vht_cap; - u32 width, control_freq; + u32 width, control_freq, cap; if (WARN_ON(!cfg80211_chandef_valid(chandef))) return false; @@ -370,7 +370,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, return false; break; case NL80211_CHAN_WIDTH_80P80: - if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)) + cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; + if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) return false; case NL80211_CHAN_WIDTH_80: if (!vht_cap->vht_supported) @@ -381,7 +382,9 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, case NL80211_CHAN_WIDTH_160: if (!vht_cap->vht_supported) return false; - if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ)) + cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; + if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && + cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) return false; prohibited_flags |= IEEE80211_CHAN_NO_160MHZ; width = 160; diff --git a/net/wireless/core.c b/net/wireless/core.c index 73405e00c800..64fcbae020d2 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -876,6 +876,7 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev, cfg80211_leave_mesh(rdev, dev); break; case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, dev); break; default: diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index d80e47194d49..e62c1ad4e4c9 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -269,6 +269,8 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, if (chan->flags & IEEE80211_CHAN_DISABLED) continue; wdev->wext.ibss.chandef.chan = chan; + wdev->wext.ibss.chandef.center_freq1 = + chan->center_freq; break; } @@ -353,6 +355,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, if (chan) { wdev->wext.ibss.chandef.chan = chan; wdev->wext.ibss.chandef.width = NL80211_CHAN_WIDTH_20_NOHT; + wdev->wext.ibss.chandef.center_freq1 = freq; wdev->wext.ibss.channel_fixed = true; } else { /* cfg80211_ibss_wext_join will pick one if needed */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b14b7e3cb6e6..90a0e552cb32 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -471,10 +471,12 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb, goto out_unlock; } *rdev = wiphy_to_dev((*wdev)->wiphy); - cb->args[0] = (*rdev)->wiphy_idx; + /* 0 is the first index - add 1 to parse only once */ + cb->args[0] = (*rdev)->wiphy_idx + 1; cb->args[1] = (*wdev)->identifier; } else { - struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0]); + /* subtract the 1 again here */ + struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1); struct wireless_dev *tmp; if (!wiphy) { @@ -2627,6 +2629,9 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->get_key) return -EOPNOTSUPP; + if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) + return -ENOENT; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -2646,10 +2651,6 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr)) goto nla_put_failure; - if (pairwise && mac_addr && - !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) - return -ENOENT; - err = rdev_get_key(rdev, dev, key_idx, pairwise, mac_addr, &cookie, get_key_callback); @@ -2820,7 +2821,7 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) wdev_lock(dev->ieee80211_ptr); err = nl80211_key_allowed(dev->ieee80211_ptr); - if (key.type == NL80211_KEYTYPE_PAIRWISE && mac_addr && + if (key.type == NL80211_KEYTYPE_GROUP && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) err = -ENOENT; @@ -4031,6 +4032,16 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) if (parse_station_flags(info, dev->ieee80211_ptr->iftype, ¶ms)) return -EINVAL; + /* HT/VHT requires QoS, but if we don't have that just ignore HT/VHT + * as userspace might just pass through the capabilities from the IEs + * directly, rather than enforcing this restriction and returning an + * error in this case. + */ + if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) { + params.ht_capa = NULL; + params.vht_capa = NULL; + } + /* When you run into this, adjust the code below for the new flag */ BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7); @@ -6566,6 +6577,9 @@ int cfg80211_testmode_reply(struct sk_buff *skb) void *hdr = ((void **)skb->cb)[1]; struct nlattr *data = ((void **)skb->cb)[2]; + /* clear CB data for netlink core to own from now on */ + memset(skb->cb, 0, sizeof(skb->cb)); + if (WARN_ON(!rdev->testmode_info)) { kfree_skb(skb); return -EINVAL; @@ -6588,12 +6602,17 @@ EXPORT_SYMBOL(cfg80211_testmode_alloc_event_skb); void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp) { + struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0]; void *hdr = ((void **)skb->cb)[1]; struct nlattr *data = ((void **)skb->cb)[2]; + /* clear CB data for netlink core to own from now on */ + memset(skb->cb, 0, sizeof(skb->cb)); + nla_nest_end(skb, data); genlmsg_end(skb, hdr); - genlmsg_multicast(skb, 0, nl80211_testmode_mcgrp.id, gfp); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), skb, 0, + nl80211_testmode_mcgrp.id, gfp); } EXPORT_SYMBOL(cfg80211_testmode_event); #endif @@ -10028,7 +10047,8 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, genlmsg_end(msg, hdr); - genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, gfp); + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); return; nla_put_failure: diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c index 7d604c06c3dc..722da616438c 100644 --- a/net/wireless/radiotap.c +++ b/net/wireless/radiotap.c @@ -97,6 +97,10 @@ int ieee80211_radiotap_iterator_init( struct ieee80211_radiotap_header *radiotap_header, int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns) { + /* check the radiotap header can actually be present */ + if (max_length < sizeof(struct ieee80211_radiotap_header)) + return -EINVAL; + /* Linux only supports version 0 radiotap format */ if (radiotap_header->it_version) return -EINVAL; @@ -120,6 +124,10 @@ int ieee80211_radiotap_iterator_init( /* find payload start allowing for extended bitmap(s) */ if (iterator->_bitmap_shifter & (1<<IEEE80211_RADIOTAP_EXT)) { + if ((unsigned long)iterator->_arg - + (unsigned long)iterator->_rtheader + sizeof(uint32_t) > + (unsigned long)iterator->_max_length) + return -EINVAL; while (get_unaligned_le32(iterator->_arg) & (1 << IEEE80211_RADIOTAP_EXT)) { iterator->_arg += sizeof(uint32_t); @@ -131,7 +139,8 @@ int ieee80211_radiotap_iterator_init( */ if ((unsigned long)iterator->_arg - - (unsigned long)iterator->_rtheader > + (unsigned long)iterator->_rtheader + + sizeof(uint32_t) > (unsigned long)iterator->_max_length) return -EINVAL; } diff --git a/net/wireless/scan.c b/net/wireless/scan.c index fd99ea495b7e..81019ee3ddc8 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -253,10 +253,10 @@ void __cfg80211_sched_scan_results(struct work_struct *wk) rdev = container_of(wk, struct cfg80211_registered_device, sched_scan_results_wk); - request = rdev->sched_scan_req; - mutex_lock(&rdev->sched_scan_mtx); + request = rdev->sched_scan_req; + /* we don't have sched_scan_req anymore if the scan is stopping */ if (request) { if (request->flags & NL80211_SCAN_FLAG_FLUSH) { diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 5755bc14abbd..bc5a75b1aef8 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1972,7 +1972,8 @@ TRACE_EVENT(cfg80211_michael_mic_failure, MAC_ASSIGN(addr, addr); __entry->key_type = key_type; __entry->key_id = key_id; - memcpy(__entry->tsc, tsc, 6); + if (tsc) + memcpy(__entry->tsc, tsc, 6); ), TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT ", key type: %d, key id: %d, tsc: %pm", NETDEV_PR_ARG, MAC_PR_ARG(addr), __entry->key_type, diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 37ca9694aabe..f96af3b96322 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1340,10 +1340,9 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, if (sx25) { sx25->sx25_family = AF_X25; sx25->sx25_addr = x25->dest_addr; + msg->msg_namelen = sizeof(*sx25); } - msg->msg_namelen = sizeof(struct sockaddr_x25); - x25_check_rbuf(sk); rc = copied; out_free_dgram: @@ -1583,11 +1582,11 @@ out_cud_release: case SIOCX25CALLACCPTAPPRV: { rc = -EINVAL; lock_sock(sk); - if (sk->sk_state != TCP_CLOSE) - break; - clear_bit(X25_ACCPT_APPRV_FLAG, &x25->flags); + if (sk->sk_state == TCP_CLOSE) { + clear_bit(X25_ACCPT_APPRV_FLAG, &x25->flags); + rc = 0; + } release_sock(sk); - rc = 0; break; } @@ -1595,14 +1594,15 @@ out_cud_release: rc = -EINVAL; lock_sock(sk); if (sk->sk_state != TCP_ESTABLISHED) - break; + goto out_sendcallaccpt_release; /* must call accptapprv above */ if (test_bit(X25_ACCPT_APPRV_FLAG, &x25->flags)) - break; + goto out_sendcallaccpt_release; x25_write_internal(sk, X25_CALL_ACCEPTED); x25->state = X25_STATE_3; - release_sock(sk); rc = 0; +out_sendcallaccpt_release: + release_sock(sk); break; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 3f565e495ac6..7a70a5a5671a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2362,7 +2362,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) link = &xfrm_dispatch[type]; /* All operations require privileges, even GET */ - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (!netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) || |