diff options
Diffstat (limited to 'net')
555 files changed, 20456 insertions, 11249 deletions
diff --git a/net/802/garp.c b/net/802/garp.c index 5d9630a0eb93..b38ee6dcba45 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -397,7 +397,7 @@ static void garp_join_timer_arm(struct garp_applicant *app) { unsigned long delay; - delay = (u64)msecs_to_jiffies(garp_join_time) * net_random() >> 32; + delay = (u64)msecs_to_jiffies(garp_join_time) * prandom_u32() >> 32; mod_timer(&app->join_timer, jiffies + delay); } diff --git a/net/802/hippi.c b/net/802/hippi.c index 51a1f530417d..5ff2a718ddca 100644 --- a/net/802/hippi.c +++ b/net/802/hippi.c @@ -172,14 +172,14 @@ EXPORT_SYMBOL(hippi_mac_addr); int hippi_neigh_setup_dev(struct net_device *dev, struct neigh_parms *p) { /* Never send broadcast/multicast ARP messages */ - p->mcast_probes = 0; + NEIGH_VAR_INIT(p, MCAST_PROBES, 0); /* In IPv6 unicast probes are valid even on NBMA, * because they are encapsulated in normal IPv6 protocol. * Should be a generic flag. */ if (p->tbl->family != AF_INET6) - p->ucast_probes = 0; + NEIGH_VAR_INIT(p, UCAST_PROBES, 0); return 0; } EXPORT_SYMBOL(hippi_neigh_setup_dev); diff --git a/net/802/mrp.c b/net/802/mrp.c index 3ed616215870..72db2785ef2c 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -583,7 +583,7 @@ static void mrp_join_timer_arm(struct mrp_applicant *app) { unsigned long delay; - delay = (u64)msecs_to_jiffies(mrp_join_time) * net_random() >> 32; + delay = (u64)msecs_to_jiffies(mrp_join_time) * prandom_u32() >> 32; mod_timer(&app->join_timer, jiffies + delay); } diff --git a/net/8021q/Kconfig b/net/8021q/Kconfig index b85a91fa61f1..42320180967f 100644 --- a/net/8021q/Kconfig +++ b/net/8021q/Kconfig @@ -6,11 +6,11 @@ config VLAN_8021Q tristate "802.1Q/802.1ad VLAN Support" ---help--- Select this and you will be able to create 802.1Q VLAN interfaces - on your ethernet interfaces. 802.1Q VLAN supports almost - everything a regular ethernet interface does, including - firewalling, bridging, and of course IP traffic. You will need - the 'vconfig' tool from the VLAN project in order to effectively - use VLANs. See the VLAN web page for more information: + on your Ethernet interfaces. 802.1Q VLAN supports almost + everything a regular Ethernet interface does, including + firewalling, bridging, and of course IP traffic. You will need + the 'ip' utility in order to effectively use VLANs. + See the VLAN web page for more information: <http://www.candelatech.com/~greear/vlan.html> To compile this code as a module, choose M here: the module diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index b3d17d1c49c3..ec9909935fb6 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -301,7 +301,7 @@ static void vlan_sync_address(struct net_device *dev, !ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_add(dev, vlandev->dev_addr); - memcpy(vlan->real_dev_addr, dev->dev_addr, ETH_ALEN); + ether_addr_copy(vlan->real_dev_addr, dev->dev_addr); } static void vlan_transfer_features(struct net_device *dev, diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 47c908f1f626..de51c48c4393 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -61,7 +61,7 @@ static int vlan_dev_rebuild_header(struct sk_buff *skb) pr_debug("%s: unable to resolve type %X addresses\n", dev->name, ntohs(veth->h_vlan_encapsulated_proto)); - memcpy(veth->h_source, dev->dev_addr, ETH_ALEN); + ether_addr_copy(veth->h_source, dev->dev_addr); break; } @@ -303,7 +303,7 @@ static int vlan_dev_open(struct net_device *dev) goto clear_allmulti; } - memcpy(vlan->real_dev_addr, real_dev->dev_addr, ETH_ALEN); + ether_addr_copy(vlan->real_dev_addr, real_dev->dev_addr); if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_join(dev); @@ -367,7 +367,7 @@ static int vlan_dev_set_mac_address(struct net_device *dev, void *p) dev_uc_del(real_dev, dev->dev_addr); out: - memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); + ether_addr_copy(dev->dev_addr, addr->sa_data); return 0; } diff --git a/net/9p/client.c b/net/9p/client.c index ee8fd6bd4035..9186550d77a6 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -204,7 +204,7 @@ free_and_return: return ret; } -struct p9_fcall *p9_fcall_alloc(int alloc_msize) +static struct p9_fcall *p9_fcall_alloc(int alloc_msize) { struct p9_fcall *fc; fc = kmalloc(sizeof(struct p9_fcall) + alloc_msize, GFP_NOFS); @@ -1012,9 +1012,6 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) goto destroy_tagpool; if (!clnt->trans_mod) - clnt->trans_mod = v9fs_get_trans_by_name("virtio"); - - if (!clnt->trans_mod) clnt->trans_mod = v9fs_get_default_trans(); if (clnt->trans_mod == NULL) { diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 9321a7763067..b7bd7f2961bf 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -1048,7 +1048,7 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args) static struct p9_trans_module p9_tcp_trans = { .name = "tcp", .maxsize = MAX_SOCK_BUF, - .def = 1, + .def = 0, .create = p9_fd_create_tcp, .close = p9_fd_close, .request = p9_fd_request, diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 9c5a1aa34d12..ac2666c1d011 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--; } @@ -698,7 +701,7 @@ static struct p9_trans_module p9_virtio_trans = { * page in zero copy. */ .maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3), - .def = 0, + .def = 1, .owner = THIS_MODULE, }; diff --git a/net/Kconfig b/net/Kconfig index d334678c0bd8..e411046a62e3 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -238,12 +238,19 @@ config XPS depends on SMP default y -config NETPRIO_CGROUP +config CGROUP_NET_PRIO tristate "Network priority cgroup" depends on CGROUPS ---help--- Cgroup subsystem for use in assigning processes to network priorities on - a per-interface basis + a per-interface basis. + +config CGROUP_NET_CLASSID + boolean "Network classid cgroup" + depends on CGROUPS + ---help--- + Cgroup subsystem for use as general purpose socket classid marker that is + being used in cls_cgroup and for netfilter matching. config NET_RX_BUSY_POLL boolean diff --git a/net/Makefile b/net/Makefile index 8fa2f91517f1..cbbbe6d657ca 100644 --- a/net/Makefile +++ b/net/Makefile @@ -57,7 +57,7 @@ obj-$(CONFIG_CAIF) += caif/ ifneq ($(CONFIG_DCB),) obj-y += dcb/ endif -obj-$(CONFIG_IEEE802154) += ieee802154/ +obj-y += ieee802154/ obj-$(CONFIG_MAC802154) += mac802154/ ifeq ($(CONFIG_NET),y) diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 690356fa52b9..d27b86dfb0e9 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -40,6 +40,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> +#include <linux/etherdevice.h> int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME; int sysctl_aarp_tick_time = AARP_TICK_TIME; @@ -67,7 +68,7 @@ struct aarp_entry { unsigned long expires_at; struct atalk_addr target_addr; struct net_device *dev; - char hwaddr[6]; + char hwaddr[ETH_ALEN]; unsigned short xmit_count; struct aarp_entry *next; }; @@ -134,7 +135,7 @@ static void __aarp_send_query(struct aarp_entry *a) eah->pa_len = AARP_PA_ALEN; eah->function = htons(AARP_REQUEST); - memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN); + ether_addr_copy(eah->hw_src, dev->dev_addr); eah->pa_src_zero = 0; eah->pa_src_net = sat->s_net; @@ -181,7 +182,7 @@ static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us, eah->pa_len = AARP_PA_ALEN; eah->function = htons(AARP_REPLY); - memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN); + ether_addr_copy(eah->hw_src, dev->dev_addr); eah->pa_src_zero = 0; eah->pa_src_net = us->s_net; @@ -190,7 +191,7 @@ static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us, if (!sha) memset(eah->hw_dst, '\0', ETH_ALEN); else - memcpy(eah->hw_dst, sha, ETH_ALEN); + ether_addr_copy(eah->hw_dst, sha); eah->pa_dst_zero = 0; eah->pa_dst_net = them->s_net; @@ -232,7 +233,7 @@ static void aarp_send_probe(struct net_device *dev, struct atalk_addr *us) eah->pa_len = AARP_PA_ALEN; eah->function = htons(AARP_PROBE); - memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN); + ether_addr_copy(eah->hw_src, dev->dev_addr); eah->pa_src_zero = 0; eah->pa_src_net = us->s_net; @@ -790,7 +791,7 @@ static int aarp_rcv(struct sk_buff *skb, struct net_device *dev, break; /* We can fill one in - this is good. */ - memcpy(a->hwaddr, ea->hw_src, ETH_ALEN); + ether_addr_copy(a->hwaddr, ea->hw_src); __aarp_resolved(&unresolved[hash], a, hash); if (!unresolved_count) mod_timer(&aarp_timer, diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 7d424ac6e760..02806c6b2ff3 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1566,7 +1566,7 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr { struct sock *sk = sock->sk; struct atalk_sock *at = at_sk(sk); - struct sockaddr_at *usat = (struct sockaddr_at *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_at *, usat, msg->msg_name); int flags = msg->msg_flags; int loopback = 0; struct sockaddr_at local_satalk, gsat; @@ -1764,7 +1764,7 @@ 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 && msg->msg_name) { - struct sockaddr_at *sat = msg->msg_name; + DECLARE_SOCKADDR(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; diff --git a/net/atm/lec.c b/net/atm/lec.c index f23916be18fb..5a2f602d07e1 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -521,7 +521,7 @@ send_to_lecd(struct lec_priv *priv, atmlec_msg_type type, if (data != NULL) mesg->sizeoftlvs = data->len; if (mac_addr) - memcpy(&mesg->content.normal.mac_addr, mac_addr, ETH_ALEN); + ether_addr_copy(mesg->content.normal.mac_addr, mac_addr); else mesg->content.normal.targetless_le_arp = 1; if (atm_addr) @@ -1565,7 +1565,7 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv, pr_info("LEC: Arp entry kmalloc failed\n"); return NULL; } - memcpy(to_return->mac_addr, mac_addr, ETH_ALEN); + ether_addr_copy(to_return->mac_addr, mac_addr); INIT_HLIST_NODE(&to_return->next); setup_timer(&to_return->timer, lec_arp_expire_arp, (unsigned long)to_return); @@ -1887,7 +1887,8 @@ lec_arp_update(struct lec_priv *priv, const unsigned char *mac_addr, entry = tmp; } else { entry->status = ESI_FORWARD_DIRECT; - memcpy(entry->mac_addr, mac_addr, ETH_ALEN); + ether_addr_copy(entry->mac_addr, + mac_addr); entry->last_used = jiffies; lec_arp_add(priv, entry); } @@ -2263,7 +2264,7 @@ lec_arp_check_empties(struct lec_priv *priv, &priv->lec_arp_empty_ones, next) { if (vcc == entry->vcc) { del_timer(&entry->timer); - memcpy(entry->mac_addr, src, ETH_ALEN); + ether_addr_copy(entry->mac_addr, src); entry->status = ESI_FORWARD_DIRECT; entry->last_used = jiffies; /* We might have got an entry */ diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 3af12755cd04..b71ff6b234f2 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -478,7 +478,7 @@ static const uint8_t *copy_macs(struct mpoa_client *mpc, return NULL; } } - memcpy(mpc->mps_macs, router_mac, ETH_ALEN); + ether_addr_copy(mpc->mps_macs, router_mac); tlvs += 20; if (device_type == MPS_AND_MPC) tlvs += 20; if (mps_macs > 0) memcpy(mpc->mps_macs, tlvs, mps_macs*ETH_ALEN); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 7bb1605bdfd9..c35c3f48fc0f 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1435,7 +1435,7 @@ out: static int ax25_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { - struct sockaddr_ax25 *usax = (struct sockaddr_ax25 *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_ax25 *, usax, msg->msg_name); struct sock *sk = sock->sk; struct sockaddr_ax25 sax; struct sk_buff *skb; @@ -1640,7 +1640,7 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock, ax25_digi digi; ax25_address src; const unsigned char *mac = skb_mac_header(skb); - struct sockaddr_ax25 *sax = msg->msg_name; + DECLARE_SOCKADDR(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/Makefile b/net/batman-adv/Makefile index 4f4aabbd8eab..42df18f877e9 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # -# Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # @@ -13,9 +13,7 @@ # General Public License for more details. # # You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA -# 02110-1301, USA +# along with this program; if not, see <http://www.gnu.org/licenses/>. # obj-$(CONFIG_BATMAN_ADV) += batman-adv.o diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index a4808c29ea3d..4e49666f8c65 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_BAT_ALGO_H_ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index b9c8a6eedf45..8323bced8e5b 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -243,19 +241,19 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const uint8_t *addr) size = bat_priv->num_ifaces * sizeof(uint8_t); orig_node->bat_iv.bcast_own_sum = kzalloc(size, GFP_ATOMIC); if (!orig_node->bat_iv.bcast_own_sum) - goto free_bcast_own; + goto free_orig_node; hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig, batadv_choose_orig, orig_node, &orig_node->hash_entry); if (hash_added != 0) - goto free_bcast_own; + goto free_orig_node; return orig_node; -free_bcast_own: - kfree(orig_node->bat_iv.bcast_own); free_orig_node: + /* free twice, as batadv_orig_node_new sets refcount to 2 */ + batadv_orig_node_free_ref(orig_node); batadv_orig_node_free_ref(orig_node); return NULL; @@ -268,22 +266,39 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, struct batadv_orig_node *orig_neigh) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct batadv_neigh_node *neigh_node; + struct batadv_neigh_node *neigh_node, *tmp_neigh_node; neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, orig_node); if (!neigh_node) goto out; - spin_lock_init(&neigh_node->bat_iv.lq_update_lock); + if (!atomic_inc_not_zero(&hard_iface->refcount)) { + kfree(neigh_node); + neigh_node = NULL; + goto out; + } - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Creating new neighbor %pM for orig_node %pM on interface %s\n", - neigh_addr, orig_node->orig, hard_iface->net_dev->name); + neigh_node->orig_node = orig_neigh; + neigh_node->if_incoming = hard_iface; spin_lock_bh(&orig_node->neigh_list_lock); - hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); + tmp_neigh_node = batadv_neigh_node_get(orig_node, hard_iface, + neigh_addr); + if (!tmp_neigh_node) { + hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); + } else { + kfree(neigh_node); + batadv_hardif_free_ref(hard_iface); + neigh_node = tmp_neigh_node; + } spin_unlock_bh(&orig_node->neigh_list_lock); + if (!tmp_neigh_node) + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Creating new neighbor %pM for orig_node %pM on interface %s\n", + neigh_addr, orig_node->orig, + hard_iface->net_dev->name); + out: return neigh_node; } @@ -461,17 +476,9 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, /* send a batman ogm packet */ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) { - struct batadv_hard_iface *hard_iface; struct net_device *soft_iface; struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; - struct batadv_ogm_packet *batadv_ogm_packet; - unsigned char directlink; - uint8_t *packet_pos; - - packet_pos = forw_packet->skb->data; - batadv_ogm_packet = (struct batadv_ogm_packet *)packet_pos; - directlink = (batadv_ogm_packet->flags & BATADV_DIRECTLINK ? 1 : 0); if (!forw_packet->if_incoming) { pr_err("Error - can't forward packet: incoming iface not specified\n"); @@ -481,59 +488,48 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) soft_iface = forw_packet->if_incoming->soft_iface; bat_priv = netdev_priv(soft_iface); - if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) + if (WARN_ON(!forw_packet->if_outgoing)) goto out; - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) + if (WARN_ON(forw_packet->if_outgoing->soft_iface != soft_iface)) goto out; - /* multihomed peer assumed - * non-primary OGMs are only broadcasted on their interface - */ - if ((directlink && (batadv_ogm_packet->ttl == 1)) || - (forw_packet->own && (forw_packet->if_incoming != primary_if))) { - /* FIXME: what about aggregated packets ? */ - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "%s packet (originator %pM, seqno %u, TTL %d) on interface %s [%pM]\n", - (forw_packet->own ? "Sending own" : "Forwarding"), - batadv_ogm_packet->orig, - ntohl(batadv_ogm_packet->seqno), - batadv_ogm_packet->ttl, - forw_packet->if_incoming->net_dev->name, - forw_packet->if_incoming->net_dev->dev_addr); - - /* skb is only used once and than forw_packet is free'd */ - batadv_send_skb_packet(forw_packet->skb, - forw_packet->if_incoming, - batadv_broadcast_addr); - forw_packet->skb = NULL; - + if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) goto out; - } - /* broadcast on every interface */ - rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if (hard_iface->soft_iface != soft_iface) - continue; + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; - batadv_iv_ogm_send_to_if(forw_packet, hard_iface); - } - rcu_read_unlock(); + /* only for one specific outgoing interface */ + batadv_iv_ogm_send_to_if(forw_packet, forw_packet->if_outgoing); out: if (primary_if) batadv_hardif_free_ref(primary_if); } -/* return true if new_packet can be aggregated with forw_packet */ +/** + * batadv_iv_ogm_can_aggregate - find out if an OGM can be aggregated on an + * existing forward packet + * @new_bat_ogm_packet: OGM packet to be aggregated + * @bat_priv: the bat priv with all the soft interface information + * @packet_len: (total) length of the OGM + * @send_time: timestamp (jiffies) when the packet is to be sent + * @direktlink: true if this is a direct link packet + * @if_incoming: interface where the packet was received + * @if_outgoing: interface for which the retransmission should be considered + * @forw_packet: the forwarded packet which should be checked + * + * Returns true if new_packet can be aggregated with forw_packet + */ static bool batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, struct batadv_priv *bat_priv, int packet_len, unsigned long send_time, bool directlink, const struct batadv_hard_iface *if_incoming, + const struct batadv_hard_iface *if_outgoing, const struct batadv_forw_packet *forw_packet) { struct batadv_ogm_packet *batadv_ogm_packet; @@ -567,6 +563,10 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, if (!primary_if) goto out; + /* packet is not leaving on the same interface. */ + if (forw_packet->if_outgoing != if_outgoing) + goto out; + /* packets without direct link flag and high TTL * are flooded through the net */ @@ -608,11 +608,22 @@ out: return res; } -/* create a new aggregated packet and add this packet to it */ +/** + * batadv_iv_ogm_aggregate_new - create a new aggregated packet and add this + * packet to it. + * @packet_buff: pointer to the OGM + * @packet_len: (total) length of the OGM + * @send_time: timestamp (jiffies) when the packet is to be sent + * @direct_link: whether this OGM has direct link status + * @if_incoming: interface where the packet was received + * @if_outgoing: interface for which the retransmission should be considered + * @own_packet: true if it is a self-generated ogm + */ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, int packet_len, unsigned long send_time, bool direct_link, struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing, int own_packet) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); @@ -623,6 +634,9 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, if (!atomic_inc_not_zero(&if_incoming->refcount)) return; + if (!atomic_inc_not_zero(&if_outgoing->refcount)) + goto out_free_incoming; + /* own packet should always be scheduled */ if (!own_packet) { if (!batadv_atomic_dec_not_zero(&bat_priv->batman_queue_left)) { @@ -663,6 +677,7 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, forw_packet_aggr->own = own_packet; forw_packet_aggr->if_incoming = if_incoming; + forw_packet_aggr->if_outgoing = if_outgoing; forw_packet_aggr->num_packets = 0; forw_packet_aggr->direct_link_flags = BATADV_NO_FLAGS; forw_packet_aggr->send_time = send_time; @@ -685,6 +700,8 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, return; out: + batadv_hardif_free_ref(if_outgoing); +out_free_incoming: batadv_hardif_free_ref(if_incoming); } @@ -708,10 +725,21 @@ static void batadv_iv_ogm_aggregate(struct batadv_forw_packet *forw_packet_aggr, } } +/** + * batadv_iv_ogm_queue_add - queue up an OGM for transmission + * @bat_priv: the bat priv with all the soft interface information + * @packet_buff: pointer to the OGM + * @packet_len: (total) length of the OGM + * @if_incoming: interface where the packet was received + * @if_outgoing: interface for which the retransmission should be considered + * @own_packet: true if it is a self-generated ogm + * @send_time: timestamp (jiffies) when the packet is to be sent + */ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, unsigned char *packet_buff, int packet_len, struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing, int own_packet, unsigned long send_time) { /* _aggr -> pointer to the packet we want to aggregate with @@ -737,6 +765,7 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, bat_priv, packet_len, send_time, direct_link, if_incoming, + if_outgoing, forw_packet_pos)) { forw_packet_aggr = forw_packet_pos; break; @@ -760,7 +789,8 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, batadv_iv_ogm_aggregate_new(packet_buff, packet_len, send_time, direct_link, - if_incoming, own_packet); + if_incoming, if_outgoing, + own_packet); } else { batadv_iv_ogm_aggregate(forw_packet_aggr, packet_buff, packet_len, direct_link); @@ -773,7 +803,8 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node, struct batadv_ogm_packet *batadv_ogm_packet, bool is_single_hop_neigh, bool is_from_best_next_hop, - struct batadv_hard_iface *if_incoming) + struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); uint16_t tvlv_len; @@ -818,7 +849,8 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node, batadv_iv_ogm_queue_add(bat_priv, (unsigned char *)batadv_ogm_packet, BATADV_OGM_HLEN + tvlv_len, - if_incoming, 0, batadv_iv_ogm_fwd_send_time()); + if_incoming, if_outgoing, 0, + batadv_iv_ogm_fwd_send_time()); } /** @@ -863,10 +895,11 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); unsigned char **ogm_buff = &hard_iface->bat_iv.ogm_buff; struct batadv_ogm_packet *batadv_ogm_packet; - struct batadv_hard_iface *primary_if; + struct batadv_hard_iface *primary_if, *tmp_hard_iface; int *ogm_buff_len = &hard_iface->bat_iv.ogm_buff_len; uint32_t seqno; uint16_t tvlv_len = 0; + unsigned long send_time; primary_if = batadv_primary_if_get_selected(bat_priv); @@ -889,23 +922,60 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) atomic_inc(&hard_iface->bat_iv.ogm_seqno); batadv_iv_ogm_slide_own_bcast_window(hard_iface); - batadv_iv_ogm_queue_add(bat_priv, hard_iface->bat_iv.ogm_buff, - hard_iface->bat_iv.ogm_buff_len, hard_iface, 1, - batadv_iv_ogm_emit_send_time(bat_priv)); + send_time = batadv_iv_ogm_emit_send_time(bat_priv); + + if (hard_iface != primary_if) { + /* OGMs from secondary interfaces are only scheduled on their + * respective interfaces. + */ + batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, *ogm_buff_len, + hard_iface, hard_iface, 1, send_time); + goto out; + } + + /* OGMs from primary interfaces are scheduled on all + * interfaces. + */ + rcu_read_lock(); + list_for_each_entry_rcu(tmp_hard_iface, &batadv_hardif_list, list) { + if (tmp_hard_iface->soft_iface != hard_iface->soft_iface) + continue; + batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, + *ogm_buff_len, hard_iface, + tmp_hard_iface, 1, send_time); + } + rcu_read_unlock(); + +out: if (primary_if) batadv_hardif_free_ref(primary_if); } +/** + * batadv_iv_ogm_orig_update - use OGM to update corresponding data in an + * originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: the orig node who originally emitted the ogm packet + * @orig_ifinfo: ifinfo for the outgoing interface of the orig_node + * @ethhdr: Ethernet header of the OGM + * @batadv_ogm_packet: the ogm packet + * @if_incoming: interface where the packet was received + * @if_outgoing: interface for which the retransmission should be considered + * @dup_status: the duplicate status of this ogm packet. + */ static void batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, + struct batadv_orig_ifinfo *orig_ifinfo, const struct ethhdr *ethhdr, const struct batadv_ogm_packet *batadv_ogm_packet, struct batadv_hard_iface *if_incoming, - const unsigned char *tt_buff, + struct batadv_hard_iface *if_outgoing, enum batadv_dup_status dup_status) { + struct batadv_neigh_ifinfo *neigh_ifinfo = NULL; + struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; @@ -933,12 +1003,21 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, if (dup_status != BATADV_NO_DUP) continue; - spin_lock_bh(&tmp_neigh_node->bat_iv.lq_update_lock); - batadv_ring_buffer_set(tmp_neigh_node->bat_iv.tq_recv, - &tmp_neigh_node->bat_iv.tq_index, 0); - tq_avg = batadv_ring_buffer_avg(tmp_neigh_node->bat_iv.tq_recv); - tmp_neigh_node->bat_iv.tq_avg = tq_avg; - spin_unlock_bh(&tmp_neigh_node->bat_iv.lq_update_lock); + /* only update the entry for this outgoing interface */ + neigh_ifinfo = batadv_neigh_ifinfo_get(tmp_neigh_node, + if_outgoing); + if (!neigh_ifinfo) + continue; + + spin_lock_bh(&tmp_neigh_node->ifinfo_lock); + batadv_ring_buffer_set(neigh_ifinfo->bat_iv.tq_recv, + &neigh_ifinfo->bat_iv.tq_index, 0); + tq_avg = batadv_ring_buffer_avg(neigh_ifinfo->bat_iv.tq_recv); + neigh_ifinfo->bat_iv.tq_avg = tq_avg; + spin_unlock_bh(&tmp_neigh_node->ifinfo_lock); + + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); + neigh_ifinfo = NULL; } if (!neigh_node) { @@ -960,39 +1039,49 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, "Updating existing last-hop neighbor of originator\n"); rcu_read_unlock(); + neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing); + if (!neigh_ifinfo) + goto out; neigh_node->last_seen = jiffies; - spin_lock_bh(&neigh_node->bat_iv.lq_update_lock); - batadv_ring_buffer_set(neigh_node->bat_iv.tq_recv, - &neigh_node->bat_iv.tq_index, + spin_lock_bh(&neigh_node->ifinfo_lock); + batadv_ring_buffer_set(neigh_ifinfo->bat_iv.tq_recv, + &neigh_ifinfo->bat_iv.tq_index, batadv_ogm_packet->tq); - tq_avg = batadv_ring_buffer_avg(neigh_node->bat_iv.tq_recv); - neigh_node->bat_iv.tq_avg = tq_avg; - spin_unlock_bh(&neigh_node->bat_iv.lq_update_lock); + tq_avg = batadv_ring_buffer_avg(neigh_ifinfo->bat_iv.tq_recv); + neigh_ifinfo->bat_iv.tq_avg = tq_avg; + spin_unlock_bh(&neigh_node->ifinfo_lock); if (dup_status == BATADV_NO_DUP) { - orig_node->last_ttl = batadv_ogm_packet->ttl; - neigh_node->last_ttl = batadv_ogm_packet->ttl; + orig_ifinfo->last_ttl = batadv_ogm_packet->ttl; + neigh_ifinfo->last_ttl = batadv_ogm_packet->ttl; } - batadv_bonding_candidate_add(bat_priv, orig_node, neigh_node); - /* if this neighbor already is our next hop there is nothing * to change */ - router = batadv_orig_node_get_router(orig_node); + router = batadv_orig_router_get(orig_node, if_outgoing); if (router == neigh_node) goto out; - /* if this neighbor does not offer a better TQ we won't consider it */ - if (router && (router->bat_iv.tq_avg > neigh_node->bat_iv.tq_avg)) - goto out; + if (router) { + router_ifinfo = batadv_neigh_ifinfo_get(router, if_outgoing); + if (!router_ifinfo) + goto out; + + /* if this neighbor does not offer a better TQ we won't + * consider it + */ + if (router_ifinfo->bat_iv.tq_avg > neigh_ifinfo->bat_iv.tq_avg) + goto out; + } /* if the TQ is the same and the link not more symmetric we * won't consider it either */ - if (router && (neigh_node->bat_iv.tq_avg == router->bat_iv.tq_avg)) { + if (router_ifinfo && + (neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg)) { orig_node_tmp = router->orig_node; spin_lock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); if_num = router->if_incoming->if_num; @@ -1009,7 +1098,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, goto out; } - batadv_update_route(bat_priv, orig_node, neigh_node); + batadv_update_route(bat_priv, orig_node, if_outgoing, neigh_node); goto out; unlock: @@ -1019,20 +1108,37 @@ out: batadv_neigh_node_free_ref(neigh_node); if (router) batadv_neigh_node_free_ref(router); + if (neigh_ifinfo) + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); + if (router_ifinfo) + batadv_neigh_ifinfo_free_ref(router_ifinfo); } +/** + * batadv_iv_ogm_calc_tq - calculate tq for current received ogm packet + * @orig_node: the orig node who originally emitted the ogm packet + * @orig_neigh_node: the orig node struct of the neighbor who sent the packet + * @batadv_ogm_packet: the ogm packet + * @if_incoming: interface where the packet was received + * @if_outgoing: interface for which the retransmission should be considered + * + * Returns 1 if the link can be considered bidirectional, 0 otherwise + */ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, struct batadv_ogm_packet *batadv_ogm_packet, - struct batadv_hard_iface *if_incoming) + struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node; + struct batadv_neigh_ifinfo *neigh_ifinfo; uint8_t total_count; uint8_t orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; int tq_asym_penalty, inv_asym_penalty, if_num, ret = 0; unsigned int combined_tq; + int tq_iface_penalty; /* find corresponding one hop neighbor */ rcu_read_lock(); @@ -1072,7 +1178,13 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); if_num = if_incoming->if_num; orig_eq_count = orig_neigh_node->bat_iv.bcast_own_sum[if_num]; - neigh_rq_count = neigh_node->bat_iv.real_packet_count; + neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing); + if (neigh_ifinfo) { + neigh_rq_count = neigh_ifinfo->bat_iv.real_packet_count; + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); + } else { + neigh_rq_count = 0; + } spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); /* pay attention to not get a value bigger than 100 % */ @@ -1108,15 +1220,31 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, inv_asym_penalty /= neigh_rq_max_cube; tq_asym_penalty = BATADV_TQ_MAX_VALUE - inv_asym_penalty; - combined_tq = batadv_ogm_packet->tq * tq_own * tq_asym_penalty; - combined_tq /= BATADV_TQ_MAX_VALUE * BATADV_TQ_MAX_VALUE; + /* penalize if the OGM is forwarded on the same interface. WiFi + * interfaces and other half duplex devices suffer from throughput + * drops as they can't send and receive at the same time. + */ + tq_iface_penalty = BATADV_TQ_MAX_VALUE; + if (if_outgoing && (if_incoming == if_outgoing) && + batadv_is_wifi_netdev(if_outgoing->net_dev)) + tq_iface_penalty = batadv_hop_penalty(BATADV_TQ_MAX_VALUE, + bat_priv); + + combined_tq = batadv_ogm_packet->tq * + tq_own * + tq_asym_penalty * + tq_iface_penalty; + combined_tq /= BATADV_TQ_MAX_VALUE * + BATADV_TQ_MAX_VALUE * + BATADV_TQ_MAX_VALUE; batadv_ogm_packet->tq = combined_tq; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "bidirectional: orig = %-15pM neigh = %-15pM => own_bcast = %2i, real recv = %2i, local tq: %3i, asym_penalty: %3i, total tq: %3i\n", + "bidirectional: orig = %-15pM neigh = %-15pM => own_bcast = %2i, real recv = %2i, local tq: %3i, asym_penalty: %3i, iface_penalty: %3i, total tq: %3i, if_incoming = %s, if_outgoing = %s\n", orig_node->orig, orig_neigh_node->orig, total_count, - neigh_rq_count, tq_own, - tq_asym_penalty, batadv_ogm_packet->tq); + neigh_rq_count, tq_own, tq_asym_penalty, tq_iface_penalty, + batadv_ogm_packet->tq, if_incoming->net_dev->name, + if_outgoing ? if_outgoing->net_dev->name : "DEFAULT"); /* if link has the minimum required transmission quality * consider it bidirectional @@ -1136,17 +1264,21 @@ out: * @ethhdr: ethernet header of the packet * @batadv_ogm_packet: OGM packet to be considered * @if_incoming: interface on which the OGM packet was received + * @if_outgoing: interface for which the retransmission should be considered * * Returns duplicate status as enum batadv_dup_status */ static enum batadv_dup_status batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, const struct batadv_ogm_packet *batadv_ogm_packet, - const struct batadv_hard_iface *if_incoming) + const struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_orig_node *orig_node; - struct batadv_neigh_node *tmp_neigh_node; + struct batadv_orig_ifinfo *orig_ifinfo = NULL; + struct batadv_neigh_node *neigh_node; + struct batadv_neigh_ifinfo *neigh_ifinfo; int is_dup; int32_t seq_diff; int need_update = 0; @@ -1161,27 +1293,37 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, if (!orig_node) return BATADV_NO_DUP; + orig_ifinfo = batadv_orig_ifinfo_new(orig_node, if_outgoing); + if (WARN_ON(!orig_ifinfo)) { + batadv_orig_node_free_ref(orig_node); + return 0; + } + spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); - seq_diff = seqno - orig_node->last_real_seqno; + seq_diff = seqno - orig_ifinfo->last_real_seqno; /* signalize caller that the packet is to be dropped. */ if (!hlist_empty(&orig_node->neigh_list) && batadv_window_protected(bat_priv, seq_diff, - &orig_node->batman_seqno_reset)) { + &orig_ifinfo->batman_seqno_reset)) { ret = BATADV_PROTECTED; goto out; } rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, - &orig_node->neigh_list, list) { - neigh_addr = tmp_neigh_node->addr; - is_dup = batadv_test_bit(tmp_neigh_node->bat_iv.real_bits, - orig_node->last_real_seqno, + hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) { + neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, + if_outgoing); + if (!neigh_ifinfo) + continue; + + neigh_addr = neigh_node->addr; + is_dup = batadv_test_bit(neigh_ifinfo->bat_iv.real_bits, + orig_ifinfo->last_real_seqno, seqno); if (batadv_compare_eth(neigh_addr, ethhdr->h_source) && - tmp_neigh_node->if_incoming == if_incoming) { + neigh_node->if_incoming == if_incoming) { set_mark = 1; if (is_dup) ret = BATADV_NEIGH_DUP; @@ -1192,173 +1334,78 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, } /* if the window moved, set the update flag. */ - bitmap = tmp_neigh_node->bat_iv.real_bits; + bitmap = neigh_ifinfo->bat_iv.real_bits; need_update |= batadv_bit_get_packet(bat_priv, bitmap, seq_diff, set_mark); - packet_count = bitmap_weight(tmp_neigh_node->bat_iv.real_bits, + packet_count = bitmap_weight(bitmap, BATADV_TQ_LOCAL_WINDOW_SIZE); - tmp_neigh_node->bat_iv.real_packet_count = packet_count; + neigh_ifinfo->bat_iv.real_packet_count = packet_count; + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); } rcu_read_unlock(); if (need_update) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "updating last_seqno: old %u, new %u\n", - orig_node->last_real_seqno, seqno); - orig_node->last_real_seqno = seqno; + "%s updating last_seqno: old %u, new %u\n", + if_outgoing ? if_outgoing->net_dev->name : "DEFAULT", + orig_ifinfo->last_real_seqno, seqno); + orig_ifinfo->last_real_seqno = seqno; } out: spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); batadv_orig_node_free_ref(orig_node); + if (orig_ifinfo) + batadv_orig_ifinfo_free_ref(orig_ifinfo); return ret; } -static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, - struct batadv_ogm_packet *batadv_ogm_packet, - const unsigned char *tt_buff, - struct batadv_hard_iface *if_incoming) + +/** + * batadv_iv_ogm_process_per_outif - process a batman iv OGM for an outgoing if + * @skb: the skb containing the OGM + * @orig_node: the (cached) orig node for the originator of this OGM + * @if_incoming: the interface where this packet was received + * @if_outgoing: the interface for which the packet should be considered + */ +static void +batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, + struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct batadv_hard_iface *hard_iface; - struct batadv_orig_node *orig_neigh_node, *orig_node, *orig_node_tmp; struct batadv_neigh_node *router = NULL, *router_router = NULL; + struct batadv_orig_node *orig_neigh_node; + struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *orig_neigh_router = NULL; - int has_directlink_flag; - int is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0; - int is_bidirect; - bool is_single_hop_neigh = false; - bool is_from_best_next_hop = false; - int sameseq, similar_ttl; + struct batadv_neigh_ifinfo *router_ifinfo = NULL; + struct batadv_ogm_packet *ogm_packet; enum batadv_dup_status dup_status; - uint32_t if_incoming_seqno; + bool is_from_best_next_hop = false; + bool is_single_hop_neigh = false; + bool sameseq, similar_ttl; + struct sk_buff *skb_priv; + struct ethhdr *ethhdr; uint8_t *prev_sender; + int is_bidirect; - /* Silently drop when the batman packet is actually not a - * correct packet. - * - * This might happen if a packet is padded (e.g. Ethernet has a - * minimum frame length of 64 byte) and the aggregation interprets - * it as an additional length. - * - * TODO: A more sane solution would be to have a bit in the - * batadv_ogm_packet to detect whether the packet is the last - * packet in an aggregation. Here we expect that the padding - * is always zero (or not 0x01) + /* create a private copy of the skb, as some functions change tq value + * and/or flags. */ - if (batadv_ogm_packet->packet_type != BATADV_IV_OGM) + skb_priv = skb_copy(skb, GFP_ATOMIC); + if (!skb_priv) return; - /* could be changed by schedule_own_packet() */ - if_incoming_seqno = atomic_read(&if_incoming->bat_iv.ogm_seqno); - - if (batadv_ogm_packet->flags & BATADV_DIRECTLINK) - has_directlink_flag = 1; - else - has_directlink_flag = 0; + ethhdr = eth_hdr(skb_priv); + ogm_packet = (struct batadv_ogm_packet *)(skb_priv->data + ogm_offset); - if (batadv_compare_eth(ethhdr->h_source, batadv_ogm_packet->orig)) + dup_status = batadv_iv_ogm_update_seqnos(ethhdr, ogm_packet, + if_incoming, if_outgoing); + if (batadv_compare_eth(ethhdr->h_source, ogm_packet->orig)) is_single_hop_neigh = true; - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, tq %d, TTL %d, V %d, IDF %d)\n", - ethhdr->h_source, if_incoming->net_dev->name, - if_incoming->net_dev->dev_addr, batadv_ogm_packet->orig, - batadv_ogm_packet->prev_sender, - ntohl(batadv_ogm_packet->seqno), batadv_ogm_packet->tq, - batadv_ogm_packet->ttl, - batadv_ogm_packet->version, has_directlink_flag); - - rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if (hard_iface->if_status != BATADV_IF_ACTIVE) - continue; - - if (hard_iface->soft_iface != if_incoming->soft_iface) - continue; - - if (batadv_compare_eth(ethhdr->h_source, - hard_iface->net_dev->dev_addr)) - is_my_addr = 1; - - if (batadv_compare_eth(batadv_ogm_packet->orig, - hard_iface->net_dev->dev_addr)) - is_my_orig = 1; - - if (batadv_compare_eth(batadv_ogm_packet->prev_sender, - hard_iface->net_dev->dev_addr)) - is_my_oldorig = 1; - } - rcu_read_unlock(); - - if (is_my_addr) { - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Drop packet: received my own broadcast (sender: %pM)\n", - ethhdr->h_source); - return; - } - - if (is_my_orig) { - unsigned long *word; - int offset; - int32_t bit_pos; - int16_t if_num; - uint8_t *weight; - - orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, - ethhdr->h_source); - if (!orig_neigh_node) - return; - - /* neighbor has to indicate direct link and it has to - * come via the corresponding interface - * save packet seqno for bidirectional check - */ - if (has_directlink_flag && - batadv_compare_eth(if_incoming->net_dev->dev_addr, - batadv_ogm_packet->orig)) { - if_num = if_incoming->if_num; - offset = if_num * BATADV_NUM_WORDS; - - spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); - word = &(orig_neigh_node->bat_iv.bcast_own[offset]); - bit_pos = if_incoming_seqno - 2; - bit_pos -= ntohl(batadv_ogm_packet->seqno); - batadv_set_bit(word, bit_pos); - weight = &orig_neigh_node->bat_iv.bcast_own_sum[if_num]; - *weight = bitmap_weight(word, - BATADV_TQ_LOCAL_WINDOW_SIZE); - spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); - } - - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Drop packet: originator packet from myself (via neighbor)\n"); - batadv_orig_node_free_ref(orig_neigh_node); - return; - } - - if (is_my_oldorig) { - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Drop packet: ignoring all rebroadcast echos (sender: %pM)\n", - ethhdr->h_source); - return; - } - - if (batadv_ogm_packet->flags & BATADV_NOT_BEST_NEXT_HOP) { - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Drop packet: ignoring all packets not forwarded from the best next hop (sender: %pM)\n", - ethhdr->h_source); - return; - } - - orig_node = batadv_iv_ogm_orig_get(bat_priv, batadv_ogm_packet->orig); - if (!orig_node) - return; - - dup_status = batadv_iv_ogm_update_seqnos(ethhdr, batadv_ogm_packet, - if_incoming); - if (dup_status == BATADV_PROTECTED) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: packet within seqno protection time (sender: %pM)\n", @@ -1366,27 +1413,28 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, goto out; } - if (batadv_ogm_packet->tq == 0) { + if (ogm_packet->tq == 0) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: originator packet with tq equal 0\n"); goto out; } - router = batadv_orig_node_get_router(orig_node); + router = batadv_orig_router_get(orig_node, if_outgoing); if (router) { - orig_node_tmp = router->orig_node; - router_router = batadv_orig_node_get_router(orig_node_tmp); + router_router = batadv_orig_router_get(router->orig_node, + if_outgoing); + router_ifinfo = batadv_neigh_ifinfo_get(router, if_outgoing); } - if ((router && router->bat_iv.tq_avg != 0) && + if ((router_ifinfo && router_ifinfo->bat_iv.tq_avg != 0) && (batadv_compare_eth(router->addr, ethhdr->h_source))) is_from_best_next_hop = true; - prev_sender = batadv_ogm_packet->prev_sender; + prev_sender = ogm_packet->prev_sender; /* avoid temporary routing loops */ if (router && router_router && (batadv_compare_eth(router->addr, prev_sender)) && - !(batadv_compare_eth(batadv_ogm_packet->orig, prev_sender)) && + !(batadv_compare_eth(ogm_packet->orig, prev_sender)) && (batadv_compare_eth(router->addr, router_router->addr))) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: ignoring all rebroadcast packets that may make me loop (sender: %pM)\n", @@ -1394,7 +1442,8 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, goto out; } - batadv_tvlv_ogm_receive(bat_priv, batadv_ogm_packet, orig_node); + if (if_outgoing == BATADV_IF_DEFAULT) + batadv_tvlv_ogm_receive(bat_priv, ogm_packet, orig_node); /* if sender is a direct neighbor the sender mac equals * originator mac @@ -1410,9 +1459,10 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, /* Update nc_nodes of the originator */ batadv_nc_update_nc_node(bat_priv, orig_node, orig_neigh_node, - batadv_ogm_packet, is_single_hop_neigh); + ogm_packet, is_single_hop_neigh); - orig_neigh_router = batadv_orig_node_get_router(orig_neigh_node); + orig_neigh_router = batadv_orig_router_get(orig_neigh_node, + if_outgoing); /* drop packet if sender is not a direct neighbor and if we * don't route towards it @@ -1424,28 +1474,48 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, } is_bidirect = batadv_iv_ogm_calc_tq(orig_node, orig_neigh_node, - batadv_ogm_packet, if_incoming); - - batadv_bonding_save_primary(orig_node, orig_neigh_node, - batadv_ogm_packet); + ogm_packet, if_incoming, + if_outgoing); /* update ranking if it is not a duplicate or has the same * seqno and similar ttl as the non-duplicate */ - sameseq = orig_node->last_real_seqno == ntohl(batadv_ogm_packet->seqno); - similar_ttl = orig_node->last_ttl - 3 <= batadv_ogm_packet->ttl; + orig_ifinfo = batadv_orig_ifinfo_new(orig_node, if_outgoing); + if (!orig_ifinfo) + goto out_neigh; + + sameseq = orig_ifinfo->last_real_seqno == ntohl(ogm_packet->seqno); + similar_ttl = (orig_ifinfo->last_ttl - 3) <= ogm_packet->ttl; + if (is_bidirect && ((dup_status == BATADV_NO_DUP) || - (sameseq && similar_ttl))) - batadv_iv_ogm_orig_update(bat_priv, orig_node, ethhdr, - batadv_ogm_packet, if_incoming, - tt_buff, dup_status); + (sameseq && similar_ttl))) { + batadv_iv_ogm_orig_update(bat_priv, orig_node, + orig_ifinfo, ethhdr, + ogm_packet, if_incoming, + if_outgoing, dup_status); + } + batadv_orig_ifinfo_free_ref(orig_ifinfo); + + /* only forward for specific interface, not for the default one. */ + if (if_outgoing == BATADV_IF_DEFAULT) + goto out_neigh; /* is single hop (direct) neighbor */ if (is_single_hop_neigh) { + /* OGMs from secondary interfaces should only scheduled once + * per interface where it has been received, not multiple times + */ + if ((ogm_packet->ttl <= 2) && + (if_incoming != if_outgoing)) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: OGM from secondary interface and wrong outgoing interface\n"); + goto out_neigh; + } /* mark direct link on incoming interface */ - batadv_iv_ogm_forward(orig_node, ethhdr, batadv_ogm_packet, + batadv_iv_ogm_forward(orig_node, ethhdr, ogm_packet, is_single_hop_neigh, - is_from_best_next_hop, if_incoming); + is_from_best_next_hop, if_incoming, + if_outgoing); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Forwarding packet: rebroadcast neighbor packet with direct link flag\n"); @@ -1467,9 +1537,9 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Forwarding packet: rebroadcast originator packet\n"); - batadv_iv_ogm_forward(orig_node, ethhdr, batadv_ogm_packet, + batadv_iv_ogm_forward(orig_node, ethhdr, ogm_packet, is_single_hop_neigh, is_from_best_next_hop, - if_incoming); + if_incoming, if_outgoing); out_neigh: if ((orig_neigh_node) && (!is_single_hop_neigh)) @@ -1482,6 +1552,165 @@ out: if (orig_neigh_router) batadv_neigh_node_free_ref(orig_neigh_router); + kfree_skb(skb_priv); +} + +/** + * batadv_iv_ogm_process - process an incoming batman iv OGM + * @skb: the skb containing the OGM + * @ogm_offset: offset to the OGM which should be processed (for aggregates) + * @if_incoming: the interface where this packet was receved + */ +static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset, + struct batadv_hard_iface *if_incoming) +{ + struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); + struct batadv_orig_node *orig_neigh_node, *orig_node; + struct batadv_hard_iface *hard_iface; + struct batadv_ogm_packet *ogm_packet; + uint32_t if_incoming_seqno; + bool has_directlink_flag; + struct ethhdr *ethhdr; + bool is_my_oldorig = false; + bool is_my_addr = false; + bool is_my_orig = false; + + ogm_packet = (struct batadv_ogm_packet *)(skb->data + ogm_offset); + ethhdr = eth_hdr(skb); + + /* Silently drop when the batman packet is actually not a + * correct packet. + * + * This might happen if a packet is padded (e.g. Ethernet has a + * minimum frame length of 64 byte) and the aggregation interprets + * it as an additional length. + * + * TODO: A more sane solution would be to have a bit in the + * batadv_ogm_packet to detect whether the packet is the last + * packet in an aggregation. Here we expect that the padding + * is always zero (or not 0x01) + */ + if (ogm_packet->packet_type != BATADV_IV_OGM) + return; + + /* could be changed by schedule_own_packet() */ + if_incoming_seqno = atomic_read(&if_incoming->bat_iv.ogm_seqno); + + if (ogm_packet->flags & BATADV_DIRECTLINK) + has_directlink_flag = true; + else + has_directlink_flag = false; + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, tq %d, TTL %d, V %d, IDF %d)\n", + ethhdr->h_source, if_incoming->net_dev->name, + if_incoming->net_dev->dev_addr, ogm_packet->orig, + ogm_packet->prev_sender, ntohl(ogm_packet->seqno), + ogm_packet->tq, ogm_packet->ttl, + ogm_packet->version, has_directlink_flag); + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->if_status != BATADV_IF_ACTIVE) + continue; + + if (hard_iface->soft_iface != if_incoming->soft_iface) + continue; + + if (batadv_compare_eth(ethhdr->h_source, + hard_iface->net_dev->dev_addr)) + is_my_addr = true; + + if (batadv_compare_eth(ogm_packet->orig, + hard_iface->net_dev->dev_addr)) + is_my_orig = true; + + if (batadv_compare_eth(ogm_packet->prev_sender, + hard_iface->net_dev->dev_addr)) + is_my_oldorig = true; + } + rcu_read_unlock(); + + if (is_my_addr) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: received my own broadcast (sender: %pM)\n", + ethhdr->h_source); + return; + } + + if (is_my_orig) { + unsigned long *word; + int offset; + int32_t bit_pos; + int16_t if_num; + uint8_t *weight; + + orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, + ethhdr->h_source); + if (!orig_neigh_node) + return; + + /* neighbor has to indicate direct link and it has to + * come via the corresponding interface + * save packet seqno for bidirectional check + */ + if (has_directlink_flag && + batadv_compare_eth(if_incoming->net_dev->dev_addr, + ogm_packet->orig)) { + if_num = if_incoming->if_num; + offset = if_num * BATADV_NUM_WORDS; + + spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); + word = &(orig_neigh_node->bat_iv.bcast_own[offset]); + bit_pos = if_incoming_seqno - 2; + bit_pos -= ntohl(ogm_packet->seqno); + batadv_set_bit(word, bit_pos); + weight = &orig_neigh_node->bat_iv.bcast_own_sum[if_num]; + *weight = bitmap_weight(word, + BATADV_TQ_LOCAL_WINDOW_SIZE); + spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); + } + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: originator packet from myself (via neighbor)\n"); + batadv_orig_node_free_ref(orig_neigh_node); + return; + } + + if (is_my_oldorig) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: ignoring all rebroadcast echos (sender: %pM)\n", + ethhdr->h_source); + return; + } + + if (ogm_packet->flags & BATADV_NOT_BEST_NEXT_HOP) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: ignoring all packets not forwarded from the best next hop (sender: %pM)\n", + ethhdr->h_source); + return; + } + + orig_node = batadv_iv_ogm_orig_get(bat_priv, ogm_packet->orig); + if (!orig_node) + return; + + batadv_iv_ogm_process_per_outif(skb, ogm_offset, orig_node, + if_incoming, BATADV_IF_DEFAULT); + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->if_status != BATADV_IF_ACTIVE) + continue; + + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + batadv_iv_ogm_process_per_outif(skb, ogm_offset, orig_node, + if_incoming, hard_iface); + } + rcu_read_unlock(); + batadv_orig_node_free_ref(orig_node); } @@ -1489,11 +1718,9 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, struct batadv_hard_iface *if_incoming) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct batadv_ogm_packet *batadv_ogm_packet; - struct ethhdr *ethhdr; - int buff_pos = 0, packet_len; - unsigned char *tvlv_buff, *packet_buff; + struct batadv_ogm_packet *ogm_packet; uint8_t *packet_pos; + int ogm_offset; bool ret; ret = batadv_check_management_packet(skb, if_incoming, BATADV_OGM_HLEN); @@ -1510,24 +1737,19 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, batadv_add_counter(bat_priv, BATADV_CNT_MGMT_RX_BYTES, skb->len + ETH_HLEN); - packet_len = skb_headlen(skb); - ethhdr = eth_hdr(skb); - packet_buff = skb->data; - batadv_ogm_packet = (struct batadv_ogm_packet *)packet_buff; + ogm_offset = 0; + ogm_packet = (struct batadv_ogm_packet *)skb->data; /* unpack the aggregated packets and process them one by one */ - while (batadv_iv_ogm_aggr_packet(buff_pos, packet_len, - batadv_ogm_packet->tvlv_len)) { - tvlv_buff = packet_buff + buff_pos + BATADV_OGM_HLEN; + while (batadv_iv_ogm_aggr_packet(ogm_offset, skb_headlen(skb), + ogm_packet->tvlv_len)) { + batadv_iv_ogm_process(skb, ogm_offset, if_incoming); - batadv_iv_ogm_process(ethhdr, batadv_ogm_packet, - tvlv_buff, if_incoming); + ogm_offset += BATADV_OGM_HLEN; + ogm_offset += ntohs(ogm_packet->tvlv_len); - buff_pos += BATADV_OGM_HLEN; - buff_pos += ntohs(batadv_ogm_packet->tvlv_len); - - packet_pos = packet_buff + buff_pos; - batadv_ogm_packet = (struct batadv_ogm_packet *)packet_pos; + packet_pos = skb->data + ogm_offset; + ogm_packet = (struct batadv_ogm_packet *)packet_pos; } kfree_skb(skb); @@ -1535,17 +1757,49 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, } /** + * batadv_iv_ogm_orig_print_neigh - print neighbors for the originator table + * @orig_node: the orig_node for which the neighbors are printed + * @if_outgoing: outgoing interface for these entries + * @seq: debugfs table seq_file struct + * + * Must be called while holding an rcu lock. + */ +static void +batadv_iv_ogm_orig_print_neigh(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing, + struct seq_file *seq) +{ + struct batadv_neigh_node *neigh_node; + struct batadv_neigh_ifinfo *n_ifinfo; + + hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) { + n_ifinfo = batadv_neigh_ifinfo_get(neigh_node, if_outgoing); + if (!n_ifinfo) + continue; + + seq_printf(seq, " %pM (%3i)", + neigh_node->addr, + n_ifinfo->bat_iv.tq_avg); + + batadv_neigh_ifinfo_free_ref(n_ifinfo); + } +} + +/** * batadv_iv_ogm_orig_print - print the originator table * @bat_priv: the bat priv with all the soft interface information * @seq: debugfs table seq_file struct + * @if_outgoing: the outgoing interface for which this should be printed */ static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv, - struct seq_file *seq) + struct seq_file *seq, + struct batadv_hard_iface *if_outgoing) { - struct batadv_neigh_node *neigh_node, *neigh_node_tmp; + struct batadv_neigh_node *neigh_node; struct batadv_hashtable *hash = bat_priv->orig_hash; int last_seen_msecs, last_seen_secs; struct batadv_orig_node *orig_node; + struct batadv_neigh_ifinfo *n_ifinfo; unsigned long last_seen_jiffies; struct hlist_head *head; int batman_count = 0; @@ -1560,11 +1814,17 @@ static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) { - neigh_node = batadv_orig_node_get_router(orig_node); + neigh_node = batadv_orig_router_get(orig_node, + if_outgoing); if (!neigh_node) continue; - if (neigh_node->bat_iv.tq_avg == 0) + n_ifinfo = batadv_neigh_ifinfo_get(neigh_node, + if_outgoing); + if (!n_ifinfo) + goto next; + + if (n_ifinfo->bat_iv.tq_avg == 0) goto next; last_seen_jiffies = jiffies - orig_node->last_seen; @@ -1574,22 +1834,19 @@ static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv, seq_printf(seq, "%pM %4i.%03is (%3i) %pM [%10s]:", orig_node->orig, last_seen_secs, - last_seen_msecs, neigh_node->bat_iv.tq_avg, + last_seen_msecs, n_ifinfo->bat_iv.tq_avg, neigh_node->addr, neigh_node->if_incoming->net_dev->name); - hlist_for_each_entry_rcu(neigh_node_tmp, - &orig_node->neigh_list, list) { - seq_printf(seq, " %pM (%3i)", - neigh_node_tmp->addr, - neigh_node_tmp->bat_iv.tq_avg); - } - + batadv_iv_ogm_orig_print_neigh(orig_node, if_outgoing, + seq); seq_puts(seq, "\n"); batman_count++; next: batadv_neigh_node_free_ref(neigh_node); + if (n_ifinfo) + batadv_neigh_ifinfo_free_ref(n_ifinfo); } rcu_read_unlock(); } @@ -1601,37 +1858,84 @@ next: /** * batadv_iv_ogm_neigh_cmp - compare the metrics of two neighbors * @neigh1: the first neighbor object of the comparison + * @if_outgoing1: outgoing interface for the first neighbor * @neigh2: the second neighbor object of the comparison + * @if_outgoing2: outgoing interface for the second neighbor * * Returns a value less, equal to or greater than 0 if the metric via neigh1 is * lower, the same as or higher than the metric via neigh2 */ static int batadv_iv_ogm_neigh_cmp(struct batadv_neigh_node *neigh1, - struct batadv_neigh_node *neigh2) + struct batadv_hard_iface *if_outgoing1, + struct batadv_neigh_node *neigh2, + struct batadv_hard_iface *if_outgoing2) { + struct batadv_neigh_ifinfo *neigh1_ifinfo, *neigh2_ifinfo; uint8_t tq1, tq2; + int diff; + + neigh1_ifinfo = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); + neigh2_ifinfo = batadv_neigh_ifinfo_get(neigh2, if_outgoing2); - tq1 = neigh1->bat_iv.tq_avg; - tq2 = neigh2->bat_iv.tq_avg; + if (!neigh1_ifinfo || !neigh2_ifinfo) { + diff = 0; + goto out; + } + + tq1 = neigh1_ifinfo->bat_iv.tq_avg; + tq2 = neigh2_ifinfo->bat_iv.tq_avg; + diff = tq1 - tq2; - return tq1 - tq2; +out: + if (neigh1_ifinfo) + batadv_neigh_ifinfo_free_ref(neigh1_ifinfo); + if (neigh2_ifinfo) + batadv_neigh_ifinfo_free_ref(neigh2_ifinfo); + + return diff; } /** * batadv_iv_ogm_neigh_is_eob - check if neigh1 is equally good or better than * neigh2 from the metric prospective * @neigh1: the first neighbor object of the comparison + * @if_outgoing: outgoing interface for the first neighbor * @neigh2: the second neighbor object of the comparison - * - * Returns true if the metric via neigh1 is equally good or better than the - * metric via neigh2, false otherwise. + * @if_outgoing2: outgoing interface for the second neighbor + + * Returns true if the metric via neigh1 is equally good or better than + * the metric via neigh2, false otherwise. */ -static bool batadv_iv_ogm_neigh_is_eob(struct batadv_neigh_node *neigh1, - struct batadv_neigh_node *neigh2) +static bool +batadv_iv_ogm_neigh_is_eob(struct batadv_neigh_node *neigh1, + struct batadv_hard_iface *if_outgoing1, + struct batadv_neigh_node *neigh2, + struct batadv_hard_iface *if_outgoing2) { - int diff = batadv_iv_ogm_neigh_cmp(neigh1, neigh2); + struct batadv_neigh_ifinfo *neigh1_ifinfo, *neigh2_ifinfo; + uint8_t tq1, tq2; + bool ret; + + neigh1_ifinfo = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); + neigh2_ifinfo = batadv_neigh_ifinfo_get(neigh2, if_outgoing2); + + /* we can't say that the metric is better */ + if (!neigh1_ifinfo || !neigh2_ifinfo) { + ret = false; + goto out; + } + + tq1 = neigh1_ifinfo->bat_iv.tq_avg; + tq2 = neigh2_ifinfo->bat_iv.tq_avg; + ret = (tq1 - tq2) > -BATADV_TQ_SIMILARITY_THRESHOLD; - return diff > -BATADV_TQ_SIMILARITY_THRESHOLD; +out: + if (neigh1_ifinfo) + batadv_neigh_ifinfo_free_ref(neigh1_ifinfo); + if (neigh2_ifinfo) + batadv_neigh_ifinfo_free_ref(neigh2_ifinfo); + + return ret; } static struct batadv_algo_ops batadv_batman_iv __read_mostly = { diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 973982414d58..9586750022f5 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index a81b9322e382..cc2407351d36 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_BITARRAY_H_ diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 28eb5e6d0a02..05f0712be5e7 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -132,7 +130,9 @@ static void batadv_claim_free_ref(struct batadv_bla_claim *claim) call_rcu(&claim->rcu, batadv_claim_free_rcu); } -/* @bat_priv: the bat priv with all the soft interface information +/** + * batadv_claim_hash_find + * @bat_priv: the bat priv with all the soft interface information * @data: search data (may be local/static data) * * looks for a claim in the hash, and returns it if found @@ -451,7 +451,9 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv, batadv_backbone_gw_free_ref(backbone_gw); } -/* @bat_priv: the bat priv with all the soft interface information +/** + * batadv_bla_answer_request - answer a bla request by sending own claims + * @bat_priv: the bat priv with all the soft interface information * @vid: the vid where the request came on * * Repeat all of our own claims, and finally send an ANNOUNCE frame @@ -497,7 +499,9 @@ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, batadv_backbone_gw_free_ref(backbone_gw); } -/* @backbone_gw: the backbone gateway from whom we are out of sync +/** + * batadv_bla_send_request - send a request to repeat claims + * @backbone_gw: the backbone gateway from whom we are out of sync * * When the crc is wrong, ask the backbone gateway for a full table update. * After the request, it will repeat all of his own claims and finally @@ -522,7 +526,9 @@ static void batadv_bla_send_request(struct batadv_bla_backbone_gw *backbone_gw) } } -/* @bat_priv: the bat priv with all the soft interface information +/** + * batadv_bla_send_announce + * @bat_priv: the bat priv with all the soft interface information * @backbone_gw: our backbone gateway which should be announced * * This function sends an announcement. It is called from multiple @@ -846,7 +852,9 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv, } -/* @bat_priv: the bat priv with all the soft interface information +/** + * batadv_bla_process_claim + * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * * Check if this is a claim frame, and process it accordingly. @@ -1313,7 +1321,9 @@ out: -/* @bat_priv: the bat priv with all the soft interface information +/** + * batadv_bla_is_backbone_gw_orig + * @bat_priv: the bat priv with all the soft interface information * @orig: originator mac address * @vid: VLAN identifier * diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index da173e760e77..43c985d92c3e 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_BLA_H_ diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 049a7a2ac5b6..b758881be108 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -250,6 +248,19 @@ static int batadv_originators_open(struct inode *inode, struct file *file) return single_open(file, batadv_orig_seq_print_text, net_dev); } +/** + * batadv_originators_hardif_open - handles debugfs output for the + * originator table of an hard interface + * @inode: inode pointer to debugfs file + * @file: pointer to the seq_file + */ +static int batadv_originators_hardif_open(struct inode *inode, + struct file *file) +{ + struct net_device *net_dev = (struct net_device *)inode->i_private; + return single_open(file, batadv_orig_hardif_seq_print_text, net_dev); +} + static int batadv_gateways_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; @@ -371,6 +382,28 @@ static struct batadv_debuginfo *batadv_mesh_debuginfos[] = { NULL, }; +#define BATADV_HARDIF_DEBUGINFO(_name, _mode, _open) \ +struct batadv_debuginfo batadv_hardif_debuginfo_##_name = { \ + .attr = { \ + .name = __stringify(_name), \ + .mode = _mode, \ + }, \ + .fops = { \ + .owner = THIS_MODULE, \ + .open = _open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ + }, \ +}; +static BATADV_HARDIF_DEBUGINFO(originators, S_IRUGO, + batadv_originators_hardif_open); + +static struct batadv_debuginfo *batadv_hardif_debuginfos[] = { + &batadv_hardif_debuginfo_originators, + NULL, +}; + void batadv_debugfs_init(void) { struct batadv_debuginfo **bat_debug; @@ -398,6 +431,7 @@ void batadv_debugfs_init(void) return; err: debugfs_remove_recursive(batadv_debugfs); + batadv_debugfs = NULL; } void batadv_debugfs_destroy(void) @@ -406,6 +440,59 @@ void batadv_debugfs_destroy(void) batadv_debugfs = NULL; } +/** + * batadv_debugfs_add_hardif - creates the base directory for a hard interface + * in debugfs. + * @hard_iface: hard interface which should be added. + */ +int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface) +{ + struct batadv_debuginfo **bat_debug; + struct dentry *file; + + if (!batadv_debugfs) + goto out; + + hard_iface->debug_dir = debugfs_create_dir(hard_iface->net_dev->name, + batadv_debugfs); + if (!hard_iface->debug_dir) + goto out; + + for (bat_debug = batadv_hardif_debuginfos; *bat_debug; ++bat_debug) { + file = debugfs_create_file(((*bat_debug)->attr).name, + S_IFREG | ((*bat_debug)->attr).mode, + hard_iface->debug_dir, + hard_iface->net_dev, + &(*bat_debug)->fops); + if (!file) + goto rem_attr; + } + + return 0; +rem_attr: + debugfs_remove_recursive(hard_iface->debug_dir); + hard_iface->debug_dir = NULL; +out: +#ifdef CONFIG_DEBUG_FS + return -ENOMEM; +#else + return 0; +#endif /* CONFIG_DEBUG_FS */ +} + +/** + * batadv_debugfs_del_hardif - delete the base directory for a hard interface + * in debugfs. + * @hard_iface: hard interface which is deleted. + */ +void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface) +{ + if (batadv_debugfs) { + debugfs_remove_recursive(hard_iface->debug_dir); + hard_iface->debug_dir = NULL; + } +} + int batadv_debugfs_add_meshif(struct net_device *dev) { struct batadv_priv *bat_priv = netdev_priv(dev); diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index f8c3849edff4..37c4d6ddd04d 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_DEBUGFS_H_ @@ -26,5 +24,7 @@ void batadv_debugfs_init(void); void batadv_debugfs_destroy(void); int batadv_debugfs_add_meshif(struct net_device *dev); void batadv_debugfs_del_meshif(struct net_device *dev); +int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface); +void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface); #endif /* _NET_BATMAN_ADV_DEBUGFS_H_ */ diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index b316a4cb6f14..edee50411892 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: * * Antonio Quartulli * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/if_ether.h> @@ -141,7 +139,7 @@ static int batadv_compare_dat(const struct hlist_node *node, const void *data2) const void *data1 = container_of(node, struct batadv_dat_entry, hash_entry); - return (memcmp(data1, data2, sizeof(__be32)) == 0 ? 1 : 0); + return memcmp(data1, data2, sizeof(__be32)) == 0 ? 1 : 0; } /** @@ -591,7 +589,8 @@ static bool batadv_dat_send_data(struct batadv_priv *bat_priv, if (cand[i].type == BATADV_DAT_CANDIDATE_NOT_FOUND) continue; - neigh_node = batadv_orig_node_get_router(cand[i].orig_node); + neigh_node = batadv_orig_router_get(cand[i].orig_node, + BATADV_IF_DEFAULT); if (!neigh_node) goto free_orig; @@ -1039,9 +1038,9 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, if (hdr_size == sizeof(struct batadv_unicast_4addr_packet)) err = batadv_send_skb_via_tt_4addr(bat_priv, skb_new, BATADV_P_DAT_CACHE_REPLY, - vid); + NULL, vid); else - err = batadv_send_skb_via_tt(bat_priv, skb_new, vid); + err = batadv_send_skb_via_tt(bat_priv, skb_new, NULL, vid); if (err != NET_XMIT_DROP) { batadv_inc_counter(bat_priv, BATADV_CNT_DAT_CACHED_REPLY_TX); diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index 60d853beb8d8..ac9be9b67a25 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors: * * Antonio Quartulli * @@ -12,13 +12,11 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ -#ifndef _NET_BATMAN_ADV_ARP_H_ -#define _NET_BATMAN_ADV_ARP_H_ +#ifndef _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_ +#define _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_ #ifdef CONFIG_BATMAN_ADV_DAT @@ -169,4 +167,4 @@ static inline void batadv_dat_inc_counter(struct batadv_priv *bat_priv, #endif /* CONFIG_BATMAN_ADV_DAT */ -#endif /* _NET_BATMAN_ADV_ARP_H_ */ +#endif /* _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_ */ diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 6ddb6145ffb5..88df9b1d552d 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index ca029e2676e7..5d7a0e66a22b 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_FRAGMENTATION_H_ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 2449afaa7638..55cf2260d295 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -30,11 +28,17 @@ #include <linux/udp.h> #include <linux/if_vlan.h> -/* This is the offset of the options field in a dhcp packet starting at - * the beginning of the dhcp header +/* These are the offsets of the "hw type" and "hw address length" in the dhcp + * packet starting at the beginning of the dhcp header */ -#define BATADV_DHCP_OPTIONS_OFFSET 240 -#define BATADV_DHCP_REQUEST 3 +#define BATADV_DHCP_HTYPE_OFFSET 1 +#define BATADV_DHCP_HLEN_OFFSET 2 +/* Value of htype representing Ethernet */ +#define BATADV_DHCP_HTYPE_ETHERNET 0x01 +/* This is the offset of the "chaddr" field in the dhcp packet starting at the + * beginning of the dhcp header + */ +#define BATADV_DHCP_CHADDR_OFFSET 28 static void batadv_gw_node_free_ref(struct batadv_gw_node *gw_node) { @@ -105,7 +109,18 @@ static void batadv_gw_select(struct batadv_priv *bat_priv, spin_unlock_bh(&bat_priv->gw.list_lock); } -void batadv_gw_deselect(struct batadv_priv *bat_priv) +/** + * batadv_gw_reselect - force a gateway reselection + * @bat_priv: the bat priv with all the soft interface information + * + * Set a flag to remind the GW component to perform a new gateway reselection. + * However this function does not ensure that the current gateway is going to be + * deselected. The reselection mechanism may elect the same gateway once again. + * + * This means that invoking batadv_gw_reselect() does not guarantee a gateway + * change and therefore a uevent is not necessarily expected. + */ +void batadv_gw_reselect(struct batadv_priv *bat_priv) { atomic_set(&bat_priv->gw.reselect, 1); } @@ -114,6 +129,7 @@ static struct batadv_gw_node * batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) { struct batadv_neigh_node *router; + struct batadv_neigh_ifinfo *router_ifinfo; struct batadv_gw_node *gw_node, *curr_gw = NULL; uint32_t max_gw_factor = 0, tmp_gw_factor = 0; uint32_t gw_divisor; @@ -130,14 +146,19 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) continue; orig_node = gw_node->orig_node; - router = batadv_orig_node_get_router(orig_node); + router = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT); if (!router) continue; + router_ifinfo = batadv_neigh_ifinfo_get(router, + BATADV_IF_DEFAULT); + if (!router_ifinfo) + goto next; + if (!atomic_inc_not_zero(&gw_node->refcount)) goto next; - tq_avg = router->bat_iv.tq_avg; + tq_avg = router_ifinfo->bat_iv.tq_avg; switch (atomic_read(&bat_priv->gw_sel_class)) { case 1: /* fast connection */ @@ -182,6 +203,8 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) next: batadv_neigh_node_free_ref(router); + if (router_ifinfo) + batadv_neigh_ifinfo_free_ref(router_ifinfo); } rcu_read_unlock(); @@ -207,6 +230,11 @@ void batadv_gw_check_client_stop(struct batadv_priv *bat_priv) if (!curr_gw) return; + /* deselect the current gateway so that next time that client mode is + * enabled a proper GW_ADD event can be sent + */ + batadv_gw_select(bat_priv, NULL); + /* if batman-adv is switching the gw client mode off and a gateway was * already selected, send a DEL uevent */ @@ -219,6 +247,7 @@ void batadv_gw_election(struct batadv_priv *bat_priv) { struct batadv_gw_node *curr_gw = NULL, *next_gw = NULL; struct batadv_neigh_node *router = NULL; + struct batadv_neigh_ifinfo *router_ifinfo = NULL; char gw_addr[18] = { '\0' }; if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_CLIENT) @@ -237,9 +266,17 @@ void batadv_gw_election(struct batadv_priv *bat_priv) if (next_gw) { sprintf(gw_addr, "%pM", next_gw->orig_node->orig); - router = batadv_orig_node_get_router(next_gw->orig_node); + router = batadv_orig_router_get(next_gw->orig_node, + BATADV_IF_DEFAULT); if (!router) { - batadv_gw_deselect(bat_priv); + batadv_gw_reselect(bat_priv); + goto out; + } + + router_ifinfo = batadv_neigh_ifinfo_get(router, + BATADV_IF_DEFAULT); + if (!router_ifinfo) { + batadv_gw_reselect(bat_priv); goto out; } } @@ -256,7 +293,8 @@ void batadv_gw_election(struct batadv_priv *bat_priv) next_gw->bandwidth_down / 10, next_gw->bandwidth_down % 10, next_gw->bandwidth_up / 10, - next_gw->bandwidth_up % 10, router->bat_iv.tq_avg); + next_gw->bandwidth_up % 10, + router_ifinfo->bat_iv.tq_avg); batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_ADD, gw_addr); } else { @@ -266,7 +304,8 @@ void batadv_gw_election(struct batadv_priv *bat_priv) next_gw->bandwidth_down / 10, next_gw->bandwidth_down % 10, next_gw->bandwidth_up / 10, - next_gw->bandwidth_up % 10, router->bat_iv.tq_avg); + next_gw->bandwidth_up % 10, + router_ifinfo->bat_iv.tq_avg); batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_CHANGE, gw_addr); } @@ -280,33 +319,47 @@ out: batadv_gw_node_free_ref(next_gw); if (router) batadv_neigh_node_free_ref(router); + if (router_ifinfo) + batadv_neigh_ifinfo_free_ref(router_ifinfo); } void batadv_gw_check_election(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { + struct batadv_neigh_ifinfo *router_orig_tq = NULL; + struct batadv_neigh_ifinfo *router_gw_tq = NULL; struct batadv_orig_node *curr_gw_orig; struct batadv_neigh_node *router_gw = NULL, *router_orig = NULL; uint8_t gw_tq_avg, orig_tq_avg; curr_gw_orig = batadv_gw_get_selected_orig(bat_priv); if (!curr_gw_orig) - goto deselect; + goto reselect; - router_gw = batadv_orig_node_get_router(curr_gw_orig); + router_gw = batadv_orig_router_get(curr_gw_orig, BATADV_IF_DEFAULT); if (!router_gw) - goto deselect; + goto reselect; + + router_gw_tq = batadv_neigh_ifinfo_get(router_gw, + BATADV_IF_DEFAULT); + if (!router_gw_tq) + goto reselect; /* this node already is the gateway */ if (curr_gw_orig == orig_node) goto out; - router_orig = batadv_orig_node_get_router(orig_node); + router_orig = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT); if (!router_orig) goto out; - gw_tq_avg = router_gw->bat_iv.tq_avg; - orig_tq_avg = router_orig->bat_iv.tq_avg; + router_orig_tq = batadv_neigh_ifinfo_get(router_orig, + BATADV_IF_DEFAULT); + if (!router_orig_tq) + goto out; + + gw_tq_avg = router_gw_tq->bat_iv.tq_avg; + orig_tq_avg = router_orig_tq->bat_iv.tq_avg; /* the TQ value has to be better */ if (orig_tq_avg < gw_tq_avg) @@ -323,8 +376,8 @@ void batadv_gw_check_election(struct batadv_priv *bat_priv, "Restarting gateway selection: better gateway found (tq curr: %i, tq new: %i)\n", gw_tq_avg, orig_tq_avg); -deselect: - batadv_gw_deselect(bat_priv); +reselect: + batadv_gw_reselect(bat_priv); out: if (curr_gw_orig) batadv_orig_node_free_ref(curr_gw_orig); @@ -332,6 +385,10 @@ out: batadv_neigh_node_free_ref(router_gw); if (router_orig) batadv_neigh_node_free_ref(router_orig); + if (router_gw_tq) + batadv_neigh_ifinfo_free_ref(router_gw_tq); + if (router_orig_tq) + batadv_neigh_ifinfo_free_ref(router_orig_tq); return; } @@ -454,7 +511,7 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, */ curr_gw = batadv_gw_get_selected_gw_node(bat_priv); if (gw_node == curr_gw) - batadv_gw_deselect(bat_priv); + batadv_gw_reselect(bat_priv); } out: @@ -480,7 +537,7 @@ void batadv_gw_node_purge(struct batadv_priv *bat_priv) struct batadv_gw_node *gw_node, *curr_gw; struct hlist_node *node_tmp; unsigned long timeout = msecs_to_jiffies(2 * BATADV_PURGE_TIMEOUT); - int do_deselect = 0; + int do_reselect = 0; curr_gw = batadv_gw_get_selected_gw_node(bat_priv); @@ -494,7 +551,7 @@ void batadv_gw_node_purge(struct batadv_priv *bat_priv) continue; if (curr_gw == gw_node) - do_deselect = 1; + do_reselect = 1; hlist_del_rcu(&gw_node->list); batadv_gw_node_free_ref(gw_node); @@ -502,9 +559,9 @@ void batadv_gw_node_purge(struct batadv_priv *bat_priv) spin_unlock_bh(&bat_priv->gw.list_lock); - /* gw_deselect() needs to acquire the gw_list_lock */ - if (do_deselect) - batadv_gw_deselect(bat_priv); + /* gw_reselect() needs to acquire the gw_list_lock */ + if (do_reselect) + batadv_gw_reselect(bat_priv); if (curr_gw) batadv_gw_node_free_ref(curr_gw); @@ -517,28 +574,36 @@ static int batadv_write_buffer_text(struct batadv_priv *bat_priv, { struct batadv_gw_node *curr_gw; struct batadv_neigh_node *router; + struct batadv_neigh_ifinfo *router_ifinfo = NULL; int ret = -1; - router = batadv_orig_node_get_router(gw_node->orig_node); + router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); if (!router) goto out; + router_ifinfo = batadv_neigh_ifinfo_get(router, BATADV_IF_DEFAULT); + if (!router_ifinfo) + goto out; + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); ret = seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %u.%u/%u.%u MBit\n", (curr_gw == gw_node ? "=>" : " "), gw_node->orig_node->orig, - router->bat_iv.tq_avg, router->addr, + router_ifinfo->bat_iv.tq_avg, router->addr, router->if_incoming->net_dev->name, gw_node->bandwidth_down / 10, gw_node->bandwidth_down % 10, gw_node->bandwidth_up / 10, gw_node->bandwidth_up % 10); - batadv_neigh_node_free_ref(router); if (curr_gw) batadv_gw_node_free_ref(curr_gw); out: + if (router_ifinfo) + batadv_neigh_ifinfo_free_ref(router_ifinfo); + if (router) + batadv_neigh_node_free_ref(router); return ret; } @@ -582,80 +647,39 @@ out: return 0; } -/* this call might reallocate skb data */ -static bool batadv_is_type_dhcprequest(struct sk_buff *skb, int header_len) -{ - int ret = false; - unsigned char *p; - int pkt_len; - - if (skb_linearize(skb) < 0) - goto out; - - pkt_len = skb_headlen(skb); - - if (pkt_len < header_len + BATADV_DHCP_OPTIONS_OFFSET + 1) - goto out; - - p = skb->data + header_len + BATADV_DHCP_OPTIONS_OFFSET; - pkt_len -= header_len + BATADV_DHCP_OPTIONS_OFFSET + 1; - - /* Access the dhcp option lists. Each entry is made up by: - * - octet 1: option type - * - octet 2: option data len (only if type != 255 and 0) - * - octet 3: option data - */ - while (*p != 255 && !ret) { - /* p now points to the first octet: option type */ - if (*p == 53) { - /* type 53 is the message type option. - * Jump the len octet and go to the data octet - */ - if (pkt_len < 2) - goto out; - p += 2; - - /* check if the message type is what we need */ - if (*p == BATADV_DHCP_REQUEST) - ret = true; - break; - } else if (*p == 0) { - /* option type 0 (padding), just go forward */ - if (pkt_len < 1) - goto out; - pkt_len--; - p++; - } else { - /* This is any other option. So we get the length... */ - if (pkt_len < 1) - goto out; - pkt_len--; - p++; - - /* ...and then we jump over the data */ - if (pkt_len < 1 + (*p)) - goto out; - pkt_len -= 1 + (*p); - p += 1 + (*p); - } - } -out: - return ret; -} - -/* this call might reallocate skb data */ -bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) +/** + * batadv_gw_dhcp_recipient_get - check if a packet is a DHCP message + * @skb: the packet to check + * @header_len: a pointer to the batman-adv header size + * @chaddr: buffer where the client address will be stored. Valid + * only if the function returns BATADV_DHCP_TO_CLIENT + * + * Returns: + * - BATADV_DHCP_NO if the packet is not a dhcp message or if there was an error + * while parsing it + * - BATADV_DHCP_TO_SERVER if this is a message going to the DHCP server + * - BATADV_DHCP_TO_CLIENT if this is a message going to a DHCP client + * + * This function may re-allocate the data buffer of the skb passed as argument. + */ +enum batadv_dhcp_recipient +batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, + uint8_t *chaddr) { + enum batadv_dhcp_recipient ret = BATADV_DHCP_NO; struct ethhdr *ethhdr; struct iphdr *iphdr; struct ipv6hdr *ipv6hdr; struct udphdr *udphdr; struct vlan_ethhdr *vhdr; + int chaddr_offset; __be16 proto; + uint8_t *p; /* check for ethernet header */ if (!pskb_may_pull(skb, *header_len + ETH_HLEN)) - return false; + return BATADV_DHCP_NO; + ethhdr = (struct ethhdr *)skb->data; proto = ethhdr->h_proto; *header_len += ETH_HLEN; @@ -663,7 +687,7 @@ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) /* check for initial vlan header */ if (proto == htons(ETH_P_8021Q)) { if (!pskb_may_pull(skb, *header_len + VLAN_HLEN)) - return false; + return BATADV_DHCP_NO; vhdr = (struct vlan_ethhdr *)skb->data; proto = vhdr->h_vlan_encapsulated_proto; @@ -674,32 +698,34 @@ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) switch (proto) { case htons(ETH_P_IP): if (!pskb_may_pull(skb, *header_len + sizeof(*iphdr))) - return false; + return BATADV_DHCP_NO; + iphdr = (struct iphdr *)(skb->data + *header_len); *header_len += iphdr->ihl * 4; /* check for udp header */ if (iphdr->protocol != IPPROTO_UDP) - return false; + return BATADV_DHCP_NO; break; case htons(ETH_P_IPV6): if (!pskb_may_pull(skb, *header_len + sizeof(*ipv6hdr))) - return false; + return BATADV_DHCP_NO; + ipv6hdr = (struct ipv6hdr *)(skb->data + *header_len); *header_len += sizeof(*ipv6hdr); /* check for udp header */ if (ipv6hdr->nexthdr != IPPROTO_UDP) - return false; + return BATADV_DHCP_NO; break; default: - return false; + return BATADV_DHCP_NO; } if (!pskb_may_pull(skb, *header_len + sizeof(*udphdr))) - return false; + return BATADV_DHCP_NO; /* skb->data might have been reallocated by pskb_may_pull() */ ethhdr = (struct ethhdr *)skb->data; @@ -710,17 +736,40 @@ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) *header_len += sizeof(*udphdr); /* check for bootp port */ - if ((proto == htons(ETH_P_IP)) && - (udphdr->dest != htons(67))) - return false; + switch (proto) { + case htons(ETH_P_IP): + if (udphdr->dest == htons(67)) + ret = BATADV_DHCP_TO_SERVER; + else if (udphdr->source == htons(67)) + ret = BATADV_DHCP_TO_CLIENT; + break; + case htons(ETH_P_IPV6): + if (udphdr->dest == htons(547)) + ret = BATADV_DHCP_TO_SERVER; + else if (udphdr->source == htons(547)) + ret = BATADV_DHCP_TO_CLIENT; + break; + } - if ((proto == htons(ETH_P_IPV6)) && - (udphdr->dest != htons(547))) - return false; + chaddr_offset = *header_len + BATADV_DHCP_CHADDR_OFFSET; + /* store the client address if the message is going to a client */ + if (ret == BATADV_DHCP_TO_CLIENT && + pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) { + /* check if the DHCP packet carries an Ethernet DHCP */ + p = skb->data + *header_len + BATADV_DHCP_HTYPE_OFFSET; + if (*p != BATADV_DHCP_HTYPE_ETHERNET) + return BATADV_DHCP_NO; + + /* check if the DHCP packet carries a valid Ethernet address */ + p = skb->data + *header_len + BATADV_DHCP_HLEN_OFFSET; + if (*p != ETH_ALEN) + return BATADV_DHCP_NO; + + memcpy(chaddr, skb->data + chaddr_offset, ETH_ALEN); + } - return true; + return ret; } - /** * batadv_gw_out_of_range - check if the dhcp request destination is the best gw * @bat_priv: the bat priv with all the soft interface information @@ -734,6 +783,7 @@ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) * false otherwise. * * This call might reallocate skb data. + * Must be invoked only when the DHCP packet is going TO a DHCP SERVER. */ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct sk_buff *skb) @@ -741,19 +791,14 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct batadv_neigh_node *neigh_curr = NULL, *neigh_old = NULL; struct batadv_orig_node *orig_dst_node = NULL; struct batadv_gw_node *gw_node = NULL, *curr_gw = NULL; - struct ethhdr *ethhdr; - bool ret, out_of_range = false; - unsigned int header_len = 0; + struct batadv_neigh_ifinfo *curr_ifinfo, *old_ifinfo; + struct ethhdr *ethhdr = (struct ethhdr *)skb->data; + bool out_of_range = false; uint8_t curr_tq_avg; unsigned short vid; vid = batadv_get_vid(skb, 0); - ret = batadv_gw_is_dhcp_target(skb, &header_len); - if (!ret) - goto out; - - ethhdr = (struct ethhdr *)skb->data; orig_dst_node = batadv_transtable_search(bat_priv, ethhdr->h_source, ethhdr->h_dest, vid); if (!orig_dst_node) @@ -763,10 +808,6 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, if (!gw_node->bandwidth_down == 0) goto out; - ret = batadv_is_type_dhcprequest(skb, header_len); - if (!ret) - goto out; - switch (atomic_read(&bat_priv->gw_mode)) { case BATADV_GW_MODE_SERVER: /* If we are a GW then we are our best GW. We can artificially @@ -792,7 +833,14 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, if (!neigh_curr) goto out; - curr_tq_avg = neigh_curr->bat_iv.tq_avg; + curr_ifinfo = batadv_neigh_ifinfo_get(neigh_curr, + BATADV_IF_DEFAULT); + if (!curr_ifinfo) + goto out; + + curr_tq_avg = curr_ifinfo->bat_iv.tq_avg; + batadv_neigh_ifinfo_free_ref(curr_ifinfo); + break; case BATADV_GW_MODE_OFF: default: @@ -803,8 +851,13 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, if (!neigh_old) goto out; - if (curr_tq_avg - neigh_old->bat_iv.tq_avg > BATADV_GW_THRESHOLD) + old_ifinfo = batadv_neigh_ifinfo_get(neigh_old, BATADV_IF_DEFAULT); + if (!old_ifinfo) + goto out; + + if ((curr_tq_avg - old_ifinfo->bat_iv.tq_avg) > BATADV_GW_THRESHOLD) out_of_range = true; + batadv_neigh_ifinfo_free_ref(old_ifinfo); out: if (orig_dst_node) diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index d95c2d23195e..7ee53bb7d50f 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,16 +12,14 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ #define _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ void batadv_gw_check_client_stop(struct batadv_priv *bat_priv); -void batadv_gw_deselect(struct batadv_priv *bat_priv); +void batadv_gw_reselect(struct batadv_priv *bat_priv); void batadv_gw_election(struct batadv_priv *bat_priv); struct batadv_orig_node * batadv_gw_get_selected_orig(struct batadv_priv *bat_priv); @@ -34,7 +32,9 @@ void batadv_gw_node_delete(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node); void batadv_gw_node_purge(struct batadv_priv *bat_priv); int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset); -bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len); bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct sk_buff *skb); +enum batadv_dhcp_recipient +batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, + uint8_t *chaddr); #endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */ diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index b211b0f9cb78..6f5e621f220a 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -164,7 +162,7 @@ ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff, if ((down_curr == down_new) && (up_curr == up_new)) return count; - batadv_gw_deselect(bat_priv); + batadv_gw_reselect(bat_priv); batadv_info(net_dev, "Changing gateway bandwidth from: '%u.%u/%u.%u MBit' to: '%u.%u/%u.%u MBit'\n", down_curr / 10, down_curr % 10, up_curr / 10, up_curr % 10, diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index 56384a4cd18c..aa5116561947 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_GATEWAY_COMMON_H_ diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 57c2a19dcb5c..b851cc580853 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -25,6 +23,7 @@ #include "translation-table.h" #include "routing.h" #include "sysfs.h" +#include "debugfs.h" #include "originator.h" #include "hash.h" #include "bridge_loop_avoidance.h" @@ -88,15 +87,13 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) return false; /* recurse over the parent device */ - parent_dev = dev_get_by_index(&init_net, net_dev->iflink); + parent_dev = __dev_get_by_index(&init_net, net_dev->iflink); /* if we got a NULL parent_dev there is something broken.. */ if (WARN(!parent_dev, "Cannot find parent device")) return false; ret = batadv_is_on_batman_iface(parent_dev); - if (parent_dev) - dev_put(parent_dev); return ret; } @@ -244,7 +241,7 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); const struct batadv_hard_iface *hard_iface; - int min_mtu = ETH_DATA_LEN; + int min_mtu = INT_MAX; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { @@ -259,8 +256,6 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) } rcu_read_unlock(); - atomic_set(&bat_priv->packet_size_max, min_mtu); - if (atomic_read(&bat_priv->fragmentation) == 0) goto out; @@ -271,13 +266,21 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) min_mtu = min_t(int, min_mtu, BATADV_FRAG_MAX_FRAG_SIZE); min_mtu -= sizeof(struct batadv_frag_packet); min_mtu *= BATADV_FRAG_MAX_FRAGMENTS; - atomic_set(&bat_priv->packet_size_max, min_mtu); - - /* with fragmentation enabled we can fragment external packets easily */ - min_mtu = min_t(int, min_mtu, ETH_DATA_LEN); out: - return min_mtu - batadv_max_header_len(); + /* report to the other components the maximum amount of bytes that + * batman-adv can send over the wire (without considering the payload + * overhead). For example, this value is used by TT to compute the + * maximum local table table size + */ + atomic_set(&bat_priv->packet_size_max, min_mtu); + + /* the real soft-interface MTU is computed by removing the payload + * overhead from the maximum amount of bytes that was just computed. + * + * However batman-adv does not support MTUs bigger than ETH_DATA_LEN + */ + return min_t(int, min_mtu - batadv_max_header_len(), ETH_DATA_LEN); } /* adjusts the MTU if a new interface with a smaller MTU appeared. */ @@ -541,6 +544,7 @@ static void batadv_hardif_remove_interface_finish(struct work_struct *work) hard_iface = container_of(work, struct batadv_hard_iface, cleanup_work); + batadv_debugfs_del_hardif(hard_iface); batadv_sysfs_del_hardif(&hard_iface->hardif_obj); batadv_hardif_free_ref(hard_iface); } @@ -571,6 +575,11 @@ batadv_hardif_add_interface(struct net_device *net_dev) hard_iface->net_dev = net_dev; hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; + + ret = batadv_debugfs_add_hardif(hard_iface); + if (ret) + goto free_sysfs; + INIT_LIST_HEAD(&hard_iface->list); INIT_WORK(&hard_iface->cleanup_work, batadv_hardif_remove_interface_finish); @@ -587,6 +596,8 @@ batadv_hardif_add_interface(struct net_device *net_dev) return hard_iface; +free_sysfs: + batadv_sysfs_del_hardif(&hard_iface->hardif_obj); free_if: kfree(hard_iface); release_dev: diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index df4c8bd45c40..1918cd50b62e 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_HARD_INTERFACE_H_ @@ -42,6 +40,7 @@ enum batadv_hard_if_cleanup { extern struct notifier_block batadv_hard_if_notifier; bool batadv_is_wifi_netdev(struct net_device *net_device); +bool batadv_is_wifi_iface(int ifindex); struct batadv_hard_iface* batadv_hardif_get_by_netdev(const struct net_device *net_dev); int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, @@ -53,6 +52,11 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface); void batadv_update_min_mtu(struct net_device *soft_iface); void batadv_hardif_free_rcu(struct rcu_head *rcu); +/** + * batadv_hardif_free_ref - decrement the hard interface refcounter and + * possibly free it + * @hard_iface: the hard interface to free + */ static inline void batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface) { @@ -60,6 +64,18 @@ batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface) call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu); } +/** + * batadv_hardif_free_ref_now - decrement the hard interface refcounter and + * possibly free it (without rcu callback) + * @hard_iface: the hard interface to free + */ +static inline void +batadv_hardif_free_ref_now(struct batadv_hard_iface *hard_iface) +{ + if (atomic_dec_and_test(&hard_iface->refcount)) + batadv_hardif_free_rcu(&hard_iface->rcu); +} + static inline struct batadv_hard_iface * batadv_primary_if_get_selected(struct batadv_priv *bat_priv) { diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 7198dafd3bf3..63bdf7e94f1e 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 1b4da72f2093..539fc1266793 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_HASH_H_ diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 130cc3217e2b..abb9d6e0388b 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -217,7 +215,8 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, if (!orig_node) goto dst_unreach; - neigh_node = batadv_orig_node_get_router(orig_node); + neigh_node = batadv_orig_router_get(orig_node, + BATADV_IF_DEFAULT); if (!neigh_node) goto dst_unreach; diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 6665080dff79..0c33950aa4aa 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_ICMP_SOCKET_H_ diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index faba0f61ad53..66ae135b9f27 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/crc32c.h> @@ -421,13 +419,23 @@ static void batadv_recv_handler_init(void) for (i = BATADV_UNICAST_MIN; i <= BATADV_UNICAST_MAX; i++) batadv_rx_handler[i] = batadv_recv_unhandled_unicast_packet; - /* compile time checks for struct member offsets */ - BUILD_BUG_ON(offsetof(struct batadv_unicast_4addr_packet, src) != 10); - BUILD_BUG_ON(offsetof(struct batadv_unicast_packet, dest) != 4); - BUILD_BUG_ON(offsetof(struct batadv_unicast_tvlv_packet, dst) != 4); - BUILD_BUG_ON(offsetof(struct batadv_frag_packet, dest) != 4); - BUILD_BUG_ON(offsetof(struct batadv_icmp_packet, dst) != 4); - BUILD_BUG_ON(offsetof(struct batadv_icmp_packet_rr, dst) != 4); + /* compile time checks for sizes */ + BUILD_BUG_ON(sizeof(struct batadv_bla_claim_dst) != 6); + BUILD_BUG_ON(sizeof(struct batadv_ogm_packet) != 24); + BUILD_BUG_ON(sizeof(struct batadv_icmp_header) != 20); + BUILD_BUG_ON(sizeof(struct batadv_icmp_packet) != 20); + BUILD_BUG_ON(sizeof(struct batadv_icmp_packet_rr) != 116); + BUILD_BUG_ON(sizeof(struct batadv_unicast_packet) != 10); + BUILD_BUG_ON(sizeof(struct batadv_unicast_4addr_packet) != 18); + BUILD_BUG_ON(sizeof(struct batadv_frag_packet) != 20); + BUILD_BUG_ON(sizeof(struct batadv_bcast_packet) != 14); + BUILD_BUG_ON(sizeof(struct batadv_coded_packet) != 46); + BUILD_BUG_ON(sizeof(struct batadv_unicast_tvlv_packet) != 20); + BUILD_BUG_ON(sizeof(struct batadv_tvlv_hdr) != 4); + BUILD_BUG_ON(sizeof(struct batadv_tvlv_gateway_data) != 8); + BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_vlan_data) != 8); + BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_change) != 12); + BUILD_BUG_ON(sizeof(struct batadv_tvlv_roam_adv) != 8); /* broadcast packet */ batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet; @@ -1173,6 +1181,32 @@ unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len) return vid; } +/** + * batadv_vlan_ap_isola_get - return the AP isolation status for the given vlan + * @bat_priv: the bat priv with all the soft interface information + * @vid: the VLAN identifier for which the AP isolation attributed as to be + * looked up + * + * Returns true if AP isolation is on for the VLAN idenfied by vid, false + * otherwise + */ +bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid) +{ + bool ap_isolation_enabled = false; + struct batadv_softif_vlan *vlan; + + /* if the AP isolation is requested on a VLAN, then check for its + * setting in the proper VLAN private data structure + */ + vlan = batadv_softif_vlan_get(bat_priv, vid); + if (vlan) { + ap_isolation_enabled = atomic_read(&vlan->ap_isolation); + batadv_softif_vlan_free_ref(vlan); + } + + return ap_isolation_enabled; +} + static int batadv_param_set_ra(const char *val, const struct kernel_param *kp) { struct batadv_algo_ops *bat_algo_ops; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index f94f287b8670..9374f1a51348 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_MAIN_H_ @@ -26,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2013.5.0" +#define BATADV_SOURCE_VERSION "2014.1.0" #endif /* B.A.T.M.A.N. parameters */ @@ -72,6 +70,14 @@ #define BATADV_NULL_IFINDEX 0 /* dummy ifindex used to avoid iface checks */ +#define BATADV_NO_MARK 0 + +/* default interface for multi interface operation. The default interface is + * used for communication which originated locally (i.e. is not forwarded) + * or where special forwarding is not desired/necessary. + */ +#define BATADV_IF_DEFAULT ((struct batadv_hard_iface *)NULL) + #define BATADV_NUM_WORDS BITS_TO_LONGS(BATADV_TQ_LOCAL_WINDOW_SIZE) #define BATADV_LOG_BUF_LEN 8192 /* has to be a power of 2 */ @@ -266,7 +272,7 @@ static inline void batadv_dbg(int type __always_unused, */ static inline int batadv_compare_eth(const void *data1, const void *data2) { - return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); + return ether_addr_equal_unaligned(data1, data2); } /** @@ -369,5 +375,6 @@ void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, uint8_t *src, uint8_t *dst, uint8_t type, uint8_t version, void *tvlv_value, uint16_t tvlv_value_len); unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len); +bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid); #endif /* _NET_BATMAN_ADV_MAIN_H_ */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 511d7e1eea38..f1b604d88dc3 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/debugfs.h> @@ -720,9 +718,21 @@ static bool batadv_can_nc_with_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_ogm_packet *ogm_packet) { - if (orig_node->last_real_seqno != ntohl(ogm_packet->seqno)) + struct batadv_orig_ifinfo *orig_ifinfo; + uint32_t last_real_seqno; + uint8_t last_ttl; + + orig_ifinfo = batadv_orig_ifinfo_get(orig_node, BATADV_IF_DEFAULT); + if (!orig_ifinfo) return false; - if (orig_node->last_ttl != ogm_packet->ttl + 1) + + last_ttl = orig_ifinfo->last_ttl; + last_real_seqno = orig_ifinfo->last_real_seqno; + batadv_orig_ifinfo_free_ref(orig_ifinfo); + + if (last_real_seqno != ntohl(ogm_packet->seqno)) + return false; + if (last_ttl != ogm_packet->ttl + 1) return false; if (!batadv_compare_eth(ogm_packet->orig, ogm_packet->prev_sender)) return false; @@ -1010,6 +1020,8 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, struct batadv_coded_packet *coded_packet; struct batadv_neigh_node *neigh_tmp, *router_neigh; struct batadv_neigh_node *router_coding = NULL; + struct batadv_neigh_ifinfo *router_neigh_ifinfo = NULL; + struct batadv_neigh_ifinfo *router_coding_ifinfo = NULL; uint8_t *first_source, *first_dest, *second_source, *second_dest; __be32 packet_id1, packet_id2; size_t count; @@ -1019,19 +1031,34 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, int coded_size = sizeof(*coded_packet); int header_add = coded_size - unicast_size; - router_neigh = batadv_orig_node_get_router(neigh_node->orig_node); + /* TODO: do we need to consider the outgoing interface for + * coded packets? + */ + router_neigh = batadv_orig_router_get(neigh_node->orig_node, + BATADV_IF_DEFAULT); if (!router_neigh) goto out; + router_neigh_ifinfo = batadv_neigh_ifinfo_get(router_neigh, + BATADV_IF_DEFAULT); + if (!router_neigh_ifinfo) + goto out; + neigh_tmp = nc_packet->neigh_node; - router_coding = batadv_orig_node_get_router(neigh_tmp->orig_node); + router_coding = batadv_orig_router_get(neigh_tmp->orig_node, + BATADV_IF_DEFAULT); if (!router_coding) goto out; - tq_tmp = batadv_nc_random_weight_tq(router_neigh->bat_iv.tq_avg); - tq_weighted_neigh = tq_tmp; - tq_tmp = batadv_nc_random_weight_tq(router_coding->bat_iv.tq_avg); - tq_weighted_coding = tq_tmp; + router_coding_ifinfo = batadv_neigh_ifinfo_get(router_coding, + BATADV_IF_DEFAULT); + if (!router_coding_ifinfo) + goto out; + + tq_tmp = router_neigh_ifinfo->bat_iv.tq_avg; + tq_weighted_neigh = batadv_nc_random_weight_tq(tq_tmp); + tq_tmp = router_coding_ifinfo->bat_iv.tq_avg; + tq_weighted_coding = batadv_nc_random_weight_tq(tq_tmp); /* Select one destination for the MAC-header dst-field based on * weighted TQ-values. @@ -1155,6 +1182,10 @@ out: batadv_neigh_node_free_ref(router_neigh); if (router_coding) batadv_neigh_node_free_ref(router_coding); + if (router_neigh_ifinfo) + batadv_neigh_ifinfo_free_ref(router_neigh_ifinfo); + if (router_coding_ifinfo) + batadv_neigh_ifinfo_free_ref(router_coding_ifinfo); return res; } diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index d4fd315b5261..358c0d686ab0 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2012-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_NETWORK_CODING_H_ @@ -64,7 +62,6 @@ static inline int batadv_nc_mesh_init(struct batadv_priv *bat_priv) static inline void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { - return; } static inline void @@ -74,7 +71,6 @@ batadv_nc_update_nc_node(struct batadv_priv *bat_priv, struct batadv_ogm_packet *ogm_packet, int is_single_hop_neigh) { - return; } static inline void @@ -83,17 +79,14 @@ batadv_nc_purge_orig(struct batadv_priv *bat_priv, bool (*to_purge)(struct batadv_priv *, struct batadv_nc_node *)) { - return; } static inline void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv) { - return; } static inline void batadv_nc_init_orig(struct batadv_orig_node *orig_node) { - return; } static inline bool batadv_nc_skb_forward(struct sk_buff *skb, @@ -106,14 +99,12 @@ static inline void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv, struct sk_buff *skb) { - return; } static inline void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv, struct sk_buff *skb) { - return; } static inline int batadv_nc_nodes_seq_print_text(struct seq_file *seq, diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 8ab14340d10f..853941629dc1 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -41,7 +39,7 @@ int batadv_compare_orig(const struct hlist_node *node, const void *data2) const void *data1 = container_of(node, struct batadv_orig_node, hash_entry); - return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); + return batadv_compare_eth(data1, data2); } /** @@ -150,20 +148,114 @@ err: return -ENOMEM; } +/** + * batadv_neigh_ifinfo_free_rcu - free the neigh_ifinfo object + * @rcu: rcu pointer of the neigh_ifinfo object + */ +static void batadv_neigh_ifinfo_free_rcu(struct rcu_head *rcu) +{ + struct batadv_neigh_ifinfo *neigh_ifinfo; + + neigh_ifinfo = container_of(rcu, struct batadv_neigh_ifinfo, rcu); + + if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) + batadv_hardif_free_ref_now(neigh_ifinfo->if_outgoing); + + kfree(neigh_ifinfo); +} + +/** + * batadv_neigh_ifinfo_free_now - decrement the refcounter and possibly free + * the neigh_ifinfo (without rcu callback) + * @neigh_ifinfo: the neigh_ifinfo object to release + */ +static void +batadv_neigh_ifinfo_free_ref_now(struct batadv_neigh_ifinfo *neigh_ifinfo) +{ + if (atomic_dec_and_test(&neigh_ifinfo->refcount)) + batadv_neigh_ifinfo_free_rcu(&neigh_ifinfo->rcu); +} + +/** + * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly free + * the neigh_ifinfo + * @neigh_ifinfo: the neigh_ifinfo object to release + */ +void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo) +{ + if (atomic_dec_and_test(&neigh_ifinfo->refcount)) + call_rcu(&neigh_ifinfo->rcu, batadv_neigh_ifinfo_free_rcu); +} + +/** + * batadv_neigh_node_free_rcu - free the neigh_node + * @rcu: rcu pointer of the neigh_node + */ +static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) +{ + struct hlist_node *node_tmp; + struct batadv_neigh_node *neigh_node; + struct batadv_neigh_ifinfo *neigh_ifinfo; + + neigh_node = container_of(rcu, struct batadv_neigh_node, rcu); + + hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, + &neigh_node->ifinfo_list, list) { + batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo); + } + batadv_hardif_free_ref_now(neigh_node->if_incoming); + + kfree(neigh_node); +} + +/** + * batadv_neigh_node_free_ref_now - decrement the neighbors refcounter + * and possibly free it (without rcu callback) + * @neigh_node: neigh neighbor to free + */ +static void +batadv_neigh_node_free_ref_now(struct batadv_neigh_node *neigh_node) +{ + if (atomic_dec_and_test(&neigh_node->refcount)) + batadv_neigh_node_free_rcu(&neigh_node->rcu); +} + +/** + * batadv_neigh_node_free_ref - decrement the neighbors refcounter + * and possibly free it + * @neigh_node: neigh neighbor to free + */ void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node) { if (atomic_dec_and_test(&neigh_node->refcount)) - kfree_rcu(neigh_node, rcu); + call_rcu(&neigh_node->rcu, batadv_neigh_node_free_rcu); } -/* increases the refcounter of a found router */ +/** + * batadv_orig_node_get_router - router to the originator depending on iface + * @orig_node: the orig node for the router + * @if_outgoing: the interface where the payload packet has been received or + * the OGM should be sent to + * + * Returns the neighbor which should be router for this orig_node/iface. + * + * The object is returned with refcounter increased by 1. + */ struct batadv_neigh_node * -batadv_orig_node_get_router(struct batadv_orig_node *orig_node) +batadv_orig_router_get(struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *if_outgoing) { - struct batadv_neigh_node *router; + struct batadv_orig_ifinfo *orig_ifinfo; + struct batadv_neigh_node *router = NULL; rcu_read_lock(); - router = rcu_dereference(orig_node->router); + hlist_for_each_entry_rcu(orig_ifinfo, &orig_node->ifinfo_list, list) { + if (orig_ifinfo->if_outgoing != if_outgoing) + continue; + + router = rcu_dereference(orig_ifinfo->router); + break; + } if (router && !atomic_inc_not_zero(&router->refcount)) router = NULL; @@ -173,6 +265,164 @@ batadv_orig_node_get_router(struct batadv_orig_node *orig_node) } /** + * batadv_orig_ifinfo_get - find the ifinfo from an orig_node + * @orig_node: the orig node to be queried + * @if_outgoing: the interface for which the ifinfo should be acquired + * + * Returns the requested orig_ifinfo or NULL if not found. + * + * The object is returned with refcounter increased by 1. + */ +struct batadv_orig_ifinfo * +batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_orig_ifinfo *tmp, *orig_ifinfo = NULL; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp, &orig_node->ifinfo_list, + list) { + if (tmp->if_outgoing != if_outgoing) + continue; + + if (!atomic_inc_not_zero(&tmp->refcount)) + continue; + + orig_ifinfo = tmp; + break; + } + rcu_read_unlock(); + + return orig_ifinfo; +} + +/** + * batadv_orig_ifinfo_new - search and possibly create an orig_ifinfo object + * @orig_node: the orig node to be queried + * @if_outgoing: the interface for which the ifinfo should be acquired + * + * Returns NULL in case of failure or the orig_ifinfo object for the if_outgoing + * interface otherwise. The object is created and added to the list + * if it does not exist. + * + * The object is returned with refcounter increased by 1. + */ +struct batadv_orig_ifinfo * +batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_orig_ifinfo *orig_ifinfo = NULL; + unsigned long reset_time; + + spin_lock_bh(&orig_node->neigh_list_lock); + + orig_ifinfo = batadv_orig_ifinfo_get(orig_node, if_outgoing); + if (orig_ifinfo) + goto out; + + orig_ifinfo = kzalloc(sizeof(*orig_ifinfo), GFP_ATOMIC); + if (!orig_ifinfo) + goto out; + + if (if_outgoing != BATADV_IF_DEFAULT && + !atomic_inc_not_zero(&if_outgoing->refcount)) { + kfree(orig_ifinfo); + orig_ifinfo = NULL; + goto out; + } + + reset_time = jiffies - 1; + reset_time -= msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); + orig_ifinfo->batman_seqno_reset = reset_time; + orig_ifinfo->if_outgoing = if_outgoing; + INIT_HLIST_NODE(&orig_ifinfo->list); + atomic_set(&orig_ifinfo->refcount, 2); + hlist_add_head_rcu(&orig_ifinfo->list, + &orig_node->ifinfo_list); +out: + spin_unlock_bh(&orig_node->neigh_list_lock); + return orig_ifinfo; +} + +/** + * batadv_neigh_ifinfo_get - find the ifinfo from an neigh_node + * @neigh_node: the neigh node to be queried + * @if_outgoing: the interface for which the ifinfo should be acquired + * + * The object is returned with refcounter increased by 1. + * + * Returns the requested neigh_ifinfo or NULL if not found + */ +struct batadv_neigh_ifinfo * +batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_neigh_ifinfo *neigh_ifinfo = NULL, + *tmp_neigh_ifinfo; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_neigh_ifinfo, &neigh->ifinfo_list, + list) { + if (tmp_neigh_ifinfo->if_outgoing != if_outgoing) + continue; + + if (!atomic_inc_not_zero(&tmp_neigh_ifinfo->refcount)) + continue; + + neigh_ifinfo = tmp_neigh_ifinfo; + break; + } + rcu_read_unlock(); + + return neigh_ifinfo; +} + +/** + * batadv_neigh_ifinfo_new - search and possibly create an neigh_ifinfo object + * @neigh_node: the neigh node to be queried + * @if_outgoing: the interface for which the ifinfo should be acquired + * + * Returns NULL in case of failure or the neigh_ifinfo object for the + * if_outgoing interface otherwise. The object is created and added to the list + * if it does not exist. + * + * The object is returned with refcounter increased by 1. + */ +struct batadv_neigh_ifinfo * +batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_neigh_ifinfo *neigh_ifinfo; + + spin_lock_bh(&neigh->ifinfo_lock); + + neigh_ifinfo = batadv_neigh_ifinfo_get(neigh, if_outgoing); + if (neigh_ifinfo) + goto out; + + neigh_ifinfo = kzalloc(sizeof(*neigh_ifinfo), GFP_ATOMIC); + if (!neigh_ifinfo) + goto out; + + if (if_outgoing && !atomic_inc_not_zero(&if_outgoing->refcount)) { + kfree(neigh_ifinfo); + neigh_ifinfo = NULL; + goto out; + } + + INIT_HLIST_NODE(&neigh_ifinfo->list); + atomic_set(&neigh_ifinfo->refcount, 2); + neigh_ifinfo->if_outgoing = if_outgoing; + + hlist_add_head_rcu(&neigh_ifinfo->list, &neigh->ifinfo_list); + +out: + spin_unlock_bh(&neigh->ifinfo_lock); + + return neigh_ifinfo; +} + +/** * batadv_neigh_node_new - create and init a new neigh_node object * @hard_iface: the interface where the neighbour is connected to * @neigh_addr: the mac address of the neighbour interface @@ -193,13 +443,13 @@ batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, goto out; INIT_HLIST_NODE(&neigh_node->list); + INIT_HLIST_HEAD(&neigh_node->ifinfo_list); + spin_lock_init(&neigh_node->ifinfo_lock); memcpy(neigh_node->addr, neigh_addr, ETH_ALEN); neigh_node->if_incoming = hard_iface; neigh_node->orig_node = orig_node; - INIT_LIST_HEAD(&neigh_node->bonding_list); - /* extra reference for return */ atomic_set(&neigh_node->refcount, 2); @@ -207,30 +457,104 @@ out: return neigh_node; } +/** + * batadv_neigh_node_get - retrieve a neighbour from the list + * @orig_node: originator which the neighbour belongs to + * @hard_iface: the interface where this neighbour is connected to + * @addr: the address of the neighbour + * + * Looks for and possibly returns a neighbour belonging to this originator list + * which is connected through the provided hard interface. + * Returns NULL if the neighbour is not found. + */ +struct batadv_neigh_node * +batadv_neigh_node_get(const struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *hard_iface, + const uint8_t *addr) +{ + struct batadv_neigh_node *tmp_neigh_node, *res = NULL; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { + if (!batadv_compare_eth(tmp_neigh_node->addr, addr)) + continue; + + if (tmp_neigh_node->if_incoming != hard_iface) + continue; + + if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) + continue; + + res = tmp_neigh_node; + break; + } + rcu_read_unlock(); + + return res; +} + +/** + * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object + * @rcu: rcu pointer of the orig_ifinfo object + */ +static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu) +{ + struct batadv_orig_ifinfo *orig_ifinfo; + + orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu); + + if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT) + batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing); + + kfree(orig_ifinfo); +} + +/** + * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free + * the orig_ifinfo (without rcu callback) + * @orig_ifinfo: the orig_ifinfo object to release + */ +static void +batadv_orig_ifinfo_free_ref_now(struct batadv_orig_ifinfo *orig_ifinfo) +{ + if (atomic_dec_and_test(&orig_ifinfo->refcount)) + batadv_orig_ifinfo_free_rcu(&orig_ifinfo->rcu); +} + +/** + * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free + * the orig_ifinfo + * @orig_ifinfo: the orig_ifinfo object to release + */ +void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo) +{ + if (atomic_dec_and_test(&orig_ifinfo->refcount)) + call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu); +} + static void batadv_orig_node_free_rcu(struct rcu_head *rcu) { struct hlist_node *node_tmp; - struct batadv_neigh_node *neigh_node, *tmp_neigh_node; + struct batadv_neigh_node *neigh_node; struct batadv_orig_node *orig_node; + struct batadv_orig_ifinfo *orig_ifinfo; orig_node = container_of(rcu, struct batadv_orig_node, rcu); spin_lock_bh(&orig_node->neigh_list_lock); - /* for all bonding members ... */ - list_for_each_entry_safe(neigh_node, tmp_neigh_node, - &orig_node->bond_list, bonding_list) { - list_del_rcu(&neigh_node->bonding_list); - batadv_neigh_node_free_ref(neigh_node); - } - /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { hlist_del_rcu(&neigh_node->list); - batadv_neigh_node_free_ref(neigh_node); + batadv_neigh_node_free_ref_now(neigh_node); } + hlist_for_each_entry_safe(orig_ifinfo, node_tmp, + &orig_node->ifinfo_list, list) { + hlist_del_rcu(&orig_ifinfo->list); + batadv_orig_ifinfo_free_ref_now(orig_ifinfo); + } spin_unlock_bh(&orig_node->neigh_list_lock); /* Free nc_nodes */ @@ -327,8 +651,8 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, return NULL; INIT_HLIST_HEAD(&orig_node->neigh_list); - INIT_LIST_HEAD(&orig_node->bond_list); INIT_LIST_HEAD(&orig_node->vlan_list); + INIT_HLIST_HEAD(&orig_node->ifinfo_list); spin_lock_init(&orig_node->bcast_seqno_lock); spin_lock_init(&orig_node->neigh_list_lock); spin_lock_init(&orig_node->tt_buff_lock); @@ -344,15 +668,11 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, orig_node->bat_priv = bat_priv; memcpy(orig_node->orig, addr, ETH_ALEN); batadv_dat_init_orig_node_addr(orig_node); - orig_node->router = NULL; atomic_set(&orig_node->last_ttvn, 0); orig_node->tt_buff = NULL; orig_node->tt_buff_len = 0; reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); orig_node->bcast_seqno_reset = reset_time; - orig_node->batman_seqno_reset = reset_time; - - atomic_set(&orig_node->bond_candidates, 0); /* create a vlan object for the "untagged" LAN */ vlan = batadv_orig_node_vlan_new(orig_node, BATADV_NO_FLAGS); @@ -376,20 +696,76 @@ free_orig_node: return NULL; } +/** + * batadv_purge_orig_ifinfo - purge obsolete ifinfo entries from originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be checked + * + * Returns true if any ifinfo entry was purged, false otherwise. + */ +static bool +batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node) +{ + struct batadv_orig_ifinfo *orig_ifinfo; + struct batadv_hard_iface *if_outgoing; + struct hlist_node *node_tmp; + bool ifinfo_purged = false; + + spin_lock_bh(&orig_node->neigh_list_lock); + + /* for all ifinfo objects for this originator */ + hlist_for_each_entry_safe(orig_ifinfo, node_tmp, + &orig_node->ifinfo_list, list) { + if_outgoing = orig_ifinfo->if_outgoing; + + /* always keep the default interface */ + if (if_outgoing == BATADV_IF_DEFAULT) + continue; + + /* don't purge if the interface is not (going) down */ + if ((if_outgoing->if_status != BATADV_IF_INACTIVE) && + (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) && + (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)) + continue; + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "router/ifinfo purge: originator %pM, iface: %s\n", + orig_node->orig, if_outgoing->net_dev->name); + + ifinfo_purged = true; + + hlist_del_rcu(&orig_ifinfo->list); + batadv_orig_ifinfo_free_ref(orig_ifinfo); + if (orig_node->last_bonding_candidate == orig_ifinfo) { + orig_node->last_bonding_candidate = NULL; + batadv_orig_ifinfo_free_ref(orig_ifinfo); + } + } + + spin_unlock_bh(&orig_node->neigh_list_lock); + + return ifinfo_purged; +} + + +/** + * batadv_purge_orig_neighbors - purges neighbors from originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be checked + * + * Returns true if any neighbor was purged, false otherwise + */ static bool batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, - struct batadv_orig_node *orig_node, - struct batadv_neigh_node **best_neigh) + struct batadv_orig_node *orig_node) { - struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; bool neigh_purged = false; unsigned long last_seen; struct batadv_hard_iface *if_incoming; - *best_neigh = NULL; - spin_lock_bh(&orig_node->neigh_list_lock); /* for all neighbors towards this originator ... */ @@ -418,15 +794,7 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, neigh_purged = true; hlist_del_rcu(&neigh_node->list); - batadv_bonding_candidate_del(orig_node, neigh_node); batadv_neigh_node_free_ref(neigh_node); - } else { - /* store the best_neighbour if this is the first - * iteration or if a better neighbor has been found - */ - if (!*best_neigh || - bao->bat_neigh_cmp(neigh_node, *best_neigh) > 0) - *best_neigh = neigh_node; } } @@ -434,10 +802,57 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, return neigh_purged; } +/** + * batadv_find_best_neighbor - finds the best neighbor after purging + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be checked + * @if_outgoing: the interface for which the metric should be compared + * + * Returns the current best neighbor, with refcount increased. + */ +static struct batadv_neigh_node * +batadv_find_best_neighbor(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_neigh_node *best = NULL, *neigh; + struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; + + rcu_read_lock(); + hlist_for_each_entry_rcu(neigh, &orig_node->neigh_list, list) { + if (best && (bao->bat_neigh_cmp(neigh, if_outgoing, + best, if_outgoing) <= 0)) + continue; + + if (!atomic_inc_not_zero(&neigh->refcount)) + continue; + + if (best) + batadv_neigh_node_free_ref(best); + + best = neigh; + } + rcu_read_unlock(); + + return best; +} + +/** + * batadv_purge_orig_node - purges obsolete information from an orig_node + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be checked + * + * This function checks if the orig_node or substructures of it have become + * obsolete, and purges this information if that's the case. + * + * Returns true if the orig_node is to be removed, false otherwise. + */ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct batadv_neigh_node *best_neigh_node; + struct batadv_hard_iface *hard_iface; + bool changed; if (batadv_has_timed_out(orig_node->last_seen, 2 * BATADV_PURGE_TIMEOUT)) { @@ -446,12 +861,39 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, orig_node->orig, jiffies_to_msecs(orig_node->last_seen)); return true; - } else { - if (batadv_purge_orig_neighbors(bat_priv, orig_node, - &best_neigh_node)) - batadv_update_route(bat_priv, orig_node, - best_neigh_node); } + changed = batadv_purge_orig_ifinfo(bat_priv, orig_node); + changed = changed || batadv_purge_orig_neighbors(bat_priv, orig_node); + + if (!changed) + return false; + + /* first for NULL ... */ + best_neigh_node = batadv_find_best_neighbor(bat_priv, orig_node, + BATADV_IF_DEFAULT); + batadv_update_route(bat_priv, orig_node, BATADV_IF_DEFAULT, + best_neigh_node); + if (best_neigh_node) + batadv_neigh_node_free_ref(best_neigh_node); + + /* ... then for all other interfaces. */ + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->if_status != BATADV_IF_ACTIVE) + continue; + + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + best_neigh_node = batadv_find_best_neighbor(bat_priv, + orig_node, + hard_iface); + batadv_update_route(bat_priv, orig_node, hard_iface, + best_neigh_node); + if (best_neigh_node) + batadv_neigh_node_free_ref(best_neigh_node); + } + rcu_read_unlock(); return false; } @@ -534,8 +976,54 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) return 0; } - bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq); + bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, + BATADV_IF_DEFAULT); + + return 0; +} + +/** + * batadv_orig_hardif_seq_print_text - writes originator infos for a specific + * outgoing interface + * @seq: debugfs table seq_file struct + * @offset: not used + * + * Returns 0 + */ +int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset) +{ + struct net_device *net_dev = (struct net_device *)seq->private; + struct batadv_hard_iface *hard_iface; + struct batadv_priv *bat_priv; + + hard_iface = batadv_hardif_get_by_netdev(net_dev); + + if (!hard_iface || !hard_iface->soft_iface) { + seq_puts(seq, "Interface not known to B.A.T.M.A.N.\n"); + goto out; + } + + bat_priv = netdev_priv(hard_iface->soft_iface); + if (!bat_priv->bat_algo_ops->bat_orig_print) { + seq_puts(seq, + "No printing function for this routing protocol\n"); + goto out; + } + + if (hard_iface->if_status != BATADV_IF_ACTIVE) { + seq_puts(seq, "Interface not active\n"); + goto out; + } + + seq_printf(seq, "[B.A.T.M.A.N. adv %s, IF/MAC: %s/%pM (%s %s)]\n", + BATADV_SOURCE_VERSION, hard_iface->net_dev->name, + hard_iface->net_dev->dev_addr, + hard_iface->soft_iface->name, bat_priv->bat_algo_ops->name); + bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, hard_iface); + +out: + batadv_hardif_free_ref(hard_iface); return 0; } diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 6f77d808a916..db3a9ed734cb 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_ORIGINATOR_H_ @@ -31,13 +29,35 @@ void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_neigh_node * +batadv_neigh_node_get(const struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *hard_iface, + const uint8_t *addr); +struct batadv_neigh_node * batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, const uint8_t *neigh_addr, struct batadv_orig_node *orig_node); void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node); struct batadv_neigh_node * -batadv_orig_node_get_router(struct batadv_orig_node *orig_node); +batadv_orig_router_get(struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *if_outgoing); +struct batadv_neigh_ifinfo * +batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, + struct batadv_hard_iface *if_outgoing); +struct batadv_neigh_ifinfo * +batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, + struct batadv_hard_iface *if_outgoing); +void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo); + +struct batadv_orig_ifinfo * +batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing); +struct batadv_orig_ifinfo * +batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *if_outgoing); +void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo); + int batadv_orig_seq_print_text(struct seq_file *seq, void *offset); +int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, int max_if_num); int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 2dd8f2422550..0a381d1174c1 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_PACKET_H_ @@ -117,6 +115,7 @@ enum batadv_tt_client_flags { BATADV_TT_CLIENT_DEL = BIT(0), BATADV_TT_CLIENT_ROAM = BIT(1), BATADV_TT_CLIENT_WIFI = BIT(4), + BATADV_TT_CLIENT_ISOLA = BIT(5), BATADV_TT_CLIENT_NOPURGE = BIT(8), BATADV_TT_CLIENT_NEW = BIT(9), BATADV_TT_CLIENT_PENDING = BIT(10), diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 46278bfb8fdb..a953d5b196a3 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -35,13 +33,32 @@ static int batadv_route_unicast_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); +/** + * _batadv_update_route - set the router for this originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be configured + * @recv_if: the receive interface for which this route is set + * @neigh_node: neighbor which should be the next router + * + * This function does not perform any error checks + */ static void _batadv_update_route(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, + struct batadv_hard_iface *recv_if, struct batadv_neigh_node *neigh_node) { + struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *curr_router; - curr_router = batadv_orig_node_get_router(orig_node); + orig_ifinfo = batadv_orig_ifinfo_get(orig_node, recv_if); + if (!orig_ifinfo) + return; + + rcu_read_lock(); + curr_router = rcu_dereference(orig_ifinfo->router); + if (curr_router && !atomic_inc_not_zero(&curr_router->refcount)) + curr_router = NULL; + rcu_read_unlock(); /* route deleted */ if ((curr_router) && (!neigh_node)) { @@ -71,16 +88,25 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, neigh_node = NULL; spin_lock_bh(&orig_node->neigh_list_lock); - rcu_assign_pointer(orig_node->router, neigh_node); + rcu_assign_pointer(orig_ifinfo->router, neigh_node); spin_unlock_bh(&orig_node->neigh_list_lock); + batadv_orig_ifinfo_free_ref(orig_ifinfo); /* decrease refcount of previous best neighbor */ if (curr_router) batadv_neigh_node_free_ref(curr_router); } +/** + * batadv_update_route - set the router for this originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node which is to be configured + * @recv_if: the receive interface for which this route is set + * @neigh_node: neighbor which should be the next router + */ void batadv_update_route(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, + struct batadv_hard_iface *recv_if, struct batadv_neigh_node *neigh_node) { struct batadv_neigh_node *router = NULL; @@ -88,125 +114,16 @@ void batadv_update_route(struct batadv_priv *bat_priv, if (!orig_node) goto out; - router = batadv_orig_node_get_router(orig_node); + router = batadv_orig_router_get(orig_node, recv_if); if (router != neigh_node) - _batadv_update_route(bat_priv, orig_node, neigh_node); - -out: - if (router) - batadv_neigh_node_free_ref(router); -} - -/* caller must hold the neigh_list_lock */ -void batadv_bonding_candidate_del(struct batadv_orig_node *orig_node, - struct batadv_neigh_node *neigh_node) -{ - /* this neighbor is not part of our candidate list */ - if (list_empty(&neigh_node->bonding_list)) - goto out; - - list_del_rcu(&neigh_node->bonding_list); - INIT_LIST_HEAD(&neigh_node->bonding_list); - batadv_neigh_node_free_ref(neigh_node); - atomic_dec(&orig_node->bond_candidates); - -out: - return; -} - -/** - * batadv_bonding_candidate_add - consider a new link for bonding mode towards - * the given originator - * @bat_priv: the bat priv with all the soft interface information - * @orig_node: the target node - * @neigh_node: the neighbor representing the new link to consider for bonding - * mode - */ -void batadv_bonding_candidate_add(struct batadv_priv *bat_priv, - struct batadv_orig_node *orig_node, - struct batadv_neigh_node *neigh_node) -{ - struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; - struct batadv_neigh_node *tmp_neigh_node, *router = NULL; - uint8_t interference_candidate = 0; - - spin_lock_bh(&orig_node->neigh_list_lock); - - /* only consider if it has the same primary address ... */ - if (!batadv_compare_eth(orig_node->orig, - neigh_node->orig_node->primary_addr)) - goto candidate_del; - - router = batadv_orig_node_get_router(orig_node); - if (!router) - goto candidate_del; - - - /* ... and is good enough to be considered */ - if (bao->bat_neigh_is_equiv_or_better(neigh_node, router)) - goto candidate_del; - - /* check if we have another candidate with the same mac address or - * interface. If we do, we won't select this candidate because of - * possible interference. - */ - hlist_for_each_entry_rcu(tmp_neigh_node, - &orig_node->neigh_list, list) { - if (tmp_neigh_node == neigh_node) - continue; - - /* we only care if the other candidate is even - * considered as candidate. - */ - if (list_empty(&tmp_neigh_node->bonding_list)) - continue; - - if ((neigh_node->if_incoming == tmp_neigh_node->if_incoming) || - (batadv_compare_eth(neigh_node->addr, - tmp_neigh_node->addr))) { - interference_candidate = 1; - break; - } - } - - /* don't care further if it is an interference candidate */ - if (interference_candidate) - goto candidate_del; - - /* this neighbor already is part of our candidate list */ - if (!list_empty(&neigh_node->bonding_list)) - goto out; - - if (!atomic_inc_not_zero(&neigh_node->refcount)) - goto out; - - list_add_rcu(&neigh_node->bonding_list, &orig_node->bond_list); - atomic_inc(&orig_node->bond_candidates); - goto out; - -candidate_del: - batadv_bonding_candidate_del(orig_node, neigh_node); + _batadv_update_route(bat_priv, orig_node, recv_if, neigh_node); out: - spin_unlock_bh(&orig_node->neigh_list_lock); - if (router) batadv_neigh_node_free_ref(router); } -/* copy primary address for bonding */ -void -batadv_bonding_save_primary(const struct batadv_orig_node *orig_node, - struct batadv_orig_node *orig_neigh_node, - const struct batadv_ogm_packet *batman_ogm_packet) -{ - if (!(batman_ogm_packet->flags & BATADV_PRIMARIES_FIRST_HOP)) - return; - - memcpy(orig_neigh_node->primary_addr, orig_node->orig, ETH_ALEN); -} - /* checks whether the host restarted and is in the protection time. * returns: * 0 if the packet is to be accepted @@ -461,114 +378,6 @@ out: return ret; } -/* In the bonding case, send the packets in a round - * robin fashion over the remaining interfaces. - * - * This method rotates the bonding list and increases the - * returned router's refcount. - */ -static struct batadv_neigh_node * -batadv_find_bond_router(struct batadv_orig_node *primary_orig, - const struct batadv_hard_iface *recv_if) -{ - struct batadv_neigh_node *tmp_neigh_node; - struct batadv_neigh_node *router = NULL, *first_candidate = NULL; - - rcu_read_lock(); - list_for_each_entry_rcu(tmp_neigh_node, &primary_orig->bond_list, - bonding_list) { - if (!first_candidate) - first_candidate = tmp_neigh_node; - - /* recv_if == NULL on the first node. */ - if (tmp_neigh_node->if_incoming == recv_if) - continue; - - if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) - continue; - - router = tmp_neigh_node; - break; - } - - /* use the first candidate if nothing was found. */ - if (!router && first_candidate && - atomic_inc_not_zero(&first_candidate->refcount)) - router = first_candidate; - - if (!router) - goto out; - - /* selected should point to the next element - * after the current router - */ - spin_lock_bh(&primary_orig->neigh_list_lock); - /* this is a list_move(), which unfortunately - * does not exist as rcu version - */ - list_del_rcu(&primary_orig->bond_list); - list_add_rcu(&primary_orig->bond_list, - &router->bonding_list); - spin_unlock_bh(&primary_orig->neigh_list_lock); - -out: - rcu_read_unlock(); - return router; -} - -/** - * batadv_find_ifalter_router - find the best of the remaining candidates which - * are not using this interface - * @bat_priv: the bat priv with all the soft interface information - * @primary_orig: the destination - * @recv_if: the interface that the router returned by this function has to not - * use - * - * Returns the best candidate towards primary_orig that is not using recv_if. - * Increases the returned neighbor's refcount - */ -static struct batadv_neigh_node * -batadv_find_ifalter_router(struct batadv_priv *bat_priv, - struct batadv_orig_node *primary_orig, - const struct batadv_hard_iface *recv_if) -{ - struct batadv_neigh_node *router = NULL, *first_candidate = NULL; - struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; - struct batadv_neigh_node *tmp_neigh_node; - - rcu_read_lock(); - list_for_each_entry_rcu(tmp_neigh_node, &primary_orig->bond_list, - bonding_list) { - if (!first_candidate) - first_candidate = tmp_neigh_node; - - /* recv_if == NULL on the first node. */ - if (tmp_neigh_node->if_incoming == recv_if) - continue; - - if (router && bao->bat_neigh_cmp(tmp_neigh_node, router)) - continue; - - if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) - continue; - - /* decrement refcount of previously selected router */ - if (router) - batadv_neigh_node_free_ref(router); - - /* we found a better router (or at least one valid router) */ - router = tmp_neigh_node; - } - - /* use the first candidate if nothing was found. */ - if (!router && first_candidate && - atomic_inc_not_zero(&first_candidate->refcount)) - router = first_candidate; - - rcu_read_unlock(); - return router; -} - /** * batadv_check_unicast_packet - Check for malformed unicast packets * @bat_priv: the bat priv with all the soft interface information @@ -606,95 +415,141 @@ static int batadv_check_unicast_packet(struct batadv_priv *bat_priv, return 0; } -/* find a suitable router for this originator, and use - * bonding if possible. increases the found neighbors - * refcount. +/** + * batadv_find_router - find a suitable router for this originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: the destination node + * @recv_if: pointer to interface this packet was received on + * + * Returns the router which should be used for this orig_node on + * this interface, or NULL if not available. */ struct batadv_neigh_node * batadv_find_router(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, - const struct batadv_hard_iface *recv_if) + struct batadv_hard_iface *recv_if) { - struct batadv_orig_node *primary_orig_node; - struct batadv_orig_node *router_orig; - struct batadv_neigh_node *router; - static uint8_t zero_mac[ETH_ALEN] = {0, 0, 0, 0, 0, 0}; - int bonding_enabled; - uint8_t *primary_addr; + struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; + struct batadv_neigh_node *first_candidate_router = NULL; + struct batadv_neigh_node *next_candidate_router = NULL; + struct batadv_neigh_node *router, *cand_router = NULL; + struct batadv_neigh_node *last_cand_router = NULL; + struct batadv_orig_ifinfo *cand, *first_candidate = NULL; + struct batadv_orig_ifinfo *next_candidate = NULL; + struct batadv_orig_ifinfo *last_candidate; + bool last_candidate_found = false; if (!orig_node) return NULL; - router = batadv_orig_node_get_router(orig_node); - if (!router) - goto err; + router = batadv_orig_router_get(orig_node, recv_if); - /* without bonding, the first node should - * always choose the default router. + /* only consider bonding for recv_if == BATADV_IF_DEFAULT (first hop) + * and if activated. + */ + if (recv_if == BATADV_IF_DEFAULT || !atomic_read(&bat_priv->bonding) || + !router) + return router; + + /* bonding: loop through the list of possible routers found + * for the various outgoing interfaces and find a candidate after + * the last chosen bonding candidate (next_candidate). If no such + * router is found, use the first candidate found (the previously + * chosen bonding candidate might have been the last one in the list). + * If this can't be found either, return the previously choosen + * router - obviously there are no other candidates. */ - bonding_enabled = atomic_read(&bat_priv->bonding); - rcu_read_lock(); - /* select default router to output */ - router_orig = router->orig_node; - if (!router_orig) - goto err_unlock; + last_candidate = orig_node->last_bonding_candidate; + if (last_candidate) + last_cand_router = rcu_dereference(last_candidate->router); - if ((!recv_if) && (!bonding_enabled)) - goto return_router; + hlist_for_each_entry_rcu(cand, &orig_node->ifinfo_list, list) { + /* acquire some structures and references ... */ + if (!atomic_inc_not_zero(&cand->refcount)) + continue; - primary_addr = router_orig->primary_addr; + cand_router = rcu_dereference(cand->router); + if (!cand_router) + goto next; - /* if we have something in the primary_addr, we can search - * for a potential bonding candidate. - */ - if (batadv_compare_eth(primary_addr, zero_mac)) - goto return_router; + if (!atomic_inc_not_zero(&cand_router->refcount)) { + cand_router = NULL; + goto next; + } - /* find the orig_node which has the primary interface. might - * even be the same as our router_orig in many cases - */ - if (batadv_compare_eth(primary_addr, router_orig->orig)) { - primary_orig_node = router_orig; - } else { - primary_orig_node = batadv_orig_hash_find(bat_priv, - primary_addr); - if (!primary_orig_node) - goto return_router; + /* alternative candidate should be good enough to be + * considered + */ + if (!bao->bat_neigh_is_equiv_or_better(cand_router, + cand->if_outgoing, + router, recv_if)) + goto next; + + /* don't use the same router twice */ + if (last_cand_router == cand_router) + goto next; + + /* mark the first possible candidate */ + if (!first_candidate) { + atomic_inc(&cand_router->refcount); + atomic_inc(&cand->refcount); + first_candidate = cand; + first_candidate_router = cand_router; + } + + /* check if the loop has already passed the previously selected + * candidate ... this function should select the next candidate + * AFTER the previously used bonding candidate. + */ + if (!last_candidate || last_candidate_found) { + next_candidate = cand; + next_candidate_router = cand_router; + break; + } - batadv_orig_node_free_ref(primary_orig_node); + if (last_candidate == cand) + last_candidate_found = true; +next: + /* free references */ + if (cand_router) { + batadv_neigh_node_free_ref(cand_router); + cand_router = NULL; + } + batadv_orig_ifinfo_free_ref(cand); } + rcu_read_unlock(); - /* with less than 2 candidates, we can't do any - * bonding and prefer the original router. - */ - if (atomic_read(&primary_orig_node->bond_candidates) < 2) - goto return_router; + /* last_bonding_candidate is reset below, remove the old reference. */ + if (orig_node->last_bonding_candidate) + batadv_orig_ifinfo_free_ref(orig_node->last_bonding_candidate); - /* all nodes between should choose a candidate which - * is is not on the interface where the packet came - * in. + /* After finding candidates, handle the three cases: + * 1) there is a next candidate, use that + * 2) there is no next candidate, use the first of the list + * 3) there is no candidate at all, return the default router */ - batadv_neigh_node_free_ref(router); + if (next_candidate) { + batadv_neigh_node_free_ref(router); - if (bonding_enabled) - router = batadv_find_bond_router(primary_orig_node, recv_if); - else - router = batadv_find_ifalter_router(bat_priv, primary_orig_node, - recv_if); + /* remove references to first candidate, we don't need it. */ + if (first_candidate) { + batadv_neigh_node_free_ref(first_candidate_router); + batadv_orig_ifinfo_free_ref(first_candidate); + } + router = next_candidate_router; + orig_node->last_bonding_candidate = next_candidate; + } else if (first_candidate) { + batadv_neigh_node_free_ref(router); -return_router: - if (router && router->if_incoming->if_status != BATADV_IF_ACTIVE) - goto err_unlock; + /* refcounting has already been done in the loop above. */ + router = first_candidate_router; + orig_node->last_bonding_candidate = first_candidate; + } else { + orig_node->last_bonding_candidate = NULL; + } - rcu_read_unlock(); return router; -err_unlock: - rcu_read_unlock(); -err: - if (router) - batadv_neigh_node_free_ref(router); - return NULL; } static int batadv_route_unicast_packet(struct sk_buff *skb, @@ -833,7 +688,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, int is_old_ttvn; /* check if there is enough data before accessing it */ - if (pskb_may_pull(skb, hdr_len + ETH_HLEN) < 0) + if (!pskb_may_pull(skb, hdr_len + ETH_HLEN)) return 0; /* create a copy of the skb (in case of for re-routing) to modify it. */ @@ -1063,6 +918,8 @@ int batadv_recv_unicast_tvlv(struct sk_buff *skb, if (ret != NET_RX_SUCCESS) ret = batadv_route_unicast_packet(skb, recv_if); + else + consume_skb(skb); return ret; } @@ -1135,6 +992,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, int hdr_size = sizeof(*bcast_packet); int ret = NET_RX_DROP; int32_t seq_diff; + uint32_t seqno; /* drop packet if it has not necessary minimum size */ if (unlikely(!pskb_may_pull(skb, hdr_size))) @@ -1170,12 +1028,13 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, spin_lock_bh(&orig_node->bcast_seqno_lock); + seqno = ntohl(bcast_packet->seqno); /* check whether the packet is a duplicate */ if (batadv_test_bit(orig_node->bcast_bits, orig_node->last_bcast_seqno, - ntohl(bcast_packet->seqno))) + seqno)) goto spin_unlock; - seq_diff = ntohl(bcast_packet->seqno) - orig_node->last_bcast_seqno; + seq_diff = seqno - orig_node->last_bcast_seqno; /* check whether the packet is old and the host just restarted. */ if (batadv_window_protected(bat_priv, seq_diff, @@ -1186,7 +1045,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, * if required. */ if (batadv_bit_get_packet(bat_priv, orig_node->bcast_bits, seq_diff, 1)) - orig_node->last_bcast_seqno = ntohl(bcast_packet->seqno); + orig_node->last_bcast_seqno = seqno; spin_unlock_bh(&orig_node->bcast_seqno_lock); diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 19544ddb81b5..557d3d12a9ab 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_ROUTING_H_ @@ -25,6 +23,7 @@ bool batadv_check_management_packet(struct sk_buff *skb, int header_len); void batadv_update_route(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, + struct batadv_hard_iface *recv_if, struct batadv_neigh_node *neigh_node); int batadv_recv_icmp_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); @@ -45,16 +44,7 @@ int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb, struct batadv_neigh_node * batadv_find_router(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, - const struct batadv_hard_iface *recv_if); -void batadv_bonding_candidate_del(struct batadv_orig_node *orig_node, - struct batadv_neigh_node *neigh_node); -void batadv_bonding_candidate_add(struct batadv_priv *bat_priv, - struct batadv_orig_node *orig_node, - struct batadv_neigh_node *neigh_node); -void batadv_bonding_save_primary(const struct batadv_orig_node *orig_node, - struct batadv_orig_node *orig_neigh_node, - const struct batadv_ogm_packet - *batman_ogm_packet); + struct batadv_hard_iface *recv_if); int batadv_window_protected(struct batadv_priv *bat_priv, int32_t seq_num_diff, unsigned long *last_reset); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index fba4dcfcfac2..843febd1e519 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -256,9 +254,9 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, unsigned short vid) { - struct ethhdr *ethhdr = (struct ethhdr *)skb->data; + struct ethhdr *ethhdr; struct batadv_unicast_packet *unicast_packet; - int ret = NET_XMIT_DROP; + int ret = NET_XMIT_DROP, hdr_size; if (!orig_node) goto out; @@ -267,12 +265,16 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, case BATADV_UNICAST: if (!batadv_send_skb_prepare_unicast(skb, orig_node)) goto out; + + hdr_size = sizeof(*unicast_packet); break; case BATADV_UNICAST_4ADDR: if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb, orig_node, packet_subtype)) goto out; + + hdr_size = sizeof(struct batadv_unicast_4addr_packet); break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It @@ -281,6 +283,7 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, goto out; } + ethhdr = (struct ethhdr *)(skb->data + hdr_size); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route @@ -321,13 +324,23 @@ out: */ int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, - int packet_subtype, unsigned short vid) + int packet_subtype, uint8_t *dst_hint, + unsigned short vid) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct batadv_orig_node *orig_node; + uint8_t *src, *dst; + + src = ethhdr->h_source; + dst = ethhdr->h_dest; + + /* if we got an hint! let's send the packet to this client (if any) */ + if (dst_hint) { + src = NULL; + dst = dst_hint; + } + orig_node = batadv_transtable_search(bat_priv, src, dst, vid); - orig_node = batadv_transtable_search(bat_priv, ethhdr->h_source, - ethhdr->h_dest, vid); return batadv_send_skb_unicast(bat_priv, skb, packet_type, packet_subtype, orig_node, vid); } @@ -379,6 +392,8 @@ static void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet) kfree_skb(forw_packet->skb); if (forw_packet->if_incoming) batadv_hardif_free_ref(forw_packet->if_incoming); + if (forw_packet->if_outgoing) + batadv_hardif_free_ref(forw_packet->if_outgoing); kfree(forw_packet); } @@ -442,6 +457,7 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, forw_packet->skb = newskb; forw_packet->if_incoming = primary_if; + forw_packet->if_outgoing = NULL; /* how often did we send the bcast packet ? */ forw_packet->num_packets = 0; @@ -537,11 +553,16 @@ void batadv_send_outstanding_bat_ogm_packet(struct work_struct *work) bat_priv->bat_algo_ops->bat_ogm_emit(forw_packet); - /* we have to have at least one packet in the queue - * to determine the queues wake up time unless we are - * shutting down + /* we have to have at least one packet in the queue to determine the + * queues wake up time unless we are shutting down. + * + * only re-schedule if this is the "original" copy, e.g. the OGM of the + * primary interface should only be rescheduled once per period, but + * this function will be called for the forw_packet instances of the + * other secondary interfaces as well. */ - if (forw_packet->own) + if (forw_packet->own && + forw_packet->if_incoming == forw_packet->if_outgoing) batadv_schedule_bat_ogm(forw_packet->if_incoming); out: @@ -602,7 +623,8 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, * we delete only packets belonging to the given interface */ if ((hard_iface) && - (forw_packet->if_incoming != hard_iface)) + (forw_packet->if_incoming != hard_iface) && + (forw_packet->if_outgoing != hard_iface)) continue; spin_unlock_bh(&bat_priv->forw_bat_list_lock); diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index aa2e2537a739..aaddaa9661ce 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_SEND_H_ @@ -40,7 +38,8 @@ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv, int packet_subtype); int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, - int packet_subtype, unsigned short vid); + int packet_subtype, uint8_t *dst_hint, + unsigned short vid); int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid); @@ -57,11 +56,11 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, * Returns NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ static inline int batadv_send_skb_via_tt(struct batadv_priv *bat_priv, - struct sk_buff *skb, + struct sk_buff *skb, uint8_t *dst_hint, unsigned short vid) { return batadv_send_skb_via_tt_generic(bat_priv, skb, BATADV_UNICAST, 0, - vid); + dst_hint, vid); } /** @@ -81,11 +80,12 @@ static inline int batadv_send_skb_via_tt(struct batadv_priv *bat_priv, static inline int batadv_send_skb_via_tt_4addr(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_subtype, + uint8_t *dst_hint, unsigned short vid) { return batadv_send_skb_via_tt_generic(bat_priv, skb, BATADV_UNICAST_4ADDR, - packet_subtype, vid); + packet_subtype, dst_hint, vid); } #endif /* _NET_BATMAN_ADV_SEND_H_ */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index a8f99d1486c0..f82c267e1886 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -121,7 +119,7 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) batadv_tt_local_remove(bat_priv, old_addr, BATADV_NO_FLAGS, "mac address changed", false); batadv_tt_local_add(dev, addr->sa_data, BATADV_NO_FLAGS, - BATADV_NULL_IFINDEX); + BATADV_NULL_IFINDEX, BATADV_NO_MARK); } return 0; @@ -162,6 +160,8 @@ static int batadv_interface_tx(struct sk_buff *skb, 0x00, 0x00}; static const uint8_t ectp_addr[ETH_ALEN] = {0xCF, 0x00, 0x00, 0x00, 0x00, 0x00}; + enum batadv_dhcp_recipient dhcp_rcp = BATADV_DHCP_NO; + uint8_t *dst_hint = NULL, chaddr[ETH_ALEN]; struct vlan_ethhdr *vhdr; unsigned int header_len = 0; int data_len = skb->len, ret; @@ -169,6 +169,7 @@ static int batadv_interface_tx(struct sk_buff *skb, bool do_bcast = false, client_added; unsigned short vid; uint32_t seqno; + int gw_mode; if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) goto dropped; @@ -198,7 +199,8 @@ static int batadv_interface_tx(struct sk_buff *skb, /* Register the client MAC in the transtable */ if (!is_multicast_ether_addr(ethhdr->h_source)) { client_added = batadv_tt_local_add(soft_iface, ethhdr->h_source, - vid, skb->skb_iif); + vid, skb->skb_iif, + skb->mark); if (!client_added) goto dropped; } @@ -215,36 +217,39 @@ static int batadv_interface_tx(struct sk_buff *skb, if (batadv_compare_eth(ethhdr->h_dest, ectp_addr)) goto dropped; + gw_mode = atomic_read(&bat_priv->gw_mode); if (is_multicast_ether_addr(ethhdr->h_dest)) { - do_bcast = true; - - switch (atomic_read(&bat_priv->gw_mode)) { - case BATADV_GW_MODE_SERVER: - /* gateway servers should not send dhcp - * requests into the mesh - */ - ret = batadv_gw_is_dhcp_target(skb, &header_len); - if (ret) - goto dropped; - break; - case BATADV_GW_MODE_CLIENT: - /* gateway clients should send dhcp requests - * via unicast to their gateway - */ - ret = batadv_gw_is_dhcp_target(skb, &header_len); - if (ret) - do_bcast = false; - break; - case BATADV_GW_MODE_OFF: - default: - break; + /* if gw mode is off, broadcast every packet */ + if (gw_mode == BATADV_GW_MODE_OFF) { + do_bcast = true; + goto send; } - /* reminder: ethhdr might have become unusable from here on - * (batadv_gw_is_dhcp_target() might have reallocated skb data) + dhcp_rcp = batadv_gw_dhcp_recipient_get(skb, &header_len, + chaddr); + /* skb->data may have been modified by + * batadv_gw_dhcp_recipient_get() */ + ethhdr = (struct ethhdr *)skb->data; + /* if gw_mode is on, broadcast any non-DHCP message. + * All the DHCP packets are going to be sent as unicast + */ + if (dhcp_rcp == BATADV_DHCP_NO) { + do_bcast = true; + goto send; + } + + if (dhcp_rcp == BATADV_DHCP_TO_CLIENT) + dst_hint = chaddr; + else if ((gw_mode == BATADV_GW_MODE_SERVER) && + (dhcp_rcp == BATADV_DHCP_TO_SERVER)) + /* gateways should not forward any DHCP message if + * directed to a DHCP server + */ + goto dropped; } +send: batadv_skb_set_priority(skb, 0); /* ethernet packet should be broadcasted */ @@ -290,22 +295,22 @@ static int batadv_interface_tx(struct sk_buff *skb, /* unicast packet */ } else { - if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_OFF) { + /* DHCP packets going to a server will use the GW feature */ + if (dhcp_rcp == BATADV_DHCP_TO_SERVER) { ret = batadv_gw_out_of_range(bat_priv, skb); if (ret) goto dropped; - } - - if (batadv_dat_snoop_outgoing_arp_request(bat_priv, skb)) - goto dropped; - - batadv_dat_snoop_outgoing_arp_reply(bat_priv, skb); - - if (is_multicast_ether_addr(ethhdr->h_dest)) ret = batadv_send_skb_via_gw(bat_priv, skb, vid); - else - ret = batadv_send_skb_via_tt(bat_priv, skb, vid); + } else { + if (batadv_dat_snoop_outgoing_arp_request(bat_priv, + skb)) + goto dropped; + batadv_dat_snoop_outgoing_arp_reply(bat_priv, skb); + + ret = batadv_send_skb_via_tt(bat_priv, skb, dst_hint, + vid); + } if (ret == NET_XMIT_DROP) goto dropped_freed; } @@ -394,9 +399,23 @@ void batadv_interface_rx(struct net_device *soft_iface, batadv_tt_add_temporary_global_entry(bat_priv, orig_node, ethhdr->h_source, vid); - if (batadv_is_ap_isolated(bat_priv, ethhdr->h_source, ethhdr->h_dest, - vid)) + if (is_multicast_ether_addr(ethhdr->h_dest)) { + /* set the mark on broadcast packets if AP isolation is ON and + * the packet is coming from an "isolated" client + */ + if (batadv_vlan_ap_isola_get(bat_priv, vid) && + batadv_tt_global_is_isolated(bat_priv, ethhdr->h_source, + vid)) { + /* save bits in skb->mark not covered by the mask and + * apply the mark on the rest + */ + skb->mark &= ~bat_priv->isolation_mark_mask; + skb->mark |= bat_priv->isolation_mark; + } + } else if (batadv_is_ap_isolated(bat_priv, ethhdr->h_source, + ethhdr->h_dest, vid)) { goto dropped; + } netif_rx(skb); goto out; @@ -485,7 +504,7 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) */ batadv_tt_local_add(bat_priv->soft_iface, bat_priv->soft_iface->dev_addr, vid, - BATADV_NULL_IFINDEX); + BATADV_NULL_IFINDEX, BATADV_NO_MARK); spin_lock_bh(&bat_priv->softif_vlan_list_lock); hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list); @@ -678,7 +697,7 @@ static int batadv_softif_init_late(struct net_device *dev) atomic_set(&bat_priv->gw.bandwidth_down, 100); atomic_set(&bat_priv->gw.bandwidth_up, 20); atomic_set(&bat_priv->orig_interval, 1000); - atomic_set(&bat_priv->hop_penalty, 30); + atomic_set(&bat_priv->hop_penalty, 15); #ifdef CONFIG_BATMAN_ADV_DEBUG atomic_set(&bat_priv->log_level, 0); #endif @@ -697,6 +716,8 @@ static int batadv_softif_init_late(struct net_device *dev) #endif bat_priv->tt.last_changeset = NULL; bat_priv->tt.last_changeset_len = 0; + bat_priv->isolation_mark = 0; + bat_priv->isolation_mark_mask = 0; /* randomize initial seqno to avoid collision */ get_random_bytes(&random_seqno, sizeof(random_seqno)); diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 06fc91ff5a02..dbab22fd89a5 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_SOFT_INTERFACE_H_ diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 6335433310af..e456bf6bb284 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -329,10 +327,10 @@ static ssize_t batadv_show_bat_algo(struct kobject *kobj, return sprintf(buff, "%s\n", bat_priv->bat_algo_ops->name); } -static void batadv_post_gw_deselect(struct net_device *net_dev) +static void batadv_post_gw_reselect(struct net_device *net_dev) { struct batadv_priv *bat_priv = netdev_priv(net_dev); - batadv_gw_deselect(bat_priv); + batadv_gw_reselect(bat_priv); } static ssize_t batadv_show_gw_mode(struct kobject *kobj, struct attribute *attr, @@ -408,7 +406,16 @@ static ssize_t batadv_store_gw_mode(struct kobject *kobj, batadv_info(net_dev, "Changing gw mode from: %s to: %s\n", curr_gw_mode_str, buff); - batadv_gw_deselect(bat_priv); + /* Invoking batadv_gw_reselect() is not enough to really de-select the + * current GW. It will only instruct the gateway client code to perform + * a re-election the next time that this is needed. + * + * When gw client mode is being switched off the current GW must be + * de-selected explicitly otherwise no GW_ADD uevent is thrown on + * client mode re-activation. This is operation is performed in + * batadv_gw_check_client_stop(). + */ + batadv_gw_reselect(bat_priv); /* always call batadv_gw_check_client_stop() before changing the gateway * state */ @@ -443,6 +450,74 @@ static ssize_t batadv_store_gw_bwidth(struct kobject *kobj, return batadv_gw_bandwidth_set(net_dev, buff, count); } +/** + * batadv_show_isolation_mark - print the current isolation mark/mask + * @kobj: kobject representing the private mesh sysfs directory + * @attr: the batman-adv attribute the user is interacting with + * @buff: the buffer that will contain the data to send back to the user + * + * Returns the number of bytes written into 'buff' on success or a negative + * error code in case of failure + */ +static ssize_t batadv_show_isolation_mark(struct kobject *kobj, + struct attribute *attr, char *buff) +{ + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); + + return sprintf(buff, "%#.8x/%#.8x\n", bat_priv->isolation_mark, + bat_priv->isolation_mark_mask); +} + +/** + * batadv_store_isolation_mark - parse and store the isolation mark/mask entered + * by the user + * @kobj: kobject representing the private mesh sysfs directory + * @attr: the batman-adv attribute the user is interacting with + * @buff: the buffer containing the user data + * @count: number of bytes in the buffer + * + * Returns 'count' on success or a negative error code in case of failure + */ +static ssize_t batadv_store_isolation_mark(struct kobject *kobj, + struct attribute *attr, char *buff, + size_t count) +{ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); + struct batadv_priv *bat_priv = netdev_priv(net_dev); + uint32_t mark, mask; + char *mask_ptr; + + /* parse the mask if it has been specified, otherwise assume the mask is + * the biggest possible + */ + mask = 0xFFFFFFFF; + mask_ptr = strchr(buff, '/'); + if (mask_ptr) { + *mask_ptr = '\0'; + mask_ptr++; + + /* the mask must be entered in hex base as it is going to be a + * bitmask and not a prefix length + */ + if (kstrtou32(mask_ptr, 16, &mask) < 0) + return -EINVAL; + } + + /* the mark can be entered in any base */ + if (kstrtou32(buff, 0, &mark) < 0) + return -EINVAL; + + bat_priv->isolation_mark_mask = mask; + /* erase bits not covered by the mask */ + bat_priv->isolation_mark = mark & bat_priv->isolation_mark_mask; + + batadv_info(net_dev, + "New skb mark for extended isolation: %#.8x/%#.8x\n", + bat_priv->isolation_mark, bat_priv->isolation_mark_mask); + + return count; +} + BATADV_ATTR_SIF_BOOL(aggregated_ogms, S_IRUGO | S_IWUSR, NULL); BATADV_ATTR_SIF_BOOL(bonding, S_IRUGO | S_IWUSR, NULL); #ifdef CONFIG_BATMAN_ADV_BLA @@ -461,7 +536,7 @@ BATADV_ATTR_SIF_UINT(orig_interval, S_IRUGO | S_IWUSR, 2 * BATADV_JITTER, BATADV_ATTR_SIF_UINT(hop_penalty, S_IRUGO | S_IWUSR, 0, BATADV_TQ_MAX_VALUE, NULL); BATADV_ATTR_SIF_UINT(gw_sel_class, S_IRUGO | S_IWUSR, 1, BATADV_TQ_MAX_VALUE, - batadv_post_gw_deselect); + batadv_post_gw_reselect); static BATADV_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, batadv_show_gw_bwidth, batadv_store_gw_bwidth); #ifdef CONFIG_BATMAN_ADV_DEBUG @@ -471,6 +546,8 @@ BATADV_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, BATADV_DBG_ALL, NULL); BATADV_ATTR_SIF_BOOL(network_coding, S_IRUGO | S_IWUSR, batadv_nc_status_update); #endif +static BATADV_ATTR(isolation_mark, S_IRUGO | S_IWUSR, + batadv_show_isolation_mark, batadv_store_isolation_mark); static struct batadv_attribute *batadv_mesh_attrs[] = { &batadv_attr_aggregated_ogms, @@ -494,6 +571,7 @@ static struct batadv_attribute *batadv_mesh_attrs[] = { #ifdef CONFIG_BATMAN_ADV_NC &batadv_attr_network_coding, #endif + &batadv_attr_isolation_mark, NULL, }; diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index c7d725de50ad..b715b60db7cd 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_SYSFS_H_ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index ff625fedbc5e..959dde721c46 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "main.h" @@ -51,7 +49,7 @@ static int batadv_compare_tt(const struct hlist_node *node, const void *data2) const void *data1 = container_of(node, struct batadv_tt_common_entry, hash_entry); - return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); + return batadv_compare_eth(data1, data2); } /** @@ -476,11 +474,13 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv, * @vid: VLAN identifier * @ifindex: index of the interface where the client is connected to (useful to * identify wireless clients) + * @mark: the value contained in the skb->mark field of the received packet (if + * any) * * Returns true if the client was successfully added, false otherwise. */ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, - unsigned short vid, int ifindex) + unsigned short vid, int ifindex, uint32_t mark) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); struct batadv_tt_local_entry *tt_local; @@ -491,6 +491,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, int hash_added, table_size, packet_size_max; bool ret = false, roamed_back = false; uint8_t remote_flags; + uint32_t match_mark; if (ifindex != BATADV_NULL_IFINDEX) in_dev = dev_get_by_index(&init_net, ifindex); @@ -615,6 +616,17 @@ check_roaming: else tt_local->common.flags &= ~BATADV_TT_CLIENT_WIFI; + /* check the mark in the skb: if it's equal to the configured + * isolation_mark, it means the packet is coming from an isolated + * non-mesh client + */ + match_mark = (mark & bat_priv->isolation_mark_mask); + if (bat_priv->isolation_mark_mask && + match_mark == bat_priv->isolation_mark) + tt_local->common.flags |= BATADV_TT_CLIENT_ISOLA; + else + tt_local->common.flags &= ~BATADV_TT_CLIENT_ISOLA; + /* if any "dynamic" flag has been modified, resend an ADD event for this * entry so that all the nodes can get the new flags */ @@ -875,7 +887,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) seq_printf(seq, "Locally retrieved addresses (from %s) announced via TT (TTVN: %u):\n", net_dev->name, (uint8_t)atomic_read(&bat_priv->tt.vn)); - seq_printf(seq, " %-13s %s %-7s %-9s (%-10s)\n", "Client", "VID", + seq_printf(seq, " %-13s %s %-8s %-9s (%-10s)\n", "Client", "VID", "Flags", "Last seen", "CRC"); for (i = 0; i < hash->size; i++) { @@ -903,7 +915,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) } seq_printf(seq, - " * %pM %4i [%c%c%c%c%c] %3u.%03u (%#.8x)\n", + " * %pM %4i [%c%c%c%c%c%c] %3u.%03u (%#.8x)\n", tt_common_entry->addr, BATADV_PRINT_VID(tt_common_entry->vid), (tt_common_entry->flags & @@ -915,6 +927,8 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) BATADV_TT_CLIENT_PENDING ? 'X' : '.'), (tt_common_entry->flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.'), + (tt_common_entry->flags & + BATADV_TT_CLIENT_ISOLA ? 'I' : '.'), no_purge ? 0 : last_seen_secs, no_purge ? 0 : last_seen_msecs, vlan->tt.crc); @@ -1368,7 +1382,8 @@ out: return ret; } -/* batadv_transtable_best_orig - Get best originator list entry from tt entry +/** + * batadv_transtable_best_orig - Get best originator list entry from tt entry * @bat_priv: the bat priv with all the soft interface information * @tt_global_entry: global translation table entry to be analyzed * @@ -1386,12 +1401,14 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv, head = &tt_global_entry->orig_list; hlist_for_each_entry_rcu(orig_entry, head, list) { - router = batadv_orig_node_get_router(orig_entry->orig_node); + router = batadv_orig_router_get(orig_entry->orig_node, + BATADV_IF_DEFAULT); if (!router) continue; if (best_router && - bao->bat_neigh_cmp(router, best_router) <= 0) { + bao->bat_neigh_cmp(router, BATADV_IF_DEFAULT, + best_router, BATADV_IF_DEFAULT) <= 0) { batadv_neigh_node_free_ref(router); continue; } @@ -1410,8 +1427,9 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv, return best_entry; } -/* batadv_tt_global_print_entry - print all orig nodes who announce the address - * for this global entry +/** + * batadv_tt_global_print_entry - print all orig nodes who announce the address + * for this global entry * @bat_priv: the bat priv with all the soft interface information * @tt_global_entry: global translation table entry to be printed * @seq: debugfs table seq_file struct @@ -1447,13 +1465,14 @@ batadv_tt_global_print_entry(struct batadv_priv *bat_priv, last_ttvn = atomic_read(&best_entry->orig_node->last_ttvn); seq_printf(seq, - " %c %pM %4i (%3u) via %pM (%3u) (%#.8x) [%c%c%c]\n", + " %c %pM %4i (%3u) via %pM (%3u) (%#.8x) [%c%c%c%c]\n", '*', tt_global_entry->common.addr, BATADV_PRINT_VID(tt_global_entry->common.vid), best_entry->ttvn, best_entry->orig_node->orig, last_ttvn, vlan->tt.crc, (flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'), (flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.'), + (flags & BATADV_TT_CLIENT_ISOLA ? 'I' : '.'), (flags & BATADV_TT_CLIENT_TEMP ? 'T' : '.')); batadv_orig_node_vlan_free_ref(vlan); @@ -1478,13 +1497,14 @@ print_list: last_ttvn = atomic_read(&orig_entry->orig_node->last_ttvn); seq_printf(seq, - " %c %pM %4d (%3u) via %pM (%3u) (%#.8x) [%c%c%c]\n", + " %c %pM %4d (%3u) via %pM (%3u) (%#.8x) [%c%c%c%c]\n", '+', tt_global_entry->common.addr, BATADV_PRINT_VID(tt_global_entry->common.vid), orig_entry->ttvn, orig_entry->orig_node->orig, last_ttvn, vlan->tt.crc, (flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'), (flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.'), + (flags & BATADV_TT_CLIENT_ISOLA ? 'I' : '.'), (flags & BATADV_TT_CLIENT_TEMP ? 'T' : '.')); batadv_orig_node_vlan_free_ref(vlan); @@ -1853,6 +1873,11 @@ _batadv_is_ap_isolated(struct batadv_tt_local_entry *tt_local_entry, tt_global_entry->common.flags & BATADV_TT_CLIENT_WIFI) ret = true; + /* check if the two clients are marked as isolated */ + if (tt_local_entry->common.flags & BATADV_TT_CLIENT_ISOLA && + tt_global_entry->common.flags & BATADV_TT_CLIENT_ISOLA) + ret = true; + return ret; } @@ -1879,19 +1904,8 @@ struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, struct batadv_tt_global_entry *tt_global_entry = NULL; struct batadv_orig_node *orig_node = NULL; struct batadv_tt_orig_list_entry *best_entry; - bool ap_isolation_enabled = false; - struct batadv_softif_vlan *vlan; - /* if the AP isolation is requested on a VLAN, then check for its - * setting in the proper VLAN private data structure - */ - vlan = batadv_softif_vlan_get(bat_priv, vid); - if (vlan) { - ap_isolation_enabled = atomic_read(&vlan->ap_isolation); - batadv_softif_vlan_free_ref(vlan); - } - - if (src && ap_isolation_enabled) { + if (src && batadv_vlan_ap_isola_get(bat_priv, vid)) { tt_local_entry = batadv_tt_local_hash_find(bat_priv, src, vid); if (!tt_local_entry || (tt_local_entry->common.flags & BATADV_TT_CLIENT_PENDING)) @@ -1961,6 +1975,7 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, struct hlist_head *head; uint32_t i, crc_tmp, crc = 0; uint8_t flags; + __be16 tmp_vid; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1997,8 +2012,11 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, orig_node)) continue; - crc_tmp = crc32c(0, &tt_common->vid, - sizeof(tt_common->vid)); + /* use network order to read the VID: this ensures that + * every node reads the bytes in the same order. + */ + tmp_vid = htons(tt_common->vid); + crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid)); /* compute the CRC on flags that have to be kept in sync * among nodes @@ -2032,6 +2050,7 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, struct hlist_head *head; uint32_t i, crc_tmp, crc = 0; uint8_t flags; + __be16 tmp_vid; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -2050,8 +2069,11 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, if (tt_common->flags & BATADV_TT_CLIENT_NEW) continue; - crc_tmp = crc32c(0, &tt_common->vid, - sizeof(tt_common->vid)); + /* use network order to read the VID: this ensures that + * every node reads the bytes in the same order. + */ + tmp_vid = htons(tt_common->vid); + crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid)); /* compute the CRC on flags that have to be kept in sync * among nodes @@ -2248,6 +2270,7 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, { struct batadv_tvlv_tt_vlan_data *tt_vlan_tmp; struct batadv_orig_node_vlan *vlan; + uint32_t crc; int i; /* check if each received CRC matches the locally stored one */ @@ -2267,7 +2290,10 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, if (!vlan) return false; - if (vlan->tt.crc != ntohl(tt_vlan_tmp->crc)) + crc = vlan->tt.crc; + batadv_orig_node_vlan_free_ref(vlan); + + if (crc != ntohl(tt_vlan_tmp->crc)) return false; } @@ -3204,7 +3230,6 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv, spin_lock_bh(&orig_node->tt_lock); - tt_change = (struct batadv_tvlv_tt_change *)tt_buff; batadv_tt_update_changes(bat_priv, orig_node, tt_num_changes, ttvn, tt_change); @@ -3567,3 +3592,29 @@ int batadv_tt_init(struct batadv_priv *bat_priv) return 1; } + +/** + * batadv_tt_global_is_isolated - check if a client is marked as isolated + * @bat_priv: the bat priv with all the soft interface information + * @addr: the mac address of the client + * @vid: the identifier of the VLAN where this client is connected + * + * Returns true if the client is marked with the TT_CLIENT_ISOLA flag, false + * otherwise + */ +bool batadv_tt_global_is_isolated(struct batadv_priv *bat_priv, + const uint8_t *addr, unsigned short vid) +{ + struct batadv_tt_global_entry *tt; + bool ret; + + tt = batadv_tt_global_hash_find(bat_priv, addr, vid); + if (!tt) + return false; + + ret = tt->common.flags & BATADV_TT_CLIENT_ISOLA; + + batadv_tt_global_entry_free_ref(tt); + + return ret; +} diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 026b1ffa6746..20a1d7861ded 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ @@ -22,7 +20,7 @@ int batadv_tt_init(struct batadv_priv *bat_priv); bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, - unsigned short vid, int ifindex); + unsigned short vid, int ifindex, uint32_t mark); uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, const uint8_t *addr, unsigned short vid, const char *message, bool roaming); @@ -50,5 +48,7 @@ bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const unsigned char *addr, unsigned short vid); +bool batadv_tt_global_is_isolated(struct batadv_priv *bat_priv, + const uint8_t *addr, unsigned short vid); #endif /* _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 91dd369b0ff2..78370ab31f9c 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -12,9 +12,7 @@ * General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _NET_BATMAN_ADV_TYPES_H_ @@ -36,6 +34,18 @@ #endif /* CONFIG_BATMAN_ADV_DAT */ /** + * enum batadv_dhcp_recipient - dhcp destination + * @BATADV_DHCP_NO: packet is not a dhcp message + * @BATADV_DHCP_TO_SERVER: dhcp message is directed to a server + * @BATADV_DHCP_TO_CLIENT: dhcp message is directed to a client + */ +enum batadv_dhcp_recipient { + BATADV_DHCP_NO = 0, + BATADV_DHCP_TO_SERVER, + BATADV_DHCP_TO_CLIENT, +}; + +/** * BATADV_TT_REMOTE_MASK - bitmask selecting the flags that are sent over the * wire only */ @@ -74,6 +84,7 @@ struct batadv_hard_iface_bat_iv { * @rcu: struct used for freeing in an RCU-safe manner * @bat_iv: BATMAN IV specific per hard interface data * @cleanup_work: work queue callback item for hard interface deinit + * @debug_dir: dentry for nc subdir in batman-adv directory in debugfs */ struct batadv_hard_iface { struct list_head list; @@ -88,6 +99,29 @@ struct batadv_hard_iface { struct rcu_head rcu; struct batadv_hard_iface_bat_iv bat_iv; struct work_struct cleanup_work; + struct dentry *debug_dir; +}; + +/** + * struct batadv_orig_ifinfo - originator info per outgoing interface + * @list: list node for orig_node::ifinfo_list + * @if_outgoing: pointer to outgoing hard interface + * @router: router that should be used to reach this originator + * @last_real_seqno: last and best known sequence number + * @last_ttl: ttl of last received packet + * @batman_seqno_reset: time when the batman seqno window was reset + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ +struct batadv_orig_ifinfo { + struct hlist_node list; + struct batadv_hard_iface *if_outgoing; + struct batadv_neigh_node __rcu *router; /* rcu protected pointer */ + uint32_t last_real_seqno; + uint8_t last_ttl; + unsigned long batman_seqno_reset; + atomic_t refcount; + struct rcu_head rcu; }; /** @@ -165,11 +199,11 @@ struct batadv_orig_bat_iv { * struct batadv_orig_node - structure for orig_list maintaining nodes of mesh * @orig: originator ethernet address * @primary_addr: hosts primary interface address - * @router: router that should be used to reach this originator + * @ifinfo_list: list for routers per outgoing interface + * @last_bonding_candidate: pointer to last ifinfo of last used router * @batadv_dat_addr_t: address of the orig node in the distributed hash * @last_seen: time when last packet from this node was received * @bcast_seqno_reset: time when the broadcast seqno window was reset - * @batman_seqno_reset: time when the batman seqno window was reset * @capabilities: announced capabilities of this originator * @last_ttvn: last seen translation table version number * @tt_buff: last tt changeset this node received from the orig node @@ -182,19 +216,15 @@ struct batadv_orig_bat_iv { * made up by two operations (data structure update and metdata -CRC/TTVN- * recalculation) and they have to be executed atomically in order to avoid * another thread to read the table/metadata between those. - * @last_real_seqno: last and best known sequence number - * @last_ttl: ttl of last received packet * @bcast_bits: bitfield containing the info which payload broadcast originated * from this orig node this host already has seen (relative to * last_bcast_seqno) * @last_bcast_seqno: last broadcast sequence number received by this host * @neigh_list: list of potential next hop neighbor towards this orig node - * @neigh_list_lock: lock protecting neigh_list, router and bonding_list + * @neigh_list_lock: lock protecting neigh_list and router * @hash_entry: hlist node for batadv_priv::orig_hash * @bat_priv: pointer to soft_iface this orig node belongs to * @bcast_seqno_lock: lock protecting bcast_bits & last_bcast_seqno - * @bond_candidates: how many candidates are available - * @bond_list: list of bonding candidates * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner * @in_coding_list: list of nodes this orig can hear @@ -210,13 +240,13 @@ struct batadv_orig_bat_iv { struct batadv_orig_node { uint8_t orig[ETH_ALEN]; uint8_t primary_addr[ETH_ALEN]; - struct batadv_neigh_node __rcu *router; /* rcu protected pointer */ + struct hlist_head ifinfo_list; + struct batadv_orig_ifinfo *last_bonding_candidate; #ifdef CONFIG_BATMAN_ADV_DAT batadv_dat_addr_t dat_addr; #endif unsigned long last_seen; unsigned long bcast_seqno_reset; - unsigned long batman_seqno_reset; uint8_t capabilities; atomic_t last_ttvn; unsigned char *tt_buff; @@ -225,19 +255,15 @@ struct batadv_orig_node { bool tt_initialised; /* prevents from changing the table while reading it */ spinlock_t tt_lock; - uint32_t last_real_seqno; - uint8_t last_ttl; DECLARE_BITMAP(bcast_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); uint32_t last_bcast_seqno; struct hlist_head neigh_list; - /* neigh_list_lock protects: neigh_list, router & bonding_list */ + /* neigh_list_lock protects: neigh_list and router */ spinlock_t neigh_list_lock; struct hlist_node hash_entry; struct batadv_priv *bat_priv; /* bcast_seqno_lock protects: bcast_bits & last_bcast_seqno */ spinlock_t bcast_seqno_lock; - atomic_t bond_candidates; - struct list_head bond_list; atomic_t refcount; struct rcu_head rcu; #ifdef CONFIG_BATMAN_ADV_NC @@ -283,49 +309,64 @@ struct batadv_gw_node { }; /** - * struct batadv_neigh_bat_iv - B.A.T.M.A.N. IV specific structure for single - * hop neighbors + * struct batadv_neigh_node - structure for single hops neighbors + * @list: list node for batadv_orig_node::neigh_list + * @orig_node: pointer to corresponding orig_node + * @addr: the MAC address of the neighboring interface + * @ifinfo_list: list for routing metrics per outgoing interface + * @ifinfo_lock: lock protecting private ifinfo members and list + * @if_incoming: pointer to incoming hard interface + * @last_seen: when last packet via this neighbor was received + * @last_ttl: last received ttl from this neigh node + * @rcu: struct used for freeing in an RCU-safe manner + * @bat_iv: B.A.T.M.A.N. IV private structure + */ +struct batadv_neigh_node { + struct hlist_node list; + struct batadv_orig_node *orig_node; + uint8_t addr[ETH_ALEN]; + struct hlist_head ifinfo_list; + spinlock_t ifinfo_lock; /* protects ifinfo_list and its members */ + struct batadv_hard_iface *if_incoming; + unsigned long last_seen; + atomic_t refcount; + struct rcu_head rcu; +}; + +/** + * struct batadv_neigh_node_bat_iv - neighbor information per outgoing + * interface for BATMAN IV * @tq_recv: ring buffer of received TQ values from this neigh node * @tq_index: ring buffer index * @tq_avg: averaged tq of all tq values in the ring buffer (tq_recv) * @real_bits: bitfield containing the number of OGMs received from this neigh * node (relative to orig_node->last_real_seqno) * @real_packet_count: counted result of real_bits - * @lq_update_lock: lock protecting tq_recv & tq_index */ -struct batadv_neigh_bat_iv { +struct batadv_neigh_ifinfo_bat_iv { uint8_t tq_recv[BATADV_TQ_GLOBAL_WINDOW_SIZE]; uint8_t tq_index; uint8_t tq_avg; DECLARE_BITMAP(real_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); uint8_t real_packet_count; - spinlock_t lq_update_lock; /* protects tq_recv & tq_index */ }; /** - * struct batadv_neigh_node - structure for single hops neighbors - * @list: list node for batadv_orig_node::neigh_list - * @orig_node: pointer to corresponding orig_node - * @addr: the MAC address of the neighboring interface - * @if_incoming: pointer to incoming hard interface - * @last_seen: when last packet via this neighbor was received + * struct batadv_neigh_ifinfo - neighbor information per outgoing interface + * @list: list node for batadv_neigh_node::ifinfo_list + * @if_outgoing: pointer to outgoing hard interface + * @bat_iv: B.A.T.M.A.N. IV private structure * @last_ttl: last received ttl from this neigh node - * @bonding_list: list node for batadv_orig_node::bond_list * @refcount: number of contexts the object is used - * @rcu: struct used for freeing in an RCU-safe manner - * @bat_iv: B.A.T.M.A.N. IV private structure + * @rcu: struct used for freeing in a RCU-safe manner */ -struct batadv_neigh_node { +struct batadv_neigh_ifinfo { struct hlist_node list; - struct batadv_orig_node *orig_node; - uint8_t addr[ETH_ALEN]; - struct batadv_hard_iface *if_incoming; - unsigned long last_seen; + struct batadv_hard_iface *if_outgoing; + struct batadv_neigh_ifinfo_bat_iv bat_iv; uint8_t last_ttl; - struct list_head bonding_list; atomic_t refcount; struct rcu_head rcu; - struct batadv_neigh_bat_iv bat_iv; }; /** @@ -687,6 +728,8 @@ struct batadv_priv { #ifdef CONFIG_BATMAN_ADV_DEBUG atomic_t log_level; #endif + uint32_t isolation_mark; + uint32_t isolation_mark_mask; atomic_t bcast_seqno; atomic_t bcast_queue_left; atomic_t batman_queue_left; @@ -981,8 +1024,10 @@ struct batadv_skb_cb { * @direct_link_flags: direct link flags for aggregated OGM packets * @num_packets: counter for bcast packet retransmission * @delayed_work: work queue callback item for packet sending - * @if_incoming: pointer incoming hard-iface or primary iface if locally - * generated packet + * @if_incoming: pointer to incoming hard-iface or primary iface if + * locally generated packet + * @if_outgoing: packet where the packet should be sent to, or NULL if + * unspecified */ struct batadv_forw_packet { struct hlist_node list; @@ -994,6 +1039,7 @@ struct batadv_forw_packet { uint8_t num_packets; struct delayed_work delayed_work; struct batadv_hard_iface *if_incoming; + struct batadv_hard_iface *if_outgoing; }; /** @@ -1007,9 +1053,11 @@ struct batadv_forw_packet { * @bat_primary_iface_set: called when primary interface is selected / changed * @bat_ogm_schedule: prepare a new outgoing OGM for the send queue * @bat_ogm_emit: send scheduled OGM - * @bat_neigh_cmp: compare the metrics of two neighbors - * @bat_neigh_is_equiv_or_better: check if neigh1 is equally good or - * better than neigh2 from the metric prospective + * @bat_neigh_cmp: compare the metrics of two neighbors for their respective + * outgoing interfaces + * @bat_neigh_is_equiv_or_better: check if neigh1 is equally good or better + * than neigh2 for their respective outgoing interface from the metric + * prospective * @bat_orig_print: print the originator table (optional) * @bat_orig_free: free the resources allocated by the routing algorithm for an * orig_node object @@ -1028,11 +1076,17 @@ struct batadv_algo_ops { void (*bat_ogm_schedule)(struct batadv_hard_iface *hard_iface); void (*bat_ogm_emit)(struct batadv_forw_packet *forw_packet); int (*bat_neigh_cmp)(struct batadv_neigh_node *neigh1, - struct batadv_neigh_node *neigh2); - bool (*bat_neigh_is_equiv_or_better)(struct batadv_neigh_node *neigh1, - struct batadv_neigh_node *neigh2); + struct batadv_hard_iface *if_outgoing1, + struct batadv_neigh_node *neigh2, + struct batadv_hard_iface *if_outgoing2); + bool (*bat_neigh_is_equiv_or_better) + (struct batadv_neigh_node *neigh1, + struct batadv_hard_iface *if_outgoing1, + struct batadv_neigh_node *neigh2, + struct batadv_hard_iface *if_outgoing2); /* orig_node handling API */ - void (*bat_orig_print)(struct batadv_priv *priv, struct seq_file *seq); + void (*bat_orig_print)(struct batadv_priv *priv, struct seq_file *seq, + struct batadv_hard_iface *hard_iface); void (*bat_orig_free)(struct batadv_orig_node *orig_node); int (*bat_orig_add_if)(struct batadv_orig_node *orig_node, int max_if_num); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c new file mode 100644 index 000000000000..adb3ea04adaa --- /dev/null +++ b/net/bluetooth/6lowpan.c @@ -0,0 +1,860 @@ +/* + Copyright (c) 2013 Intel Corp. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License version 2 and + only version 2 as published by the Free Software Foundation. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. +*/ + +#include <linux/if_arp.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> + +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/addrconf.h> + +#include <net/af_ieee802154.h> /* to get the address type */ + +#include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci_core.h> +#include <net/bluetooth/l2cap.h> + +#include "6lowpan.h" + +#include "../ieee802154/6lowpan.h" /* for the compression support */ + +#define IFACE_NAME_TEMPLATE "bt%d" +#define EUI64_ADDR_LEN 8 + +struct skb_cb { + struct in6_addr addr; + struct l2cap_conn *conn; +}; +#define lowpan_cb(skb) ((struct skb_cb *)((skb)->cb)) + +/* The devices list contains those devices that we are acting + * as a proxy. The BT 6LoWPAN device is a virtual device that + * connects to the Bluetooth LE device. The real connection to + * BT device is done via l2cap layer. There exists one + * virtual device / one BT 6LoWPAN network (=hciX device). + * The list contains struct lowpan_dev elements. + */ +static LIST_HEAD(bt_6lowpan_devices); +static DEFINE_RWLOCK(devices_lock); + +struct lowpan_peer { + struct list_head list; + struct l2cap_conn *conn; + + /* peer addresses in various formats */ + unsigned char eui64_addr[EUI64_ADDR_LEN]; + struct in6_addr peer_addr; +}; + +struct lowpan_dev { + struct list_head list; + + struct hci_dev *hdev; + struct net_device *netdev; + struct list_head peers; + atomic_t peer_count; /* number of items in peers list */ + + struct work_struct delete_netdev; + struct delayed_work notify_peers; +}; + +static inline struct lowpan_dev *lowpan_dev(const struct net_device *netdev) +{ + return netdev_priv(netdev); +} + +static inline void peer_add(struct lowpan_dev *dev, struct lowpan_peer *peer) +{ + list_add(&peer->list, &dev->peers); + atomic_inc(&dev->peer_count); +} + +static inline bool peer_del(struct lowpan_dev *dev, struct lowpan_peer *peer) +{ + list_del(&peer->list); + + if (atomic_dec_and_test(&dev->peer_count)) { + BT_DBG("last peer"); + return true; + } + + return false; +} + +static inline struct lowpan_peer *peer_lookup_ba(struct lowpan_dev *dev, + bdaddr_t *ba, __u8 type) +{ + struct lowpan_peer *peer, *tmp; + + BT_DBG("peers %d addr %pMR type %d", atomic_read(&dev->peer_count), + ba, type); + + list_for_each_entry_safe(peer, tmp, &dev->peers, list) { + BT_DBG("addr %pMR type %d", + &peer->conn->hcon->dst, peer->conn->hcon->dst_type); + + if (bacmp(&peer->conn->hcon->dst, ba)) + continue; + + if (type == peer->conn->hcon->dst_type) + return peer; + } + + return NULL; +} + +static inline struct lowpan_peer *peer_lookup_conn(struct lowpan_dev *dev, + struct l2cap_conn *conn) +{ + struct lowpan_peer *peer, *tmp; + + list_for_each_entry_safe(peer, tmp, &dev->peers, list) { + if (peer->conn == conn) + return peer; + } + + return NULL; +} + +static struct lowpan_peer *lookup_peer(struct l2cap_conn *conn) +{ + struct lowpan_dev *entry, *tmp; + struct lowpan_peer *peer = NULL; + unsigned long flags; + + read_lock_irqsave(&devices_lock, flags); + + list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) { + peer = peer_lookup_conn(entry, conn); + if (peer) + break; + } + + read_unlock_irqrestore(&devices_lock, flags); + + return peer; +} + +static struct lowpan_dev *lookup_dev(struct l2cap_conn *conn) +{ + struct lowpan_dev *entry, *tmp; + struct lowpan_dev *dev = NULL; + unsigned long flags; + + read_lock_irqsave(&devices_lock, flags); + + list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) { + if (conn->hcon->hdev == entry->hdev) { + dev = entry; + break; + } + } + + read_unlock_irqrestore(&devices_lock, flags); + + return dev; +} + +static int give_skb_to_upper(struct sk_buff *skb, struct net_device *dev) +{ + struct sk_buff *skb_cp; + int ret; + + skb_cp = skb_copy(skb, GFP_ATOMIC); + if (!skb_cp) + return -ENOMEM; + + ret = netif_rx(skb_cp); + + BT_DBG("receive skb %d", ret); + if (ret < 0) + return NET_RX_DROP; + + return ret; +} + +static int process_data(struct sk_buff *skb, struct net_device *netdev, + struct l2cap_conn *conn) +{ + const u8 *saddr, *daddr; + u8 iphc0, iphc1; + struct lowpan_dev *dev; + struct lowpan_peer *peer; + unsigned long flags; + + dev = lowpan_dev(netdev); + + read_lock_irqsave(&devices_lock, flags); + peer = peer_lookup_conn(dev, conn); + read_unlock_irqrestore(&devices_lock, flags); + if (!peer) + goto drop; + + saddr = peer->eui64_addr; + daddr = dev->netdev->dev_addr; + + /* at least two bytes will be used for the encoding */ + if (skb->len < 2) + goto drop; + + if (lowpan_fetch_skb_u8(skb, &iphc0)) + goto drop; + + if (lowpan_fetch_skb_u8(skb, &iphc1)) + goto drop; + + return lowpan_process_data(skb, netdev, + saddr, IEEE802154_ADDR_LONG, EUI64_ADDR_LEN, + daddr, IEEE802154_ADDR_LONG, EUI64_ADDR_LEN, + iphc0, iphc1, give_skb_to_upper); + +drop: + kfree_skb(skb); + return -EINVAL; +} + +static int recv_pkt(struct sk_buff *skb, struct net_device *dev, + struct l2cap_conn *conn) +{ + struct sk_buff *local_skb; + int ret; + + if (!netif_running(dev)) + goto drop; + + if (dev->type != ARPHRD_6LOWPAN) + goto drop; + + /* check that it's our buffer */ + if (skb->data[0] == LOWPAN_DISPATCH_IPV6) { + /* Copy the packet so that the IPv6 header is + * properly aligned. + */ + local_skb = skb_copy_expand(skb, NET_SKB_PAD - 1, + skb_tailroom(skb), GFP_ATOMIC); + if (!local_skb) + goto drop; + + local_skb->protocol = htons(ETH_P_IPV6); + local_skb->pkt_type = PACKET_HOST; + + skb_reset_network_header(local_skb); + skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); + + if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) { + kfree_skb(local_skb); + goto drop; + } + + dev->stats.rx_bytes += skb->len; + dev->stats.rx_packets++; + + kfree_skb(local_skb); + kfree_skb(skb); + } else { + switch (skb->data[0] & 0xe0) { + case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ + local_skb = skb_clone(skb, GFP_ATOMIC); + if (!local_skb) + goto drop; + + ret = process_data(local_skb, dev, conn); + if (ret != NET_RX_SUCCESS) + goto drop; + + dev->stats.rx_bytes += skb->len; + dev->stats.rx_packets++; + + kfree_skb(skb); + break; + default: + break; + } + } + + return NET_RX_SUCCESS; + +drop: + kfree_skb(skb); + return NET_RX_DROP; +} + +/* Packet from BT LE device */ +int bt_6lowpan_recv(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct lowpan_dev *dev; + struct lowpan_peer *peer; + int err; + + peer = lookup_peer(conn); + if (!peer) + return -ENOENT; + + dev = lookup_dev(conn); + if (!dev || !dev->netdev) + return -ENOENT; + + err = recv_pkt(skb, dev->netdev, conn); + BT_DBG("recv pkt %d", err); + + return err; +} + +static inline int skbuff_copy(void *msg, int len, int count, int mtu, + struct sk_buff *skb, struct net_device *dev) +{ + struct sk_buff **frag; + int sent = 0; + + memcpy(skb_put(skb, count), msg, count); + + sent += count; + msg += count; + len -= count; + + dev->stats.tx_bytes += count; + dev->stats.tx_packets++; + + raw_dump_table(__func__, "Sending", skb->data, skb->len); + + /* Continuation fragments (no L2CAP header) */ + frag = &skb_shinfo(skb)->frag_list; + while (len > 0) { + struct sk_buff *tmp; + + count = min_t(unsigned int, mtu, len); + + tmp = bt_skb_alloc(count, GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + + *frag = tmp; + + memcpy(skb_put(*frag, count), msg, count); + + raw_dump_table(__func__, "Sending fragment", + (*frag)->data, count); + + (*frag)->priority = skb->priority; + + sent += count; + msg += count; + len -= count; + + skb->len += (*frag)->len; + skb->data_len += (*frag)->len; + + frag = &(*frag)->next; + + dev->stats.tx_bytes += count; + dev->stats.tx_packets++; + } + + return sent; +} + +static struct sk_buff *create_pdu(struct l2cap_conn *conn, void *msg, + size_t len, u32 priority, + struct net_device *dev) +{ + struct sk_buff *skb; + int err, count; + struct l2cap_hdr *lh; + + /* FIXME: This mtu check should be not needed and atm is only used for + * testing purposes + */ + if (conn->mtu > (L2CAP_LE_MIN_MTU + L2CAP_HDR_SIZE)) + conn->mtu = L2CAP_LE_MIN_MTU + L2CAP_HDR_SIZE; + + count = min_t(unsigned int, (conn->mtu - L2CAP_HDR_SIZE), len); + + BT_DBG("conn %p len %zu mtu %d count %d", conn, len, conn->mtu, count); + + skb = bt_skb_alloc(count + L2CAP_HDR_SIZE, GFP_ATOMIC); + if (!skb) + return ERR_PTR(-ENOMEM); + + skb->priority = priority; + + lh = (struct l2cap_hdr *)skb_put(skb, L2CAP_HDR_SIZE); + lh->cid = cpu_to_le16(L2CAP_FC_6LOWPAN); + lh->len = cpu_to_le16(len); + + err = skbuff_copy(msg, len, count, conn->mtu, skb, dev); + if (unlikely(err < 0)) { + kfree_skb(skb); + BT_DBG("skbuff copy %d failed", err); + return ERR_PTR(err); + } + + return skb; +} + +static int conn_send(struct l2cap_conn *conn, + void *msg, size_t len, u32 priority, + struct net_device *dev) +{ + struct sk_buff *skb; + + skb = create_pdu(conn, msg, len, priority, dev); + if (IS_ERR(skb)) + return -EINVAL; + + BT_DBG("conn %p skb %p len %d priority %u", conn, skb, skb->len, + skb->priority); + + hci_send_acl(conn->hchan, skb, ACL_START); + + return 0; +} + +static void get_dest_bdaddr(struct in6_addr *ip6_daddr, + bdaddr_t *addr, u8 *addr_type) +{ + u8 *eui64; + + eui64 = ip6_daddr->s6_addr + 8; + + addr->b[0] = eui64[7]; + addr->b[1] = eui64[6]; + addr->b[2] = eui64[5]; + addr->b[3] = eui64[2]; + addr->b[4] = eui64[1]; + addr->b[5] = eui64[0]; + + addr->b[5] ^= 2; + + /* Set universal/local bit to 0 */ + if (addr->b[5] & 1) { + addr->b[5] &= ~1; + *addr_type = ADDR_LE_DEV_PUBLIC; + } else { + *addr_type = ADDR_LE_DEV_RANDOM; + } +} + +static int header_create(struct sk_buff *skb, struct net_device *netdev, + unsigned short type, const void *_daddr, + const void *_saddr, unsigned int len) +{ + struct ipv6hdr *hdr; + struct lowpan_dev *dev; + struct lowpan_peer *peer; + bdaddr_t addr, *any = BDADDR_ANY; + u8 *saddr, *daddr = any->b; + u8 addr_type; + + if (type != ETH_P_IPV6) + return -EINVAL; + + hdr = ipv6_hdr(skb); + + dev = lowpan_dev(netdev); + + if (ipv6_addr_is_multicast(&hdr->daddr)) { + memcpy(&lowpan_cb(skb)->addr, &hdr->daddr, + sizeof(struct in6_addr)); + lowpan_cb(skb)->conn = NULL; + } else { + unsigned long flags; + + /* Get destination BT device from skb. + * If there is no such peer then discard the packet. + */ + get_dest_bdaddr(&hdr->daddr, &addr, &addr_type); + + BT_DBG("dest addr %pMR type %d", &addr, addr_type); + + read_lock_irqsave(&devices_lock, flags); + peer = peer_lookup_ba(dev, &addr, addr_type); + read_unlock_irqrestore(&devices_lock, flags); + + if (!peer) { + BT_DBG("no such peer %pMR found", &addr); + return -ENOENT; + } + + daddr = peer->eui64_addr; + + memcpy(&lowpan_cb(skb)->addr, &hdr->daddr, + sizeof(struct in6_addr)); + lowpan_cb(skb)->conn = peer->conn; + } + + saddr = dev->netdev->dev_addr; + + return lowpan_header_compress(skb, netdev, type, daddr, saddr, len); +} + +/* Packet to BT LE device */ +static int send_pkt(struct l2cap_conn *conn, const void *saddr, + const void *daddr, struct sk_buff *skb, + struct net_device *netdev) +{ + raw_dump_table(__func__, "raw skb data dump before fragmentation", + skb->data, skb->len); + + return conn_send(conn, skb->data, skb->len, 0, netdev); +} + +static void send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev) +{ + struct sk_buff *local_skb; + struct lowpan_dev *entry, *tmp; + unsigned long flags; + + read_lock_irqsave(&devices_lock, flags); + + list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) { + struct lowpan_peer *pentry, *ptmp; + struct lowpan_dev *dev; + + if (entry->netdev != netdev) + continue; + + dev = lowpan_dev(entry->netdev); + + list_for_each_entry_safe(pentry, ptmp, &dev->peers, list) { + local_skb = skb_clone(skb, GFP_ATOMIC); + + send_pkt(pentry->conn, netdev->dev_addr, + pentry->eui64_addr, local_skb, netdev); + + kfree_skb(local_skb); + } + } + + read_unlock_irqrestore(&devices_lock, flags); +} + +static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + int err = 0; + unsigned char *eui64_addr; + struct lowpan_dev *dev; + struct lowpan_peer *peer; + bdaddr_t addr; + u8 addr_type; + + if (ipv6_addr_is_multicast(&lowpan_cb(skb)->addr)) { + /* We need to send the packet to every device + * behind this interface. + */ + send_mcast_pkt(skb, netdev); + } else { + unsigned long flags; + + get_dest_bdaddr(&lowpan_cb(skb)->addr, &addr, &addr_type); + eui64_addr = lowpan_cb(skb)->addr.s6_addr + 8; + dev = lowpan_dev(netdev); + + read_lock_irqsave(&devices_lock, flags); + peer = peer_lookup_ba(dev, &addr, addr_type); + read_unlock_irqrestore(&devices_lock, flags); + + BT_DBG("xmit from %s to %pMR (%pI6c) peer %p", netdev->name, + &addr, &lowpan_cb(skb)->addr, peer); + + if (peer && peer->conn) + err = send_pkt(peer->conn, netdev->dev_addr, + eui64_addr, skb, netdev); + } + dev_kfree_skb(skb); + + if (err) + BT_DBG("ERROR: xmit failed (%d)", err); + + return (err < 0) ? NET_XMIT_DROP : err; +} + +static const struct net_device_ops netdev_ops = { + .ndo_start_xmit = bt_xmit, +}; + +static struct header_ops header_ops = { + .create = header_create, +}; + +static void netdev_setup(struct net_device *dev) +{ + dev->addr_len = EUI64_ADDR_LEN; + dev->type = ARPHRD_6LOWPAN; + + dev->hard_header_len = 0; + dev->needed_tailroom = 0; + dev->mtu = IPV6_MIN_MTU; + dev->tx_queue_len = 0; + dev->flags = IFF_RUNNING | IFF_POINTOPOINT; + dev->watchdog_timeo = 0; + + dev->netdev_ops = &netdev_ops; + dev->header_ops = &header_ops; + dev->destructor = free_netdev; +} + +static struct device_type bt_type = { + .name = "bluetooth", +}; + +static void set_addr(u8 *eui, u8 *addr, u8 addr_type) +{ + /* addr is the BT address in little-endian format */ + eui[0] = addr[5]; + eui[1] = addr[4]; + eui[2] = addr[3]; + eui[3] = 0xFF; + eui[4] = 0xFE; + eui[5] = addr[2]; + eui[6] = addr[1]; + eui[7] = addr[0]; + + eui[0] ^= 2; + + /* Universal/local bit set, RFC 4291 */ + if (addr_type == ADDR_LE_DEV_PUBLIC) + eui[0] |= 1; + else + eui[0] &= ~1; +} + +static void set_dev_addr(struct net_device *netdev, bdaddr_t *addr, + u8 addr_type) +{ + netdev->addr_assign_type = NET_ADDR_PERM; + set_addr(netdev->dev_addr, addr->b, addr_type); + netdev->dev_addr[0] ^= 2; +} + +static void ifup(struct net_device *netdev) +{ + int err; + + rtnl_lock(); + err = dev_open(netdev); + if (err < 0) + BT_INFO("iface %s cannot be opened (%d)", netdev->name, err); + rtnl_unlock(); +} + +static void do_notify_peers(struct work_struct *work) +{ + struct lowpan_dev *dev = container_of(work, struct lowpan_dev, + notify_peers.work); + + netdev_notify_peers(dev->netdev); /* send neighbour adv at startup */ +} + +static bool is_bt_6lowpan(struct hci_conn *hcon) +{ + if (hcon->type != LE_LINK) + return false; + + return test_bit(HCI_CONN_6LOWPAN, &hcon->flags); +} + +static int add_peer_conn(struct l2cap_conn *conn, struct lowpan_dev *dev) +{ + struct lowpan_peer *peer; + unsigned long flags; + + peer = kzalloc(sizeof(*peer), GFP_ATOMIC); + if (!peer) + return -ENOMEM; + + peer->conn = conn; + memset(&peer->peer_addr, 0, sizeof(struct in6_addr)); + + /* RFC 2464 ch. 5 */ + peer->peer_addr.s6_addr[0] = 0xFE; + peer->peer_addr.s6_addr[1] = 0x80; + set_addr((u8 *)&peer->peer_addr.s6_addr + 8, conn->hcon->dst.b, + conn->hcon->dst_type); + + memcpy(&peer->eui64_addr, (u8 *)&peer->peer_addr.s6_addr + 8, + EUI64_ADDR_LEN); + peer->eui64_addr[0] ^= 2; /* second bit-flip (Universe/Local) + * is done according RFC2464 + */ + + raw_dump_inline(__func__, "peer IPv6 address", + (unsigned char *)&peer->peer_addr, 16); + raw_dump_inline(__func__, "peer EUI64 address", peer->eui64_addr, 8); + + write_lock_irqsave(&devices_lock, flags); + INIT_LIST_HEAD(&peer->list); + peer_add(dev, peer); + write_unlock_irqrestore(&devices_lock, flags); + + /* Notifying peers about us needs to be done without locks held */ + INIT_DELAYED_WORK(&dev->notify_peers, do_notify_peers); + schedule_delayed_work(&dev->notify_peers, msecs_to_jiffies(100)); + + return 0; +} + +/* This gets called when BT LE 6LoWPAN device is connected. We then + * create network device that acts as a proxy between BT LE device + * and kernel network stack. + */ +int bt_6lowpan_add_conn(struct l2cap_conn *conn) +{ + struct lowpan_peer *peer = NULL; + struct lowpan_dev *dev; + struct net_device *netdev; + int err = 0; + unsigned long flags; + + if (!is_bt_6lowpan(conn->hcon)) + return 0; + + peer = lookup_peer(conn); + if (peer) + return -EEXIST; + + dev = lookup_dev(conn); + if (dev) + return add_peer_conn(conn, dev); + + netdev = alloc_netdev(sizeof(*dev), IFACE_NAME_TEMPLATE, netdev_setup); + if (!netdev) + return -ENOMEM; + + set_dev_addr(netdev, &conn->hcon->src, conn->hcon->src_type); + + netdev->netdev_ops = &netdev_ops; + SET_NETDEV_DEV(netdev, &conn->hcon->dev); + SET_NETDEV_DEVTYPE(netdev, &bt_type); + + err = register_netdev(netdev); + if (err < 0) { + BT_INFO("register_netdev failed %d", err); + free_netdev(netdev); + goto out; + } + + BT_DBG("ifindex %d peer bdaddr %pMR my addr %pMR", + netdev->ifindex, &conn->hcon->dst, &conn->hcon->src); + set_bit(__LINK_STATE_PRESENT, &netdev->state); + + dev = netdev_priv(netdev); + dev->netdev = netdev; + dev->hdev = conn->hcon->hdev; + INIT_LIST_HEAD(&dev->peers); + + write_lock_irqsave(&devices_lock, flags); + INIT_LIST_HEAD(&dev->list); + list_add(&dev->list, &bt_6lowpan_devices); + write_unlock_irqrestore(&devices_lock, flags); + + ifup(netdev); + + return add_peer_conn(conn, dev); + +out: + return err; +} + +static void delete_netdev(struct work_struct *work) +{ + struct lowpan_dev *entry = container_of(work, struct lowpan_dev, + delete_netdev); + + unregister_netdev(entry->netdev); + + /* The entry pointer is deleted in device_event() */ +} + +int bt_6lowpan_del_conn(struct l2cap_conn *conn) +{ + struct lowpan_dev *entry, *tmp; + struct lowpan_dev *dev = NULL; + struct lowpan_peer *peer; + int err = -ENOENT; + unsigned long flags; + bool last = false; + + if (!conn || !is_bt_6lowpan(conn->hcon)) + return 0; + + write_lock_irqsave(&devices_lock, flags); + + list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) { + dev = lowpan_dev(entry->netdev); + peer = peer_lookup_conn(dev, conn); + if (peer) { + last = peer_del(dev, peer); + err = 0; + break; + } + } + + if (!err && last && dev && !atomic_read(&dev->peer_count)) { + write_unlock_irqrestore(&devices_lock, flags); + + cancel_delayed_work_sync(&dev->notify_peers); + + /* bt_6lowpan_del_conn() is called with hci dev lock held which + * means that we must delete the netdevice in worker thread. + */ + INIT_WORK(&entry->delete_netdev, delete_netdev); + schedule_work(&entry->delete_netdev); + } else { + write_unlock_irqrestore(&devices_lock, flags); + } + + return err; +} + +static int device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct lowpan_dev *entry, *tmp; + unsigned long flags; + + if (netdev->type != ARPHRD_6LOWPAN) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_UNREGISTER: + write_lock_irqsave(&devices_lock, flags); + list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, + list) { + if (entry->netdev == netdev) { + list_del(&entry->list); + kfree(entry); + break; + } + } + write_unlock_irqrestore(&devices_lock, flags); + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block bt_6lowpan_dev_notifier = { + .notifier_call = device_event, +}; + +int bt_6lowpan_init(void) +{ + return register_netdevice_notifier(&bt_6lowpan_dev_notifier); +} + +void bt_6lowpan_cleanup(void) +{ + unregister_netdevice_notifier(&bt_6lowpan_dev_notifier); +} diff --git a/net/bluetooth/6lowpan.h b/net/bluetooth/6lowpan.h new file mode 100644 index 000000000000..680eac808d74 --- /dev/null +++ b/net/bluetooth/6lowpan.h @@ -0,0 +1,26 @@ +/* + Copyright (c) 2013 Intel Corp. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License version 2 and + only version 2 as published by the Free Software Foundation. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. +*/ + +#ifndef __6LOWPAN_H +#define __6LOWPAN_H + +#include <linux/skbuff.h> +#include <net/bluetooth/l2cap.h> + +int bt_6lowpan_recv(struct l2cap_conn *conn, struct sk_buff *skb); +int bt_6lowpan_add_conn(struct l2cap_conn *conn); +int bt_6lowpan_del_conn(struct l2cap_conn *conn); +int bt_6lowpan_init(void); +void bt_6lowpan_cleanup(void); + +#endif /* __6LOWPAN_H */ diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index d3f3f7b1d32c..985b56070d26 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -12,6 +12,7 @@ menuconfig BT select CRYPTO_AES select CRYPTO_ECB select CRYPTO_SHA256 + select 6LOWPAN_IPHC help Bluetooth is low-cost, low-power, short-range wireless technology. It was designed as a replacement for cables and other short-range diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 6a791e73e39d..80cb215826e8 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -10,6 +10,6 @@ obj-$(CONFIG_BT_HIDP) += hidp/ bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \ hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o sco.o lib.o \ - a2mp.o amp.o + a2mp.o amp.o 6lowpan.o subdir-ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 56ca494621c6..0c5866bb49b6 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -31,7 +31,7 @@ #include <net/bluetooth/bluetooth.h> #include <linux/proc_fs.h> -#define VERSION "2.17" +#define VERSION "2.18" /* Bluetooth sockets */ #define BT_MAX_PROTO 8 diff --git a/net/bluetooth/bnep/bnep.h b/net/bluetooth/bnep/bnep.h index e7ee5314f39a..5a5b16f365e9 100644 --- a/net/bluetooth/bnep/bnep.h +++ b/net/bluetooth/bnep/bnep.h @@ -12,8 +12,7 @@ GNU General Public License for more details. You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _BNEP_H diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 6ccc4eb9e55e..5e8663c194c1 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -636,6 +636,49 @@ static int conn_max_interval_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(conn_max_interval_fops, conn_max_interval_get, conn_max_interval_set, "%llu\n"); +static ssize_t lowpan_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[3]; + + buf[0] = test_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags) ? 'Y' : 'N'; + buf[1] = '\n'; + buf[2] = '\0'; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t lowpan_write(struct file *fp, const char __user *user_buffer, + size_t count, loff_t *position) +{ + struct hci_dev *hdev = fp->private_data; + bool enable; + char buf[32]; + size_t buf_size = min(count, (sizeof(buf)-1)); + + if (copy_from_user(buf, user_buffer, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + + if (strtobool(buf, &enable) < 0) + return -EINVAL; + + if (enable == test_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags)) + return -EALREADY; + + change_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags); + + return count; +} + +static const struct file_operations lowpan_debugfs_fops = { + .open = simple_open, + .read = lowpan_read, + .write = lowpan_write, + .llseek = default_llseek, +}; + /* ---- HCI requests ---- */ static void hci_req_sync_complete(struct hci_dev *hdev, u8 result) @@ -1228,7 +1271,7 @@ static void hci_set_event_mask_page_2(struct hci_request *req) /* If Connectionless Slave Broadcast master role is supported * enable all necessary events for it. */ - if (hdev->features[2][0] & 0x01) { + if (lmp_csb_master_capable(hdev)) { events[1] |= 0x40; /* Triggered Clock Capture */ events[1] |= 0x80; /* Synchronization Train Complete */ events[2] |= 0x10; /* Slave Page Response Timeout */ @@ -1238,7 +1281,7 @@ static void hci_set_event_mask_page_2(struct hci_request *req) /* If Connectionless Slave Broadcast slave role is supported * enable all necessary events for it. */ - if (hdev->features[2][0] & 0x02) { + if (lmp_csb_slave_capable(hdev)) { events[2] |= 0x01; /* Synchronization Train Received */ events[2] |= 0x02; /* CSB Receive */ events[2] |= 0x04; /* CSB Timeout */ @@ -1261,8 +1304,13 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt) * as supported send it. If not supported assume that the controller * does not have actual support for stored link keys which makes this * command redundant anyway. + * + * Some controllers indicate that they support handling deleting + * stored link keys, but they don't. The quirk lets a driver + * just disable this command. */ - if (hdev->commands[6] & 0x80) { + if (hdev->commands[6] & 0x80 && + !test_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks)) { struct hci_cp_delete_stored_link_key cp; bacpy(&cp.bdaddr, BDADDR_ANY); @@ -1275,15 +1323,17 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt) hci_setup_link_policy(req); if (lmp_le_capable(hdev)) { - /* If the controller has a public BD_ADDR, then by - * default use that one. If this is a LE only - * controller without one, default to the random - * address. - */ - if (bacmp(&hdev->bdaddr, BDADDR_ANY)) - hdev->own_addr_type = ADDR_LE_DEV_PUBLIC; - else - hdev->own_addr_type = ADDR_LE_DEV_RANDOM; + if (test_bit(HCI_SETUP, &hdev->dev_flags)) { + /* If the controller has a public BD_ADDR, then + * by default use that one. If this is a LE only + * controller without a public address, default + * to the random address. + */ + if (bacmp(&hdev->bdaddr, BDADDR_ANY)) + hdev->own_addr_type = ADDR_LE_DEV_PUBLIC; + else + hdev->own_addr_type = ADDR_LE_DEV_RANDOM; + } hci_set_le_support(req); } @@ -1307,7 +1357,7 @@ static void hci_init4_req(struct hci_request *req, unsigned long opt) hci_set_event_mask_page_2(req); /* Check for Synchronization Train support */ - if (hdev->features[2][0] & 0x04) + if (lmp_sync_train_capable(hdev)) hci_req_add(req, HCI_OP_READ_SYNC_TRAIN_PARAMS, 0, NULL); } @@ -1404,6 +1454,8 @@ static int __hci_init(struct hci_dev *hdev) hdev, &conn_min_interval_fops); debugfs_create_file("conn_max_interval", 0644, hdev->debugfs, hdev, &conn_max_interval_fops); + debugfs_create_file("6lowpan", 0644, hdev->debugfs, hdev, + &lowpan_debugfs_fops); } return 0; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 5935f748c0f9..5f812455a450 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -486,7 +486,10 @@ static void hci_cc_read_local_commands(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - if (!rp->status) + if (rp->status) + return; + + if (test_bit(HCI_SETUP, &hdev->dev_flags)) memcpy(hdev->commands, rp->commands, sizeof(hdev->commands)); } @@ -538,12 +541,6 @@ static void hci_cc_read_local_features(struct hci_dev *hdev, if (hdev->features[0][5] & LMP_EDR_3S_ESCO) hdev->esco_type |= (ESCO_2EV5 | ESCO_3EV5); - - BT_DBG("%s features 0x%.2x%.2x%.2x%.2x%.2x%.2x%.2x%.2x", hdev->name, - hdev->features[0][0], hdev->features[0][1], - hdev->features[0][2], hdev->features[0][3], - hdev->features[0][4], hdev->features[0][5], - hdev->features[0][6], hdev->features[0][7]); } static void hci_cc_read_local_ext_features(struct hci_dev *hdev, @@ -1782,7 +1779,9 @@ static u8 hci_to_mgmt_reason(u8 err) static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_disconn_complete *ev = (void *) skb->data; + u8 reason = hci_to_mgmt_reason(ev->reason); struct hci_conn *conn; + u8 type; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); @@ -1792,43 +1791,38 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (!conn) goto unlock; - if (ev->status == 0) - conn->state = BT_CLOSED; + if (ev->status) { + mgmt_disconnect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, ev->status); + goto unlock; + } - if (test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags) && - (conn->type == ACL_LINK || conn->type == LE_LINK)) { - if (ev->status) { - mgmt_disconnect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, ev->status); - } else { - u8 reason = hci_to_mgmt_reason(ev->reason); + conn->state = BT_CLOSED; - mgmt_device_disconnected(hdev, &conn->dst, conn->type, - conn->dst_type, reason); - } - } + if (test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + mgmt_device_disconnected(hdev, &conn->dst, conn->type, + conn->dst_type, reason); - if (ev->status == 0) { - u8 type = conn->type; + if (conn->type == ACL_LINK && conn->flush_key) + hci_remove_link_key(hdev, &conn->dst); - if (type == ACL_LINK && conn->flush_key) - hci_remove_link_key(hdev, &conn->dst); - hci_proto_disconn_cfm(conn, ev->reason); - hci_conn_del(conn); + type = conn->type; - /* Re-enable advertising if necessary, since it might - * have been disabled by the connection. From the - * HCI_LE_Set_Advertise_Enable command description in - * the core specification (v4.0): - * "The Controller shall continue advertising until the Host - * issues an LE_Set_Advertise_Enable command with - * Advertising_Enable set to 0x00 (Advertising is disabled) - * or until a connection is created or until the Advertising - * is timed out due to Directed Advertising." - */ - if (type == LE_LINK) - mgmt_reenable_advertising(hdev); - } + hci_proto_disconn_cfm(conn, ev->reason); + hci_conn_del(conn); + + /* Re-enable advertising if necessary, since it might + * have been disabled by the connection. From the + * HCI_LE_Set_Advertise_Enable command description in + * the core specification (v4.0): + * "The Controller shall continue advertising until the Host + * issues an LE_Set_Advertise_Enable command with + * Advertising_Enable set to 0x00 (Advertising is disabled) + * or until a connection is created or until the Advertising + * is timed out due to Directed Advertising." + */ + if (type == LE_LINK) + mgmt_reenable_advertising(hdev); unlock: hci_dev_unlock(hdev); @@ -3539,6 +3533,9 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->handle = __le16_to_cpu(ev->handle); conn->state = BT_CONNECTED; + if (test_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags)) + set_bit(HCI_CONN_6LOWPAN, &conn->flags); + hci_conn_add_sysfs(conn); hci_proto_connect_cfm(conn, ev->status); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 4af3821df880..b0ad2c752d73 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -40,6 +40,7 @@ #include "smp.h" #include "a2mp.h" #include "amp.h" +#include "6lowpan.h" bool disable_ertm; @@ -49,6 +50,9 @@ static u8 l2cap_fixed_chan[8] = { L2CAP_FC_L2CAP | L2CAP_FC_CONNLESS, }; static LIST_HEAD(chan_list); static DEFINE_RWLOCK(chan_list_lock); +static u16 le_max_credits = L2CAP_LE_MAX_CREDITS; +static u16 le_default_mps = L2CAP_LE_DEFAULT_MPS; + static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, u8 code, u8 ident, u16 dlen, void *data); static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, @@ -213,9 +217,14 @@ int l2cap_add_scid(struct l2cap_chan *chan, __u16 scid) static u16 l2cap_alloc_cid(struct l2cap_conn *conn) { - u16 cid = L2CAP_CID_DYN_START; + u16 cid, dyn_end; + + if (conn->hcon->type == LE_LINK) + dyn_end = L2CAP_CID_LE_DYN_END; + else + dyn_end = L2CAP_CID_DYN_END; - for (; cid < L2CAP_CID_DYN_END; cid++) { + for (cid = L2CAP_CID_DYN_START; cid < dyn_end; cid++) { if (!__l2cap_get_chan_by_scid(conn, cid)) return cid; } @@ -490,6 +499,18 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan) set_bit(FLAG_FORCE_ACTIVE, &chan->flags); } +static void l2cap_le_flowctl_init(struct l2cap_chan *chan) +{ + chan->sdu = NULL; + chan->sdu_last_frag = NULL; + chan->sdu_len = 0; + chan->tx_credits = 0; + chan->rx_credits = le_max_credits; + chan->mps = min_t(u16, chan->imtu, L2CAP_LE_DEFAULT_MPS); + + skb_queue_head_init(&chan->tx_q); +} + void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) { BT_DBG("conn %p, psm 0x%2.2x, dcid 0x%4.4x", conn, @@ -502,12 +523,12 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) switch (chan->chan_type) { case L2CAP_CHAN_CONN_ORIENTED: if (conn->hcon->type == LE_LINK) { - /* LE connection */ - chan->omtu = L2CAP_DEFAULT_MTU; - if (chan->dcid == L2CAP_CID_ATT) + if (chan->dcid == L2CAP_CID_ATT) { + chan->omtu = L2CAP_DEFAULT_MTU; chan->scid = L2CAP_CID_ATT; - else + } else { chan->scid = l2cap_alloc_cid(conn); + } } else { /* Alloc CID for connection-oriented socket */ chan->scid = l2cap_alloc_cid(conn); @@ -597,6 +618,10 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) case L2CAP_MODE_BASIC: break; + case L2CAP_MODE_LE_FLOWCTL: + skb_queue_purge(&chan->tx_q); + break; + case L2CAP_MODE_ERTM: __clear_retrans_timer(chan); __clear_monitor_timer(chan); @@ -617,6 +642,50 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) return; } +static void l2cap_chan_le_connect_reject(struct l2cap_chan *chan) +{ + struct l2cap_conn *conn = chan->conn; + struct l2cap_le_conn_rsp rsp; + u16 result; + + if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) + result = L2CAP_CR_AUTHORIZATION; + else + result = L2CAP_CR_BAD_PSM; + + l2cap_state_change(chan, BT_DISCONN); + + rsp.dcid = cpu_to_le16(chan->scid); + rsp.mtu = cpu_to_le16(chan->imtu); + rsp.mps = cpu_to_le16(chan->mps); + rsp.credits = cpu_to_le16(chan->rx_credits); + rsp.result = cpu_to_le16(result); + + l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CONN_RSP, sizeof(rsp), + &rsp); +} + +static void l2cap_chan_connect_reject(struct l2cap_chan *chan) +{ + struct l2cap_conn *conn = chan->conn; + struct l2cap_conn_rsp rsp; + u16 result; + + if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) + result = L2CAP_CR_SEC_BLOCK; + else + result = L2CAP_CR_BAD_PSM; + + l2cap_state_change(chan, BT_DISCONN); + + rsp.scid = cpu_to_le16(chan->dcid); + rsp.dcid = cpu_to_le16(chan->scid); + rsp.result = cpu_to_le16(result); + rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); + + l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp); +} + void l2cap_chan_close(struct l2cap_chan *chan, int reason) { struct l2cap_conn *conn = chan->conn; @@ -630,8 +699,10 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) case BT_CONNECTED: case BT_CONFIG: - if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && - conn->hcon->type == ACL_LINK) { + /* ATT uses L2CAP_CHAN_CONN_ORIENTED so we must also + * check for chan->psm. + */ + if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && chan->psm) { __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); l2cap_send_disconn_req(chan, reason); } else @@ -639,24 +710,11 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) break; case BT_CONNECT2: - if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && - conn->hcon->type == ACL_LINK) { - struct l2cap_conn_rsp rsp; - __u16 result; - - if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) - result = L2CAP_CR_SEC_BLOCK; - else - result = L2CAP_CR_BAD_PSM; - - l2cap_state_change(chan, BT_DISCONN); - - rsp.scid = cpu_to_le16(chan->dcid); - rsp.dcid = cpu_to_le16(chan->scid); - rsp.result = cpu_to_le16(result); - rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); - l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, - sizeof(rsp), &rsp); + if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED) { + if (conn->hcon->type == ACL_LINK) + l2cap_chan_connect_reject(chan); + else if (conn->hcon->type == LE_LINK) + l2cap_chan_le_connect_reject(chan); } l2cap_chan_del(chan, reason); @@ -726,6 +784,9 @@ int l2cap_chan_check_security(struct l2cap_chan *chan) struct l2cap_conn *conn = chan->conn; __u8 auth_type; + if (conn->hcon->type == LE_LINK) + return smp_conn_security(conn->hcon, chan->sec_level); + auth_type = l2cap_get_auth_type(chan); return hci_conn_security(conn->hcon, chan->sec_level, auth_type); @@ -1152,16 +1213,57 @@ static void l2cap_chan_ready(struct l2cap_chan *chan) chan->conf_state = 0; __clear_chan_timer(chan); + if (chan->mode == L2CAP_MODE_LE_FLOWCTL && !chan->tx_credits) + chan->ops->suspend(chan); + chan->state = BT_CONNECTED; chan->ops->ready(chan); } +static void l2cap_le_connect(struct l2cap_chan *chan) +{ + struct l2cap_conn *conn = chan->conn; + struct l2cap_le_conn_req req; + + if (test_and_set_bit(FLAG_LE_CONN_REQ_SENT, &chan->flags)) + return; + + req.psm = chan->psm; + req.scid = cpu_to_le16(chan->scid); + req.mtu = cpu_to_le16(chan->imtu); + req.mps = cpu_to_le16(chan->mps); + req.credits = cpu_to_le16(chan->rx_credits); + + chan->ident = l2cap_get_ident(conn); + + l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CONN_REQ, + sizeof(req), &req); +} + +static void l2cap_le_start(struct l2cap_chan *chan) +{ + struct l2cap_conn *conn = chan->conn; + + if (!smp_conn_security(conn->hcon, chan->sec_level)) + return; + + if (!chan->psm) { + l2cap_chan_ready(chan); + return; + } + + if (chan->state == BT_CONNECT) + l2cap_le_connect(chan); +} + static void l2cap_start_connection(struct l2cap_chan *chan) { if (__amp_capable(chan)) { BT_DBG("chan %p AMP capable: discover AMPs", chan); a2mp_discover_amp(chan); + } else if (chan->conn->hcon->type == LE_LINK) { + l2cap_le_start(chan); } else { l2cap_send_conn_req(chan); } @@ -1172,7 +1274,7 @@ static void l2cap_do_start(struct l2cap_chan *chan) struct l2cap_conn *conn = chan->conn; if (conn->hcon->type == LE_LINK) { - l2cap_chan_ready(chan); + l2cap_le_start(chan); return; } @@ -1367,6 +1469,8 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn) BT_DBG(""); + bt_6lowpan_add_conn(conn); + /* Check if we have socket listening on cid */ pchan = l2cap_global_chan_by_scid(BT_LISTEN, L2CAP_CID_ATT, &hcon->src, &hcon->dst); @@ -1430,9 +1534,7 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) } if (hcon->type == LE_LINK) { - if (smp_conn_security(hcon, chan->sec_level)) - l2cap_chan_ready(chan); - + l2cap_le_start(chan); } else if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { l2cap_chan_ready(chan); @@ -1703,7 +1805,8 @@ EXPORT_SYMBOL(l2cap_conn_put); */ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, bdaddr_t *src, - bdaddr_t *dst) + bdaddr_t *dst, + u8 link_type) { struct l2cap_chan *c, *c1 = NULL; @@ -1713,6 +1816,12 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, if (state && c->state != state) continue; + if (link_type == ACL_LINK && c->src_type != BDADDR_BREDR) + continue; + + if (link_type == LE_LINK && c->src_type == BDADDR_BREDR) + continue; + if (c->psm == psm) { int src_match, dst_match; int src_any, dst_any; @@ -1739,6 +1848,18 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, return c1; } +static bool is_valid_psm(u16 psm, u8 dst_type) +{ + if (!psm) + return false; + + if (bdaddr_type_is_le(dst_type)) + return (psm <= 0x00ff); + + /* PSM must be odd and lsb of upper byte must be 0 */ + return ((psm & 0x0101) == 0x0001); +} + int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, bdaddr_t *dst, u8 dst_type) { @@ -1759,8 +1880,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, l2cap_chan_lock(chan); - /* PSM must be odd and lsb of upper byte must be 0 */ - if ((__le16_to_cpu(psm) & 0x0101) != 0x0001 && !cid && + if (!is_valid_psm(__le16_to_cpu(psm), dst_type) && !cid && chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; goto done; @@ -1774,6 +1894,9 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, switch (chan->mode) { case L2CAP_MODE_BASIC: break; + case L2CAP_MODE_LE_FLOWCTL: + l2cap_le_flowctl_init(chan); + break; case L2CAP_MODE_ERTM: case L2CAP_MODE_STREAMING: if (!disable_ertm) @@ -2432,6 +2555,89 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, return 0; } +static struct sk_buff *l2cap_create_le_flowctl_pdu(struct l2cap_chan *chan, + struct msghdr *msg, + size_t len, u16 sdulen) +{ + struct l2cap_conn *conn = chan->conn; + struct sk_buff *skb; + int err, count, hlen; + struct l2cap_hdr *lh; + + BT_DBG("chan %p len %zu", chan, len); + + if (!conn) + return ERR_PTR(-ENOTCONN); + + hlen = L2CAP_HDR_SIZE; + + if (sdulen) + hlen += L2CAP_SDULEN_SIZE; + + count = min_t(unsigned int, (conn->mtu - hlen), len); + + skb = chan->ops->alloc_skb(chan, count + hlen, + msg->msg_flags & MSG_DONTWAIT); + if (IS_ERR(skb)) + return skb; + + /* Create L2CAP header */ + lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh->cid = cpu_to_le16(chan->dcid); + lh->len = cpu_to_le16(len + (hlen - L2CAP_HDR_SIZE)); + + if (sdulen) + put_unaligned_le16(sdulen, skb_put(skb, L2CAP_SDULEN_SIZE)); + + err = l2cap_skbuff_fromiovec(chan, msg, len, count, skb); + if (unlikely(err < 0)) { + kfree_skb(skb); + return ERR_PTR(err); + } + + return skb; +} + +static int l2cap_segment_le_sdu(struct l2cap_chan *chan, + struct sk_buff_head *seg_queue, + struct msghdr *msg, size_t len) +{ + struct sk_buff *skb; + size_t pdu_len; + u16 sdu_len; + + BT_DBG("chan %p, msg %p, len %zu", chan, msg, len); + + pdu_len = chan->conn->mtu - L2CAP_HDR_SIZE; + + pdu_len = min_t(size_t, pdu_len, chan->remote_mps); + + sdu_len = len; + pdu_len -= L2CAP_SDULEN_SIZE; + + while (len > 0) { + if (len <= pdu_len) + pdu_len = len; + + skb = l2cap_create_le_flowctl_pdu(chan, msg, pdu_len, sdu_len); + if (IS_ERR(skb)) { + __skb_queue_purge(seg_queue); + return PTR_ERR(skb); + } + + __skb_queue_tail(seg_queue, skb); + + len -= pdu_len; + + if (sdu_len) { + sdu_len = 0; + pdu_len += L2CAP_SDULEN_SIZE; + } + } + + return 0; +} + int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, u32 priority) { @@ -2453,6 +2659,40 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, } switch (chan->mode) { + case L2CAP_MODE_LE_FLOWCTL: + /* Check outgoing MTU */ + if (len > chan->omtu) + return -EMSGSIZE; + + if (!chan->tx_credits) + return -EAGAIN; + + __skb_queue_head_init(&seg_queue); + + err = l2cap_segment_le_sdu(chan, &seg_queue, msg, len); + + if (chan->state != BT_CONNECTED) { + __skb_queue_purge(&seg_queue); + err = -ENOTCONN; + } + + if (err) + return err; + + skb_queue_splice_tail_init(&seg_queue, &chan->tx_q); + + while (chan->tx_credits && !skb_queue_empty(&chan->tx_q)) { + l2cap_do_send(chan, skb_dequeue(&chan->tx_q)); + chan->tx_credits--; + } + + if (!chan->tx_credits) + chan->ops->suspend(chan); + + err = len; + + break; + case L2CAP_MODE_BASIC: /* Check outgoing MTU */ if (len > chan->omtu) @@ -3592,6 +3832,23 @@ static int l2cap_build_conf_rsp(struct l2cap_chan *chan, void *data, return ptr - data; } +void __l2cap_le_connect_rsp_defer(struct l2cap_chan *chan) +{ + struct l2cap_le_conn_rsp rsp; + struct l2cap_conn *conn = chan->conn; + + BT_DBG("chan %p", chan); + + rsp.dcid = cpu_to_le16(chan->scid); + rsp.mtu = cpu_to_le16(chan->imtu); + rsp.mps = cpu_to_le16(chan->mps); + rsp.credits = cpu_to_le16(chan->rx_credits); + rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS); + + l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CONN_RSP, sizeof(rsp), + &rsp); +} + void __l2cap_connect_rsp_defer(struct l2cap_chan *chan) { struct l2cap_conn_rsp rsp; @@ -3713,7 +3970,7 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, /* Check if we have socket listening on psm */ pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src, - &conn->hcon->dst); + &conn->hcon->dst, ACL_LINK); if (!pchan) { result = L2CAP_CR_BAD_PSM; goto sendresp; @@ -5155,18 +5412,17 @@ static inline int l2cap_check_conn_param(u16 min, u16 max, u16 latency, static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, - u8 *data) + u16 cmd_len, u8 *data) { struct hci_conn *hcon = conn->hcon; struct l2cap_conn_param_update_req *req; struct l2cap_conn_param_update_rsp rsp; - u16 min, max, latency, to_multiplier, cmd_len; + u16 min, max, latency, to_multiplier; int err; if (!(hcon->link_mode & HCI_LM_MASTER)) return -EINVAL; - cmd_len = __le16_to_cpu(cmd->len); if (cmd_len != sizeof(struct l2cap_conn_param_update_req)) return -EPROTO; @@ -5196,6 +5452,65 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, return 0; } +static int l2cap_le_connect_rsp(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u16 cmd_len, + u8 *data) +{ + struct l2cap_le_conn_rsp *rsp = (struct l2cap_le_conn_rsp *) data; + u16 dcid, mtu, mps, credits, result; + struct l2cap_chan *chan; + int err; + + if (cmd_len < sizeof(*rsp)) + return -EPROTO; + + dcid = __le16_to_cpu(rsp->dcid); + mtu = __le16_to_cpu(rsp->mtu); + mps = __le16_to_cpu(rsp->mps); + credits = __le16_to_cpu(rsp->credits); + result = __le16_to_cpu(rsp->result); + + if (result == L2CAP_CR_SUCCESS && (mtu < 23 || mps < 23)) + return -EPROTO; + + BT_DBG("dcid 0x%4.4x mtu %u mps %u credits %u result 0x%2.2x", + dcid, mtu, mps, credits, result); + + mutex_lock(&conn->chan_lock); + + chan = __l2cap_get_chan_by_ident(conn, cmd->ident); + if (!chan) { + err = -EBADSLT; + goto unlock; + } + + err = 0; + + l2cap_chan_lock(chan); + + switch (result) { + case L2CAP_CR_SUCCESS: + chan->ident = 0; + chan->dcid = dcid; + chan->omtu = mtu; + chan->remote_mps = mps; + chan->tx_credits = credits; + l2cap_chan_ready(chan); + break; + + default: + l2cap_chan_del(chan, ECONNREFUSED); + break; + } + + l2cap_chan_unlock(chan); + +unlock: + mutex_unlock(&conn->chan_lock); + + return err; +} + static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data) @@ -5276,23 +5591,235 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, return err; } +static int l2cap_le_connect_req(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u16 cmd_len, + u8 *data) +{ + struct l2cap_le_conn_req *req = (struct l2cap_le_conn_req *) data; + struct l2cap_le_conn_rsp rsp; + struct l2cap_chan *chan, *pchan; + u16 dcid, scid, credits, mtu, mps; + __le16 psm; + u8 result; + + if (cmd_len != sizeof(*req)) + return -EPROTO; + + scid = __le16_to_cpu(req->scid); + mtu = __le16_to_cpu(req->mtu); + mps = __le16_to_cpu(req->mps); + psm = req->psm; + dcid = 0; + credits = 0; + + if (mtu < 23 || mps < 23) + return -EPROTO; + + BT_DBG("psm 0x%2.2x scid 0x%4.4x mtu %u mps %u", __le16_to_cpu(psm), + scid, mtu, mps); + + /* Check if we have socket listening on psm */ + pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src, + &conn->hcon->dst, LE_LINK); + if (!pchan) { + result = L2CAP_CR_BAD_PSM; + chan = NULL; + goto response; + } + + mutex_lock(&conn->chan_lock); + l2cap_chan_lock(pchan); + + if (!smp_sufficient_security(conn->hcon, pchan->sec_level)) { + result = L2CAP_CR_AUTHENTICATION; + chan = NULL; + goto response_unlock; + } + + /* Check if we already have channel with that dcid */ + if (__l2cap_get_chan_by_dcid(conn, scid)) { + result = L2CAP_CR_NO_MEM; + chan = NULL; + goto response_unlock; + } + + chan = pchan->ops->new_connection(pchan); + if (!chan) { + result = L2CAP_CR_NO_MEM; + goto response_unlock; + } + + l2cap_le_flowctl_init(chan); + + bacpy(&chan->src, &conn->hcon->src); + bacpy(&chan->dst, &conn->hcon->dst); + chan->src_type = bdaddr_type(conn->hcon, conn->hcon->src_type); + chan->dst_type = bdaddr_type(conn->hcon, conn->hcon->dst_type); + chan->psm = psm; + chan->dcid = scid; + chan->omtu = mtu; + chan->remote_mps = mps; + chan->tx_credits = __le16_to_cpu(req->credits); + + __l2cap_chan_add(conn, chan); + dcid = chan->scid; + credits = chan->rx_credits; + + __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); + + chan->ident = cmd->ident; + + if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { + l2cap_state_change(chan, BT_CONNECT2); + result = L2CAP_CR_PEND; + chan->ops->defer(chan); + } else { + l2cap_chan_ready(chan); + result = L2CAP_CR_SUCCESS; + } + +response_unlock: + l2cap_chan_unlock(pchan); + mutex_unlock(&conn->chan_lock); + + if (result == L2CAP_CR_PEND) + return 0; + +response: + if (chan) { + rsp.mtu = cpu_to_le16(chan->imtu); + rsp.mps = cpu_to_le16(chan->mps); + } else { + rsp.mtu = 0; + rsp.mps = 0; + } + + rsp.dcid = cpu_to_le16(dcid); + rsp.credits = cpu_to_le16(credits); + rsp.result = cpu_to_le16(result); + + l2cap_send_cmd(conn, cmd->ident, L2CAP_LE_CONN_RSP, sizeof(rsp), &rsp); + + return 0; +} + +static inline int l2cap_le_credits(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u16 cmd_len, + u8 *data) +{ + struct l2cap_le_credits *pkt; + struct l2cap_chan *chan; + u16 cid, credits; + + if (cmd_len != sizeof(*pkt)) + return -EPROTO; + + pkt = (struct l2cap_le_credits *) data; + cid = __le16_to_cpu(pkt->cid); + credits = __le16_to_cpu(pkt->credits); + + BT_DBG("cid 0x%4.4x credits 0x%4.4x", cid, credits); + + chan = l2cap_get_chan_by_dcid(conn, cid); + if (!chan) + return -EBADSLT; + + chan->tx_credits += credits; + + while (chan->tx_credits && !skb_queue_empty(&chan->tx_q)) { + l2cap_do_send(chan, skb_dequeue(&chan->tx_q)); + chan->tx_credits--; + } + + if (chan->tx_credits) + chan->ops->resume(chan); + + l2cap_chan_unlock(chan); + + return 0; +} + +static inline int l2cap_le_command_rej(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u16 cmd_len, + u8 *data) +{ + struct l2cap_cmd_rej_unk *rej = (struct l2cap_cmd_rej_unk *) data; + struct l2cap_chan *chan; + + if (cmd_len < sizeof(*rej)) + return -EPROTO; + + mutex_lock(&conn->chan_lock); + + chan = __l2cap_get_chan_by_ident(conn, cmd->ident); + if (!chan) + goto done; + + l2cap_chan_lock(chan); + l2cap_chan_del(chan, ECONNREFUSED); + l2cap_chan_unlock(chan); + +done: + mutex_unlock(&conn->chan_lock); + return 0; +} + static inline int l2cap_le_sig_cmd(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, u8 *data) + struct l2cap_cmd_hdr *cmd, u16 cmd_len, + u8 *data) { + int err = 0; + + if (!enable_lecoc) { + switch (cmd->code) { + case L2CAP_LE_CONN_REQ: + case L2CAP_LE_CONN_RSP: + case L2CAP_LE_CREDITS: + case L2CAP_DISCONN_REQ: + case L2CAP_DISCONN_RSP: + return -EINVAL; + } + } + switch (cmd->code) { case L2CAP_COMMAND_REJ: - return 0; + l2cap_le_command_rej(conn, cmd, cmd_len, data); + break; case L2CAP_CONN_PARAM_UPDATE_REQ: - return l2cap_conn_param_update_req(conn, cmd, data); + err = l2cap_conn_param_update_req(conn, cmd, cmd_len, data); + break; case L2CAP_CONN_PARAM_UPDATE_RSP: - return 0; + break; + + case L2CAP_LE_CONN_RSP: + l2cap_le_connect_rsp(conn, cmd, cmd_len, data); + break; + + case L2CAP_LE_CONN_REQ: + err = l2cap_le_connect_req(conn, cmd, cmd_len, data); + break; + + case L2CAP_LE_CREDITS: + err = l2cap_le_credits(conn, cmd, cmd_len, data); + break; + + case L2CAP_DISCONN_REQ: + err = l2cap_disconnect_req(conn, cmd, cmd_len, data); + break; + + case L2CAP_DISCONN_RSP: + l2cap_disconnect_rsp(conn, cmd, cmd_len, data); + break; default: BT_ERR("Unknown LE signaling command 0x%2.2x", cmd->code); - return -EINVAL; + err = -EINVAL; + break; } + + return err; } static inline void l2cap_le_sig_channel(struct l2cap_conn *conn, @@ -5321,7 +5848,7 @@ static inline void l2cap_le_sig_channel(struct l2cap_conn *conn, goto drop; } - err = l2cap_le_sig_cmd(conn, cmd, skb->data); + err = l2cap_le_sig_cmd(conn, cmd, len, skb->data); if (err) { struct l2cap_cmd_rej_unk rej; @@ -6312,6 +6839,121 @@ drop: return 0; } +static void l2cap_chan_le_send_credits(struct l2cap_chan *chan) +{ + struct l2cap_conn *conn = chan->conn; + struct l2cap_le_credits pkt; + u16 return_credits; + + /* We return more credits to the sender only after the amount of + * credits falls below half of the initial amount. + */ + if (chan->rx_credits >= (le_max_credits + 1) / 2) + return; + + return_credits = le_max_credits - chan->rx_credits; + + BT_DBG("chan %p returning %u credits to sender", chan, return_credits); + + chan->rx_credits += return_credits; + + pkt.cid = cpu_to_le16(chan->scid); + pkt.credits = cpu_to_le16(return_credits); + + chan->ident = l2cap_get_ident(conn); + + l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CREDITS, sizeof(pkt), &pkt); +} + +static int l2cap_le_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) +{ + int err; + + if (!chan->rx_credits) { + BT_ERR("No credits to receive LE L2CAP data"); + return -ENOBUFS; + } + + if (chan->imtu < skb->len) { + BT_ERR("Too big LE L2CAP PDU"); + return -ENOBUFS; + } + + chan->rx_credits--; + BT_DBG("rx_credits %u -> %u", chan->rx_credits + 1, chan->rx_credits); + + l2cap_chan_le_send_credits(chan); + + err = 0; + + if (!chan->sdu) { + u16 sdu_len; + + sdu_len = get_unaligned_le16(skb->data); + skb_pull(skb, L2CAP_SDULEN_SIZE); + + BT_DBG("Start of new SDU. sdu_len %u skb->len %u imtu %u", + sdu_len, skb->len, chan->imtu); + + if (sdu_len > chan->imtu) { + BT_ERR("Too big LE L2CAP SDU length received"); + err = -EMSGSIZE; + goto failed; + } + + if (skb->len > sdu_len) { + BT_ERR("Too much LE L2CAP data received"); + err = -EINVAL; + goto failed; + } + + if (skb->len == sdu_len) + return chan->ops->recv(chan, skb); + + chan->sdu = skb; + chan->sdu_len = sdu_len; + chan->sdu_last_frag = skb; + + return 0; + } + + BT_DBG("SDU fragment. chan->sdu->len %u skb->len %u chan->sdu_len %u", + chan->sdu->len, skb->len, chan->sdu_len); + + if (chan->sdu->len + skb->len > chan->sdu_len) { + BT_ERR("Too much LE L2CAP data received"); + err = -EINVAL; + goto failed; + } + + append_skb_frag(chan->sdu, skb, &chan->sdu_last_frag); + skb = NULL; + + if (chan->sdu->len == chan->sdu_len) { + err = chan->ops->recv(chan, chan->sdu); + if (!err) { + chan->sdu = NULL; + chan->sdu_last_frag = NULL; + chan->sdu_len = 0; + } + } + +failed: + if (err) { + kfree_skb(skb); + kfree_skb(chan->sdu); + chan->sdu = NULL; + chan->sdu_last_frag = NULL; + chan->sdu_len = 0; + } + + /* We can't return an error here since we took care of the skb + * freeing internally. An error return would cause the caller to + * do a double-free of the skb. + */ + return 0; +} + static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk_buff *skb) { @@ -6341,6 +6983,12 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, goto drop; switch (chan->mode) { + case L2CAP_MODE_LE_FLOWCTL: + if (l2cap_le_data_rcv(chan, skb) < 0) + goto drop; + + goto done; + case L2CAP_MODE_BASIC: /* If socket recv buffers overflows we drop data here * which is *bad* because L2CAP has to be reliable. @@ -6380,7 +7028,8 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, if (hcon->type != ACL_LINK) goto drop; - chan = l2cap_global_chan_by_psm(0, psm, &hcon->src, &hcon->dst); + chan = l2cap_global_chan_by_psm(0, psm, &hcon->src, &hcon->dst, + ACL_LINK); if (!chan) goto drop; @@ -6473,6 +7122,10 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) l2cap_conn_del(conn->hcon, EACCES); break; + case L2CAP_FC_6LOWPAN: + bt_6lowpan_recv(conn, skb); + break; + default: l2cap_data_channel(conn, cid, skb); break; @@ -6540,6 +7193,8 @@ void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason) { BT_DBG("hcon %p reason %d", hcon, reason); + bt_6lowpan_del_conn(hcon->l2cap_data); + l2cap_conn_del(hcon, bt_to_errno(reason)); } @@ -6612,11 +7267,10 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) } if (chan->state == BT_CONNECT) { - if (!status) { + if (!status) l2cap_start_connection(chan); - } else { + else __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); - } } else if (chan->state == BT_CONNECT2) { struct l2cap_conn_rsp rsp; __u16 res, stat; @@ -6817,11 +7471,19 @@ int __init l2cap_init(void) l2cap_debugfs = debugfs_create_file("l2cap", 0444, bt_debugfs, NULL, &l2cap_debugfs_fops); + debugfs_create_u16("l2cap_le_max_credits", 0466, bt_debugfs, + &le_max_credits); + debugfs_create_u16("l2cap_le_default_mps", 0466, bt_debugfs, + &le_default_mps); + + bt_6lowpan_init(); + return 0; } void l2cap_exit(void) { + bt_6lowpan_cleanup(); debugfs_remove(l2cap_debugfs); l2cap_cleanup_sockets(); } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 7cc24d263caa..d58f76bcebd1 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -27,6 +27,7 @@ /* Bluetooth L2CAP sockets. */ +#include <linux/module.h> #include <linux/export.h> #include <net/bluetooth/bluetooth.h> @@ -35,6 +36,8 @@ #include "smp.h" +bool enable_lecoc; + static struct bt_sock_list l2cap_sk_list = { .lock = __RW_LOCK_UNLOCKED(l2cap_sk_list.lock) }; @@ -50,6 +53,32 @@ bool l2cap_is_socket(struct socket *sock) } EXPORT_SYMBOL(l2cap_is_socket); +static int l2cap_validate_bredr_psm(u16 psm) +{ + /* PSM must be odd and lsb of upper byte must be 0 */ + if ((psm & 0x0101) != 0x0001) + return -EINVAL; + + /* Restrict usage of well-known PSMs */ + if (psm < 0x1001 && !capable(CAP_NET_BIND_SERVICE)) + return -EACCES; + + return 0; +} + +static int l2cap_validate_le_psm(u16 psm) +{ + /* Valid LE_PSM ranges are defined only until 0x00ff */ + if (psm > 0x00ff) + return -EINVAL; + + /* Restrict fixed, SIG assigned PSM values to CAP_NET_BIND_SERVICE */ + if (psm <= 0x007f && !capable(CAP_NET_BIND_SERVICE)) + return -EACCES; + + return 0; +} + static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) { struct sock *sk = sock->sk; @@ -73,11 +102,11 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) return -EINVAL; if (bdaddr_type_is_le(la.l2_bdaddr_type)) { - /* Connection oriented channels are not supported on LE */ - if (la.l2_psm) + if (!enable_lecoc && la.l2_psm) return -EINVAL; /* We only allow ATT user space socket */ - if (la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT)) + if (la.l2_cid && + la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT)) return -EINVAL; } @@ -91,17 +120,13 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) if (la.l2_psm) { __u16 psm = __le16_to_cpu(la.l2_psm); - /* PSM must be odd and lsb of upper byte must be 0 */ - if ((psm & 0x0101) != 0x0001) { - err = -EINVAL; - goto done; - } + if (la.l2_bdaddr_type == BDADDR_BREDR) + err = l2cap_validate_bredr_psm(psm); + else + err = l2cap_validate_le_psm(psm); - /* Restrict usage of well-known PSMs */ - if (psm < 0x1001 && !capable(CAP_NET_BIND_SERVICE)) { - err = -EACCES; + if (err) goto done; - } } if (la.l2_cid) @@ -122,11 +147,17 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) __le16_to_cpu(la.l2_psm) == L2CAP_PSM_RFCOMM) chan->sec_level = BT_SECURITY_SDP; break; + case L2CAP_CHAN_RAW: + chan->sec_level = BT_SECURITY_SDP; + break; } bacpy(&chan->src, &la.l2_bdaddr); chan->src_type = la.l2_bdaddr_type; + if (chan->psm && bdaddr_type_is_le(chan->src_type)) + chan->mode = L2CAP_MODE_LE_FLOWCTL; + chan->state = BT_BOUND; sk->sk_state = BT_BOUND; @@ -189,14 +220,17 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, return -EINVAL; if (bdaddr_type_is_le(la.l2_bdaddr_type)) { - /* Connection oriented channels are not supported on LE */ - if (la.l2_psm) + if (!enable_lecoc && la.l2_psm) return -EINVAL; /* We only allow ATT user space socket */ - if (la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT)) + if (la.l2_cid && + la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT)) return -EINVAL; } + if (chan->psm && bdaddr_type_is_le(chan->src_type)) + chan->mode = L2CAP_MODE_LE_FLOWCTL; + err = l2cap_chan_connect(chan, la.l2_psm, __le16_to_cpu(la.l2_cid), &la.l2_bdaddr, la.l2_bdaddr_type); if (err) @@ -234,6 +268,7 @@ static int l2cap_sock_listen(struct socket *sock, int backlog) switch (chan->mode) { case L2CAP_MODE_BASIC: + case L2CAP_MODE_LE_FLOWCTL: break; case L2CAP_MODE_ERTM: case L2CAP_MODE_STREAMING: @@ -360,6 +395,16 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, switch (optname) { case L2CAP_OPTIONS: + /* LE sockets should use BT_SNDMTU/BT_RCVMTU, but since + * legacy ATT code depends on getsockopt for + * L2CAP_OPTIONS we need to let this pass. + */ + if (bdaddr_type_is_le(chan->src_type) && + chan->scid != L2CAP_CID_ATT) { + err = -EINVAL; + break; + } + memset(&opts, 0, sizeof(opts)); opts.imtu = chan->imtu; opts.omtu = chan->omtu; @@ -514,6 +559,41 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, err = -EFAULT; break; + case BT_SNDMTU: + if (!enable_lecoc) { + err = -EPROTONOSUPPORT; + break; + } + + if (!bdaddr_type_is_le(chan->src_type)) { + err = -EINVAL; + break; + } + + if (sk->sk_state != BT_CONNECTED) { + err = -ENOTCONN; + break; + } + + if (put_user(chan->omtu, (u16 __user *) optval)) + err = -EFAULT; + break; + + case BT_RCVMTU: + if (!enable_lecoc) { + err = -EPROTONOSUPPORT; + break; + } + + if (!bdaddr_type_is_le(chan->src_type)) { + err = -EINVAL; + break; + } + + if (put_user(chan->imtu, (u16 __user *) optval)) + err = -EFAULT; + break; + default: err = -ENOPROTOOPT; break; @@ -554,6 +634,11 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, switch (optname) { case L2CAP_OPTIONS: + if (bdaddr_type_is_le(chan->src_type)) { + err = -EINVAL; + break; + } + if (sk->sk_state == BT_CONNECTED) { err = -EINVAL; break; @@ -585,6 +670,8 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, chan->mode = opts.mode; switch (chan->mode) { + case L2CAP_MODE_LE_FLOWCTL: + break; case L2CAP_MODE_BASIC: clear_bit(CONF_STATE2_DEVICE, &chan->conf_state); break; @@ -807,6 +894,47 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; + case BT_SNDMTU: + if (!enable_lecoc) { + err = -EPROTONOSUPPORT; + break; + } + + if (!bdaddr_type_is_le(chan->src_type)) { + err = -EINVAL; + break; + } + + /* Setting is not supported as it's the remote side that + * decides this. + */ + err = -EPERM; + break; + + case BT_RCVMTU: + if (!enable_lecoc) { + err = -EPROTONOSUPPORT; + break; + } + + if (!bdaddr_type_is_le(chan->src_type)) { + err = -EINVAL; + break; + } + + if (sk->sk_state == BT_CONNECTED) { + err = -EISCONN; + break; + } + + if (get_user(opt, (u32 __user *) optval)) { + err = -EFAULT; + break; + } + + chan->imtu = opt; + break; + default: err = -ENOPROTOOPT; break; @@ -859,10 +987,16 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { - sk->sk_state = BT_CONFIG; - pi->chan->state = BT_CONFIG; + if (bdaddr_type_is_le(pi->chan->src_type)) { + sk->sk_state = BT_CONNECTED; + pi->chan->state = BT_CONNECTED; + __l2cap_le_connect_rsp_defer(pi->chan); + } else { + sk->sk_state = BT_CONFIG; + pi->chan->state = BT_CONFIG; + __l2cap_connect_rsp_defer(pi->chan); + } - __l2cap_connect_rsp_defer(pi->chan); err = 0; goto done; } @@ -1236,6 +1370,14 @@ static long l2cap_sock_get_sndtimeo_cb(struct l2cap_chan *chan) return sk->sk_sndtimeo; } +static void l2cap_sock_suspend_cb(struct l2cap_chan *chan) +{ + struct sock *sk = chan->data; + + set_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags); + sk->sk_state_change(sk); +} + static struct l2cap_ops l2cap_chan_ops = { .name = "L2CAP Socket Interface", .new_connection = l2cap_sock_new_connection_cb, @@ -1246,6 +1388,7 @@ static struct l2cap_ops l2cap_chan_ops = { .ready = l2cap_sock_ready_cb, .defer = l2cap_sock_defer_cb, .resume = l2cap_sock_resume_cb, + .suspend = l2cap_sock_suspend_cb, .set_shutdown = l2cap_sock_set_shutdown_cb, .get_sndtimeo = l2cap_sock_get_sndtimeo_cb, .alloc_skb = l2cap_sock_alloc_skb_cb, @@ -1270,7 +1413,7 @@ static void l2cap_sock_destruct(struct sock *sk) static void l2cap_skb_msg_name(struct sk_buff *skb, void *msg_name, int *msg_namelen) { - struct sockaddr_l2 *la = (struct sockaddr_l2 *) msg_name; + DECLARE_SOCKADDR(struct sockaddr_l2 *, la, msg_name); memset(la, 0, sizeof(struct sockaddr_l2)); la->l2_family = AF_BLUETOOTH; @@ -1303,6 +1446,8 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) chan->tx_win_max = pchan->tx_win_max; chan->sec_level = pchan->sec_level; chan->flags = pchan->flags; + chan->tx_credits = pchan->tx_credits; + chan->rx_credits = pchan->rx_credits; security_sk_clone(parent, sk); } else { @@ -1469,3 +1614,6 @@ void l2cap_cleanup_sockets(void) bt_sock_unregister(BTPROTO_L2CAP); proto_unregister(&l2cap_proto); } + +module_param(enable_lecoc, bool, 0644); +MODULE_PARM_DESC(enable_lecoc, "Enable support for LE CoC"); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 074d83690a41..a03ca3ca91bf 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1264,7 +1264,7 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, if (cp->val == 0x02) { /* Limited discoverable mode */ - hci_cp.num_iac = 2; + hci_cp.num_iac = min_t(u8, hdev->num_iac, 2); hci_cp.iac_lap[0] = 0x00; /* LIAC */ hci_cp.iac_lap[1] = 0x8b; hci_cp.iac_lap[2] = 0x9e; @@ -4595,6 +4595,9 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, struct mgmt_ev_device_disconnected ev; struct sock *sk = NULL; + if (link_type != ACL_LINK && link_type != LE_LINK) + return; + mgmt_pending_foreach(MGMT_OP_DISCONNECT, hdev, disconnect_rsp, &sk); bacpy(&ev.addr.bdaddr, bdaddr); @@ -4613,6 +4616,8 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status) { + u8 bdaddr_type = link_to_bdaddr(link_type, addr_type); + struct mgmt_cp_disconnect *cp; struct mgmt_rp_disconnect rp; struct pending_cmd *cmd; @@ -4623,8 +4628,16 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, if (!cmd) return; + cp = cmd->param; + + if (bacmp(bdaddr, &cp->addr.bdaddr)) + return; + + if (cp->addr.type != bdaddr_type) + return; + bacpy(&rp.addr.bdaddr, bdaddr); - rp.addr.type = link_to_bdaddr(link_type, addr_type); + rp.addr.type = bdaddr_type; cmd_complete(cmd->sk, cmd->index, MGMT_OP_DISCONNECT, mgmt_status(status), &rp, sizeof(rp)); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 84fcf9fff3ea..f9c0980abeea 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -58,6 +58,7 @@ struct rfcomm_dev { uint modem_status; struct rfcomm_dlc *dlc; + wait_queue_head_t conn_wait; struct device *tty_dev; @@ -103,20 +104,60 @@ static void rfcomm_dev_destruct(struct tty_port *port) module_put(THIS_MODULE); } -/* device-specific initialization: open the dlc */ -static int rfcomm_dev_activate(struct tty_port *port, struct tty_struct *tty) +static struct device *rfcomm_get_device(struct rfcomm_dev *dev) { - struct rfcomm_dev *dev = container_of(port, struct rfcomm_dev, port); + struct hci_dev *hdev; + struct hci_conn *conn; - return rfcomm_dlc_open(dev->dlc, &dev->src, &dev->dst, dev->channel); + hdev = hci_get_route(&dev->dst, &dev->src); + if (!hdev) + return NULL; + + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &dev->dst); + + hci_dev_put(hdev); + + return conn ? &conn->dev : NULL; } -/* we block the open until the dlc->state becomes BT_CONNECTED */ -static int rfcomm_dev_carrier_raised(struct tty_port *port) +/* device-specific initialization: open the dlc */ +static int rfcomm_dev_activate(struct tty_port *port, struct tty_struct *tty) { struct rfcomm_dev *dev = container_of(port, struct rfcomm_dev, port); + DEFINE_WAIT(wait); + int err; + + err = rfcomm_dlc_open(dev->dlc, &dev->src, &dev->dst, dev->channel); + if (err) + return err; + + while (1) { + prepare_to_wait(&dev->conn_wait, &wait, TASK_INTERRUPTIBLE); + + if (dev->dlc->state == BT_CLOSED) { + err = -dev->err; + break; + } + + if (dev->dlc->state == BT_CONNECTED) + break; + + if (signal_pending(current)) { + err = -ERESTARTSYS; + break; + } + + tty_unlock(tty); + schedule(); + tty_lock(tty); + } + finish_wait(&dev->conn_wait, &wait); + + if (!err) + device_move(dev->tty_dev, rfcomm_get_device(dev), + DPM_ORDER_DEV_AFTER_PARENT); - return (dev->dlc->state == BT_CONNECTED); + return err; } /* device-specific cleanup: close the dlc */ @@ -135,7 +176,6 @@ static const struct tty_port_operations rfcomm_port_ops = { .destruct = rfcomm_dev_destruct, .activate = rfcomm_dev_activate, .shutdown = rfcomm_dev_shutdown, - .carrier_raised = rfcomm_dev_carrier_raised, }; static struct rfcomm_dev *__rfcomm_dev_get(int id) @@ -169,22 +209,6 @@ static struct rfcomm_dev *rfcomm_dev_get(int id) return dev; } -static struct device *rfcomm_get_device(struct rfcomm_dev *dev) -{ - struct hci_dev *hdev; - struct hci_conn *conn; - - hdev = hci_get_route(&dev->dst, &dev->src); - if (!hdev) - return NULL; - - conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &dev->dst); - - hci_dev_put(hdev); - - return conn ? &conn->dev : NULL; -} - static ssize_t show_address(struct device *tty_dev, struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); @@ -258,6 +282,7 @@ static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) tty_port_init(&dev->port); dev->port.ops = &rfcomm_port_ops; + init_waitqueue_head(&dev->conn_wait); skb_queue_head_init(&dev->pending); @@ -437,7 +462,8 @@ static int rfcomm_release_dev(void __user *arg) tty_kref_put(tty); } - if (!test_and_set_bit(RFCOMM_TTY_RELEASED, &dev->flags)) + if (!test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags) && + !test_and_set_bit(RFCOMM_TTY_RELEASED, &dev->flags)) tty_port_put(&dev->port); tty_port_put(&dev->port); @@ -575,12 +601,9 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) BT_DBG("dlc %p dev %p err %d", dlc, dev, err); dev->err = err; - if (dlc->state == BT_CONNECTED) { - device_move(dev->tty_dev, rfcomm_get_device(dev), - DPM_ORDER_DEV_AFTER_PARENT); + wake_up_interruptible(&dev->conn_wait); - wake_up_interruptible(&dev->port.open_wait); - } else if (dlc->state == BT_CLOSED) + if (dlc->state == BT_CLOSED) tty_port_tty_hangup(&dev->port, false); } @@ -670,10 +693,20 @@ static int rfcomm_tty_install(struct tty_driver *driver, struct tty_struct *tty) /* install the tty_port */ err = tty_port_install(&dev->port, driver, tty); - if (err) + if (err) { rfcomm_tty_cleanup(tty); + return err; + } - return err; + /* take over the tty_port reference if the port was created with the + * flag RFCOMM_RELEASE_ONHUP. This will force the release of the port + * when the last process closes the tty. The behaviour is expected by + * userspace. + */ + if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) + tty_port_put(&dev->port); + + return 0; } static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp) @@ -1010,10 +1043,6 @@ static void rfcomm_tty_hangup(struct tty_struct *tty) BT_DBG("tty %p dev %p", tty, dev); tty_port_hangup(&dev->port); - - if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags) && - !test_and_set_bit(RFCOMM_TTY_RELEASED, &dev->flags)) - tty_port_put(&dev->port); } static int rfcomm_tty_tiocmget(struct tty_struct *tty) @@ -1096,7 +1125,7 @@ int __init rfcomm_init_ttys(void) rfcomm_tty_driver->subtype = SERIAL_TYPE_NORMAL; rfcomm_tty_driver->flags = TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV; rfcomm_tty_driver->init_termios = tty_std_termios; - rfcomm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL; + rfcomm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL | CLOCAL; rfcomm_tty_driver->init_termios.c_lflag &= ~ICANON; tty_set_operations(rfcomm_tty_driver, &rfcomm_ops); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 4b07acb8293c..45007362683b 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -53,8 +53,7 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) { struct blkcipher_desc desc; struct scatterlist sg; - int err, iv_len; - unsigned char iv[128]; + int err; if (tfm == NULL) { BT_ERR("tfm %p", tfm); @@ -72,12 +71,6 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) sg_init_one(&sg, r, 16); - iv_len = crypto_blkcipher_ivsize(tfm); - if (iv_len) { - memset(&iv, 0xff, iv_len); - crypto_blkcipher_set_iv(tfm, iv, iv_len); - } - err = crypto_blkcipher_encrypt(&desc, &sg, &sg, 16); if (err) BT_ERR("Encrypt data error %d", err); @@ -143,13 +136,6 @@ static int smp_s1(struct crypto_blkcipher *tfm, u8 k[16], u8 r1[16], return err; } -static int smp_rand(u8 *buf) -{ - get_random_bytes(buf, 16); - - return 0; -} - static struct sk_buff *smp_build_cmd(struct l2cap_conn *conn, u8 code, u16 dlen, void *data) { @@ -257,11 +243,11 @@ static u8 check_enc_key_size(struct l2cap_conn *conn, __u8 max_key_size) return 0; } -static void smp_failure(struct l2cap_conn *conn, u8 reason, u8 send) +static void smp_failure(struct l2cap_conn *conn, u8 reason) { struct hci_conn *hcon = conn->hcon; - if (send) + if (reason) smp_send_cmd(conn, SMP_CMD_PAIRING_FAIL, sizeof(reason), &reason); @@ -406,7 +392,7 @@ static void confirm_work(struct work_struct *work) return; error: - smp_failure(conn, reason, 1); + smp_failure(conn, reason); } static void random_work(struct work_struct *work) @@ -490,7 +476,7 @@ static void random_work(struct work_struct *work) return; error: - smp_failure(conn, reason, 1); + smp_failure(conn, reason); } static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) @@ -555,10 +541,10 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey) break; case MGMT_OP_USER_PASSKEY_NEG_REPLY: case MGMT_OP_USER_CONFIRM_NEG_REPLY: - smp_failure(conn, SMP_PASSKEY_ENTRY_FAILED, 1); + smp_failure(conn, SMP_PASSKEY_ENTRY_FAILED); return 0; default: - smp_failure(conn, SMP_PASSKEY_ENTRY_FAILED, 1); + smp_failure(conn, SMP_PASSKEY_ENTRY_FAILED); return -EOPNOTSUPP; } @@ -606,9 +592,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (check_enc_key_size(conn, key_size)) return SMP_ENC_KEY_SIZE; - ret = smp_rand(smp->prnd); - if (ret) - return SMP_UNSPECIFIED; + get_random_bytes(smp->prnd, sizeof(smp->prnd)); smp->prsp[0] = SMP_CMD_PAIRING_RSP; memcpy(&smp->prsp[1], &rsp, sizeof(rsp)); @@ -644,9 +628,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) if (check_enc_key_size(conn, key_size)) return SMP_ENC_KEY_SIZE; - ret = smp_rand(smp->prnd); - if (ret) - return SMP_UNSPECIFIED; + get_random_bytes(smp->prnd, sizeof(smp->prnd)); smp->prsp[0] = SMP_CMD_PAIRING_RSP; memcpy(&smp->prsp[1], rsp, sizeof(*rsp)); @@ -768,6 +750,17 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) return 0; } +bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level) +{ + if (sec_level == BT_SECURITY_LOW) + return true; + + if (hcon->sec_level >= sec_level) + return true; + + return false; +} + int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) { struct l2cap_conn *conn = hcon->l2cap_data; @@ -779,10 +772,7 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) if (!test_bit(HCI_LE_ENABLED, &hcon->hdev->dev_flags)) return 1; - if (sec_level == BT_SECURITY_LOW) - return 1; - - if (hcon->sec_level >= sec_level) + if (smp_sufficient_security(hcon, sec_level)) return 1; if (hcon->link_mode & HCI_LM_MASTER) @@ -895,7 +885,7 @@ int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) break; case SMP_CMD_PAIRING_FAIL: - smp_failure(conn, skb->data[0], 0); + smp_failure(conn, 0); reason = 0; err = -EPERM; break; @@ -941,7 +931,7 @@ int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) done: if (reason) - smp_failure(conn, reason, 1); + smp_failure(conn, reason); kfree_skb(skb); return err; diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index f8ba07f3e5fa..a700bcb490d7 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -136,6 +136,7 @@ struct smp_chan { }; /* SMP Commands */ +bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level); int smp_conn_security(struct hci_conn *hcon, __u8 sec_level); int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb); int smp_distribute_keys(struct l2cap_conn *conn, __u8 force); diff --git a/net/bridge/br.c b/net/bridge/br.c index ba780cc8e515..19311aafcf5a 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -22,14 +22,29 @@ #include "br_private.h" -static const struct stp_proto br_stp_proto = { - .rcv = br_stp_rcv, -}; +static void __net_exit br_net_exit(struct net *net) +{ + struct net_device *dev; + LIST_HEAD(list); + + rtnl_lock(); + for_each_netdev(net, dev) + if (dev->priv_flags & IFF_EBRIDGE) + br_dev_delete(dev, &list); + + unregister_netdevice_many(&list); + rtnl_unlock(); + +} static struct pernet_operations br_net_ops = { .exit = br_net_exit, }; +static const struct stp_proto br_stp_proto = { + .rcv = br_stp_rcv, +}; + static int __init br_init(void) { int err; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index f00cfd2a0143..63f0455c0bc3 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -32,7 +32,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) const unsigned char *dest = skb->data; struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; - struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats); + struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); u16 vid = 0; rcu_read_lock(); @@ -90,12 +90,12 @@ static int br_dev_init(struct net_device *dev) struct net_bridge *br = netdev_priv(dev); int i; - br->stats = alloc_percpu(struct br_cpu_netstats); + br->stats = alloc_percpu(struct pcpu_sw_netstats); if (!br->stats) return -ENOMEM; for_each_possible_cpu(i) { - struct br_cpu_netstats *br_dev_stats; + struct pcpu_sw_netstats *br_dev_stats; br_dev_stats = per_cpu_ptr(br->stats, i); u64_stats_init(&br_dev_stats->syncp); } @@ -135,12 +135,12 @@ static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct net_bridge *br = netdev_priv(dev); - struct br_cpu_netstats tmp, sum = { 0 }; + struct pcpu_sw_netstats tmp, sum = { 0 }; unsigned int cpu; for_each_possible_cpu(cpu) { unsigned int start; - const struct br_cpu_netstats *bstats + const struct pcpu_sw_netstats *bstats = per_cpu_ptr(br->stats, cpu); do { start = u64_stats_fetch_begin_bh(&bstats->syncp); @@ -187,8 +187,7 @@ static int br_set_mac_address(struct net_device *dev, void *p) spin_lock_bh(&br->lock); if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) { - memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); - br_fdb_change_mac_address(br, addr->sa_data); + /* Mac address will be changed in br_stp_change_bridge_id(). */ br_stp_change_bridge_id(br, addr->sa_data); } spin_unlock_bh(&br->lock); @@ -226,6 +225,33 @@ static void br_netpoll_cleanup(struct net_device *dev) br_netpoll_disable(p); } +static int __br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) +{ + struct netpoll *np; + int err; + + np = kzalloc(sizeof(*p->np), gfp); + if (!np) + return -ENOMEM; + + err = __netpoll_setup(np, p->dev, gfp); + if (err) { + kfree(np); + return err; + } + + p->np = np; + return err; +} + +int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) +{ + if (!p->br->dev->npinfo) + return 0; + + return __br_netpoll_enable(p, gfp); +} + static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp) { @@ -236,7 +262,7 @@ static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, list_for_each_entry(p, &br->port_list, list) { if (!p->dev) continue; - err = br_netpoll_enable(p, gfp); + err = __br_netpoll_enable(p, gfp); if (err) goto fail; } @@ -249,28 +275,6 @@ fail: goto out; } -int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) -{ - struct netpoll *np; - int err; - - if (!p->br->dev->npinfo) - return 0; - - np = kzalloc(sizeof(*p->np), gfp); - if (!np) - return -ENOMEM; - - err = __netpoll_setup(np, p->dev, gfp); - if (err) { - kfree(np); - return err; - } - - p->np = np; - return err; -} - void br_netpoll_disable(struct net_bridge_port *p) { struct netpoll *np = p->np; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 33e8f23acddd..9203d5a1943f 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -27,6 +27,9 @@ #include "br_private.h" static struct kmem_cache *br_fdb_cache __read_mostly; +static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, + const unsigned char *addr, + __u16 vid); static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid); static void fdb_notify(struct net_bridge *br, @@ -89,11 +92,57 @@ static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) call_rcu(&f->rcu, fdb_rcu_free); } +/* Delete a local entry if no other port had the same address. */ +static void fdb_delete_local(struct net_bridge *br, + const struct net_bridge_port *p, + struct net_bridge_fdb_entry *f) +{ + const unsigned char *addr = f->addr.addr; + u16 vid = f->vlan_id; + struct net_bridge_port *op; + + /* Maybe another port has same hw addr? */ + list_for_each_entry(op, &br->port_list, list) { + if (op != p && ether_addr_equal(op->dev->dev_addr, addr) && + (!vid || nbp_vlan_find(op, vid))) { + f->dst = op; + f->added_by_user = 0; + return; + } + } + + /* Maybe bridge device has same hw addr? */ + if (p && ether_addr_equal(br->dev->dev_addr, addr) && + (!vid || br_vlan_find(br, vid))) { + f->dst = NULL; + f->added_by_user = 0; + return; + } + + fdb_delete(br, f); +} + +void br_fdb_find_delete_local(struct net_bridge *br, + const struct net_bridge_port *p, + const unsigned char *addr, u16 vid) +{ + struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; + struct net_bridge_fdb_entry *f; + + spin_lock_bh(&br->hash_lock); + f = fdb_find(head, addr, vid); + if (f && f->is_local && !f->added_by_user && f->dst == p) + fdb_delete_local(br, p, f); + spin_unlock_bh(&br->hash_lock); +} + void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) { struct net_bridge *br = p->br; - bool no_vlan = (nbp_get_vlan_info(p) == NULL) ? true : false; + struct net_port_vlans *pv = nbp_get_vlan_info(p); + bool no_vlan = !pv; int i; + u16 vid; spin_lock_bh(&br->hash_lock); @@ -104,38 +153,34 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) struct net_bridge_fdb_entry *f; f = hlist_entry(h, struct net_bridge_fdb_entry, hlist); - if (f->dst == p && f->is_local) { - /* maybe another port has same hw addr? */ - struct net_bridge_port *op; - u16 vid = f->vlan_id; - list_for_each_entry(op, &br->port_list, list) { - if (op != p && - ether_addr_equal(op->dev->dev_addr, - f->addr.addr) && - nbp_vlan_find(op, vid)) { - f->dst = op; - goto insert; - } - } - + if (f->dst == p && f->is_local && !f->added_by_user) { /* delete old one */ - fdb_delete(br, f); -insert: - /* insert new address, may fail if invalid - * address or dup. - */ - fdb_insert(br, p, newaddr, vid); + fdb_delete_local(br, p, f); /* if this port has no vlan information * configured, we can safely be done at * this point. */ if (no_vlan) - goto done; + goto insert; } } } +insert: + /* insert new address, may fail if invalid address or dup. */ + fdb_insert(br, p, newaddr, 0); + + if (no_vlan) + goto done; + + /* Now add entries for every VLAN configured on the port. + * This function runs under RTNL so the bitmap will not change + * from under us. + */ + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) + fdb_insert(br, p, newaddr, vid); + done: spin_unlock_bh(&br->hash_lock); } @@ -146,10 +191,12 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) struct net_port_vlans *pv; u16 vid = 0; + spin_lock_bh(&br->hash_lock); + /* If old entry was unassociated with any port, then delete it. */ f = __br_fdb_get(br, br->dev->dev_addr, 0); if (f && f->is_local && !f->dst) - fdb_delete(br, f); + fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, 0); @@ -159,14 +206,16 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) */ pv = br_get_vlan_info(br); if (!pv) - return; + goto out; 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); + fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, vid); } +out: + spin_unlock_bh(&br->hash_lock); } void br_fdb_cleanup(unsigned long _data) @@ -235,25 +284,11 @@ void br_fdb_delete_by_port(struct net_bridge *br, if (f->is_static && !do_all) continue; - /* - * if multiple ports all have the same device address - * then when one port is deleted, assign - * the local entry to other port - */ - if (f->is_local) { - struct net_bridge_port *op; - list_for_each_entry(op, &br->port_list, list) { - if (op != p && - ether_addr_equal(op->dev->dev_addr, - f->addr.addr)) { - f->dst = op; - goto skip_delete; - } - } - } - fdb_delete(br, f); - skip_delete: ; + if (f->is_local) + fdb_delete_local(br, p, f); + else + fdb_delete(br, f); } } spin_unlock_bh(&br->hash_lock); @@ -397,6 +432,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, fdb->vlan_id = vid; fdb->is_local = 0; fdb->is_static = 0; + fdb->added_by_user = 0; fdb->updated = fdb->used = jiffies; hlist_add_head_rcu(&fdb->hlist, head); } @@ -447,7 +483,7 @@ int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source, } void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr, u16 vid) + const unsigned char *addr, u16 vid, bool added_by_user) { struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; @@ -473,13 +509,18 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, /* fastpath: update of existing entry */ fdb->dst = source; fdb->updated = jiffies; + if (unlikely(added_by_user)) + fdb->added_by_user = 1; } } else { spin_lock(&br->hash_lock); if (likely(!fdb_find(head, addr, vid))) { fdb = fdb_create(head, source, addr, vid); - if (fdb) + if (fdb) { + if (unlikely(added_by_user)) + fdb->added_by_user = 1; fdb_notify(br, fdb, RTM_NEWNEIGH); + } } /* else we lose race and someone else inserts * it first, don't bother updating @@ -570,8 +611,7 @@ static void fdb_notify(struct net_bridge *br, rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } /* Dump information about entries, in response to GETNEIGH */ @@ -648,6 +688,7 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, modified = true; } + fdb->added_by_user = 1; fdb->used = jiffies; if (modified) { @@ -665,7 +706,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, if (ndm->ndm_flags & NTF_USE) { rcu_read_lock(); - br_fdb_update(p->br, p, addr, vid); + br_fdb_update(p->br, p, addr, vid, true); rcu_read_unlock(); } else { spin_lock_bh(&p->br->hash_lock); @@ -750,8 +791,7 @@ out: return err; } -int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, - u16 vlan) +static int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vlan) { struct hlist_head *head = &br->hash[br_mac_hash(addr, vlan)]; struct net_bridge_fdb_entry *fdb; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 4b81b1471789..d3409e6b5453 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -26,13 +26,13 @@ static int deliver_clone(const struct net_bridge_port *prev, void (*__packet_hook)(const struct net_bridge_port *p, struct sk_buff *skb)); -/* Don't forward packets to originating port or forwarding diasabled */ +/* Don't forward packets to originating port or forwarding disabled */ static inline int should_deliver(const struct net_bridge_port *p, const struct sk_buff *skb) { - return (((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && + return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && br_allowed_egress(p->br, nbp_get_vlan_info(p), skb) && - p->state == BR_STATE_FORWARDING); + p->state == BR_STATE_FORWARDING; } static inline unsigned int packet_length(const struct sk_buff *skb) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 4bf02adb5dc2..54d207d3a31c 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -61,7 +61,7 @@ static int port_cost(struct net_device *dev) } -/* Check for port carrier transistions. */ +/* Check for port carrier transitions. */ void br_port_carrier_check(struct net_bridge_port *p) { struct net_device *dev = p->dev; @@ -389,6 +389,9 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (br->dev->needed_headroom < dev->needed_headroom) br->dev->needed_headroom = dev->needed_headroom; + if (br_fdb_insert(br, p, dev->dev_addr, 0)) + netdev_err(dev, "failed insert local address bridge forwarding table\n"); + spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); @@ -404,9 +407,6 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) dev_set_mtu(br->dev, br_min_mtu(br)); - if (br_fdb_insert(br, p, dev->dev_addr, 0)) - netdev_err(dev, "failed insert local address bridge forwarding table\n"); - kobject_uevent(&p->kobj, KOBJ_ADD); return 0; @@ -455,18 +455,3 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) return 0; } - -void __net_exit br_net_exit(struct net *net) -{ - struct net_device *dev; - LIST_HEAD(list); - - rtnl_lock(); - for_each_netdev(net, dev) - if (dev->priv_flags & IFF_EBRIDGE) - br_dev_delete(dev, &list); - - unregister_netdevice_many(&list); - rtnl_unlock(); - -} diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 7e73c32e205d..28d544627422 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -28,7 +28,7 @@ static int br_pass_frame_up(struct sk_buff *skb) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); - struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats); + struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); u64_stats_update_begin(&brstats->syncp); brstats->rx_packets++; @@ -77,7 +77,7 @@ int br_handle_frame_finish(struct sk_buff *skb) /* insert into forwarding database after filtering to avoid spoofing */ br = p->br; if (p->flags & BR_LEARNING) - br_fdb_update(br, p, eth_hdr(skb)->h_source, vid); + br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false); if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) && br_multicast_rcv(br, p, skb, vid)) @@ -148,7 +148,7 @@ static int br_handle_local_finish(struct sk_buff *skb) br_vlan_get_tag(skb, &vid); if (p->flags & BR_LEARNING) - br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid); + br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false); return 0; /* process further */ } diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index cd8c3a44ab7d..a9a4a1b7863d 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -381,7 +381,7 @@ int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { struct net_bridge *br = netdev_priv(dev); - switch(cmd) { + switch (cmd) { case SIOCDEVPRIVATE: return old_dev_ioctl(dev, rq, cmd); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 80cad2cf02a7..b008c59a92c4 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -1001,7 +1001,7 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = { #ifdef CONFIG_SYSCTL static int brnf_sysctl_call_tables(struct ctl_table *ctl, int write, - void __user * buffer, size_t * lenp, loff_t * ppos) + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index f75d92e4f96b..e74b6d530cb6 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -195,8 +195,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port) rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_LINK, err); + rtnl_set_sk_err(net, RTNLGRP_LINK, err); } @@ -373,7 +372,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh) p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself if the AF_SPEC - * is set to see if someone is setting vlan info on the brigde + * is set to see if someone is setting vlan info on the bridge */ if (!p && !afspec) return -EINVAL; @@ -389,7 +388,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh) err = br_setport(p, tb); spin_unlock_bh(&p->br->lock); } else { - /* Binary compatability with old RSTP */ + /* Binary compatibility with old RSTP */ if (nla_len(protinfo) < sizeof(u8)) return -EINVAL; @@ -482,9 +481,7 @@ int __init br_netlink_init(void) int err; br_mdb_init(); - err = rtnl_af_register(&br_af_ops); - if (err) - goto out; + rtnl_af_register(&br_af_ops); err = rtnl_link_register(&br_link_ops); if (err) @@ -494,7 +491,6 @@ int __init br_netlink_init(void) out_af: rtnl_af_unregister(&br_af_ops); -out: br_mdb_uninit(); return err; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 045d56eaeca2..3ba11bc99b65 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -104,6 +104,7 @@ struct net_bridge_fdb_entry mac_addr addr; unsigned char is_local; unsigned char is_static; + unsigned char added_by_user; __u16 vlan_id; }; @@ -210,21 +211,13 @@ static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device * rtnl_dereference(dev->rx_handler_data) : NULL; } -struct br_cpu_netstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; -}; - struct net_bridge { spinlock_t lock; struct list_head port_list; struct net_device *dev; - struct br_cpu_netstats __percpu *stats; + struct pcpu_sw_netstats __percpu *stats; spinlock_t hash_lock; struct hlist_head hash[BR_HASH_SIZE]; #ifdef CONFIG_BRIDGE_NETFILTER @@ -378,6 +371,9 @@ static inline void br_netpoll_disable(struct net_bridge_port *p) int br_fdb_init(void); void br_fdb_fini(void); void br_fdb_flush(struct net_bridge *br); +void br_fdb_find_delete_local(struct net_bridge *br, + const struct net_bridge_port *p, + const unsigned char *addr, u16 vid); void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr); void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr); void br_fdb_cleanup(unsigned long arg); @@ -391,8 +387,7 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, unsigned long count, int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid); void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr, u16 vid); -int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vid); + const unsigned char *addr, u16 vid, bool added_by_user); int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr); @@ -415,7 +410,6 @@ void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, void br_port_carrier_check(struct net_bridge_port *p); int br_add_bridge(struct net *net, const char *name); int br_del_bridge(struct net *net, const char *name); -void br_net_exit(struct net *net); int br_add_if(struct net_bridge *br, struct net_device *dev); int br_del_if(struct net_bridge *br, struct net_device *dev); int br_min_mtu(const struct net_bridge *br); @@ -593,6 +587,7 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags); int br_vlan_delete(struct net_bridge *br, u16 vid); void br_vlan_flush(struct net_bridge *br); +bool br_vlan_find(struct net_bridge *br, u16 vid); int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags); int nbp_vlan_delete(struct net_bridge_port *port, u16 vid); @@ -674,6 +669,11 @@ static inline void br_vlan_flush(struct net_bridge *br) { } +static inline bool br_vlan_find(struct net_bridge *br, u16 vid) +{ + return false; +} + static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) { return -EOPNOTSUPP; @@ -721,7 +721,7 @@ void br_netfilter_fini(void); void br_netfilter_rtable_init(struct net_bridge *); #else #define br_netfilter_init() (0) -#define br_netfilter_fini() do { } while(0) +#define br_netfilter_fini() do { } while (0) #define br_netfilter_rtable_init(x) #endif diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 656a6f3e40de..189ba1e7d851 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -194,6 +194,8 @@ void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr) wasroot = br_is_root_bridge(br); + br_fdb_change_mac_address(br, addr); + memcpy(oldaddr, br->bridge_id.addr, ETH_ALEN); memcpy(br->bridge_id.addr, addr, ETH_ALEN); memcpy(br->dev->dev_addr, addr, ETH_ALEN); diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 950663d4d330..558c46d19e05 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -110,7 +110,7 @@ static void br_tcn_timer_expired(unsigned long arg) if (!br_is_root_bridge(br) && (br->dev->flags & IFF_UP)) { br_transmit_tcn(br); - mod_timer(&br->tcn_timer,jiffies + br->bridge_hello_time); + mod_timer(&br->tcn_timer, jiffies + br->bridge_hello_time); } spin_unlock(&br->lock); } diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 3b9637fb7939..8dac65552f19 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -49,53 +49,51 @@ static ssize_t store_bridge_parm(struct device *d, } -static ssize_t show_forward_delay(struct device *d, +static ssize_t forward_delay_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->forward_delay)); } -static ssize_t store_forward_delay(struct device *d, +static ssize_t forward_delay_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_set_forward_delay); } -static DEVICE_ATTR(forward_delay, S_IRUGO | S_IWUSR, - show_forward_delay, store_forward_delay); +static DEVICE_ATTR_RW(forward_delay); -static ssize_t show_hello_time(struct device *d, struct device_attribute *attr, +static ssize_t hello_time_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%lu\n", jiffies_to_clock_t(to_bridge(d)->hello_time)); } -static ssize_t store_hello_time(struct device *d, +static ssize_t hello_time_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_set_hello_time); } -static DEVICE_ATTR(hello_time, S_IRUGO | S_IWUSR, show_hello_time, - store_hello_time); +static DEVICE_ATTR_RW(hello_time); -static ssize_t show_max_age(struct device *d, struct device_attribute *attr, +static ssize_t max_age_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%lu\n", jiffies_to_clock_t(to_bridge(d)->max_age)); } -static ssize_t store_max_age(struct device *d, struct device_attribute *attr, +static ssize_t max_age_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_set_max_age); } -static DEVICE_ATTR(max_age, S_IRUGO | S_IWUSR, show_max_age, store_max_age); +static DEVICE_ATTR_RW(max_age); -static ssize_t show_ageing_time(struct device *d, +static ssize_t ageing_time_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -108,16 +106,15 @@ static int set_ageing_time(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_ageing_time(struct device *d, +static ssize_t ageing_time_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_ageing_time); } -static DEVICE_ATTR(ageing_time, S_IRUGO | S_IWUSR, show_ageing_time, - store_ageing_time); +static DEVICE_ATTR_RW(ageing_time); -static ssize_t show_stp_state(struct device *d, +static ssize_t stp_state_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -125,7 +122,7 @@ static ssize_t show_stp_state(struct device *d, } -static ssize_t store_stp_state(struct device *d, +static ssize_t stp_state_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { @@ -147,20 +144,21 @@ static ssize_t store_stp_state(struct device *d, return len; } -static DEVICE_ATTR(stp_state, S_IRUGO | S_IWUSR, show_stp_state, - store_stp_state); +static DEVICE_ATTR_RW(stp_state); -static ssize_t show_group_fwd_mask(struct device *d, - struct device_attribute *attr, char *buf) +static ssize_t group_fwd_mask_show(struct device *d, + struct device_attribute *attr, + char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%#x\n", br->group_fwd_mask); } -static ssize_t store_group_fwd_mask(struct device *d, - struct device_attribute *attr, const char *buf, - size_t len) +static ssize_t group_fwd_mask_store(struct device *d, + struct device_attribute *attr, + const char *buf, + size_t len) { struct net_bridge *br = to_bridge(d); char *endp; @@ -180,10 +178,9 @@ static ssize_t store_group_fwd_mask(struct device *d, return len; } -static DEVICE_ATTR(group_fwd_mask, S_IRUGO | S_IWUSR, show_group_fwd_mask, - store_group_fwd_mask); +static DEVICE_ATTR_RW(group_fwd_mask); -static ssize_t show_priority(struct device *d, struct device_attribute *attr, +static ssize_t priority_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -197,93 +194,91 @@ static int set_priority(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_priority(struct device *d, struct device_attribute *attr, - const char *buf, size_t len) +static ssize_t priority_store(struct device *d, struct device_attribute *attr, + const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_priority); } -static DEVICE_ATTR(priority, S_IRUGO | S_IWUSR, show_priority, store_priority); +static DEVICE_ATTR_RW(priority); -static ssize_t show_root_id(struct device *d, struct device_attribute *attr, +static ssize_t root_id_show(struct device *d, struct device_attribute *attr, char *buf) { return br_show_bridge_id(buf, &to_bridge(d)->designated_root); } -static DEVICE_ATTR(root_id, S_IRUGO, show_root_id, NULL); +static DEVICE_ATTR_RO(root_id); -static ssize_t show_bridge_id(struct device *d, struct device_attribute *attr, +static ssize_t bridge_id_show(struct device *d, struct device_attribute *attr, char *buf) { return br_show_bridge_id(buf, &to_bridge(d)->bridge_id); } -static DEVICE_ATTR(bridge_id, S_IRUGO, show_bridge_id, NULL); +static DEVICE_ATTR_RO(bridge_id); -static ssize_t show_root_port(struct device *d, struct device_attribute *attr, +static ssize_t root_port_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", to_bridge(d)->root_port); } -static DEVICE_ATTR(root_port, S_IRUGO, show_root_port, NULL); +static DEVICE_ATTR_RO(root_port); -static ssize_t show_root_path_cost(struct device *d, +static ssize_t root_path_cost_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", to_bridge(d)->root_path_cost); } -static DEVICE_ATTR(root_path_cost, S_IRUGO, show_root_path_cost, NULL); +static DEVICE_ATTR_RO(root_path_cost); -static ssize_t show_topology_change(struct device *d, +static ssize_t topology_change_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", to_bridge(d)->topology_change); } -static DEVICE_ATTR(topology_change, S_IRUGO, show_topology_change, NULL); +static DEVICE_ATTR_RO(topology_change); -static ssize_t show_topology_change_detected(struct device *d, +static ssize_t topology_change_detected_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br->topology_change_detected); } -static DEVICE_ATTR(topology_change_detected, S_IRUGO, - show_topology_change_detected, NULL); +static DEVICE_ATTR_RO(topology_change_detected); -static ssize_t show_hello_timer(struct device *d, +static ssize_t hello_timer_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%ld\n", br_timer_value(&br->hello_timer)); } -static DEVICE_ATTR(hello_timer, S_IRUGO, show_hello_timer, NULL); +static DEVICE_ATTR_RO(hello_timer); -static ssize_t show_tcn_timer(struct device *d, struct device_attribute *attr, +static ssize_t tcn_timer_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%ld\n", br_timer_value(&br->tcn_timer)); } -static DEVICE_ATTR(tcn_timer, S_IRUGO, show_tcn_timer, NULL); +static DEVICE_ATTR_RO(tcn_timer); -static ssize_t show_topology_change_timer(struct device *d, +static ssize_t topology_change_timer_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%ld\n", br_timer_value(&br->topology_change_timer)); } -static DEVICE_ATTR(topology_change_timer, S_IRUGO, show_topology_change_timer, - NULL); +static DEVICE_ATTR_RO(topology_change_timer); -static ssize_t show_gc_timer(struct device *d, struct device_attribute *attr, +static ssize_t gc_timer_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%ld\n", br_timer_value(&br->gc_timer)); } -static DEVICE_ATTR(gc_timer, S_IRUGO, show_gc_timer, NULL); +static DEVICE_ATTR_RO(gc_timer); -static ssize_t show_group_addr(struct device *d, +static ssize_t group_addr_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -293,7 +288,7 @@ static ssize_t show_group_addr(struct device *d, br->group_addr[4], br->group_addr[5]); } -static ssize_t store_group_addr(struct device *d, +static ssize_t group_addr_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { @@ -324,10 +319,9 @@ static ssize_t store_group_addr(struct device *d, return len; } -static DEVICE_ATTR(group_addr, S_IRUGO | S_IWUSR, - show_group_addr, store_group_addr); +static DEVICE_ATTR_RW(group_addr); -static ssize_t store_flush(struct device *d, +static ssize_t flush_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { @@ -339,26 +333,25 @@ static ssize_t store_flush(struct device *d, br_fdb_flush(br); return len; } -static DEVICE_ATTR(flush, S_IWUSR, NULL, store_flush); +static DEVICE_ATTR_WO(flush); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING -static ssize_t show_multicast_router(struct device *d, +static ssize_t multicast_router_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br->multicast_router); } -static ssize_t store_multicast_router(struct device *d, +static ssize_t multicast_router_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_multicast_set_router); } -static DEVICE_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router, - store_multicast_router); +static DEVICE_ATTR_RW(multicast_router); -static ssize_t show_multicast_snooping(struct device *d, +static ssize_t multicast_snooping_show(struct device *d, struct device_attribute *attr, char *buf) { @@ -366,18 +359,17 @@ static ssize_t show_multicast_snooping(struct device *d, return sprintf(buf, "%d\n", !br->multicast_disabled); } -static ssize_t store_multicast_snooping(struct device *d, +static ssize_t multicast_snooping_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_multicast_toggle); } -static DEVICE_ATTR(multicast_snooping, S_IRUGO | S_IWUSR, - show_multicast_snooping, store_multicast_snooping); +static DEVICE_ATTR_RW(multicast_snooping); -static ssize_t show_multicast_query_use_ifaddr(struct device *d, - struct device_attribute *attr, - char *buf) +static ssize_t multicast_query_use_ifaddr_show(struct device *d, + struct device_attribute *attr, + char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br->multicast_query_use_ifaddr); @@ -390,17 +382,15 @@ static int set_query_use_ifaddr(struct net_bridge *br, unsigned long val) } static ssize_t -store_multicast_query_use_ifaddr(struct device *d, +multicast_query_use_ifaddr_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_query_use_ifaddr); } -static DEVICE_ATTR(multicast_query_use_ifaddr, S_IRUGO | S_IWUSR, - show_multicast_query_use_ifaddr, - store_multicast_query_use_ifaddr); +static DEVICE_ATTR_RW(multicast_query_use_ifaddr); -static ssize_t show_multicast_querier(struct device *d, +static ssize_t multicast_querier_show(struct device *d, struct device_attribute *attr, char *buf) { @@ -408,16 +398,15 @@ static ssize_t show_multicast_querier(struct device *d, return sprintf(buf, "%d\n", br->multicast_querier); } -static ssize_t store_multicast_querier(struct device *d, +static ssize_t multicast_querier_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_multicast_set_querier); } -static DEVICE_ATTR(multicast_querier, S_IRUGO | S_IWUSR, - show_multicast_querier, store_multicast_querier); +static DEVICE_ATTR_RW(multicast_querier); -static ssize_t show_hash_elasticity(struct device *d, +static ssize_t hash_elasticity_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -430,31 +419,29 @@ static int set_elasticity(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_hash_elasticity(struct device *d, +static ssize_t hash_elasticity_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_elasticity); } -static DEVICE_ATTR(hash_elasticity, S_IRUGO | S_IWUSR, show_hash_elasticity, - store_hash_elasticity); +static DEVICE_ATTR_RW(hash_elasticity); -static ssize_t show_hash_max(struct device *d, struct device_attribute *attr, +static ssize_t hash_max_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%u\n", br->hash_max); } -static ssize_t store_hash_max(struct device *d, struct device_attribute *attr, +static ssize_t hash_max_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_multicast_set_hash_max); } -static DEVICE_ATTR(hash_max, S_IRUGO | S_IWUSR, show_hash_max, - store_hash_max); +static DEVICE_ATTR_RW(hash_max); -static ssize_t show_multicast_last_member_count(struct device *d, +static ssize_t multicast_last_member_count_show(struct device *d, struct device_attribute *attr, char *buf) { @@ -468,17 +455,15 @@ static int set_last_member_count(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_multicast_last_member_count(struct device *d, +static ssize_t multicast_last_member_count_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_last_member_count); } -static DEVICE_ATTR(multicast_last_member_count, S_IRUGO | S_IWUSR, - show_multicast_last_member_count, - store_multicast_last_member_count); +static DEVICE_ATTR_RW(multicast_last_member_count); -static ssize_t show_multicast_startup_query_count( +static ssize_t multicast_startup_query_count_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -491,17 +476,15 @@ static int set_startup_query_count(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_multicast_startup_query_count( +static ssize_t multicast_startup_query_count_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_startup_query_count); } -static DEVICE_ATTR(multicast_startup_query_count, S_IRUGO | S_IWUSR, - show_multicast_startup_query_count, - store_multicast_startup_query_count); +static DEVICE_ATTR_RW(multicast_startup_query_count); -static ssize_t show_multicast_last_member_interval( +static ssize_t multicast_last_member_interval_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -515,17 +498,15 @@ static int set_last_member_interval(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_multicast_last_member_interval( +static ssize_t multicast_last_member_interval_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_last_member_interval); } -static DEVICE_ATTR(multicast_last_member_interval, S_IRUGO | S_IWUSR, - show_multicast_last_member_interval, - store_multicast_last_member_interval); +static DEVICE_ATTR_RW(multicast_last_member_interval); -static ssize_t show_multicast_membership_interval( +static ssize_t multicast_membership_interval_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -539,17 +520,15 @@ static int set_membership_interval(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_multicast_membership_interval( +static ssize_t multicast_membership_interval_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_membership_interval); } -static DEVICE_ATTR(multicast_membership_interval, S_IRUGO | S_IWUSR, - show_multicast_membership_interval, - store_multicast_membership_interval); +static DEVICE_ATTR_RW(multicast_membership_interval); -static ssize_t show_multicast_querier_interval(struct device *d, +static ssize_t multicast_querier_interval_show(struct device *d, struct device_attribute *attr, char *buf) { @@ -564,17 +543,15 @@ static int set_querier_interval(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_multicast_querier_interval(struct device *d, +static ssize_t multicast_querier_interval_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_querier_interval); } -static DEVICE_ATTR(multicast_querier_interval, S_IRUGO | S_IWUSR, - show_multicast_querier_interval, - store_multicast_querier_interval); +static DEVICE_ATTR_RW(multicast_querier_interval); -static ssize_t show_multicast_query_interval(struct device *d, +static ssize_t multicast_query_interval_show(struct device *d, struct device_attribute *attr, char *buf) { @@ -589,17 +566,15 @@ static int set_query_interval(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_multicast_query_interval(struct device *d, +static ssize_t multicast_query_interval_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_query_interval); } -static DEVICE_ATTR(multicast_query_interval, S_IRUGO | S_IWUSR, - show_multicast_query_interval, - store_multicast_query_interval); +static DEVICE_ATTR_RW(multicast_query_interval); -static ssize_t show_multicast_query_response_interval( +static ssize_t multicast_query_response_interval_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -614,17 +589,15 @@ static int set_query_response_interval(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_multicast_query_response_interval( +static ssize_t multicast_query_response_interval_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_query_response_interval); } -static DEVICE_ATTR(multicast_query_response_interval, S_IRUGO | S_IWUSR, - show_multicast_query_response_interval, - store_multicast_query_response_interval); +static DEVICE_ATTR_RW(multicast_query_response_interval); -static ssize_t show_multicast_startup_query_interval( +static ssize_t multicast_startup_query_interval_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -639,18 +612,16 @@ static int set_startup_query_interval(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_multicast_startup_query_interval( +static ssize_t multicast_startup_query_interval_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_startup_query_interval); } -static DEVICE_ATTR(multicast_startup_query_interval, S_IRUGO | S_IWUSR, - show_multicast_startup_query_interval, - store_multicast_startup_query_interval); +static DEVICE_ATTR_RW(multicast_startup_query_interval); #endif #ifdef CONFIG_BRIDGE_NETFILTER -static ssize_t show_nf_call_iptables( +static ssize_t nf_call_iptables_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -663,16 +634,15 @@ static int set_nf_call_iptables(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_nf_call_iptables( +static ssize_t nf_call_iptables_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_nf_call_iptables); } -static DEVICE_ATTR(nf_call_iptables, S_IRUGO | S_IWUSR, - show_nf_call_iptables, store_nf_call_iptables); +static DEVICE_ATTR_RW(nf_call_iptables); -static ssize_t show_nf_call_ip6tables( +static ssize_t nf_call_ip6tables_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -685,16 +655,15 @@ static int set_nf_call_ip6tables(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_nf_call_ip6tables( +static ssize_t nf_call_ip6tables_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_nf_call_ip6tables); } -static DEVICE_ATTR(nf_call_ip6tables, S_IRUGO | S_IWUSR, - show_nf_call_ip6tables, store_nf_call_ip6tables); +static DEVICE_ATTR_RW(nf_call_ip6tables); -static ssize_t show_nf_call_arptables( +static ssize_t nf_call_arptables_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); @@ -707,17 +676,16 @@ static int set_nf_call_arptables(struct net_bridge *br, unsigned long val) return 0; } -static ssize_t store_nf_call_arptables( +static ssize_t nf_call_arptables_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_nf_call_arptables); } -static DEVICE_ATTR(nf_call_arptables, S_IRUGO | S_IWUSR, - show_nf_call_arptables, store_nf_call_arptables); +static DEVICE_ATTR_RW(nf_call_arptables); #endif #ifdef CONFIG_BRIDGE_VLAN_FILTERING -static ssize_t show_vlan_filtering(struct device *d, +static ssize_t vlan_filtering_show(struct device *d, struct device_attribute *attr, char *buf) { @@ -725,14 +693,13 @@ static ssize_t show_vlan_filtering(struct device *d, return sprintf(buf, "%d\n", br->vlan_enabled); } -static ssize_t store_vlan_filtering(struct device *d, +static ssize_t vlan_filtering_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_vlan_filter_toggle); } -static DEVICE_ATTR(vlan_filtering, S_IRUGO | S_IWUSR, - show_vlan_filtering, store_vlan_filtering); +static DEVICE_ATTR_RW(vlan_filtering); #endif static struct attribute *bridge_attrs[] = { diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 2a2cdb756d51..dd595bd7fa82 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -26,7 +26,7 @@ struct brport_attribute { int (*store)(struct net_bridge_port *, unsigned long); }; -#define BRPORT_ATTR(_name,_mode,_show,_store) \ +#define BRPORT_ATTR(_name, _mode, _show, _store) \ const struct brport_attribute brport_attr_##_name = { \ .attr = {.name = __stringify(_name), \ .mode = _mode }, \ @@ -209,21 +209,21 @@ static const struct brport_attribute *brport_attrs[] = { #define to_brport_attr(_at) container_of(_at, struct brport_attribute, attr) #define to_brport(obj) container_of(obj, struct net_bridge_port, kobj) -static ssize_t brport_show(struct kobject * kobj, - struct attribute * attr, char * buf) +static ssize_t brport_show(struct kobject *kobj, + struct attribute *attr, char *buf) { - struct brport_attribute * brport_attr = to_brport_attr(attr); - struct net_bridge_port * p = to_brport(kobj); + struct brport_attribute *brport_attr = to_brport_attr(attr); + struct net_bridge_port *p = to_brport(kobj); return brport_attr->show(p, buf); } -static ssize_t brport_store(struct kobject * kobj, - struct attribute * attr, - const char * buf, size_t count) +static ssize_t brport_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t count) { - struct brport_attribute * brport_attr = to_brport_attr(attr); - struct net_bridge_port * p = to_brport(kobj); + struct brport_attribute *brport_attr = to_brport_attr(attr); + struct net_bridge_port *p = to_brport(kobj); ssize_t ret = -EINVAL; char *endp; unsigned long val; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index af5ebd18d705..8249ca764c79 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -146,32 +146,11 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, /* At this point, we know that the frame was filtered and contains * a valid vlan id. If the vlan id is set in the untagged bitmap, - * send untagged; otherwise, send taged. + * send untagged; otherwise, send tagged. */ br_vlan_get_tag(skb, &vid); if (test_bit(vid, pv->untagged_bitmap)) skb = br_vlan_untag(skb); - else { - /* Egress policy says "send tagged". If output device - * is the bridge, we need to add the VLAN header - * ourselves since we'll be going through the RX path. - * Sending to ports puts the frame on the TX path and - * we let dev_hard_start_xmit() add the header. - */ - if (skb->protocol != htons(ETH_P_8021Q) && - pv->port_idx == 0) { - /* vlan_put_tag expects skb->data to point to - * mac header. - */ - skb_push(skb, ETH_HLEN); - skb = __vlan_put_tag(skb, skb->vlan_proto, skb->vlan_tci); - if (!skb) - goto out; - /* put skb->data back to where it was */ - skb_pull(skb, ETH_HLEN); - skb->vlan_tci = 0; - } - } out: return skb; @@ -296,9 +275,7 @@ int br_vlan_delete(struct net_bridge *br, u16 vid) if (!pv) return -EINVAL; - spin_lock_bh(&br->hash_lock); - fdb_delete_by_addr(br, br->dev->dev_addr, vid); - spin_unlock_bh(&br->hash_lock); + br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); __vlan_del(pv, vid); return 0; @@ -316,6 +293,25 @@ void br_vlan_flush(struct net_bridge *br) __vlan_flush(pv); } +bool br_vlan_find(struct net_bridge *br, u16 vid) +{ + struct net_port_vlans *pv; + bool found = false; + + rcu_read_lock(); + pv = rcu_dereference(br->vlan_info); + + if (!pv) + goto out; + + if (test_bit(vid, pv->vlan_bitmap)) + found = true; + +out: + rcu_read_unlock(); + return found; +} + int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) { if (!rtnl_trylock()) @@ -380,9 +376,7 @@ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) if (!pv) return -EINVAL; - spin_lock_bh(&port->br->hash_lock); - fdb_delete_by_addr(port->br, port->dev->dev_addr, vid); - spin_unlock_bh(&port->br->hash_lock); + br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); return __vlan_del(pv, vid); } diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index 19c37a4929bc..5322a36867a3 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -96,7 +96,7 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, bitmask = NF_LOG_MASK; if ((bitmask & EBT_LOG_IP) && eth_hdr(skb)->h_proto == - htons(ETH_P_IP)){ + htons(ETH_P_IP)) { const struct iphdr *ih; struct iphdr _iph; diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index f8f0bd1a1d51..0f6b118d6cb2 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -35,7 +35,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par) return EBT_DROP; if (ap->ar_hln != ETH_ALEN) goto out; - if (skb_store_bits(skb, sizeof(_ah), info->mac,ETH_ALEN)) + if (skb_store_bits(skb, sizeof(_ah), info->mac, ETH_ALEN)) return EBT_DROP; } out: diff --git a/net/bridge/netfilter/ebt_vlan.c b/net/bridge/netfilter/ebt_vlan.c index eae67bf0446c..8d3f8c7651f0 100644 --- a/net/bridge/netfilter/ebt_vlan.c +++ b/net/bridge/netfilter/ebt_vlan.c @@ -14,8 +14,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/if_ether.h> diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index dbd1c783431b..d2cdf5d6e98c 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -23,8 +23,7 @@ static struct ebt_entries initial_chain = { .policy = EBT_ACCEPT, }; -static struct ebt_replace_kernel initial_table = -{ +static struct ebt_replace_kernel initial_table = { .name = "broute", .valid_hooks = 1 << NF_BR_BROUTING, .entries_size = sizeof(struct ebt_entries), @@ -41,8 +40,7 @@ static int check(const struct ebt_table_info *info, unsigned int valid_hooks) return 0; } -static const struct ebt_table broute_table = -{ +static const struct ebt_table broute_table = { .name = "broute", .table = &initial_table, .valid_hooks = 1 << NF_BR_BROUTING, diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index bb2da7b706e7..ce205aabf9c5 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -14,8 +14,7 @@ #define FILTER_VALID_HOOKS ((1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | \ (1 << NF_BR_LOCAL_OUT)) -static struct ebt_entries initial_chains[] = -{ +static struct ebt_entries initial_chains[] = { { .name = "INPUT", .policy = EBT_ACCEPT, @@ -30,8 +29,7 @@ static struct ebt_entries initial_chains[] = }, }; -static struct ebt_replace_kernel initial_table = -{ +static struct ebt_replace_kernel initial_table = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .entries_size = 3 * sizeof(struct ebt_entries), @@ -50,8 +48,7 @@ static int check(const struct ebt_table_info *info, unsigned int valid_hooks) return 0; } -static const struct ebt_table frame_filter = -{ +static const struct ebt_table frame_filter = { .name = "filter", .table = &initial_table, .valid_hooks = FILTER_VALID_HOOKS, diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index bd238f1f105b..a0ac2984fb6c 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -14,8 +14,7 @@ #define NAT_VALID_HOOKS ((1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_OUT) | \ (1 << NF_BR_POST_ROUTING)) -static struct ebt_entries initial_chains[] = -{ +static struct ebt_entries initial_chains[] = { { .name = "PREROUTING", .policy = EBT_ACCEPT, @@ -30,8 +29,7 @@ static struct ebt_entries initial_chains[] = } }; -static struct ebt_replace_kernel initial_table = -{ +static struct ebt_replace_kernel initial_table = { .name = "nat", .valid_hooks = NAT_VALID_HOOKS, .entries_size = 3 * sizeof(struct ebt_entries), @@ -50,8 +48,7 @@ static int check(const struct ebt_table_info *info, unsigned int valid_hooks) return 0; } -static struct ebt_table frame_nat = -{ +static struct ebt_table frame_nat = { .name = "nat", .table = &initial_table, .valid_hooks = NAT_VALID_HOOKS, diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index ac7802428384..0e474b13463b 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -118,10 +118,10 @@ ebt_dev_check(const char *entry, const struct net_device *device) /* 1 is the wildcard token */ while (entry[i] != '\0' && entry[i] != 1 && entry[i] == devname[i]) i++; - return (devname[i] != entry[i] && entry[i] != 1); + return devname[i] != entry[i] && entry[i] != 1; } -#define FWINV2(bool,invflg) ((bool) ^ !!(e->invflags & invflg)) +#define FWINV2(bool, invflg) ((bool) ^ !!(e->invflags & invflg)) /* process standard matches */ static inline int ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb, @@ -1441,7 +1441,7 @@ static int copy_everything_to_user(struct ebt_table *t, void __user *user, return -EFAULT; if (*len != sizeof(struct ebt_replace) + entries_size + - (tmp.num_counters? nentries * sizeof(struct ebt_counter): 0)) + (tmp.num_counters ? nentries * sizeof(struct ebt_counter) : 0)) return -EINVAL; if (tmp.nentries != nentries) { @@ -1477,7 +1477,7 @@ static int do_ebt_set_ctl(struct sock *sk, if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - switch(cmd) { + switch (cmd) { case EBT_SO_SET_ENTRIES: ret = do_replace(net, user, len); break; @@ -1507,10 +1507,10 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) if (!t) return ret; - switch(cmd) { + switch (cmd) { case EBT_SO_GET_INFO: case EBT_SO_GET_INIT_INFO: - if (*len != sizeof(struct ebt_replace)){ + if (*len != sizeof(struct ebt_replace)) { ret = -EINVAL; mutex_unlock(&ebt_mutex); break; @@ -1525,7 +1525,7 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) tmp.valid_hooks = t->table->valid_hooks; } mutex_unlock(&ebt_mutex); - if (copy_to_user(user, &tmp, *len) != 0){ + if (copy_to_user(user, &tmp, *len) != 0) { BUGPRINT("c2u Didn't work\n"); ret = -EFAULT; break; @@ -2375,8 +2375,7 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd, } #endif -static struct nf_sockopt_ops ebt_sockopts = -{ +static struct nf_sockopt_ops ebt_sockopts = { .pf = PF_INET, .set_optmin = EBT_BASE_CTL, .set_optmax = EBT_SO_SET_MAX + 1, diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c index cf54b22818c8..5bcc0d8b31f2 100644 --- a/net/bridge/netfilter/nf_tables_bridge.c +++ b/net/bridge/netfilter/nf_tables_bridge.c @@ -14,10 +14,30 @@ #include <linux/netfilter_bridge.h> #include <net/netfilter/nf_tables.h> +static unsigned int +nft_do_chain_bridge(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nft_pktinfo pkt; + + nft_set_pktinfo(&pkt, ops, skb, in, out); + + return nft_do_chain(&pkt, ops); +} + static struct nft_af_info nft_af_bridge __read_mostly = { .family = NFPROTO_BRIDGE, .nhooks = NF_BR_NUMHOOKS, .owner = THIS_MODULE, + .nops = 1, + .hooks = { + [NF_BR_LOCAL_IN] = nft_do_chain_bridge, + [NF_BR_FORWARD] = nft_do_chain_bridge, + [NF_BR_LOCAL_OUT] = nft_do_chain_bridge, + }, }; static int nf_tables_bridge_init_net(struct net *net) @@ -48,32 +68,14 @@ static struct pernet_operations nf_tables_bridge_net_ops = { .exit = nf_tables_bridge_exit_net, }; -static unsigned int -nft_do_chain_bridge(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct nft_pktinfo pkt; - - nft_set_pktinfo(&pkt, ops, skb, in, out); - - return nft_do_chain_pktinfo(&pkt, ops); -} - -static struct nf_chain_type filter_bridge = { - .family = NFPROTO_BRIDGE, +static const struct nf_chain_type filter_bridge = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, + .family = NFPROTO_BRIDGE, + .owner = THIS_MODULE, .hook_mask = (1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | (1 << NF_BR_LOCAL_OUT), - .fn = { - [NF_BR_LOCAL_IN] = nft_do_chain_bridge, - [NF_BR_FORWARD] = nft_do_chain_bridge, - [NF_BR_LOCAL_OUT] = nft_do_chain_bridge, - }, }; static int __init nf_tables_bridge_init(void) diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 4dca159435cf..edbca468fa73 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -22,6 +22,7 @@ #include <net/pkt_sched.h> #include <net/caif/caif_device.h> #include <net/caif/caif_layer.h> +#include <net/caif/caif_dev.h> #include <net/caif/cfpkt.h> #include <net/caif/cfcnfg.h> #include <net/caif/cfserl.h> diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index 75ed04b78fa4..ba02db022900 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -14,6 +14,7 @@ #include <linux/mii.h> #include <linux/usb.h> #include <linux/usb/usbnet.h> +#include <linux/etherdevice.h> #include <net/netns/generic.h> #include <net/caif/caif_dev.h> #include <net/caif/caif_layer.h> @@ -105,8 +106,8 @@ static struct cflayer *cfusbl_create(int phyid, u8 ethaddr[ETH_ALEN], * 5-11 source address * 12-13 protocol type */ - memcpy(&this->tx_eth_hdr[ETH_ALEN], braddr, ETH_ALEN); - memcpy(&this->tx_eth_hdr[ETH_ALEN], ethaddr, ETH_ALEN); + ether_addr_copy(&this->tx_eth_hdr[ETH_ALEN], braddr); + ether_addr_copy(&this->tx_eth_hdr[ETH_ALEN], ethaddr); this->tx_eth_hdr[12] = cpu_to_be16(ETH_P_802_EX1) & 0xff; this->tx_eth_hdr[13] = (cpu_to_be16(ETH_P_802_EX1) >> 8) & 0xff; pr_debug("caif ethernet TX-header dst:%pM src:%pM type:%02x%02x\n", diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c index 353f793d1b3b..a6e115463052 100644 --- a/net/caif/cfsrvl.c +++ b/net/caif/cfsrvl.c @@ -15,6 +15,7 @@ #include <net/caif/caif_layer.h> #include <net/caif/cfsrvl.h> #include <net/caif/cfpkt.h> +#include <net/caif/caif_dev.h> #define SRVL_CTRL_PKT_SIZE 1 #define SRVL_FLOW_OFF 0x81 diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 7344a8fa1bb0..4589ff67bfa9 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -285,7 +285,7 @@ static int chnl_net_open(struct net_device *dev) goto error; } - lldev = dev_get_by_index(dev_net(dev), llifindex); + lldev = __dev_get_by_index(dev_net(dev), llifindex); if (lldev == NULL) { pr_debug("no interface?\n"); @@ -307,7 +307,6 @@ static int chnl_net_open(struct net_device *dev) mtu = min_t(int, dev->mtu, lldev->mtu - (headroom + tailroom)); mtu = min_t(int, GPRS_PDP_MTU, mtu); dev_set_mtu(dev, mtu); - dev_put(lldev); if (mtu < 100) { pr_warn("CAIF Interface MTU too small (%d)\n", mtu); diff --git a/net/can/af_can.c b/net/can/af_can.c index d249874a366d..a27f8aad9e99 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> @@ -290,7 +291,7 @@ 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 46f20bfafc0e..dcb75c0e66c1 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); @@ -1256,8 +1256,7 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock, if (!ifindex && msg->msg_name) { /* no bound device as default => check msg_name */ - struct sockaddr_can *addr = - (struct sockaddr_can *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); if (msg->msg_namelen < sizeof(*addr)) return -EINVAL; @@ -1568,6 +1567,7 @@ static int bcm_recvmsg(struct kiocb *iocb, struct socket *sock, sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name) { + __sockaddr_check_size(sizeof(struct sockaddr_can)); msg->msg_namelen = sizeof(struct sockaddr_can); memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } diff --git a/net/can/gw.c b/net/can/gw.c index 3f9b0f3a2818..ac31891967da 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -839,23 +839,21 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh) if (!gwj->ccgw.src_idx || !gwj->ccgw.dst_idx) goto out; - gwj->src.dev = dev_get_by_index(&init_net, gwj->ccgw.src_idx); + gwj->src.dev = __dev_get_by_index(&init_net, gwj->ccgw.src_idx); if (!gwj->src.dev) goto out; - /* check for CAN netdev not using header_ops - see gw_rcv() */ - if (gwj->src.dev->type != ARPHRD_CAN || gwj->src.dev->header_ops) - goto put_src_out; + if (gwj->src.dev->type != ARPHRD_CAN) + goto out; - gwj->dst.dev = dev_get_by_index(&init_net, gwj->ccgw.dst_idx); + gwj->dst.dev = __dev_get_by_index(&init_net, gwj->ccgw.dst_idx); if (!gwj->dst.dev) - goto put_src_out; + goto out; - /* check for CAN netdev not using header_ops - see gw_rcv() */ - if (gwj->dst.dev->type != ARPHRD_CAN || gwj->dst.dev->header_ops) - goto put_src_dst_out; + if (gwj->dst.dev->type != ARPHRD_CAN) + goto out; gwj->limit_hops = limhops; @@ -864,11 +862,6 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh) err = cgw_register_filter(gwj); if (!err) hlist_add_head_rcu(&gwj->list, &cgw_list); - -put_src_dst_out: - dev_put(gwj->dst.dev); -put_src_out: - dev_put(gwj->src.dev); out: if (err) kmem_cache_free(cgw_cache, gwj); diff --git a/net/can/raw.c b/net/can/raw.c index 641e1c895123..8be757cca2ec 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -675,8 +675,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, int err; if (msg->msg_name) { - struct sockaddr_can *addr = - (struct sockaddr_can *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); if (msg->msg_namelen < sizeof(*addr)) return -EINVAL; @@ -716,6 +715,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, skb->dev = dev; skb->sk = sk; + skb->priority = sk->sk_priority; err = can_send(skb, ro->loopback); @@ -775,6 +775,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name) { + __sockaddr_check_size(sizeof(struct sockaddr_can)); msg->msg_namelen = sizeof(struct sockaddr_can); memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c index bf3e6a13c215..621b5f65407f 100644 --- a/net/ceph/buffer.c +++ b/net/ceph/buffer.c @@ -6,6 +6,7 @@ #include <linux/ceph/buffer.h> #include <linux/ceph/decode.h> +#include <linux/ceph/libceph.h> /* for ceph_kv{malloc,free} */ struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp) { @@ -15,16 +16,10 @@ struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp) if (!b) return NULL; - b->vec.iov_base = kmalloc(len, gfp | __GFP_NOWARN); - if (b->vec.iov_base) { - b->is_vmalloc = false; - } else { - b->vec.iov_base = __vmalloc(len, gfp | __GFP_HIGHMEM, PAGE_KERNEL); - if (!b->vec.iov_base) { - kfree(b); - return NULL; - } - b->is_vmalloc = true; + b->vec.iov_base = ceph_kvmalloc(len, gfp); + if (!b->vec.iov_base) { + kfree(b); + return NULL; } kref_init(&b->kref); @@ -40,12 +35,7 @@ void ceph_buffer_release(struct kref *kref) struct ceph_buffer *b = container_of(kref, struct ceph_buffer, kref); dout("buffer_release %p\n", b); - if (b->vec.iov_base) { - if (b->is_vmalloc) - vfree(b->vec.iov_base); - else - kfree(b->vec.iov_base); - } + ceph_kvfree(b->vec.iov_base); kfree(b); } EXPORT_SYMBOL(ceph_buffer_release); diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 34b11ee8124e..67d7721d237e 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -15,6 +15,7 @@ #include <linux/slab.h> #include <linux/statfs.h> #include <linux/string.h> +#include <linux/vmalloc.h> #include <linux/nsproxy.h> #include <net/net_namespace.h> @@ -170,6 +171,25 @@ int ceph_compare_options(struct ceph_options *new_opt, } EXPORT_SYMBOL(ceph_compare_options); +void *ceph_kvmalloc(size_t size, gfp_t flags) +{ + if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { + void *ptr = kmalloc(size, flags | __GFP_NOWARN); + if (ptr) + return ptr; + } + + return __vmalloc(size, flags | __GFP_HIGHMEM, PAGE_KERNEL); +} + +void ceph_kvfree(const void *ptr) +{ + if (is_vmalloc_addr(ptr)) + vfree(ptr); + else + kfree(ptr); +} + static int parse_fsid(const char *str, struct ceph_fsid *fsid) { @@ -461,8 +481,8 @@ EXPORT_SYMBOL(ceph_client_id); * create a fresh client instance */ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, - unsigned int supported_features, - unsigned int required_features) + u64 supported_features, + u64 required_features) { struct ceph_client *client; struct ceph_entity_addr *myaddr = NULL; diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c index 089613234f03..16bc199d9a62 100644 --- a/net/ceph/crush/crush.c +++ b/net/ceph/crush/crush.c @@ -116,11 +116,14 @@ void crush_destroy(struct crush_map *map) if (map->rules) { __u32 b; for (b = 0; b < map->max_rules; b++) - kfree(map->rules[b]); + crush_destroy_rule(map->rules[b]); kfree(map->rules); } kfree(map); } - +void crush_destroy_rule(struct crush_rule *rule) +{ + kfree(rule); +} diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index cbd06a91941c..b703790b4e44 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -189,7 +189,7 @@ static int terminal(int x) static int bucket_tree_choose(struct crush_bucket_tree *bucket, int x, int r) { - int n, l; + int n; __u32 w; __u64 t; @@ -197,6 +197,7 @@ static int bucket_tree_choose(struct crush_bucket_tree *bucket, n = bucket->num_nodes >> 1; while (!terminal(n)) { + int l; /* pick point in [0, w) */ w = bucket->node_weights[n]; t = (__u64)crush_hash32_4(bucket->h.hash, x, n, r, @@ -264,8 +265,12 @@ static int crush_bucket_choose(struct crush_bucket *in, int x, int r) * true if device is marked "out" (failed, fully offloaded) * of the cluster */ -static int is_out(const struct crush_map *map, const __u32 *weight, int item, int x) +static int is_out(const struct crush_map *map, + const __u32 *weight, int weight_max, + int item, int x) { + if (item >= weight_max) + return 1; if (weight[item] >= 0x10000) return 0; if (weight[item] == 0) @@ -277,7 +282,7 @@ static int is_out(const struct crush_map *map, const __u32 *weight, int item, in } /** - * crush_choose - choose numrep distinct items of given type + * crush_choose_firstn - choose numrep distinct items of given type * @map: the crush_map * @bucket: the bucket we are choose an item from * @x: crush input value @@ -285,18 +290,24 @@ static int is_out(const struct crush_map *map, const __u32 *weight, int item, in * @type: the type of item to choose * @out: pointer to output vector * @outpos: our position in that vector - * @firstn: true if choosing "first n" items, false if choosing "indep" - * @recurse_to_leaf: true if we want one device under each item of given type - * @descend_once: true if we should only try one descent before giving up + * @tries: number of attempts to make + * @recurse_tries: number of attempts to have recursive chooseleaf make + * @local_tries: localized retries + * @local_fallback_tries: localized fallback retries + * @recurse_to_leaf: true if we want one device under each item of given type (chooseleaf instead of choose) * @out2: second output vector for leaf items (if @recurse_to_leaf) */ -static int crush_choose(const struct crush_map *map, - struct crush_bucket *bucket, - const __u32 *weight, - int x, int numrep, int type, - int *out, int outpos, - int firstn, int recurse_to_leaf, - int descend_once, int *out2) +static int crush_choose_firstn(const struct crush_map *map, + struct crush_bucket *bucket, + const __u32 *weight, int weight_max, + int x, int numrep, int type, + int *out, int outpos, + unsigned int tries, + unsigned int recurse_tries, + unsigned int local_tries, + unsigned int local_fallback_tries, + int recurse_to_leaf, + int *out2) { int rep; unsigned int ftotal, flocal; @@ -325,35 +336,17 @@ static int crush_choose(const struct crush_map *map, collide = 0; retry_bucket = 0; r = rep; - if (in->alg == CRUSH_BUCKET_UNIFORM) { - /* be careful */ - if (firstn || (__u32)numrep >= in->size) - /* r' = r + f_total */ - r += ftotal; - else if (in->size % numrep == 0) - /* r'=r+(n+1)*f_local */ - r += (numrep+1) * - (flocal+ftotal); - else - /* r' = r + n*f_local */ - r += numrep * (flocal+ftotal); - } else { - if (firstn) - /* r' = r + f_total */ - r += ftotal; - else - /* r' = r + n*f_local */ - r += numrep * (flocal+ftotal); - } + /* r' = r + f_total */ + r += ftotal; /* bucket choose */ if (in->size == 0) { reject = 1; goto reject; } - if (map->choose_local_fallback_tries > 0 && + if (local_fallback_tries > 0 && flocal >= (in->size>>1) && - flocal > map->choose_local_fallback_tries) + flocal > local_fallback_tries) item = bucket_perm_choose(in, x, r); else item = crush_bucket_choose(in, x, r); @@ -394,13 +387,15 @@ static int crush_choose(const struct crush_map *map, reject = 0; if (!collide && recurse_to_leaf) { if (item < 0) { - if (crush_choose(map, + if (crush_choose_firstn(map, map->buckets[-1-item], - weight, + weight, weight_max, x, outpos+1, 0, out2, outpos, - firstn, 0, - map->chooseleaf_descend_once, + recurse_tries, 0, + local_tries, + local_fallback_tries, + 0, NULL) <= outpos) /* didn't get leaf */ reject = 1; @@ -414,6 +409,7 @@ static int crush_choose(const struct crush_map *map, /* out? */ if (itemtype == 0) reject = is_out(map, weight, + weight_max, item, x); else reject = 0; @@ -424,17 +420,14 @@ reject: ftotal++; flocal++; - if (reject && descend_once) - /* let outer call try again */ - skip_rep = 1; - else if (collide && flocal <= map->choose_local_tries) + if (collide && flocal <= local_tries) /* retry locally a few times */ retry_bucket = 1; - else if (map->choose_local_fallback_tries > 0 && - flocal <= in->size + map->choose_local_fallback_tries) + else if (local_fallback_tries > 0 && + flocal <= in->size + local_fallback_tries) /* exhaustive bucket search */ retry_bucket = 1; - else if (ftotal <= map->choose_total_tries) + else if (ftotal <= tries) /* then retry descent */ retry_descent = 1; else @@ -464,21 +457,179 @@ reject: /** + * crush_choose_indep: alternative breadth-first positionally stable mapping + * + */ +static void crush_choose_indep(const struct crush_map *map, + struct crush_bucket *bucket, + const __u32 *weight, int weight_max, + int x, int left, int numrep, int type, + int *out, int outpos, + unsigned int tries, + unsigned int recurse_tries, + int recurse_to_leaf, + int *out2, + int parent_r) +{ + struct crush_bucket *in = bucket; + int endpos = outpos + left; + int rep; + unsigned int ftotal; + int r; + int i; + int item = 0; + int itemtype; + int collide; + + dprintk("CHOOSE%s INDEP bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "", + bucket->id, x, outpos, numrep); + + /* initially my result is undefined */ + for (rep = outpos; rep < endpos; rep++) { + out[rep] = CRUSH_ITEM_UNDEF; + if (out2) + out2[rep] = CRUSH_ITEM_UNDEF; + } + + for (ftotal = 0; left > 0 && ftotal < tries; ftotal++) { + for (rep = outpos; rep < endpos; rep++) { + if (out[rep] != CRUSH_ITEM_UNDEF) + continue; + + in = bucket; /* initial bucket */ + + /* choose through intervening buckets */ + for (;;) { + /* note: we base the choice on the position + * even in the nested call. that means that + * if the first layer chooses the same bucket + * in a different position, we will tend to + * choose a different item in that bucket. + * this will involve more devices in data + * movement and tend to distribute the load. + */ + r = rep + parent_r; + + /* be careful */ + if (in->alg == CRUSH_BUCKET_UNIFORM && + in->size % numrep == 0) + /* r'=r+(n+1)*f_total */ + r += (numrep+1) * ftotal; + else + /* r' = r + n*f_total */ + r += numrep * ftotal; + + /* bucket choose */ + if (in->size == 0) { + dprintk(" empty bucket\n"); + break; + } + + item = crush_bucket_choose(in, x, r); + if (item >= map->max_devices) { + dprintk(" bad item %d\n", item); + out[rep] = CRUSH_ITEM_NONE; + if (out2) + out2[rep] = CRUSH_ITEM_NONE; + left--; + break; + } + + /* desired type? */ + if (item < 0) + itemtype = map->buckets[-1-item]->type; + else + itemtype = 0; + dprintk(" item %d type %d\n", item, itemtype); + + /* keep going? */ + if (itemtype != type) { + if (item >= 0 || + (-1-item) >= map->max_buckets) { + dprintk(" bad item type %d\n", type); + out[rep] = CRUSH_ITEM_NONE; + if (out2) + out2[rep] = + CRUSH_ITEM_NONE; + left--; + break; + } + in = map->buckets[-1-item]; + continue; + } + + /* collision? */ + collide = 0; + for (i = outpos; i < endpos; i++) { + if (out[i] == item) { + collide = 1; + break; + } + } + if (collide) + break; + + if (recurse_to_leaf) { + if (item < 0) { + crush_choose_indep(map, + map->buckets[-1-item], + weight, weight_max, + x, 1, numrep, 0, + out2, rep, + recurse_tries, 0, + 0, NULL, r); + if (out2[rep] == CRUSH_ITEM_NONE) { + /* placed nothing; no leaf */ + break; + } + } else { + /* we already have a leaf! */ + out2[rep] = item; + } + } + + /* out? */ + if (itemtype == 0 && + is_out(map, weight, weight_max, item, x)) + break; + + /* yay! */ + out[rep] = item; + left--; + break; + } + } + } + for (rep = outpos; rep < endpos; rep++) { + if (out[rep] == CRUSH_ITEM_UNDEF) { + out[rep] = CRUSH_ITEM_NONE; + } + if (out2 && out2[rep] == CRUSH_ITEM_UNDEF) { + out2[rep] = CRUSH_ITEM_NONE; + } + } +} + +/** * crush_do_rule - calculate a mapping with the given input and rule * @map: the crush_map * @ruleno: the rule id * @x: hash input * @result: pointer to result vector * @result_max: maximum result size + * @weight: weight vector (for map leaves) + * @weight_max: size of weight vector + * @scratch: scratch vector for private use; must be >= 3 * result_max */ int crush_do_rule(const struct crush_map *map, int ruleno, int x, int *result, int result_max, - const __u32 *weight) + const __u32 *weight, int weight_max, + int *scratch) { int result_len; - int a[CRUSH_MAX_SET]; - int b[CRUSH_MAX_SET]; - int c[CRUSH_MAX_SET]; + int *a = scratch; + int *b = scratch + result_max; + int *c = scratch + result_max*2; int recurse_to_leaf; int *w; int wsize = 0; @@ -489,8 +640,10 @@ int crush_do_rule(const struct crush_map *map, __u32 step; int i, j; int numrep; - int firstn; - const int descend_once = 0; + int choose_tries = map->choose_total_tries; + int choose_local_tries = map->choose_local_tries; + int choose_local_fallback_tries = map->choose_local_fallback_tries; + int choose_leaf_tries = 0; if ((__u32)ruleno >= map->max_rules) { dprintk(" bad ruleno %d\n", ruleno); @@ -503,29 +656,49 @@ int crush_do_rule(const struct crush_map *map, o = b; for (step = 0; step < rule->len; step++) { + int firstn = 0; struct crush_rule_step *curstep = &rule->steps[step]; - firstn = 0; switch (curstep->op) { case CRUSH_RULE_TAKE: w[0] = curstep->arg1; wsize = 1; break; - case CRUSH_RULE_CHOOSE_LEAF_FIRSTN: + case CRUSH_RULE_SET_CHOOSE_TRIES: + if (curstep->arg1 > 0) + choose_tries = curstep->arg1; + break; + + case CRUSH_RULE_SET_CHOOSELEAF_TRIES: + if (curstep->arg1 > 0) + choose_leaf_tries = curstep->arg1; + break; + + case CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES: + if (curstep->arg1 > 0) + choose_local_tries = curstep->arg1; + break; + + case CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES: + if (curstep->arg1 > 0) + choose_local_fallback_tries = curstep->arg1; + break; + + case CRUSH_RULE_CHOOSELEAF_FIRSTN: case CRUSH_RULE_CHOOSE_FIRSTN: firstn = 1; /* fall through */ - case CRUSH_RULE_CHOOSE_LEAF_INDEP: + case CRUSH_RULE_CHOOSELEAF_INDEP: case CRUSH_RULE_CHOOSE_INDEP: if (wsize == 0) break; recurse_to_leaf = curstep->op == - CRUSH_RULE_CHOOSE_LEAF_FIRSTN || + CRUSH_RULE_CHOOSELEAF_FIRSTN || curstep->op == - CRUSH_RULE_CHOOSE_LEAF_INDEP; + CRUSH_RULE_CHOOSELEAF_INDEP; /* reset output */ osize = 0; @@ -543,22 +716,51 @@ int crush_do_rule(const struct crush_map *map, continue; } j = 0; - osize += crush_choose(map, - map->buckets[-1-w[i]], - weight, - x, numrep, - curstep->arg2, - o+osize, j, - firstn, - recurse_to_leaf, - descend_once, c+osize); + if (firstn) { + int recurse_tries; + if (choose_leaf_tries) + recurse_tries = + choose_leaf_tries; + else if (map->chooseleaf_descend_once) + recurse_tries = 1; + else + recurse_tries = choose_tries; + osize += crush_choose_firstn( + map, + map->buckets[-1-w[i]], + weight, weight_max, + x, numrep, + curstep->arg2, + o+osize, j, + choose_tries, + recurse_tries, + choose_local_tries, + choose_local_fallback_tries, + recurse_to_leaf, + c+osize); + } else { + crush_choose_indep( + map, + map->buckets[-1-w[i]], + weight, weight_max, + x, numrep, numrep, + curstep->arg2, + o+osize, j, + choose_tries, + choose_leaf_tries ? + choose_leaf_tries : 1, + recurse_to_leaf, + c+osize, + 0); + osize += numrep; + } } if (recurse_to_leaf) /* copy final _leaf_ values to output set */ memcpy(o, c, osize*sizeof(*o)); - /* swap t and w arrays */ + /* swap o and w arrays */ tmp = o; o = w; w = tmp; diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index 83661cdc0766..258a382e75ed 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -132,7 +132,8 @@ static int osdc_show(struct seq_file *s, void *pp) req->r_osd ? req->r_osd->o_osd : -1, req->r_pgid.pool, req->r_pgid.seed); - seq_printf(s, "%.*s", req->r_oid_len, req->r_oid); + seq_printf(s, "%.*s", req->r_base_oid.name_len, + req->r_base_oid.name); if (req->r_reassert_version.epoch) seq_printf(s, "\t%u'%llu", diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 4a5df7b1cc9f..30efc5c18622 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -15,6 +15,7 @@ #include <linux/dns_resolver.h> #include <net/tcp.h> +#include <linux/ceph/ceph_features.h> #include <linux/ceph/libceph.h> #include <linux/ceph/messenger.h> #include <linux/ceph/decode.h> @@ -777,13 +778,12 @@ static void ceph_msg_data_bio_cursor_init(struct ceph_msg_data_cursor *cursor, bio = data->bio; BUG_ON(!bio); - BUG_ON(!bio->bi_vcnt); cursor->resid = min(length, data->bio_length); cursor->bio = bio; - cursor->vector_index = 0; - cursor->vector_offset = 0; - cursor->last_piece = length <= bio->bi_io_vec[0].bv_len; + cursor->bvec_iter = bio->bi_iter; + cursor->last_piece = + cursor->resid <= bio_iter_len(bio, cursor->bvec_iter); } static struct page *ceph_msg_data_bio_next(struct ceph_msg_data_cursor *cursor, @@ -792,71 +792,67 @@ static struct page *ceph_msg_data_bio_next(struct ceph_msg_data_cursor *cursor, { struct ceph_msg_data *data = cursor->data; struct bio *bio; - struct bio_vec *bio_vec; - unsigned int index; + struct bio_vec bio_vec; BUG_ON(data->type != CEPH_MSG_DATA_BIO); bio = cursor->bio; BUG_ON(!bio); - index = cursor->vector_index; - BUG_ON(index >= (unsigned int) bio->bi_vcnt); + bio_vec = bio_iter_iovec(bio, cursor->bvec_iter); - bio_vec = &bio->bi_io_vec[index]; - BUG_ON(cursor->vector_offset >= bio_vec->bv_len); - *page_offset = (size_t) (bio_vec->bv_offset + cursor->vector_offset); + *page_offset = (size_t) bio_vec.bv_offset; BUG_ON(*page_offset >= PAGE_SIZE); if (cursor->last_piece) /* pagelist offset is always 0 */ *length = cursor->resid; else - *length = (size_t) (bio_vec->bv_len - cursor->vector_offset); + *length = (size_t) bio_vec.bv_len; BUG_ON(*length > cursor->resid); BUG_ON(*page_offset + *length > PAGE_SIZE); - return bio_vec->bv_page; + return bio_vec.bv_page; } static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor, size_t bytes) { struct bio *bio; - struct bio_vec *bio_vec; - unsigned int index; + struct bio_vec bio_vec; BUG_ON(cursor->data->type != CEPH_MSG_DATA_BIO); bio = cursor->bio; BUG_ON(!bio); - index = cursor->vector_index; - BUG_ON(index >= (unsigned int) bio->bi_vcnt); - bio_vec = &bio->bi_io_vec[index]; + bio_vec = bio_iter_iovec(bio, cursor->bvec_iter); /* Advance the cursor offset */ BUG_ON(cursor->resid < bytes); cursor->resid -= bytes; - cursor->vector_offset += bytes; - if (cursor->vector_offset < bio_vec->bv_len) + + bio_advance_iter(bio, &cursor->bvec_iter, bytes); + + if (bytes < bio_vec.bv_len) return false; /* more bytes to process in this segment */ - BUG_ON(cursor->vector_offset != bio_vec->bv_len); /* Move on to the next segment, and possibly the next bio */ - if (++index == (unsigned int) bio->bi_vcnt) { + if (!cursor->bvec_iter.bi_size) { bio = bio->bi_next; - index = 0; + cursor->bio = bio; + if (bio) + cursor->bvec_iter = bio->bi_iter; + else + memset(&cursor->bvec_iter, 0, + sizeof(cursor->bvec_iter)); } - cursor->bio = bio; - cursor->vector_index = index; - cursor->vector_offset = 0; if (!cursor->last_piece) { BUG_ON(!cursor->resid); BUG_ON(!bio); /* A short read is OK, so use <= rather than == */ - if (cursor->resid <= bio->bi_io_vec[index].bv_len) + if (cursor->resid <= bio_iter_len(bio, cursor->bvec_iter)) cursor->last_piece = true; } @@ -1865,7 +1861,9 @@ int ceph_parse_ips(const char *c, const char *end, port = (port * 10) + (*p - '0'); p++; } - if (port > 65535 || port == 0) + if (port == 0) + port = CEPH_MON_PORT; + else if (port > 65535) goto bad; } else { port = CEPH_MON_PORT; @@ -1945,7 +1943,8 @@ static int process_connect(struct ceph_connection *con) { u64 sup_feat = con->msgr->supported_features; u64 req_feat = con->msgr->required_features; - u64 server_feat = le64_to_cpu(con->in_reply.features); + u64 server_feat = ceph_sanitize_features( + le64_to_cpu(con->in_reply.features)); int ret; dout("process_connect on %p tag %d\n", con, (int)con->in_tag); @@ -2853,8 +2852,8 @@ static void con_fault(struct ceph_connection *con) */ void ceph_messenger_init(struct ceph_messenger *msgr, struct ceph_entity_addr *myaddr, - u32 supported_features, - u32 required_features, + u64 supported_features, + u64 required_features, bool nocrc) { msgr->supported_features = supported_features; @@ -3126,15 +3125,8 @@ 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; if (front_len) { - if (front_len > PAGE_CACHE_SIZE) { - m->front.iov_base = __vmalloc(front_len, flags, - PAGE_KERNEL); - m->front_is_vmalloc = true; - } else { - m->front.iov_base = kmalloc(front_len, flags); - } + m->front.iov_base = ceph_kvmalloc(front_len, flags); if (m->front.iov_base == NULL) { dout("ceph_msg_new can't allocate %d bytes\n", front_len); @@ -3143,7 +3135,7 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, } else { m->front.iov_base = NULL; } - m->front.iov_len = front_len; + m->front_alloc_len = m->front.iov_len = front_len; dout("ceph_msg_new %p front %d\n", m, front_len); return m; @@ -3256,10 +3248,7 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip) void ceph_msg_kfree(struct ceph_msg *m) { dout("msg_kfree %p\n", m); - if (m->front_is_vmalloc) - vfree(m->front.iov_base); - else - kfree(m->front.iov_base); + ceph_kvfree(m->front.iov_base); kmem_cache_free(ceph_msg_cache, m); } @@ -3301,8 +3290,8 @@ 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..2ac9ef35110b 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); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 2b4b32aaa893..0676f2b199d6 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -338,7 +338,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, msg_size = 4 + 4 + 8 + 8 + 4+8; msg_size += 2 + 4 + 8 + 4 + 4; /* oloc */ msg_size += 1 + 8 + 4 + 4; /* pg_t */ - msg_size += 4 + MAX_OBJ_NAME_SIZE; + msg_size += 4 + CEPH_MAX_OID_NAME_LEN; /* oid */ msg_size += 2 + num_ops*sizeof(struct ceph_osd_op); msg_size += 8; /* snapid */ msg_size += 8; /* snap_seq */ @@ -368,6 +368,9 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, INIT_LIST_HEAD(&req->r_req_lru_item); INIT_LIST_HEAD(&req->r_osd_item); + req->r_base_oloc.pool = -1; + req->r_target_oloc.pool = -1; + /* create reply message */ if (use_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0); @@ -761,11 +764,11 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, if (num_ops > 1) osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC); - req->r_file_layout = *layout; /* keep a copy */ + req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout); - snprintf(req->r_oid, sizeof(req->r_oid), "%llx.%08llx", - vino.ino, objnum); - req->r_oid_len = strlen(req->r_oid); + snprintf(req->r_base_oid.name, sizeof(req->r_base_oid.name), + "%llx.%08llx", vino.ino, objnum); + req->r_base_oid.name_len = strlen(req->r_base_oid.name); return req; } @@ -1044,8 +1047,8 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) !ceph_con_opened(&osd->o_con)) { struct ceph_osd_request *req; - dout(" osd addr hasn't changed and connection never opened," - " letting msgr retry"); + dout("osd addr hasn't changed and connection never opened, " + "letting msgr retry\n"); /* touch each r_stamp for handle_timeout()'s benfit */ list_for_each_entry(req, &osd->o_requests, r_osd_item) req->r_stamp = jiffies; @@ -1232,6 +1235,61 @@ void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc, 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); +} + +/* + * Calculate mapping of a request to a PG. Takes tiering into account. + */ +static int __calc_request_pg(struct ceph_osdmap *osdmap, + struct ceph_osd_request *req, + struct ceph_pg *pg_out) +{ + bool need_check_tiering; + + need_check_tiering = false; + if (req->r_target_oloc.pool == -1) { + req->r_target_oloc = req->r_base_oloc; /* struct */ + need_check_tiering = true; + } + if (req->r_target_oid.name_len == 0) { + ceph_oid_copy(&req->r_target_oid, &req->r_base_oid); + need_check_tiering = true; + } + + if (need_check_tiering && + (req->r_flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) { + struct ceph_pg_pool_info *pi; + + pi = ceph_pg_pool_by_id(osdmap, req->r_target_oloc.pool); + if (pi) { + if ((req->r_flags & CEPH_OSD_FLAG_READ) && + pi->read_tier >= 0) + req->r_target_oloc.pool = pi->read_tier; + if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && + pi->write_tier >= 0) + req->r_target_oloc.pool = pi->write_tier; + } + /* !pi is caught in ceph_oloc_oid_to_pg() */ + } + + return ceph_oloc_oid_to_pg(osdmap, &req->r_target_oloc, + &req->r_target_oid, pg_out); +} + +/* * 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 @@ -1248,10 +1306,11 @@ 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, - ceph_file_layout_pg_pool(req->r_file_layout)); + + err = __calc_request_pg(osdc->osdmap, req, &pgid); if (err) { list_move(&req->r_req_lru_item, &osdc->req_notarget); return err; @@ -1264,12 +1323,18 @@ 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", @@ -1331,7 +1396,7 @@ static void __send_request(struct ceph_osd_client *osdc, /* fill in message content that changes each time we send it */ put_unaligned_le32(osdc->osdmap->epoch, req->r_request_osdmap_epoch); put_unaligned_le32(req->r_flags, req->r_request_flags); - put_unaligned_le64(req->r_pgid.pool, req->r_request_pool); + put_unaligned_le64(req->r_target_oloc.pool, req->r_request_pool); p = req->r_request_pgid; ceph_encode_64(&p, req->r_pgid.pool); ceph_encode_32(&p, req->r_pgid.seed); @@ -1362,6 +1427,40 @@ static void __send_queued(struct ceph_osd_client *osdc) } /* + * Caller should hold map_sem for read and request_mutex. + */ +static int __ceph_osdc_start_request(struct ceph_osd_client *osdc, + struct ceph_osd_request *req, + bool nofail) +{ + int rc; + + __register_request(osdc, req); + req->r_sent = 0; + req->r_got_reply = 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); + } + return rc; + } + + if (req->r_osd == NULL) { + dout("send_request %p no up osds in pg\n", req); + ceph_monc_request_next_osdmap(&osdc->client->monc); + } else { + __send_queued(osdc); + } + + return 0; +} + +/* * Timeout callback, called every N seconds when 1 or more osd * requests has been active for more than N seconds. When this * happens, we ping all OSDs with requests who have timed out to @@ -1432,6 +1531,109 @@ static void handle_osds_timeout(struct work_struct *work) round_jiffies_relative(delay)); } +static int ceph_oloc_decode(void **p, void *end, + struct ceph_object_locator *oloc) +{ + u8 struct_v, struct_cv; + u32 len; + void *struct_end; + int ret = 0; + + ceph_decode_need(p, end, 1 + 1 + 4, e_inval); + struct_v = ceph_decode_8(p); + struct_cv = ceph_decode_8(p); + if (struct_v < 3) { + pr_warn("got v %d < 3 cv %d of ceph_object_locator\n", + struct_v, struct_cv); + goto e_inval; + } + if (struct_cv > 6) { + pr_warn("got v %d cv %d > 6 of ceph_object_locator\n", + struct_v, struct_cv); + goto e_inval; + } + len = ceph_decode_32(p); + ceph_decode_need(p, end, len, e_inval); + struct_end = *p + len; + + oloc->pool = ceph_decode_64(p); + *p += 4; /* skip preferred */ + + len = ceph_decode_32(p); + if (len > 0) { + pr_warn("ceph_object_locator::key is set\n"); + goto e_inval; + } + + if (struct_v >= 5) { + len = ceph_decode_32(p); + if (len > 0) { + pr_warn("ceph_object_locator::nspace is set\n"); + goto e_inval; + } + } + + if (struct_v >= 6) { + s64 hash = ceph_decode_64(p); + if (hash != -1) { + pr_warn("ceph_object_locator::hash is set\n"); + goto e_inval; + } + } + + /* skip the rest */ + *p = struct_end; +out: + return ret; + +e_inval: + ret = -EINVAL; + goto out; +} + +static int ceph_redirect_decode(void **p, void *end, + struct ceph_request_redirect *redir) +{ + u8 struct_v, struct_cv; + u32 len; + void *struct_end; + int ret; + + ceph_decode_need(p, end, 1 + 1 + 4, e_inval); + struct_v = ceph_decode_8(p); + struct_cv = ceph_decode_8(p); + if (struct_cv > 1) { + pr_warn("got v %d cv %d > 1 of ceph_request_redirect\n", + struct_v, struct_cv); + goto e_inval; + } + len = ceph_decode_32(p); + ceph_decode_need(p, end, len, e_inval); + struct_end = *p + len; + + ret = ceph_oloc_decode(p, end, &redir->oloc); + if (ret) + goto out; + + len = ceph_decode_32(p); + if (len > 0) { + pr_warn("ceph_request_redirect::object_name is set\n"); + goto e_inval; + } + + len = ceph_decode_32(p); + *p += len; /* skip osd_instructions */ + + /* skip the rest */ + *p = struct_end; +out: + return ret; + +e_inval: + ret = -EINVAL; + goto out; +} + static void complete_request(struct ceph_osd_request *req) { complete_all(&req->r_safe_completion); /* fsync waiter */ @@ -1446,6 +1648,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, { void *p, *end; struct ceph_osd_request *req; + struct ceph_request_redirect redir; u64 tid; int object_len; unsigned int numops; @@ -1484,6 +1687,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, osdmap_epoch = ceph_decode_32(&p); /* lookup */ + down_read(&osdc->map_sem); mutex_lock(&osdc->request_mutex); req = __lookup_request(osdc, tid); if (req == NULL) { @@ -1525,10 +1729,40 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, for (i = 0; i < numops; i++) req->r_reply_op_result[i] = ceph_decode_32(&p); - already_completed = req->r_got_reply; + if (le16_to_cpu(msg->hdr.version) >= 6) { + p += 8 + 4; /* skip replay_version */ + p += 8; /* skip user_version */ - if (!req->r_got_reply) { + err = ceph_redirect_decode(&p, end, &redir); + if (err) + goto bad_put; + } else { + redir.oloc.pool = -1; + } + + if (redir.oloc.pool != -1) { + dout("redirect pool %lld\n", redir.oloc.pool); + + __unregister_request(osdc, req); + req->r_target_oloc = redir.oloc; /* struct */ + + /* + * Start redirect requests with nofail=true. If + * mapping fails, request will end up on the notarget + * list, waiting for the new osdmap (which can take + * a while), even though the original request mapped + * successfully. In the future we might want to follow + * original request's nofail setting here. + */ + err = __ceph_osdc_start_request(osdc, req, true); + BUG_ON(err); + + goto out_unlock; + } + + already_completed = req->r_got_reply; + if (!req->r_got_reply) { req->r_result = result; dout("handle_reply result %d bytes %d\n", req->r_result, bytes); @@ -1542,8 +1776,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, req->r_got_reply = 1; } else if ((flags & CEPH_OSD_FLAG_ONDISK) == 0) { dout("handle_reply tid %llu dup ack\n", tid); - mutex_unlock(&osdc->request_mutex); - goto done; + goto out_unlock; } dout("handle_reply tid %llu flags %d\n", tid, flags); @@ -1558,6 +1791,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, __unregister_request(osdc, req); mutex_unlock(&osdc->request_mutex); + up_read(&osdc->map_sem); if (!already_completed) { if (req->r_unsafe_callback && @@ -1575,15 +1809,27 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, complete_request(req); } -done: +out: dout("req=%p req->r_linger=%d\n", req, req->r_linger); ceph_osdc_put_request(req); return; +out_unlock: + mutex_unlock(&osdc->request_mutex); + up_read(&osdc->map_sem); + goto out; bad_put: + req->r_result = -EIO; + __unregister_request(osdc, req); + if (req->r_callback) + req->r_callback(req, msg); + else + complete_all(&req->r_completion); + complete_request(req); ceph_osdc_put_request(req); bad_mutex: mutex_unlock(&osdc->request_mutex); + up_read(&osdc->map_sem); bad: pr_err("corrupt osd_op_reply got %d %d\n", (int)msg->front.iov_len, le32_to_cpu(msg->hdr.front_len)); @@ -1613,14 +1859,17 @@ 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); @@ -1645,7 +1894,10 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) 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) { @@ -1665,7 +1917,8 @@ 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 */ @@ -1707,6 +1960,7 @@ 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; @@ -1720,6 +1974,8 @@ 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); @@ -1744,7 +2000,10 @@ 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); @@ -1787,7 +2046,10 @@ 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--; @@ -1804,7 +2066,9 @@ 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); @@ -2068,10 +2332,11 @@ void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, ceph_encode_32(&p, -1); /* preferred */ /* oid */ - ceph_encode_32(&p, req->r_oid_len); - memcpy(p, req->r_oid, req->r_oid_len); - dout("oid '%.*s' len %d\n", req->r_oid_len, req->r_oid, req->r_oid_len); - p += req->r_oid_len; + ceph_encode_32(&p, req->r_base_oid.name_len); + memcpy(p, req->r_base_oid.name, req->r_base_oid.name_len); + dout("oid '%.*s' len %d\n", req->r_base_oid.name_len, + req->r_base_oid.name, req->r_base_oid.name_len); + p += req->r_base_oid.name_len; /* ops--can imply data */ ceph_encode_16(&p, (u16)req->r_num_ops); @@ -2125,34 +2390,16 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req, bool nofail) { - int rc = 0; + int rc; down_read(&osdc->map_sem); mutex_lock(&osdc->request_mutex); - __register_request(osdc, req); - req->r_sent = 0; - req->r_got_reply = 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; - } - if (req->r_osd == NULL) { - dout("send_request %p no up osds in pg\n", req); - ceph_monc_request_next_osdmap(&osdc->client->monc); - } else { - __send_queued(osdc); - } - rc = 0; -out_unlock: + + rc = __ceph_osdc_start_request(osdc, req, nofail); + mutex_unlock(&osdc->request_mutex); up_read(&osdc->map_sem); + return rc; } EXPORT_SYMBOL(ceph_osdc_start_request); @@ -2278,9 +2525,12 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) err = -ENOMEM; osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify"); if (!osdc->notify_wq) - goto out_msgpool; + goto out_msgpool_reply; + return 0; +out_msgpool_reply: + ceph_msgpool_destroy(&osdc->msgpool_op_reply); out_msgpool: ceph_msgpool_destroy(&osdc->msgpool_op); out_mempool: @@ -2454,7 +2704,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, struct ceph_osd_client *osdc = osd->o_osdc; struct ceph_msg *m; struct ceph_osd_request *req; - int front = le32_to_cpu(hdr->front_len); + int front_len = le32_to_cpu(hdr->front_len); int data_len = le32_to_cpu(hdr->data_len); u64 tid; @@ -2474,12 +2724,13 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, req->r_reply, req->r_reply->con); ceph_msg_revoke_incoming(req->r_reply); - if (front > req->r_reply->front.iov_len) { + if (front_len > req->r_reply->front_alloc_len) { pr_warning("get_reply front %d > preallocated %d (%u#%llu)\n", - front, (int)req->r_reply->front.iov_len, + front_len, req->r_reply->front_alloc_len, (unsigned int)con->peer_name.type, le64_to_cpu(con->peer_name.num)); - m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front, GFP_NOFS, false); + m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS, + false); if (!m) goto out; ceph_msg_put(req->r_reply); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index dbd9a4792427..aade4a5c1c07 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -464,6 +464,11 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, u64 id) return NULL; } +struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id) +{ + return __lookup_pg_pool(&map->pg_pools, id); +} + const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id) { struct ceph_pg_pool_info *pi; @@ -514,8 +519,8 @@ static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) pr_warning("got v %d < 5 cv %d of ceph_pg_pool\n", ev, cv); return -EINVAL; } - if (cv > 7) { - pr_warning("got v %d cv %d > 7 of ceph_pg_pool\n", ev, cv); + if (cv > 9) { + pr_warning("got v %d cv %d > 9 of ceph_pg_pool\n", ev, cv); return -EINVAL; } len = ceph_decode_32(p); @@ -543,12 +548,34 @@ static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) *p += len; } - /* skip removed snaps */ + /* skip removed_snaps */ num = ceph_decode_32(p); *p += num * (8 + 8); *p += 8; /* skip auid */ pi->flags = ceph_decode_64(p); + *p += 4; /* skip crash_replay_interval */ + + if (ev >= 7) + *p += 1; /* skip min_size */ + + if (ev >= 8) + *p += 8 + 8; /* skip quota_max_* */ + + if (ev >= 9) { + /* skip tiers */ + num = ceph_decode_32(p); + *p += num * 8; + + *p += 8; /* skip tier_of */ + *p += 1; /* skip cache_mode */ + + pi->read_tier = ceph_decode_64(p); + pi->write_tier = ceph_decode_64(p); + } else { + pi->read_tier = -1; + pi->write_tier = -1; + } /* ignore the rest */ @@ -1090,25 +1117,40 @@ invalid: EXPORT_SYMBOL(ceph_calc_file_object_mapping); /* - * calculate an object layout (i.e. pgid) from an oid, - * file_layout, and osdmap + * Calculate mapping of a (oloc, oid) pair to a PG. Should only be + * called with target's (oloc, oid), since tiering isn't taken into + * account. */ -int ceph_calc_ceph_pg(struct ceph_pg *pg, const char *oid, - struct ceph_osdmap *osdmap, uint64_t pool) +int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap, + struct ceph_object_locator *oloc, + struct ceph_object_id *oid, + struct ceph_pg *pg_out) { - struct ceph_pg_pool_info *pool_info; + struct ceph_pg_pool_info *pi; - BUG_ON(!osdmap); - pool_info = __lookup_pg_pool(&osdmap->pg_pools, pool); - if (!pool_info) + pi = __lookup_pg_pool(&osdmap->pg_pools, oloc->pool); + if (!pi) return -EIO; - pg->pool = pool; - pg->seed = ceph_str_hash(pool_info->object_hash, oid, strlen(oid)); - dout("%s '%s' pgid %lld.%x\n", __func__, oid, pg->pool, pg->seed); + pg_out->pool = oloc->pool; + pg_out->seed = ceph_str_hash(pi->object_hash, oid->name, + oid->name_len); + + dout("%s '%.*s' pgid %llu.%x\n", __func__, oid->name_len, oid->name, + pg_out->pool, pg_out->seed); return 0; } -EXPORT_SYMBOL(ceph_calc_ceph_pg); +EXPORT_SYMBOL(ceph_oloc_oid_to_pg); + +static int crush_do_rule_ary(const struct crush_map *map, int ruleno, int x, + int *result, int result_max, + const __u32 *weight, int weight_max) +{ + int scratch[result_max * 3]; + + return crush_do_rule(map, ruleno, x, result, result_max, + weight, weight_max, scratch); +} /* * Calculate raw osd vector for the given pgid. Return pointer to osd @@ -1163,9 +1205,9 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, pool->pgp_num_mask) + (unsigned)pgid.pool; } - r = crush_do_rule(osdmap->crush, ruleno, pps, osds, - min_t(int, pool->size, *num), - osdmap->osd_weight); + r = crush_do_rule_ary(osdmap->crush, ruleno, pps, + osds, min_t(int, pool->size, *num), + osdmap->osd_weight, osdmap->max_osd); if (r < 0) { pr_err("error %d from crush rule: pool %lld ruleset %d type %d" " size %d\n", r, pgid.pool, pool->crush_ruleset, diff --git a/net/compat.c b/net/compat.c index dd32e34c1e2c..f50161fb812e 100644 --- a/net/compat.c +++ b/net/compat.c @@ -780,21 +780,16 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, 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/Makefile b/net/core/Makefile index b33b996f5dd6..9628c20acff6 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -21,4 +21,5 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o -obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o +obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o +obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o diff --git a/net/core/dev.c b/net/core/dev.c index 0ce469e5ec80..b1b0c8d4d7df 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -147,6 +147,8 @@ struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; struct list_head ptype_all __read_mostly; /* Taps */ static struct list_head offload_base __read_mostly; +static int netif_rx_internal(struct sk_buff *skb); + /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl * semaphore. @@ -480,7 +482,7 @@ EXPORT_SYMBOL(dev_add_offload); * and must not be freed until after all the CPU's have gone * through a quiescent state. */ -void __dev_remove_offload(struct packet_offload *po) +static void __dev_remove_offload(struct packet_offload *po) { struct list_head *head = &offload_base; struct packet_offload *po1; @@ -498,7 +500,6 @@ void __dev_remove_offload(struct packet_offload *po) out: spin_unlock(&offload_lock); } -EXPORT_SYMBOL(__dev_remove_offload); /** * dev_remove_offload - remove packet offload handler @@ -1118,6 +1119,8 @@ rollback: write_seqcount_end(&devnet_rename_seq); + netdev_adjacent_rename_links(dev, oldname); + write_lock_bh(&dev_base_lock); hlist_del_rcu(&dev->name_hlist); write_unlock_bh(&dev_base_lock); @@ -1137,6 +1140,7 @@ rollback: err = ret; write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); + memcpy(oldname, newname, IFNAMSIZ); goto rollback; } else { pr_err("%s: name change rollback failed: %d\n", @@ -1566,14 +1570,14 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); * are as for raw_notifier_call_chain(). */ -int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev, - struct netdev_notifier_info *info) +static int call_netdevice_notifiers_info(unsigned long val, + struct net_device *dev, + struct netdev_notifier_info *info) { ASSERT_RTNL(); netdev_notifier_info_init(info, dev); return raw_notifier_call_chain(&netdev_chain, val, info); } -EXPORT_SYMBOL(call_netdevice_notifiers_info); /** * call_netdevice_notifiers - call all network notifier blocks @@ -1699,7 +1703,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) skb_scrub_packet(skb, true); skb->protocol = eth_type_trans(skb, dev); - return netif_rx(skb); + return netif_rx_internal(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); @@ -2079,7 +2083,7 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) } EXPORT_SYMBOL(netif_set_real_num_tx_queues); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS /** * netif_set_real_num_rx_queues - set actual number of RX queues used * @dev: Network device @@ -2145,30 +2149,42 @@ void __netif_schedule(struct Qdisc *q) } EXPORT_SYMBOL(__netif_schedule); -void dev_kfree_skb_irq(struct sk_buff *skb) +struct dev_kfree_skb_cb { + enum skb_free_reason reason; +}; + +static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) { - if (atomic_dec_and_test(&skb->users)) { - struct softnet_data *sd; - unsigned long flags; + return (struct dev_kfree_skb_cb *)skb->cb; +} + +void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) +{ + unsigned long flags; - local_irq_save(flags); - sd = &__get_cpu_var(softnet_data); - skb->next = sd->completion_queue; - sd->completion_queue = skb; - raise_softirq_irqoff(NET_TX_SOFTIRQ); - local_irq_restore(flags); + if (likely(atomic_read(&skb->users) == 1)) { + smp_rmb(); + atomic_set(&skb->users, 0); + } else if (likely(!atomic_dec_and_test(&skb->users))) { + return; } + get_kfree_skb_cb(skb)->reason = reason; + local_irq_save(flags); + skb->next = __this_cpu_read(softnet_data.completion_queue); + __this_cpu_write(softnet_data.completion_queue, skb); + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); } -EXPORT_SYMBOL(dev_kfree_skb_irq); +EXPORT_SYMBOL(__dev_kfree_skb_irq); -void dev_kfree_skb_any(struct sk_buff *skb) +void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { if (in_irq() || irqs_disabled()) - dev_kfree_skb_irq(skb); + __dev_kfree_skb_irq(skb, reason); else dev_kfree_skb(skb); } -EXPORT_SYMBOL(dev_kfree_skb_any); +EXPORT_SYMBOL(__dev_kfree_skb_any); /** @@ -2404,7 +2420,7 @@ 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; @@ -2442,13 +2458,8 @@ static void dev_gso_skb_destructor(struct sk_buff *skb) { struct dev_gso_cb *cb; - do { - struct sk_buff *nskb = skb->next; - - skb->next = nskb->next; - nskb->next = NULL; - kfree_skb(nskb); - } while (skb->next); + kfree_skb_list(skb->next); + skb->next = NULL; cb = DEV_GSO_CB(skb); if (cb->destructor) @@ -2484,34 +2495,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) } static netdev_features_t harmonize_features(struct sk_buff *skb, - netdev_features_t features) + const struct net_device *dev, + netdev_features_t features) { if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, skb_network_protocol(skb))) { 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, features); + return harmonize_features(skb, 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)) @@ -2519,24 +2532,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - return harmonize_features(skb, features); -} -EXPORT_SYMBOL(netif_skb_features); - -/* - * Returns true if either: - * 1. skb has frag_list and the device doesn't support FRAGLIST, or - * 2. skb is fragmented and the device does not support SG. - */ -static inline int skb_needs_linearize(struct sk_buff *skb, - netdev_features_t features) -{ - return skb_is_nonlinear(skb) && - ((skb_has_frag_list(skb) && - !(features & NETIF_F_FRAGLIST)) || - (skb_shinfo(skb)->nr_frags && - !(features & NETIF_F_SG))); + return harmonize_features(skb, dev, features); } +EXPORT_SYMBOL(netif_skb_dev_features); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) @@ -2605,8 +2603,8 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, dev_queue_xmit_nit(skb, dev); skb_len = skb->len; - rc = ops->ndo_start_xmit(skb, dev); - + trace_net_dev_start_xmit(skb, dev); + rc = ops->ndo_start_xmit(skb, dev); trace_net_dev_xmit(skb, rc, dev, skb_len); if (rc == NETDEV_TX_OK) txq_trans_update(txq); @@ -2624,6 +2622,7 @@ gso: dev_queue_xmit_nit(nskb, dev); skb_len = nskb->len; + trace_net_dev_start_xmit(nskb, dev); rc = ops->ndo_start_xmit(nskb, dev); trace_net_dev_xmit(nskb, rc, dev, skb_len); if (unlikely(rc != NETDEV_TX_OK)) { @@ -2744,7 +2743,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } -#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); @@ -2781,8 +2780,9 @@ int dev_loopback_xmit(struct sk_buff *skb) EXPORT_SYMBOL(dev_loopback_xmit); /** - * dev_queue_xmit - transmit a buffer + * __dev_queue_xmit - transmit a buffer * @skb: buffer to transmit + * @accel_priv: private data used for L2 forwarding offload * * Queue a buffer for transmission to a network device. The caller must * have set the device and priority and built the buffer before calling @@ -2805,7 +2805,7 @@ EXPORT_SYMBOL(dev_loopback_xmit); * the BH enable code must have IRQs enabled so that it will not deadlock. * --BLG */ -int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) +static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) { struct net_device *dev = skb->dev; struct netdev_queue *txq; @@ -3014,7 +3014,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, } skb_reset_network_header(skb); - if (!skb_get_rxhash(skb)) + if (!skb_get_hash(skb)) goto done; flow_table = rcu_dereference(rxqueue->rps_flow_table); @@ -3159,7 +3159,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) { - new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1); + new_flow = skb_get_hash(skb) & (fl->num_buckets - 1); old_flow = fl->history[fl->history_head]; fl->history[fl->history_head] = new_flow; @@ -3227,22 +3227,7 @@ enqueue: return NET_RX_DROP; } -/** - * netif_rx - post buffer to the network code - * @skb: buffer to post - * - * This function receives a packet from a device driver and queues it for - * the upper (protocol) levels to process. It always succeeds. The buffer - * may be dropped during processing for congestion control or by the - * protocol layers. - * - * return values: - * NET_RX_SUCCESS (no congestion) - * NET_RX_DROP (packet was dropped) - * - */ - -int netif_rx(struct sk_buff *skb) +static int netif_rx_internal(struct sk_buff *skb) { int ret; @@ -3278,14 +3263,38 @@ int netif_rx(struct sk_buff *skb) } return ret; } + +/** + * netif_rx - post buffer to the network code + * @skb: buffer to post + * + * This function receives a packet from a device driver and queues it for + * the upper (protocol) levels to process. It always succeeds. The buffer + * may be dropped during processing for congestion control or by the + * protocol layers. + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped) + * + */ + +int netif_rx(struct sk_buff *skb) +{ + trace_netif_rx_entry(skb); + + return netif_rx_internal(skb); +} EXPORT_SYMBOL(netif_rx); int netif_rx_ni(struct sk_buff *skb) { int err; + trace_netif_rx_ni_entry(skb); + preempt_disable(); - err = netif_rx(skb); + err = netif_rx_internal(skb); if (local_softirq_pending()) do_softirq(); preempt_enable(); @@ -3311,7 +3320,10 @@ static void net_tx_action(struct softirq_action *h) clist = clist->next; WARN_ON(atomic_read(&skb->users)); - trace_kfree_skb(skb, net_tx_action); + if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED)) + trace_consume_skb(skb); + else + trace_kfree_skb(skb, net_tx_action); __kfree_skb(skb); } } @@ -3667,22 +3679,7 @@ static int __netif_receive_skb(struct sk_buff *skb) return ret; } -/** - * netif_receive_skb - process receive buffer from network - * @skb: buffer to process - * - * netif_receive_skb() is the main receive data processing function. - * It always succeeds. The buffer may be dropped during processing - * for congestion control or by the protocol layers. - * - * This function may only be called from softirq context and interrupts - * should be enabled. - * - * Return values (usually ignored): - * NET_RX_SUCCESS: no congestion - * NET_RX_DROP: packet was dropped - */ -int netif_receive_skb(struct sk_buff *skb) +static int netif_receive_skb_internal(struct sk_buff *skb) { net_timestamp_check(netdev_tstamp_prequeue, skb); @@ -3708,6 +3705,28 @@ int netif_receive_skb(struct sk_buff *skb) #endif return __netif_receive_skb(skb); } + +/** + * netif_receive_skb - process receive buffer from network + * @skb: buffer to process + * + * netif_receive_skb() is the main receive data processing function. + * It always succeeds. The buffer may be dropped during processing + * for congestion control or by the protocol layers. + * + * This function may only be called from softirq context and interrupts + * should be enabled. + * + * Return values (usually ignored): + * NET_RX_SUCCESS: no congestion + * NET_RX_DROP: packet was dropped + */ +int netif_receive_skb(struct sk_buff *skb) +{ + trace_netif_receive_skb_entry(skb); + + return netif_receive_skb_internal(skb); +} EXPORT_SYMBOL(netif_receive_skb); /* Network device is going away, flush any packets still pending @@ -3757,7 +3776,7 @@ static int napi_gro_complete(struct sk_buff *skb) if (ptype->type != type || !ptype->callbacks.gro_complete) continue; - err = ptype->callbacks.gro_complete(skb); + err = ptype->callbacks.gro_complete(skb, 0); break; } rcu_read_unlock(); @@ -3769,7 +3788,7 @@ static int napi_gro_complete(struct sk_buff *skb) } out: - return netif_receive_skb(skb); + return netif_receive_skb_internal(skb); } /* napi->gro_list contains packets ordered by age. @@ -3805,10 +3824,18 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff *p; unsigned int maclen = skb->dev->hard_header_len; + u32 hash = skb_get_hash_raw(skb); for (p = napi->gro_list; p; p = p->next) { unsigned long diffs; + NAPI_GRO_CB(p)->flush = 0; + + if (hash != skb_get_hash_raw(p)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; if (maclen == ETH_HLEN) @@ -3819,7 +3846,23 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) skb_gro_mac_header(skb), maclen); NAPI_GRO_CB(p)->same_flow = !diffs; - NAPI_GRO_CB(p)->flush = 0; + } +} + +static void skb_gro_reset_offset(struct sk_buff *skb) +{ + const struct skb_shared_info *pinfo = skb_shinfo(skb); + const skb_frag_t *frag0 = &pinfo->frags[0]; + + NAPI_GRO_CB(skb)->data_offset = 0; + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; + + if (skb_mac_header(skb) == skb_tail_pointer(skb) && + pinfo->nr_frags && + !PageHighMem(skb_frag_page(frag0))) { + NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); + NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); } } @@ -3838,7 +3881,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (skb_is_gso(skb) || skb_has_frag_list(skb)) goto normal; + skb_gro_reset_offset(skb); gro_list_prepare(napi, skb); + NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */ rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { @@ -3850,6 +3895,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; + NAPI_GRO_CB(skb)->udp_mark = 0; pp = ptype->callbacks.gro_receive(&napi->gro_list, skb); break; @@ -3874,10 +3920,23 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (same_flow) goto ok; - if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS) + if (NAPI_GRO_CB(skb)->flush) goto normal; - napi->gro_count++; + if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { + struct sk_buff *nskb = napi->gro_list; + + /* locate the end of the list to select the 'oldest' flow */ + while (nskb->next) { + pp = &nskb->next; + nskb = *pp; + } + *pp = NULL; + nskb->next = NULL; + napi_gro_complete(nskb); + } else { + napi->gro_count++; + } NAPI_GRO_CB(skb)->count = 1; NAPI_GRO_CB(skb)->age = jiffies; skb_shinfo(skb)->gso_size = skb_gro_len(skb); @@ -3915,12 +3974,39 @@ normal: goto pull; } +struct packet_offload *gro_find_receive_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; + + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_receive) + continue; + return ptype; + } + return NULL; +} +EXPORT_SYMBOL(gro_find_receive_by_type); + +struct packet_offload *gro_find_complete_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; + + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_complete) + continue; + return ptype; + } + return NULL; +} +EXPORT_SYMBOL(gro_find_complete_by_type); static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { switch (ret) { case GRO_NORMAL: - if (netif_receive_skb(skb)) + if (netif_receive_skb_internal(skb)) ret = GRO_DROP; break; @@ -3943,26 +4029,9 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) return ret; } -static void skb_gro_reset_offset(struct sk_buff *skb) -{ - const struct skb_shared_info *pinfo = skb_shinfo(skb); - const skb_frag_t *frag0 = &pinfo->frags[0]; - - NAPI_GRO_CB(skb)->data_offset = 0; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; - - if (skb_mac_header(skb) == skb_tail_pointer(skb) && - pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0))) { - NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); - NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); - } -} - gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { - skb_gro_reset_offset(skb); + trace_napi_gro_receive_entry(skb); return napi_skb_finish(dev_gro_receive(napi, skb), skb); } @@ -3986,8 +4055,7 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) if (!skb) { skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD); - if (skb) - napi->skb = skb; + napi->skb = skb; } return skb; } @@ -3998,12 +4066,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * { switch (ret) { case GRO_NORMAL: - case GRO_HELD: - skb->protocol = eth_type_trans(skb, skb->dev); - - if (ret == GRO_HELD) - skb_gro_pull(skb, -ETH_HLEN); - else if (netif_receive_skb(skb)) + if (netif_receive_skb_internal(skb)) ret = GRO_DROP; break; @@ -4012,6 +4075,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * napi_reuse_skb(napi, skb); break; + case GRO_HELD: case GRO_MERGED: break; } @@ -4022,36 +4086,15 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * static struct sk_buff *napi_frags_skb(struct napi_struct *napi) { struct sk_buff *skb = napi->skb; - struct ethhdr *eth; - unsigned int hlen; - unsigned int off; napi->skb = NULL; - skb_reset_mac_header(skb); - skb_gro_reset_offset(skb); - - off = skb_gro_offset(skb); - hlen = off + sizeof(*eth); - eth = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) { - eth = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!eth)) { - napi_reuse_skb(napi, skb); - skb = NULL; - goto out; - } + if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) { + napi_reuse_skb(napi, skb); + return NULL; } + skb->protocol = eth_type_trans(skb, skb->dev); - skb_gro_pull(skb, sizeof(*eth)); - - /* - * This works because the only protocols we care about don't require - * special handling. We'll fix it up properly at the end. - */ - skb->protocol = eth->h_proto; - -out: return skb; } @@ -4062,12 +4105,14 @@ gro_result_t napi_gro_frags(struct napi_struct *napi) if (!skb) return GRO_DROP; + trace_napi_gro_frags_entry(skb); + return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); } EXPORT_SYMBOL(napi_gro_frags); /* - * net_rps_action sends any pending IPI's for rps. + * net_rps_action_and_irq_enable sends any pending IPI's for rps. * Note: called with local irq disabled, but exits with local irq enabled. */ static void net_rps_action_and_irq_enable(struct softnet_data *sd) @@ -4272,17 +4317,10 @@ EXPORT_SYMBOL(netif_napi_add); void netif_napi_del(struct napi_struct *napi) { - struct sk_buff *skb, *next; - list_del_init(&napi->dev_list); napi_free_frags(napi); - for (skb = napi->gro_list; skb; skb = next) { - next = skb->next; - skb->next = NULL; - kfree_skb(skb); - } - + kfree_skb_list(napi->gro_list); napi->gro_list = NULL; napi->gro_count = 0; } @@ -4399,19 +4437,6 @@ struct netdev_adjacent { struct rcu_head rcu; }; -static struct netdev_adjacent *__netdev_find_adj_rcu(struct net_device *dev, - struct net_device *adj_dev, - struct list_head *adj_list) -{ - struct netdev_adjacent *adj; - - list_for_each_entry_rcu(adj, adj_list, list) { - if (adj->dev == adj_dev) - return adj; - } - return NULL; -} - static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev, struct net_device *adj_dev, struct list_head *adj_list) @@ -4450,13 +4475,12 @@ EXPORT_SYMBOL(netdev_has_upper_dev); * Find out if a device is linked to an upper device and return true in case * it is. The caller must hold the RTNL lock. */ -bool netdev_has_any_upper_dev(struct net_device *dev) +static bool netdev_has_any_upper_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->all_adj_list.upper); } -EXPORT_SYMBOL(netdev_has_any_upper_dev); /** * netdev_master_upper_dev_get - Get master upper device @@ -4576,6 +4600,27 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); /** + * netdev_lower_get_first_private_rcu - Get the first ->private from the + * lower neighbour list, RCU + * variant + * @dev: device + * + * Gets the first netdev_adjacent->private from the dev's lower neighbour + * list. The caller must hold RCU read lock. + */ +void *netdev_lower_get_first_private_rcu(struct net_device *dev) +{ + struct netdev_adjacent *lower; + + lower = list_first_or_null_rcu(&dev->adj_list.lower, + struct netdev_adjacent, list); + if (lower) + return lower->private; + return NULL; +} +EXPORT_SYMBOL(netdev_lower_get_first_private_rcu); + +/** * netdev_master_upper_dev_get_rcu - Get master upper device * @dev: device * @@ -4594,13 +4639,36 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) } EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); +static int netdev_adjacent_sysfs_add(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) +{ + char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? + "upper_%s" : "lower_%s", adj_dev->name); + return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), + linkname); +} +static void netdev_adjacent_sysfs_del(struct net_device *dev, + char *name, + struct list_head *dev_list) +{ + char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? + "upper_%s" : "lower_%s", name); + sysfs_remove_link(&(dev->dev.kobj), linkname); +} + +#define netdev_adjacent_is_neigh_list(dev, dev_list) \ + (dev_list == &dev->adj_list.upper || \ + dev_list == &dev->adj_list.lower) + static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list, void *private, bool master) { struct netdev_adjacent *adj; - char linkname[IFNAMSIZ+7]; int ret; adj = __netdev_find_adj(dev, adj_dev, dev_list); @@ -4623,16 +4691,8 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, pr_debug("dev_hold for %s, because of link added from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); - if (dev_list == &dev->adj_list.lower) { - sprintf(linkname, "lower_%s", adj_dev->name); - ret = sysfs_create_link(&(dev->dev.kobj), - &(adj_dev->dev.kobj), linkname); - if (ret) - goto free_adj; - } else if (dev_list == &dev->adj_list.upper) { - sprintf(linkname, "upper_%s", adj_dev->name); - ret = sysfs_create_link(&(dev->dev.kobj), - &(adj_dev->dev.kobj), linkname); + if (netdev_adjacent_is_neigh_list(dev, dev_list)) { + ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); if (ret) goto free_adj; } @@ -4652,14 +4712,8 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, return 0; remove_symlinks: - if (dev_list == &dev->adj_list.lower) { - sprintf(linkname, "lower_%s", adj_dev->name); - sysfs_remove_link(&(dev->dev.kobj), linkname); - } else if (dev_list == &dev->adj_list.upper) { - sprintf(linkname, "upper_%s", adj_dev->name); - sysfs_remove_link(&(dev->dev.kobj), linkname); - } - + if (netdev_adjacent_is_neigh_list(dev, dev_list)) + netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: kfree(adj); dev_put(adj_dev); @@ -4667,12 +4721,11 @@ free_adj: return ret; } -void __netdev_adjacent_dev_remove(struct net_device *dev, - struct net_device *adj_dev, - struct list_head *dev_list) +static void __netdev_adjacent_dev_remove(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) { struct netdev_adjacent *adj; - char linkname[IFNAMSIZ+7]; adj = __netdev_find_adj(dev, adj_dev, dev_list); @@ -4692,13 +4745,8 @@ void __netdev_adjacent_dev_remove(struct net_device *dev, if (adj->master) sysfs_remove_link(&(dev->dev.kobj), "master"); - if (dev_list == &dev->adj_list.lower) { - sprintf(linkname, "lower_%s", adj_dev->name); - sysfs_remove_link(&(dev->dev.kobj), linkname); - } else if (dev_list == &dev->adj_list.upper) { - sprintf(linkname, "upper_%s", adj_dev->name); - sysfs_remove_link(&(dev->dev.kobj), linkname); - } + if (netdev_adjacent_is_neigh_list(dev, dev_list)) + netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); pr_debug("dev_put for %s, because link removed from %s to %s\n", @@ -4707,11 +4755,11 @@ void __netdev_adjacent_dev_remove(struct net_device *dev, kfree_rcu(adj, rcu); } -int __netdev_adjacent_dev_link_lists(struct net_device *dev, - struct net_device *upper_dev, - struct list_head *up_list, - struct list_head *down_list, - void *private, bool master) +static int __netdev_adjacent_dev_link_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list, + void *private, bool master) { int ret; @@ -4730,8 +4778,8 @@ int __netdev_adjacent_dev_link_lists(struct net_device *dev, return 0; } -int __netdev_adjacent_dev_link(struct net_device *dev, - struct net_device *upper_dev) +static int __netdev_adjacent_dev_link(struct net_device *dev, + struct net_device *upper_dev) { return __netdev_adjacent_dev_link_lists(dev, upper_dev, &dev->all_adj_list.upper, @@ -4739,26 +4787,26 @@ int __netdev_adjacent_dev_link(struct net_device *dev, NULL, false); } -void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, - struct net_device *upper_dev, - struct list_head *up_list, - struct list_head *down_list) +static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list) { __netdev_adjacent_dev_remove(dev, upper_dev, up_list); __netdev_adjacent_dev_remove(upper_dev, dev, down_list); } -void __netdev_adjacent_dev_unlink(struct net_device *dev, - struct net_device *upper_dev) +static void __netdev_adjacent_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) { __netdev_adjacent_dev_unlink_lists(dev, upper_dev, &dev->all_adj_list.upper, &upper_dev->all_adj_list.lower); } -int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, - struct net_device *upper_dev, - void *private, bool master) +static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, + struct net_device *upper_dev, + void *private, bool master) { int ret = __netdev_adjacent_dev_link(dev, upper_dev); @@ -4777,8 +4825,8 @@ int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, return 0; } -void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, - struct net_device *upper_dev) +static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, + struct net_device *upper_dev) { __netdev_adjacent_dev_unlink(dev, upper_dev); __netdev_adjacent_dev_unlink_lists(dev, upper_dev, @@ -4967,20 +5015,24 @@ void netdev_upper_dev_unlink(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_dev_unlink); -void *netdev_lower_dev_get_private_rcu(struct net_device *dev, - struct net_device *lower_dev) +void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { - struct netdev_adjacent *lower; + struct netdev_adjacent *iter; - if (!lower_dev) - return NULL; - lower = __netdev_find_adj_rcu(dev, lower_dev, &dev->adj_list.lower); - if (!lower) - return NULL; + list_for_each_entry(iter, &dev->adj_list.upper, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.lower); + } - return lower->private; + list_for_each_entry(iter, &dev->adj_list.lower, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.upper); + } } -EXPORT_SYMBOL(netdev_lower_dev_get_private_rcu); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev) @@ -5314,6 +5366,17 @@ int dev_change_flags(struct net_device *dev, unsigned int flags) } EXPORT_SYMBOL(dev_change_flags); +static int __dev_set_mtu(struct net_device *dev, int new_mtu) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_change_mtu) + return ops->ndo_change_mtu(dev, new_mtu); + + dev->mtu = new_mtu; + return 0; +} + /** * dev_set_mtu - Change maximum transfer unit * @dev: device @@ -5323,8 +5386,7 @@ EXPORT_SYMBOL(dev_change_flags); */ int dev_set_mtu(struct net_device *dev, int new_mtu) { - const struct net_device_ops *ops = dev->netdev_ops; - int err; + int err, orig_mtu; if (new_mtu == dev->mtu) return 0; @@ -5336,14 +5398,25 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) if (!netif_device_present(dev)) return -ENODEV; - err = 0; - if (ops->ndo_change_mtu) - err = ops->ndo_change_mtu(dev, new_mtu); - else - dev->mtu = new_mtu; + err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) + return err; - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + orig_mtu = dev->mtu; + err = __dev_set_mtu(dev, new_mtu); + + if (!err) { + err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) { + /* setting mtu back and notifying everyone again, + * so that they have a chance to revert changes. + */ + __dev_set_mtu(dev, orig_mtu); + call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + } + } return err; } EXPORT_SYMBOL(dev_set_mtu); @@ -5697,7 +5770,7 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, } EXPORT_SYMBOL(netif_stacked_transfer_operstate); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; @@ -5836,13 +5909,8 @@ int register_netdevice(struct net_device *dev) dev->features |= NETIF_F_SOFT_FEATURES; dev->wanted_features = dev->features & dev->hw_features; - /* Turn on no cache copy if HW is doing checksum */ if (!(dev->flags & IFF_LOOPBACK)) { dev->hw_features |= NETIF_F_NOCACHE_COPY; - if (dev->features & NETIF_F_ALL_CSUM) { - dev->wanted_features |= NETIF_F_NOCACHE_COPY; - dev->features |= NETIF_F_NOCACHE_COPY; - } } /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. @@ -6229,7 +6297,7 @@ void netdev_freemem(struct net_device *dev) * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use - * and performs basic initialization. Also allocates subquue structs + * and performs basic initialization. Also allocates subqueue structs * for each queue on the device. */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, @@ -6247,7 +6315,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, return NULL; } -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS if (rxqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; @@ -6303,7 +6371,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, if (netif_alloc_netdev_queues(dev)) goto free_all; -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) @@ -6323,7 +6391,7 @@ free_all: free_pcpu: free_percpu(dev->pcpu_refcnt); netif_free_tx_queues(dev); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS kfree(dev->_rx); #endif @@ -6348,7 +6416,7 @@ void free_netdev(struct net_device *dev) release_net(dev_net(dev)); netif_free_tx_queues(dev); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS kfree(dev->_rx); #endif @@ -6618,11 +6686,11 @@ static int dev_cpu_callback(struct notifier_block *nfb, /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { - netif_rx(skb); + netif_rx_internal(skb); input_queue_head_incr(oldsd); } while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { - netif_rx(skb); + netif_rx_internal(skb); input_queue_head_incr(oldsd); } @@ -6935,28 +7003,18 @@ static int __init net_dev_init(void) for_each_possible_cpu(i) { struct softnet_data *sd = &per_cpu(softnet_data, i); - memset(sd, 0, sizeof(*sd)); skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); - sd->completion_queue = NULL; INIT_LIST_HEAD(&sd->poll_list); - sd->output_queue = NULL; sd->output_queue_tailp = &sd->output_queue; #ifdef CONFIG_RPS sd->csd.func = rps_trigger_softirq; sd->csd.info = sd; - sd->csd.flags = 0; sd->cpu = i; #endif sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; - sd->backlog.gro_list = NULL; - sd->backlog.gro_count = 0; - -#ifdef CONFIG_NET_FLOW_LIMIT - sd->flow_limit = NULL; -#endif } dev_boot_phase = 0; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index ec40a849fc42..329d5794e7dc 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -38,7 +38,7 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, ha->type = addr_type; ha->refcount = 1; ha->global_use = global; - ha->synced = sync; + ha->synced = sync ? 1 : 0; ha->sync_cnt = 0; list_add_tail_rcu(&ha->list, &list->list); list->count++; @@ -48,7 +48,8 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, - unsigned char addr_type, bool global, bool sync) + unsigned char addr_type, bool global, bool sync, + int sync_count) { struct netdev_hw_addr *ha; @@ -66,10 +67,10 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, ha->global_use = true; } if (sync) { - if (ha->synced) + if (ha->synced && sync_count) return -EEXIST; else - ha->synced = true; + ha->synced++; } ha->refcount++; return 0; @@ -84,7 +85,8 @@ static int __hw_addr_add(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { - return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false); + return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, + 0); } static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, @@ -101,7 +103,7 @@ static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, ha->global_use = false; if (sync) - ha->synced = false; + ha->synced--; if (--ha->refcount) return 0; @@ -139,7 +141,7 @@ static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, int err; err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, - false, true); + false, true, ha->sync_cnt); if (err && err != -EEXIST) return err; @@ -186,47 +188,6 @@ static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, return err; } -int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, unsigned char addr_type) -{ - int err; - struct netdev_hw_addr *ha, *ha2; - unsigned char type; - - list_for_each_entry(ha, &from_list->list, list) { - type = addr_type ? addr_type : ha->type; - err = __hw_addr_add(to_list, ha->addr, addr_len, type); - if (err) - goto unroll; - } - return 0; - -unroll: - list_for_each_entry(ha2, &from_list->list, list) { - if (ha2 == ha) - break; - type = addr_type ? addr_type : ha2->type; - __hw_addr_del(to_list, ha2->addr, addr_len, type); - } - return err; -} -EXPORT_SYMBOL(__hw_addr_add_multiple); - -void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, unsigned char addr_type) -{ - struct netdev_hw_addr *ha; - unsigned char type; - - list_for_each_entry(ha, &from_list->list, list) { - type = addr_type ? addr_type : ha->type; - __hw_addr_del(to_list, ha->addr, addr_len, type); - } -} -EXPORT_SYMBOL(__hw_addr_del_multiple); - /* This function only works where there is a strict 1-1 relationship * between source and destionation of they synch. If you ever need to * sync addresses to more then 1 destination, you need to use @@ -264,7 +225,7 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, } EXPORT_SYMBOL(__hw_addr_unsync); -void __hw_addr_flush(struct netdev_hw_addr_list *list) +static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; @@ -274,7 +235,6 @@ void __hw_addr_flush(struct netdev_hw_addr_list *list) } list->count = 0; } -EXPORT_SYMBOL(__hw_addr_flush); void __hw_addr_init(struct netdev_hw_addr_list *list) { @@ -400,59 +360,6 @@ int dev_addr_del(struct net_device *dev, const unsigned char *addr, } EXPORT_SYMBOL(dev_addr_del); -/** - * dev_addr_add_multiple - Add device addresses from another device - * @to_dev: device to which addresses will be added - * @from_dev: device from which addresses will be added - * @addr_type: address type - 0 means type will be used from from_dev - * - * Add device addresses of the one device to another. - ** - * The caller must hold the rtnl_mutex. - */ -int dev_addr_add_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type) -{ - int err; - - ASSERT_RTNL(); - - if (from_dev->addr_len != to_dev->addr_len) - return -EINVAL; - err = __hw_addr_add_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, - to_dev->addr_len, addr_type); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); - return err; -} -EXPORT_SYMBOL(dev_addr_add_multiple); - -/** - * dev_addr_del_multiple - Delete device addresses by another device - * @to_dev: device where the addresses will be deleted - * @from_dev: device supplying the addresses to be deleted - * @addr_type: address type - 0 means type will be used from from_dev - * - * Deletes addresses in to device by the list of addresses in from device. - * - * The caller must hold the rtnl_mutex. - */ -int dev_addr_del_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type) -{ - ASSERT_RTNL(); - - if (from_dev->addr_len != to_dev->addr_len) - return -EINVAL; - __hw_addr_del_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, - to_dev->addr_len, addr_type); - call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); - return 0; -} -EXPORT_SYMBOL(dev_addr_del_multiple); - /* * Unicast list handling functions */ @@ -676,7 +583,7 @@ static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_MULTICAST, global, false); + NETDEV_HW_ADDR_T_MULTICAST, global, false, 0); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 5b7d0e1d0664..cf999e09bcd2 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -327,6 +327,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) cmd == SIOCBRADDIF || cmd == SIOCBRDELIF || cmd == SIOCSHWTSTAMP || + cmd == SIOCGHWTSTAMP || cmd == SIOCWANDEV) { err = -EOPNOTSUPP; if (ops->ndo_do_ioctl) { @@ -546,6 +547,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) */ default: if (cmd == SIOCWANDEV || + cmd == SIOCGHWTSTAMP || (cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15)) { dev_load(net, ifr.ifr_name); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index f409e0bd35c0..185c341fafbd 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -745,6 +745,13 @@ 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/flow_dissector.c b/net/core/flow_dissector.c index 2fc5beaf5783..e29e810663d7 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -202,12 +202,12 @@ static __always_inline u32 __flow_hash_1word(u32 a) } /* - * __skb_get_rxhash: calculate a flow hash based on src/dst addresses + * __skb_get_hash: calculate a flow hash based on src/dst addresses * and src/dst port numbers. Sets rxhash in skb to non-zero hash value * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb * if hash is a canonical 4-tuple hash over transport ports. */ -void __skb_get_rxhash(struct sk_buff *skb) +void __skb_get_hash(struct sk_buff *skb) { struct flow_keys keys; u32 hash; @@ -234,7 +234,7 @@ void __skb_get_rxhash(struct sk_buff *skb) skb->rxhash = hash; } -EXPORT_SYMBOL(__skb_get_rxhash); +EXPORT_SYMBOL(__skb_get_hash); /* * Returns a Tx hash based on the given packet descriptor a Tx queues' number @@ -323,17 +323,6 @@ u32 __skb_get_poff(const struct sk_buff *skb) return poff; } -static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) -{ - if (unlikely(queue_index >= dev->real_num_tx_queues)) { - net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", - dev->name, queue_index, - dev->real_num_tx_queues); - return 0; - } - return queue_index; -} - static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_XPS @@ -372,7 +361,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) #endif } -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); @@ -392,7 +381,6 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) return queue_index; } -EXPORT_SYMBOL(__netdev_pick_tx); struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, @@ -403,13 +391,13 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb, - accel_priv); + queue_index = ops->ndo_select_queue(dev, skb, accel_priv, + __netdev_pick_tx); else queue_index = __netdev_pick_tx(dev, skb); if (!accel_priv) - queue_index = dev_cap_txqueue(dev, queue_index); + queue_index = netdev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 932c6d7cf666..b9e9e0d38672 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -38,6 +38,8 @@ #include <linux/random.h> #include <linux/string.h> #include <linux/log2.h> +#include <linux/inetdevice.h> +#include <net/addrconf.h> #define DEBUG #define NEIGH_DEBUG 1 @@ -115,7 +117,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh) unsigned long neigh_rand_reach_time(unsigned long base) { - return base ? (net_random() % base) + (base >> 1) : 0; + return base ? (prandom_u32() % base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); @@ -497,7 +499,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, goto out_neigh_release; } - n->confirmed = jiffies - (n->parms->base_reachable_time << 1); + n->confirmed = jiffies - (NEIGH_VAR(n->parms, BASE_REACHABLE_TIME) << 1); write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, @@ -776,7 +778,7 @@ static void neigh_periodic_work(struct work_struct *work) tbl->last_rand = jiffies; for (p = &tbl->parms; p; p = p->next) p->reachable_time = - neigh_rand_reach_time(p->base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } for (i = 0 ; i < (1 << nht->hash_shift); i++) { @@ -799,7 +801,7 @@ static void neigh_periodic_work(struct work_struct *work) if (atomic_read(&n->refcnt) == 1 && (state == NUD_FAILED || - time_after(jiffies, n->used + n->parms->gc_staletime))) { + time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; n->dead = 1; write_unlock(&n->lock); @@ -822,12 +824,12 @@ next_elt: lockdep_is_held(&tbl->lock)); } out: - /* Cycle through all hash buckets every base_reachable_time/2 ticks. - * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 - * base_reachable_time. + /* Cycle through all hash buckets every BASE_REACHABLE_TIME/2 ticks. + * ARP entry timeouts range from 1/2 BASE_REACHABLE_TIME to 3/2 + * BASE_REACHABLE_TIME. */ - schedule_delayed_work(&tbl->gc_work, - tbl->parms.base_reachable_time >> 1); + queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, + NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME) >> 1); write_unlock_bh(&tbl->lock); } @@ -835,8 +837,9 @@ static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; return (n->nud_state & NUD_PROBE) ? - p->ucast_probes : - p->ucast_probes + p->app_probes + p->mcast_probes; + NEIGH_VAR(p, UCAST_PROBES) : + NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) + + NEIGH_VAR(p, MCAST_PROBES); } static void neigh_invalidate(struct neighbour *neigh) @@ -901,12 +904,13 @@ static void neigh_timer_handler(unsigned long arg) neigh_dbg(2, "neigh %p is still alive\n", neigh); next = neigh->confirmed + neigh->parms->reachable_time; } else if (time_before_eq(now, - neigh->used + neigh->parms->delay_probe_time)) { + neigh->used + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_suspect(neigh); - next = now + neigh->parms->delay_probe_time; + next = now + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME); } else { neigh_dbg(2, "neigh %p is suspected\n", neigh); neigh->nud_state = NUD_STALE; @@ -916,7 +920,8 @@ static void neigh_timer_handler(unsigned long arg) } } else if (state & NUD_DELAY) { if (time_before_eq(now, - neigh->confirmed + neigh->parms->delay_probe_time)) { + neigh->confirmed + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is now reachable\n", neigh); neigh->nud_state = NUD_REACHABLE; neigh->updated = jiffies; @@ -928,11 +933,11 @@ static void neigh_timer_handler(unsigned long arg) neigh->nud_state = NUD_PROBE; neigh->updated = jiffies; atomic_set(&neigh->probes, 0); - next = now + neigh->parms->retrans_time; + next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME); } } else { /* NUD_PROBE|NUD_INCOMPLETE */ - next = now + neigh->parms->retrans_time; + next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME); } if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && @@ -973,13 +978,16 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) goto out_unlock_bh; if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) { - if (neigh->parms->mcast_probes + neigh->parms->app_probes) { + if (NEIGH_VAR(neigh->parms, MCAST_PROBES) + + NEIGH_VAR(neigh->parms, APP_PROBES)) { unsigned long next, now = jiffies; - atomic_set(&neigh->probes, neigh->parms->ucast_probes); + atomic_set(&neigh->probes, + NEIGH_VAR(neigh->parms, UCAST_PROBES)); neigh->nud_state = NUD_INCOMPLETE; neigh->updated = now; - next = now + max(neigh->parms->retrans_time, HZ/2); + next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), + HZ/2); neigh_add_timer(neigh, next); immediate_probe = true; } else { @@ -994,14 +1002,14 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; - neigh_add_timer(neigh, - jiffies + neigh->parms->delay_probe_time); + neigh_add_timer(neigh, jiffies + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME)); } if (neigh->nud_state == NUD_INCOMPLETE) { if (skb) { while (neigh->arp_queue_len_bytes + skb->truesize > - neigh->parms->queue_len_bytes) { + NEIGH_VAR(neigh->parms, QUEUE_LEN_BYTES)) { struct sk_buff *buff; buff = __skb_dequeue(&neigh->arp_queue); @@ -1171,7 +1179,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh_update_hhs(neigh); if (!(new & NUD_CONNECTED)) neigh->confirmed = jiffies - - (neigh->parms->base_reachable_time << 1); + (NEIGH_VAR(neigh->parms, BASE_REACHABLE_TIME) << 1); notify = 1; } if (new == old) @@ -1231,6 +1239,21 @@ out: } EXPORT_SYMBOL(neigh_update); +/* Update the neigh to listen temporarily for probe responses, even if it is + * in a NUD_FAILED state. The caller has to hold neigh->lock for writing. + */ +void __neigh_set_probe_once(struct neighbour *neigh) +{ + neigh->updated = jiffies; + if (!(neigh->nud_state & NUD_FAILED)) + return; + neigh->nud_state = NUD_PROBE; + atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); + neigh_add_timer(neigh, + jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME)); +} +EXPORT_SYMBOL(__neigh_set_probe_once); + struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, struct net_device *dev) @@ -1392,9 +1415,11 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb) { unsigned long now = jiffies; - unsigned long sched_next = now + (net_random() % p->proxy_delay); - if (tbl->proxy_queue.qlen > p->proxy_qlen) { + unsigned long sched_next = now + (prandom_u32() % + NEIGH_VAR(p, PROXY_DELAY)); + + if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { kfree_skb(skb); return; } @@ -1441,7 +1466,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, p->tbl = tbl; atomic_set(&p->refcnt, 1); p->reachable_time = - neigh_rand_reach_time(p->base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); dev_hold(dev); p->dev = dev; write_pnet(&p->net, hold_net(net)); @@ -1458,6 +1483,8 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, p->next = tbl->parms.next; tbl->parms.next = p; write_unlock_bh(&tbl->lock); + + neigh_parms_data_state_cleanall(p); } return p; } @@ -1510,7 +1537,7 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl) write_pnet(&tbl->parms.net, &init_net); atomic_set(&tbl->parms.refcnt, 1); tbl->parms.reachable_time = - neigh_rand_reach_time(tbl->parms.base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) @@ -1538,7 +1565,8 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl) rwlock_init(&tbl->lock); INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); - schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); + queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, + tbl->parms.reachable_time); setup_timer(&tbl->proxy_timer, neigh_proxy_process, (unsigned long)tbl); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); @@ -1778,24 +1806,32 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) if ((parms->dev && nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) || nla_put_u32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)) || - nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes) || + nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, + NEIGH_VAR(parms, QUEUE_LEN_BYTES)) || /* approximative value for deprecated QUEUE_LEN (in packets) */ nla_put_u32(skb, NDTPA_QUEUE_LEN, - parms->queue_len_bytes / SKB_TRUESIZE(ETH_FRAME_LEN)) || - nla_put_u32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen) || - nla_put_u32(skb, NDTPA_APP_PROBES, parms->app_probes) || - nla_put_u32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes) || - nla_put_u32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes) || + NEIGH_VAR(parms, QUEUE_LEN_BYTES) / SKB_TRUESIZE(ETH_FRAME_LEN)) || + nla_put_u32(skb, NDTPA_PROXY_QLEN, NEIGH_VAR(parms, PROXY_QLEN)) || + nla_put_u32(skb, NDTPA_APP_PROBES, NEIGH_VAR(parms, APP_PROBES)) || + nla_put_u32(skb, NDTPA_UCAST_PROBES, + NEIGH_VAR(parms, UCAST_PROBES)) || + nla_put_u32(skb, NDTPA_MCAST_PROBES, + NEIGH_VAR(parms, MCAST_PROBES)) || nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) || nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME, - parms->base_reachable_time) || - nla_put_msecs(skb, NDTPA_GC_STALETIME, parms->gc_staletime) || + NEIGH_VAR(parms, BASE_REACHABLE_TIME)) || + nla_put_msecs(skb, NDTPA_GC_STALETIME, + NEIGH_VAR(parms, GC_STALETIME)) || nla_put_msecs(skb, NDTPA_DELAY_PROBE_TIME, - parms->delay_probe_time) || - nla_put_msecs(skb, NDTPA_RETRANS_TIME, parms->retrans_time) || - nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay) || - nla_put_msecs(skb, NDTPA_PROXY_DELAY, parms->proxy_delay) || - nla_put_msecs(skb, NDTPA_LOCKTIME, parms->locktime)) + NEIGH_VAR(parms, DELAY_PROBE_TIME)) || + nla_put_msecs(skb, NDTPA_RETRANS_TIME, + NEIGH_VAR(parms, RETRANS_TIME)) || + nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, + NEIGH_VAR(parms, ANYCAST_DELAY)) || + nla_put_msecs(skb, NDTPA_PROXY_DELAY, + NEIGH_VAR(parms, PROXY_DELAY)) || + nla_put_msecs(skb, NDTPA_LOCKTIME, + NEIGH_VAR(parms, LOCKTIME))) goto nla_put_failure; return nla_nest_end(skb, nest); @@ -2011,44 +2047,57 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh) switch (i) { case NDTPA_QUEUE_LEN: - p->queue_len_bytes = nla_get_u32(tbp[i]) * - SKB_TRUESIZE(ETH_FRAME_LEN); + NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, + nla_get_u32(tbp[i]) * + SKB_TRUESIZE(ETH_FRAME_LEN)); break; case NDTPA_QUEUE_LENBYTES: - p->queue_len_bytes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, + nla_get_u32(tbp[i])); break; case NDTPA_PROXY_QLEN: - p->proxy_qlen = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, PROXY_QLEN, + nla_get_u32(tbp[i])); break; case NDTPA_APP_PROBES: - p->app_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, APP_PROBES, + nla_get_u32(tbp[i])); break; case NDTPA_UCAST_PROBES: - p->ucast_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, UCAST_PROBES, + nla_get_u32(tbp[i])); break; case NDTPA_MCAST_PROBES: - p->mcast_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, MCAST_PROBES, + nla_get_u32(tbp[i])); break; case NDTPA_BASE_REACHABLE_TIME: - p->base_reachable_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, BASE_REACHABLE_TIME, + nla_get_msecs(tbp[i])); break; case NDTPA_GC_STALETIME: - p->gc_staletime = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, GC_STALETIME, + nla_get_msecs(tbp[i])); break; case NDTPA_DELAY_PROBE_TIME: - p->delay_probe_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, DELAY_PROBE_TIME, + nla_get_msecs(tbp[i])); break; case NDTPA_RETRANS_TIME: - p->retrans_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, RETRANS_TIME, + nla_get_msecs(tbp[i])); break; case NDTPA_ANYCAST_DELAY: - p->anycast_delay = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, ANYCAST_DELAY, + nla_get_msecs(tbp[i])); break; case NDTPA_PROXY_DELAY: - p->proxy_delay = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, PROXY_DELAY, + nla_get_msecs(tbp[i])); break; case NDTPA_LOCKTIME: - p->locktime = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, LOCKTIME, + nla_get_msecs(tbp[i])); break; } } @@ -2789,133 +2838,167 @@ static int proc_unres_qlen(struct ctl_table *ctl, int write, return ret; } -enum { - NEIGH_VAR_MCAST_PROBE, - NEIGH_VAR_UCAST_PROBE, - NEIGH_VAR_APP_PROBE, - NEIGH_VAR_RETRANS_TIME, - NEIGH_VAR_BASE_REACHABLE_TIME, - NEIGH_VAR_DELAY_PROBE_TIME, - NEIGH_VAR_GC_STALETIME, - NEIGH_VAR_QUEUE_LEN, - NEIGH_VAR_QUEUE_LEN_BYTES, - NEIGH_VAR_PROXY_QLEN, - NEIGH_VAR_ANYCAST_DELAY, - NEIGH_VAR_PROXY_DELAY, - NEIGH_VAR_LOCKTIME, - NEIGH_VAR_RETRANS_TIME_MS, - NEIGH_VAR_BASE_REACHABLE_TIME_MS, - NEIGH_VAR_GC_INTERVAL, - NEIGH_VAR_GC_THRESH1, - NEIGH_VAR_GC_THRESH2, - NEIGH_VAR_GC_THRESH3, - NEIGH_VAR_MAX -}; +static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, + int family) +{ + switch (family) { + case AF_INET: + return __in_dev_arp_parms_get_rcu(dev); + case AF_INET6: + return __in6_dev_nd_parms_get_rcu(dev); + } + return NULL; +} + +static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, + int index) +{ + struct net_device *dev; + int family = neigh_parms_family(p); + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + struct neigh_parms *dst_p = + neigh_get_dev_parms_rcu(dev, family); + + if (dst_p && !test_bit(index, dst_p->data_state)) + dst_p->data[index] = p->data[index]; + } + rcu_read_unlock(); +} + +static void neigh_proc_update(struct ctl_table *ctl, int write) +{ + struct net_device *dev = ctl->extra1; + struct neigh_parms *p = ctl->extra2; + struct net *net = neigh_parms_net(p); + int index = (int *) ctl->data - p->data; + + if (!write) + return; + + set_bit(index, p->data_state); + if (!dev) /* NULL dev means this is default value */ + neigh_copy_dflt_parms(net, p, index); +} + +static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + struct ctl_table tmp = *ctl; + int ret; + + tmp.extra1 = &zero; + tmp.extra2 = &int_max; + + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + neigh_proc_update(ctl, write); + return ret; +} + +int neigh_proc_dointvec(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec); + +int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec_jiffies); + +static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} + +int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies); + +static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_unres_qlen(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} + +#define NEIGH_PARMS_DATA_OFFSET(index) \ + (&((struct neigh_parms *) 0)->data[index]) + +#define NEIGH_SYSCTL_ENTRY(attr, data_attr, name, mval, proc) \ + [NEIGH_VAR_ ## attr] = { \ + .procname = name, \ + .data = NEIGH_PARMS_DATA_OFFSET(NEIGH_VAR_ ## data_attr), \ + .maxlen = sizeof(int), \ + .mode = mval, \ + .proc_handler = proc, \ + } + +#define NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_zero_intmax) + +#define NEIGH_SYSCTL_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_jiffies) + +#define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies) + +#define NEIGH_SYSCTL_MS_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_ms_jiffies) + +#define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies) + +#define NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(attr, data_attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_unres_qlen) static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1]; } neigh_sysctl_template __read_mostly = { .neigh_vars = { - [NEIGH_VAR_MCAST_PROBE] = { - .procname = "mcast_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .extra1 = &zero, - .extra2 = &int_max, - .proc_handler = proc_dointvec_minmax, - }, - [NEIGH_VAR_UCAST_PROBE] = { - .procname = "ucast_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .extra1 = &zero, - .extra2 = &int_max, - .proc_handler = proc_dointvec_minmax, - }, - [NEIGH_VAR_APP_PROBE] = { - .procname = "app_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .extra1 = &zero, - .extra2 = &int_max, - .proc_handler = proc_dointvec_minmax, - }, - [NEIGH_VAR_RETRANS_TIME] = { - .procname = "retrans_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_BASE_REACHABLE_TIME] = { - .procname = "base_reachable_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - [NEIGH_VAR_DELAY_PROBE_TIME] = { - .procname = "delay_first_probe_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - [NEIGH_VAR_GC_STALETIME] = { - .procname = "gc_stale_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - [NEIGH_VAR_QUEUE_LEN] = { - .procname = "unres_qlen", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_unres_qlen, - }, - [NEIGH_VAR_QUEUE_LEN_BYTES] = { - .procname = "unres_qlen_bytes", - .maxlen = sizeof(int), - .mode = 0644, - .extra1 = &zero, - .proc_handler = proc_dointvec_minmax, - }, - [NEIGH_VAR_PROXY_QLEN] = { - .procname = "proxy_qlen", - .maxlen = sizeof(int), - .mode = 0644, - .extra1 = &zero, - .extra2 = &int_max, - .proc_handler = proc_dointvec_minmax, - }, - [NEIGH_VAR_ANYCAST_DELAY] = { - .procname = "anycast_delay", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_PROXY_DELAY] = { - .procname = "proxy_delay", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_LOCKTIME] = { - .procname = "locktime", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_RETRANS_TIME_MS] = { - .procname = "retrans_time_ms", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_ms_jiffies, - }, - [NEIGH_VAR_BASE_REACHABLE_TIME_MS] = { - .procname = "base_reachable_time_ms", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_ms_jiffies, - }, + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(GC_STALETIME, "gc_stale_time"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(QUEUE_LEN_BYTES, "unres_qlen_bytes"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(PROXY_QLEN, "proxy_qlen"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(ANYCAST_DELAY, "anycast_delay"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(PROXY_DELAY, "proxy_delay"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(LOCKTIME, "locktime"), + NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(QUEUE_LEN, QUEUE_LEN_BYTES, "unres_qlen"), + NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(RETRANS_TIME_MS, RETRANS_TIME, "retrans_time_ms"), + NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(BASE_REACHABLE_TIME_MS, BASE_REACHABLE_TIME, "base_reachable_time_ms"), [NEIGH_VAR_GC_INTERVAL] = { .procname = "gc_interval", .maxlen = sizeof(int), @@ -2951,31 +3034,23 @@ static struct neigh_sysctl_table { }; int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, - char *p_name, proc_handler *handler) + proc_handler *handler) { + int i; struct neigh_sysctl_table *t; - const char *dev_name_source = NULL; + const char *dev_name_source; char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ]; + char *p_name; t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL); if (!t) goto err; - t->neigh_vars[NEIGH_VAR_MCAST_PROBE].data = &p->mcast_probes; - t->neigh_vars[NEIGH_VAR_UCAST_PROBE].data = &p->ucast_probes; - t->neigh_vars[NEIGH_VAR_APP_PROBE].data = &p->app_probes; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME].data = &p->retrans_time; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].data = &p->base_reachable_time; - t->neigh_vars[NEIGH_VAR_DELAY_PROBE_TIME].data = &p->delay_probe_time; - t->neigh_vars[NEIGH_VAR_GC_STALETIME].data = &p->gc_staletime; - t->neigh_vars[NEIGH_VAR_QUEUE_LEN].data = &p->queue_len_bytes; - t->neigh_vars[NEIGH_VAR_QUEUE_LEN_BYTES].data = &p->queue_len_bytes; - t->neigh_vars[NEIGH_VAR_PROXY_QLEN].data = &p->proxy_qlen; - t->neigh_vars[NEIGH_VAR_ANYCAST_DELAY].data = &p->anycast_delay; - t->neigh_vars[NEIGH_VAR_PROXY_DELAY].data = &p->proxy_delay; - t->neigh_vars[NEIGH_VAR_LOCKTIME].data = &p->locktime; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].data = &p->retrans_time; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].data = &p->base_reachable_time; + for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) { + t->neigh_vars[i].data += (long) p; + t->neigh_vars[i].extra1 = dev; + t->neigh_vars[i].extra2 = p; + } if (dev) { dev_name_source = dev->name; @@ -2990,26 +3065,32 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = (int *)(p + 1) + 3; } - if (handler) { /* RetransTime */ t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME].extra1 = dev; /* ReachableTime */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].extra1 = dev; /* RetransTime (in milliseconds)*/ t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].extra1 = dev; /* ReachableTime (in milliseconds) */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev; } /* Don't export sysctls to unprivileged users */ if (neigh_parms_net(p)->user_ns != &init_user_ns) t->neigh_vars[0].procname = NULL; + switch (neigh_parms_family(p)) { + case AF_INET: + p_name = "ipv4"; + break; + case AF_INET6: + p_name = "ipv6"; + break; + default: + BUG(); + } + snprintf(neigh_path, sizeof(neigh_path), "net/%s/neigh/%s", p_name, dev_name_source); t->sysctl_header = diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index f3edf9635e02..93886246a0b4 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -498,17 +498,7 @@ static struct attribute_group wireless_group = { #define net_class_groups NULL #endif /* CONFIG_SYSFS */ -#ifdef CONFIG_RPS -/* - * RX queue sysfs structures and functions. - */ -struct rx_queue_attribute { - struct attribute attr; - ssize_t (*show)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, char *buf); - ssize_t (*store)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, const char *buf, size_t len); -}; +#ifdef CONFIG_SYSFS #define to_rx_queue_attr(_attr) container_of(_attr, \ struct rx_queue_attribute, attr) @@ -543,6 +533,7 @@ static const struct sysfs_ops rx_queue_sysfs_ops = { .store = rx_queue_attr_store, }; +#ifdef CONFIG_RPS static ssize_t show_rps_map(struct netdev_rx_queue *queue, struct rx_queue_attribute *attribute, char *buf) { @@ -676,8 +667,8 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, while ((mask | (mask >> 1)) != mask) mask |= (mask >> 1); /* On 64 bit arches, must check mask fits in table->mask (u32), - * and on 32bit arches, must check RPS_DEV_FLOW_TABLE_SIZE(mask + 1) - * doesnt overflow. + * and on 32bit arches, must check + * RPS_DEV_FLOW_TABLE_SIZE(mask + 1) doesn't overflow. */ #if BITS_PER_LONG > 32 if (mask > (unsigned long)(u32)mask) @@ -718,16 +709,20 @@ static struct rx_queue_attribute rps_cpus_attribute = static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute = __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR, show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); +#endif /* CONFIG_RPS */ static struct attribute *rx_queue_default_attrs[] = { +#ifdef CONFIG_RPS &rps_cpus_attribute.attr, &rps_dev_flow_table_cnt_attribute.attr, +#endif NULL }; static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); +#ifdef CONFIG_RPS struct rps_map *map; struct rps_dev_flow_table *flow_table; @@ -743,15 +738,29 @@ static void rx_queue_release(struct kobject *kobj) RCU_INIT_POINTER(queue->rps_flow_table, NULL); call_rcu(&flow_table->rcu, rps_dev_flow_table_release); } +#endif memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } +static const void *rx_queue_namespace(struct kobject *kobj) +{ + struct netdev_rx_queue *queue = to_rx_queue(kobj); + struct device *dev = &queue->dev->dev; + const void *ns = NULL; + + if (dev->class && dev->class->ns_type) + ns = dev->class->namespace(dev); + + return ns; +} + static struct kobj_type rx_queue_ktype = { .sysfs_ops = &rx_queue_sysfs_ops, .release = rx_queue_release, .default_attrs = rx_queue_default_attrs, + .namespace = rx_queue_namespace }; static int rx_queue_add_kobject(struct net_device *net, int index) @@ -763,25 +772,36 @@ static int rx_queue_add_kobject(struct net_device *net, int index) kobj->kset = net->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); - if (error) { - kobject_put(kobj); - return error; + if (error) + goto exit; + + if (net->sysfs_rx_queue_group) { + error = sysfs_create_group(kobj, net->sysfs_rx_queue_group); + if (error) + goto exit; } kobject_uevent(kobj, KOBJ_ADD); dev_hold(queue->dev); return error; +exit: + kobject_put(kobj); + return error; } -#endif /* CONFIG_RPS */ +#endif /* CONFIG_SYFS */ int net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS int i; int error = 0; +#ifndef CONFIG_RPS + if (!net->sysfs_rx_queue_group) + return 0; +#endif for (i = old_num; i < new_num; i++) { error = rx_queue_add_kobject(net, i); if (error) { @@ -790,8 +810,12 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) } } - while (--i >= new_num) + while (--i >= new_num) { + if (net->sysfs_rx_queue_group) + sysfs_remove_group(&net->_rx[i].kobj, + net->sysfs_rx_queue_group); kobject_put(&net->_rx[i].kobj); + } return error; #else @@ -1082,10 +1106,23 @@ static void netdev_queue_release(struct kobject *kobj) dev_put(queue->dev); } +static const void *netdev_queue_namespace(struct kobject *kobj) +{ + struct netdev_queue *queue = to_netdev_queue(kobj); + struct device *dev = &queue->dev->dev; + const void *ns = NULL; + + if (dev->class && dev->class->ns_type) + ns = dev->class->namespace(dev); + + return ns; +} + static struct kobj_type netdev_queue_ktype = { .sysfs_ops = &netdev_queue_sysfs_ops, .release = netdev_queue_release, .default_attrs = netdev_queue_default_attrs, + .namespace = netdev_queue_namespace, }; static int netdev_queue_add_kobject(struct net_device *net, int index) @@ -1155,9 +1192,6 @@ static int register_queue_kobjects(struct net_device *net) NULL, &net->dev.kobj); if (!net->queues_kset) return -ENOMEM; -#endif - -#ifdef CONFIG_RPS real_rx = net->real_num_rx_queues; #endif real_tx = net->real_num_tx_queues; @@ -1184,7 +1218,7 @@ static void remove_queue_kobjects(struct net_device *net) { int real_rx = 0, real_tx = 0; -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS real_rx = net->real_num_rx_queues; #endif real_tx = net->real_num_tx_queues; @@ -1358,7 +1392,7 @@ void netdev_class_remove_file_ns(struct class_attribute *class_attr, } EXPORT_SYMBOL(netdev_class_remove_file_ns); -int netdev_kobject_init(void) +int __init netdev_kobject_init(void) { kobj_ns_type_register(&net_ns_type_operations); return class_register(&net_class); diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index bd7751ec1c4d..2745a1b51e03 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -1,7 +1,7 @@ #ifndef __NET_SYSFS_H__ #define __NET_SYSFS_H__ -int netdev_kobject_init(void); +int __init netdev_kobject_init(void); int netdev_register_kobject(struct net_device *); void netdev_unregister_kobject(struct net_device *); int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c new file mode 100644 index 000000000000..719efd541668 --- /dev/null +++ b/net/core/netclassid_cgroup.c @@ -0,0 +1,120 @@ +/* + * net/core/netclassid_cgroup.c Classid Cgroupfs Handling + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Thomas Graf <tgraf@suug.ch> + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/cgroup.h> +#include <linux/fdtable.h> +#include <net/cls_cgroup.h> +#include <net/sock.h> + +static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct cgroup_cls_state, css) : NULL; +} + +struct cgroup_cls_state *task_cls_state(struct task_struct *p) +{ + return css_cls_state(task_css(p, net_cls_subsys_id)); +} +EXPORT_SYMBOL_GPL(task_cls_state); + +static struct cgroup_subsys_state * +cgrp_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cgroup_cls_state *cs; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + + return &cs->css; +} + +static int cgrp_css_online(struct cgroup_subsys_state *css) +{ + struct cgroup_cls_state *cs = css_cls_state(css); + struct cgroup_cls_state *parent = css_cls_state(css_parent(css)); + + if (parent) + cs->classid = parent->classid; + + return 0; +} + +static void cgrp_css_free(struct cgroup_subsys_state *css) +{ + kfree(css_cls_state(css)); +} + +static int update_classid(const void *v, struct file *file, unsigned n) +{ + int err; + struct socket *sock = sock_from_file(file, &err); + + if (sock) + sock->sk->sk_classid = (u32)(unsigned long)v; + + return 0; +} + +static void cgrp_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct cgroup_cls_state *cs = css_cls_state(css); + void *v = (void *)(unsigned long)cs->classid; + struct task_struct *p; + + cgroup_taskset_for_each(p, css, tset) { + task_lock(p); + iterate_fd(p->files, 0, update_classid, v); + task_unlock(p); + } +} + +static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return css_cls_state(css)->classid; +} + +static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, + u64 value) +{ + css_cls_state(css)->classid = (u32) value; + + return 0; +} + +static struct cftype ss_files[] = { + { + .name = "classid", + .read_u64 = read_classid, + .write_u64 = write_classid, + }, + { } /* terminate */ +}; + +struct cgroup_subsys net_cls_subsys = { + .name = "net_cls", + .css_alloc = cgrp_css_alloc, + .css_online = cgrp_css_online, + .css_free = cgrp_css_free, + .attach = cgrp_attach, + .subsys_id = net_cls_subsys_id, + .base_cftypes = ss_files, + .module = THIS_MODULE, +}; + +static int __init init_netclassid_cgroup(void) +{ + return cgroup_load_subsys(&net_cls_subsys); +} +__initcall(init_netclassid_cgroup); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 19fe9c717ced..a664f7829a6d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -520,8 +520,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) skb->protocol = eth->h_proto = htons(ETH_P_IP); } - memcpy(eth->h_source, np->dev->dev_addr, ETH_ALEN); - memcpy(eth->h_dest, np->remote_mac, ETH_ALEN); + ether_addr_copy(eth->h_source, np->dev->dev_addr); + ether_addr_copy(eth->h_dest, np->remote_mac); skb->dev = np->dev; @@ -948,6 +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) @@ -960,6 +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; @@ -1002,7 +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; diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 56cbb69ba024..9043caedcd08 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -30,7 +30,7 @@ #define PRIOMAP_MIN_SZ 128 /* - * Extend @dev->priomap so that it's large enough to accomodate + * Extend @dev->priomap so that it's large enough to accommodate * @target_idx. @dev->priomap.priomap_len > @target_idx after successful * return. Must be called under rtnl lock. */ diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a797fff7f222..fdac61cac1bd 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -389,6 +389,9 @@ struct pktgen_dev { #ifdef CONFIG_XFRM __u8 ipsmode; /* IPSEC mode (config) */ __u8 ipsproto; /* IPSEC type (config) */ + __u32 spi; + struct dst_entry dst; + struct dst_ops dstops; #endif char result[512]; }; @@ -654,8 +657,11 @@ static int pktgen_if_show(struct seq_file *seq, void *v) } #ifdef CONFIG_XFRM - if (pkt_dev->flags & F_IPSEC_ON) + if (pkt_dev->flags & F_IPSEC_ON) { seq_printf(seq, "IPSEC "); + if (pkt_dev->spi) + seq_printf(seq, "spi:%u", pkt_dev->spi); + } #endif if (pkt_dev->flags & F_MACSRC_RND) @@ -1434,7 +1440,7 @@ static ssize_t pktgen_if_write(struct file *file, if (!mac_pton(valstr, pkt_dev->dst_mac)) return -EINVAL; /* Set up Dest MAC */ - memcpy(&pkt_dev->hh[0], pkt_dev->dst_mac, ETH_ALEN); + ether_addr_copy(&pkt_dev->hh[0], pkt_dev->dst_mac); sprintf(pg_result, "OK: dstmac %pM", pkt_dev->dst_mac); return count; @@ -1451,7 +1457,7 @@ static ssize_t pktgen_if_write(struct file *file, if (!mac_pton(valstr, pkt_dev->src_mac)) return -EINVAL; /* Set up Src MAC */ - memcpy(&pkt_dev->hh[6], pkt_dev->src_mac, ETH_ALEN); + ether_addr_copy(&pkt_dev->hh[6], pkt_dev->src_mac); sprintf(pg_result, "OK: srcmac %pM", pkt_dev->src_mac); return count; @@ -1476,7 +1482,18 @@ static ssize_t pktgen_if_write(struct file *file, sprintf(pg_result, "OK: flows=%u", pkt_dev->cflows); return count; } +#ifdef CONFIG_XFRM + if (!strcmp(name, "spi")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + i += len; + pkt_dev->spi = value; + sprintf(pg_result, "OK: spi=%u", pkt_dev->spi); + return count; + } +#endif if (!strcmp(name, "flowlen")) { len = num_arg(&user_buffer[i], 10, &value); if (len < 0) @@ -2043,10 +2060,10 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) /* Default to the interface's mac if not explicitly set. */ if (is_zero_ether_addr(pkt_dev->src_mac)) - memcpy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr, ETH_ALEN); + ether_addr_copy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr); /* Set up Dest MAC */ - memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN); + ether_addr_copy(&(pkt_dev->hh[0]), pkt_dev->dst_mac); if (pkt_dev->flags & F_IPV6) { int i, set = 0, err = 1; @@ -2233,13 +2250,21 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) struct xfrm_state *x = pkt_dev->flows[flow].x; struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id); if (!x) { - /*slow path: we dont already have xfrm_state*/ - x = xfrm_stateonly_find(pn->net, DUMMY_MARK, - (xfrm_address_t *)&pkt_dev->cur_daddr, - (xfrm_address_t *)&pkt_dev->cur_saddr, - AF_INET, - pkt_dev->ipsmode, - pkt_dev->ipsproto, 0); + + if (pkt_dev->spi) { + /* We need as quick as possible to find the right SA + * Searching with minimum criteria to archieve this. + */ + x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); + } else { + /* slow path: we dont already have xfrm_state */ + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, + (xfrm_address_t *)&pkt_dev->cur_daddr, + (xfrm_address_t *)&pkt_dev->cur_saddr, + AF_INET, + pkt_dev->ipsmode, + pkt_dev->ipsproto, 0); + } if (x) { pkt_dev->flows[flow].x = x; set_pkt_overhead(pkt_dev); @@ -2475,31 +2500,47 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) #ifdef CONFIG_XFRM +static u32 pktgen_dst_metrics[RTAX_MAX + 1] = { + + [RTAX_HOPLIMIT] = 0x5, /* Set a static hoplimit */ +}; + static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) { struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; int err = 0; + struct net *net = dev_net(pkt_dev->odev); if (!x) return 0; /* XXX: we dont support tunnel mode for now until * we resolve the dst issue */ - if (x->props.mode != XFRM_MODE_TRANSPORT) + if ((x->props.mode != XFRM_MODE_TRANSPORT) && (pkt_dev->spi == 0)) return 0; - spin_lock(&x->lock); + /* But when user specify an valid SPI, transformation + * supports both transport/tunnel mode + ESP/AH type. + */ + if ((x->props.mode == XFRM_MODE_TUNNEL) && (pkt_dev->spi != 0)) + skb->_skb_refdst = (unsigned long)&pkt_dev->dst | SKB_DST_NOREF; + rcu_read_lock_bh(); err = x->outer_mode->output(x, skb); - if (err) + rcu_read_unlock_bh(); + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR); goto error; + } err = x->type->output(x, skb); - if (err) + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR); goto error; - + } + spin_lock_bh(&x->lock); x->curlft.bytes += skb->len; x->curlft.packets++; + spin_unlock_bh(&x->lock); error: - spin_unlock(&x->lock); return err; } @@ -3542,6 +3583,17 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) #ifdef CONFIG_XFRM pkt_dev->ipsmode = XFRM_MODE_TRANSPORT; pkt_dev->ipsproto = IPPROTO_ESP; + + /* xfrm tunnel mode needs additional dst to extract outter + * ip header protocol/ttl/id field, here creat a phony one. + * instead of looking for a valid rt, which definitely hurting + * performance under such circumstance. + */ + pkt_dev->dstops.family = AF_INET; + pkt_dev->dst.dev = pkt_dev->odev; + dst_init_metrics(&pkt_dev->dst, pktgen_dst_metrics, false); + pkt_dev->dst.child = &pkt_dev->dst; + pkt_dev->dst.ops = &pkt_dev->dstops; #endif return add_dev_to_thread(t, pkt_dev); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index cf67144d3e3c..1a0dac2ef9ad 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -365,6 +365,22 @@ void rtnl_link_unregister(struct rtnl_link_ops *ops) } EXPORT_SYMBOL_GPL(rtnl_link_unregister); +static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev) +{ + struct net_device *master_dev; + const struct rtnl_link_ops *ops; + + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (!master_dev) + return 0; + ops = master_dev->rtnl_link_ops; + if (!ops || !ops->get_slave_size) + return 0; + /* IFLA_INFO_SLAVE_DATA + nested data */ + return nla_total_size(sizeof(struct nlattr)) + + ops->get_slave_size(master_dev, dev); +} + static size_t rtnl_link_get_size(const struct net_device *dev) { const struct rtnl_link_ops *ops = dev->rtnl_link_ops; @@ -385,6 +401,8 @@ static size_t rtnl_link_get_size(const struct net_device *dev) /* IFLA_INFO_XSTATS */ size += nla_total_size(ops->get_xstats_size(dev)); + size += rtnl_link_get_slave_info_data_size(dev); + return size; } @@ -403,34 +421,16 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family) } /** - * __rtnl_af_register - Register rtnl_af_ops with rtnetlink. - * @ops: struct rtnl_af_ops * to register - * - * The caller must hold the rtnl_mutex. - * - * Returns 0 on success or a negative error code. - */ -int __rtnl_af_register(struct rtnl_af_ops *ops) -{ - list_add_tail(&ops->list, &rtnl_af_ops); - return 0; -} -EXPORT_SYMBOL_GPL(__rtnl_af_register); - -/** * rtnl_af_register - Register rtnl_af_ops with rtnetlink. * @ops: struct rtnl_af_ops * to register * * Returns 0 on success or a negative error code. */ -int rtnl_af_register(struct rtnl_af_ops *ops) +void rtnl_af_register(struct rtnl_af_ops *ops) { - int err; - rtnl_lock(); - err = __rtnl_af_register(ops); + list_add_tail(&ops->list, &rtnl_af_ops); rtnl_unlock(); - return err; } EXPORT_SYMBOL_GPL(rtnl_af_register); @@ -477,40 +477,100 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev) return size; } -static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) +static bool rtnl_have_link_slave_info(const struct net_device *dev) { - const struct rtnl_link_ops *ops = dev->rtnl_link_ops; - struct nlattr *linkinfo, *data; - int err = -EMSGSIZE; + struct net_device *master_dev; - linkinfo = nla_nest_start(skb, IFLA_LINKINFO); - if (linkinfo == NULL) - goto out; + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (master_dev && master_dev->rtnl_link_ops) + return true; + return false; +} + +static int rtnl_link_slave_info_fill(struct sk_buff *skb, + const struct net_device *dev) +{ + struct net_device *master_dev; + const struct rtnl_link_ops *ops; + struct nlattr *slave_data; + int err; + + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (!master_dev) + return 0; + ops = master_dev->rtnl_link_ops; + if (!ops) + return 0; + if (nla_put_string(skb, IFLA_INFO_SLAVE_KIND, ops->kind) < 0) + return -EMSGSIZE; + if (ops->fill_slave_info) { + slave_data = nla_nest_start(skb, IFLA_INFO_SLAVE_DATA); + if (!slave_data) + return -EMSGSIZE; + err = ops->fill_slave_info(skb, master_dev, dev); + if (err < 0) + goto err_cancel_slave_data; + nla_nest_end(skb, slave_data); + } + return 0; +err_cancel_slave_data: + nla_nest_cancel(skb, slave_data); + return err; +} + +static int rtnl_link_info_fill(struct sk_buff *skb, + const struct net_device *dev) +{ + const struct rtnl_link_ops *ops = dev->rtnl_link_ops; + struct nlattr *data; + int err; + + if (!ops) + return 0; if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0) - goto err_cancel_link; + return -EMSGSIZE; if (ops->fill_xstats) { err = ops->fill_xstats(skb, dev); if (err < 0) - goto err_cancel_link; + return err; } if (ops->fill_info) { data = nla_nest_start(skb, IFLA_INFO_DATA); - if (data == NULL) { - err = -EMSGSIZE; - goto err_cancel_link; - } + if (data == NULL) + return -EMSGSIZE; err = ops->fill_info(skb, dev); if (err < 0) goto err_cancel_data; nla_nest_end(skb, data); } - - nla_nest_end(skb, linkinfo); return 0; err_cancel_data: nla_nest_cancel(skb, data); + return err; +} + +static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) +{ + struct nlattr *linkinfo; + int err = -EMSGSIZE; + + linkinfo = nla_nest_start(skb, IFLA_LINKINFO); + if (linkinfo == NULL) + goto out; + + err = rtnl_link_info_fill(skb, dev); + if (err < 0) + goto err_cancel_link; + + err = rtnl_link_slave_info_fill(skb, dev); + if (err < 0) + goto err_cancel_link; + + nla_nest_end(skb, linkinfo); + return 0; + err_cancel_link: nla_nest_cancel(skb, linkinfo); out: @@ -1019,7 +1079,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_port_fill(skb, dev)) goto nla_put_failure; - if (dev->rtnl_link_ops) { + if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) { if (rtnl_link_fill(skb, dev) < 0) goto nla_put_failure; } @@ -1142,6 +1202,8 @@ EXPORT_SYMBOL(ifla_policy); static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_KIND] = { .type = NLA_STRING }, [IFLA_INFO_DATA] = { .type = NLA_NESTED }, + [IFLA_INFO_SLAVE_KIND] = { .type = NLA_STRING }, + [IFLA_INFO_SLAVE_DATA] = { .type = NLA_NESTED }, }; static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = { @@ -1729,7 +1791,9 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); const struct rtnl_link_ops *ops; + const struct rtnl_link_ops *m_ops = NULL; struct net_device *dev; + struct net_device *master_dev = NULL; struct ifinfomsg *ifm; char kind[MODULE_NAME_LEN]; char ifname[IFNAMSIZ]; @@ -1759,6 +1823,12 @@ replay: dev = NULL; } + if (dev) { + master_dev = netdev_master_upper_dev_get(dev); + if (master_dev) + m_ops = master_dev->rtnl_link_ops; + } + err = validate_linkmsg(dev, tb); if (err < 0) return err; @@ -1780,7 +1850,10 @@ replay: } if (1) { - struct nlattr *attr[ops ? ops->maxtype + 1 : 0], **data = NULL; + struct nlattr *attr[ops ? ops->maxtype + 1 : 0]; + struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 0]; + struct nlattr **data = NULL; + struct nlattr **slave_data = NULL; struct net *dest_net; if (ops) { @@ -1799,6 +1872,24 @@ replay: } } + if (m_ops) { + if (m_ops->slave_maxtype && + linkinfo[IFLA_INFO_SLAVE_DATA]) { + err = nla_parse_nested(slave_attr, + m_ops->slave_maxtype, + linkinfo[IFLA_INFO_SLAVE_DATA], + m_ops->slave_policy); + if (err < 0) + return err; + slave_data = slave_attr; + } + if (m_ops->slave_validate) { + err = m_ops->slave_validate(tb, slave_data); + if (err < 0) + return err; + } + } + if (dev) { int modified = 0; @@ -1818,6 +1909,17 @@ replay: modified = 1; } + if (linkinfo[IFLA_INFO_SLAVE_DATA]) { + if (!m_ops || !m_ops->slave_changelink) + return -EOPNOTSUPP; + + err = m_ops->slave_changelink(master_dev, dev, + tb, slave_data); + if (err < 0) + return err; + modified = 1; + } + return do_setlink(dev, ifm, tb, ifname, modified); } @@ -1861,16 +1963,21 @@ replay: dev->ifindex = ifm->ifi_index; - if (ops->newlink) + if (ops->newlink) { err = ops->newlink(net, dev, tb, data); - else + /* Drivers should call free_netdev() in ->destructor + * and unregister it on failure so that device could be + * finally freed in rtnl_unlock. + */ + if (err < 0) + goto out; + } else { err = register_netdevice(dev); - - if (err < 0) { - free_netdev(dev); - goto out; + if (err < 0) { + free_netdev(dev); + goto out; + } } - err = rtnl_configure_link(dev, ifm); if (err < 0) unregister_netdevice(dev); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 06e72d3cdf60..5976ef0846bd 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> @@ -65,6 +67,7 @@ #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> +#include <net/ip6_checksum.h> #include <net/xfrm.h> #include <asm/uaccess.h> @@ -74,36 +77,6 @@ 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 @@ -712,9 +685,8 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->inner_network_header = old->inner_network_header; new->inner_mac_header = old->inner_mac_header; skb_dst_copy(new, old); - new->rxhash = old->rxhash; + skb_copy_hash(new, old); new->ooo_okay = old->ooo_okay; - new->l4_rxhash = old->l4_rxhash; new->no_fcs = old->no_fcs; new->encapsulation = old->encapsulation; #ifdef CONFIG_XFRM @@ -1830,7 +1802,7 @@ 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; @@ -2122,6 +2094,91 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, } EXPORT_SYMBOL(skb_copy_and_csum_bits); + /** + * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() + * @from: source buffer + * + * Calculates the amount of linear headroom needed in the 'to' skb passed + * into skb_zerocopy(). + */ +unsigned int +skb_zerocopy_headlen(const struct sk_buff *from) +{ + unsigned int hlen = 0; + + if (!from->head_frag || + skb_headlen(from) < L1_CACHE_BYTES || + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + hlen = skb_headlen(from); + + if (skb_has_frag_list(from)) + hlen = from->len; + + return hlen; +} +EXPORT_SYMBOL_GPL(skb_zerocopy_headlen); + +/** + * skb_zerocopy - Zero copy skb to skb + * @to: destination buffer + * @from: source buffer + * @len: number of bytes to copy from source buffer + * @hlen: size of linear headroom in destination buffer + * + * Copies up to `len` bytes from `from` to `to` by creating references + * to the frags in the source buffer. + * + * The `hlen` as calculated by skb_zerocopy_headlen() specifies the + * headroom in the `to` buffer. + */ +void +skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen) +{ + int i, j = 0; + int plen = 0; /* length of skb->head fragment */ + struct page *page; + unsigned int offset; + + BUG_ON(!from->head_frag && !hlen); + + /* dont bother with small payloads */ + if (len <= skb_tailroom(to)) { + skb_copy_bits(from, 0, skb_put(to, len), len); + return; + } + + if (hlen) { + skb_copy_bits(from, 0, skb_put(to, hlen), hlen); + len -= hlen; + } else { + plen = min_t(int, skb_headlen(from), len); + if (plen) { + page = virt_to_head_page(from->head); + offset = from->data - (unsigned char *)page_address(page); + __skb_fill_page_desc(to, 0, page, offset, plen); + get_page(page); + j = 1; + len -= plen; + } + } + + to->truesize += len + plen; + to->len += len + plen; + to->data_len += len + plen; + + for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { + if (!len) + break; + skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; + skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len); + len -= skb_shinfo(to)->frags[j].size; + skb_frag_ref(to, j); + j++; + } + skb_shinfo(to)->nr_frags = j; +} +EXPORT_SYMBOL_GPL(skb_zerocopy); + void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { __wsum csum; @@ -2982,10 +3039,7 @@ perform_csum_check: return segs; err: - while ((skb = segs)) { - segs = skb->next; - kfree_skb(skb); - } + kfree_skb_list(segs); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(skb_segment); @@ -3468,6 +3522,278 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) } EXPORT_SYMBOL_GPL(skb_partial_csum_set); +static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, + unsigned int max) +{ + if (skb_headlen(skb) >= len) + return 0; + + /* If we need to pullup then pullup to the max, so we + * won't need to do it again. + */ + if (max > skb->len) + max = skb->len; + + if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) + return -ENOMEM; + + if (skb_headlen(skb) < len) + return -EPROTO; + + return 0; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * maximally sized IP and TCP or UDP headers. + */ +#define MAX_IP_HDR_LEN 128 + +static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate) +{ + unsigned int off; + bool fragment; + int err; + + fragment = false; + + err = skb_maybe_pull_tail(skb, + sizeof(struct iphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF)) + fragment = true; + + off = ip_hdrlen(skb); + + err = -EPROTO; + + if (fragment) + goto out; + + switch (ip_hdr(skb)->protocol) { + case IPPROTO_TCP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + tcp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); + break; + case IPPROTO_UDP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct udphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + udp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); + break; + default: + goto out; + } + + err = 0; + +out: + return err; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * an IPv6 header, all options, and a maximal TCP or UDP header. + */ +#define MAX_IPV6_HDR_LEN 256 + +#define OPT_HDR(type, skb, off) \ + (type *)(skb_network_header(skb) + (off)) + +static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) +{ + int err; + u8 nexthdr; + unsigned int off; + unsigned int len; + bool fragment; + bool done; + + fragment = false; + done = false; + + off = sizeof(struct ipv6hdr); + + err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + nexthdr = ipv6_hdr(skb)->nexthdr; + + len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); + while (off <= len && !done) { + switch (nexthdr) { + case IPPROTO_DSTOPTS: + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: { + struct ipv6_opt_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ipv6_opt_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_optlen(hp); + break; + } + case IPPROTO_AH: { + struct ip_auth_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ip_auth_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ip_auth_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_authlen(hp); + break; + } + case IPPROTO_FRAGMENT: { + struct frag_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct frag_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct frag_hdr, skb, off); + + if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) + fragment = true; + + nexthdr = hp->nexthdr; + off += sizeof(struct frag_hdr); + break; + } + default: + done = true; + break; + } + } + + err = -EPROTO; + + if (!done || fragment) + goto out; + + switch (nexthdr) { + case IPPROTO_TCP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + tcp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); + break; + case IPPROTO_UDP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct udphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + udp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); + break; + default: + goto out; + } + + err = 0; + +out: + return err; +} + +/** + * skb_checksum_setup - set up partial checksum offset + * @skb: the skb to set up + * @recalculate: if true the pseudo-header checksum will be recalculated + */ +int skb_checksum_setup(struct sk_buff *skb, bool recalculate) +{ + int err; + + switch (skb->protocol) { + case htons(ETH_P_IP): + err = skb_checksum_setup_ip(skb, recalculate); + break; + + case htons(ETH_P_IPV6): + err = skb_checksum_setup_ipv6(skb, recalculate); + break; + + default: + err = -EPROTO; + break; + } + + return err; +} +EXPORT_SYMBOL(skb_checksum_setup); + void __skb_warn_lro_forwarding(const struct sk_buff *skb) { net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", @@ -3592,3 +3918,26 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) nf_reset_trace(skb); } EXPORT_SYMBOL_GPL(skb_scrub_packet); + +/** + * 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); + unsigned int hdr_len; + + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + hdr_len = tcp_hdrlen(skb); + else + hdr_len = sizeof(struct udphdr); + return hdr_len + shinfo->gso_size; +} +EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); diff --git a/net/core/sock.c b/net/core/sock.c index 5393b4b719d7..5b6a9431b017 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -925,8 +925,8 @@ set_rcvbuf: EXPORT_SYMBOL(sock_setsockopt); -void cred_to_ucred(struct pid *pid, const struct cred *cred, - struct ucred *ucred) +static void cred_to_ucred(struct pid *pid, const struct cred *cred, + struct ucred *ucred) { ucred->pid = pid_vnr(pid); ucred->uid = ucred->gid = -1; @@ -937,7 +937,6 @@ void cred_to_ucred(struct pid *pid, const struct cred *cred, ucred->gid = from_kgid_munged(current_ns, cred->egid); } } -EXPORT_SYMBOL_GPL(cred_to_ucred); int sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) @@ -1168,6 +1167,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sock_flag(sk, SOCK_FILTER_LOCKED); break; + case SO_BPF_EXTENSIONS: + v.val = bpf_tell_extensions(); + break; + case SO_SELECT_ERR_QUEUE: v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; @@ -1308,19 +1311,7 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) module_put(owner); } -#if IS_ENABLED(CONFIG_NET_CLS_CGROUP) -void sock_update_classid(struct sock *sk) -{ - u32 classid; - - classid = task_cls_classid(current); - if (classid != sk->sk_classid) - sk->sk_classid = classid; -} -EXPORT_SYMBOL(sock_update_classid); -#endif - -#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) void sock_update_netprioidx(struct sock *sk) { if (in_interrupt()) @@ -1666,22 +1657,6 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, EXPORT_SYMBOL(sock_wmalloc); /* - * Allocate a skb from the socket's receive buffer. - */ -struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, - gfp_t priority) -{ - if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { - struct sk_buff *skb = alloc_skb(size, priority); - if (skb) { - skb_set_owner_r(skb, sk); - return skb; - } - } - return NULL; -} - -/* * Allocate a memory block from the socket's option memory buffer. */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) @@ -1800,7 +1775,9 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, while (order) { if (npages >= 1 << order) { page = alloc_pages(sk->sk_allocation | - __GFP_COMP | __GFP_NOWARN, + __GFP_COMP | + __GFP_NOWARN | + __GFP_NORETRY, order); if (page) goto fill_page; @@ -1865,14 +1842,12 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio) put_page(pfrag->page); } - /* We restrict high order allocations to users that can afford to wait */ - order = (prio & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0; - + order = SKB_FRAG_PAGE_ORDER; do { gfp_t gfp = prio; 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; diff --git a/net/core/stream.c b/net/core/stream.c index 512f0a24269b..301c05f26060 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -122,7 +122,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) DEFINE_WAIT(wait); if (sk_stream_memory_free(sk)) - current_timeo = vm_wait = (net_random() % (HZ / 5)) + 2; + current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2; while (1) { set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index cca444190907..cf9cd13509a7 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -122,7 +122,8 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, synchronize_rcu(); kfree(cur); } else if (!cur && cpumask_test_cpu(i, mask)) { - cur = kzalloc(len, GFP_KERNEL); + cur = kzalloc_node(len, GFP_KERNEL, + cpu_to_node(i)); if (!cur) { /* not unwinding previous changes */ ret = -ENOMEM; diff --git a/net/dcb/dcbevent.c b/net/dcb/dcbevent.c index 4f72fc40bf02..a520d8004d89 100644 --- a/net/dcb/dcbevent.c +++ b/net/dcb/dcbevent.c @@ -11,8 +11,7 @@ * more details. * * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 Temple - * Place - Suite 330, Boston, MA 02111-1307 USA. + * this program; if not, see <http://www.gnu.org/licenses/>. * * Author: John Fastabend <john.r.fastabend@intel.com> */ diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 40d5829ed36a..553644402670 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -11,8 +11,7 @@ * more details. * * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 Temple - * Place - Suite 330, Boston, MA 02111-1307 USA. + * this program; if not, see <http://www.gnu.org/licenses/>. * * Author: Lucy Liu <lucy.liu@intel.com> */ @@ -1689,21 +1688,17 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh) if (!tb[DCB_ATTR_IFNAME]) return -EINVAL; - netdev = dev_get_by_name(net, nla_data(tb[DCB_ATTR_IFNAME])); + netdev = __dev_get_by_name(net, nla_data(tb[DCB_ATTR_IFNAME])); if (!netdev) return -ENODEV; - if (!netdev->dcbnl_ops) { - ret = -EOPNOTSUPP; - goto out; - } + if (!netdev->dcbnl_ops) + return -EOPNOTSUPP; reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, portid, nlh->nlmsg_seq, nlh->nlmsg_flags, &reply_nlh); - if (!reply_skb) { - ret = -ENOBUFS; - goto out; - } + if (!reply_skb) + return -ENOBUFS; ret = fn->cb(netdev, nlh, nlh->nlmsg_seq, tb, reply_skb); if (ret < 0) { @@ -1715,7 +1710,6 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh) ret = rtnl_unicast(reply_skb, net, portid); out: - dev_put(netdev); return ret; } diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 30948784dd58..c67816647cce 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -479,7 +479,6 @@ void dccp_feat_list_purge(struct list_head *fn_list); int dccp_insert_options(struct sock *sk, struct sk_buff *skb); int dccp_insert_options_rsk(struct dccp_request_sock *, struct sk_buff *); -int dccp_insert_option_elapsed_time(struct sk_buff *skb, u32 elapsed); u32 dccp_timestamp(void); void dccp_timestamping_init(void); int dccp_insert_option(struct sk_buff *skb, unsigned char option, diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index d9f65fc66db5..22b5d818b200 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -75,7 +75,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_DCCP, - orig_sport, orig_dport, sk, true); + orig_sport, orig_dport, sk); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -989,6 +989,7 @@ static const struct net_protocol dccp_v4_protocol = { .err_handler = dccp_v4_err, .no_policy = 1, .netns_ok = 1, + .icmp_strict_tag_validation = 1, }; static const struct proto_ops inet_dccp_ops = { diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 2b90a786e475..4db3c2a1679c 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -141,6 +141,9 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; + if (!ip6_sk_accept_pmtu(sk)) + goto out; + if (sock_owned_by_user(sk)) goto out; if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) @@ -237,7 +240,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req) final_p = fl6_update_dst(&fl6, np->opt, &final); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; @@ -301,7 +304,7 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6)); /* sk = NULL, but it is safe for now. RST socket required. */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false); + dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); ip6_xmit(ctl_sk, skb, &fl6, NULL, 0); @@ -512,7 +515,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, fl6.fl6_sport = htons(ireq->ir_num); security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) goto out; } @@ -931,7 +934,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, final_p = fl6_update_dst(&fl6, np->opt, &final); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; diff --git a/net/dccp/options.c b/net/dccp/options.c index a58e0b634050..9bce31886bda 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -343,38 +343,6 @@ static inline int dccp_elapsed_time_len(const u32 elapsed_time) return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4; } -/* FIXME: This function is currently not used anywhere */ -int dccp_insert_option_elapsed_time(struct sk_buff *skb, u32 elapsed_time) -{ - const int elapsed_time_len = dccp_elapsed_time_len(elapsed_time); - const int len = 2 + elapsed_time_len; - unsigned char *to; - - if (elapsed_time_len == 0) - return 0; - - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) - return -1; - - DCCP_SKB_CB(skb)->dccpd_opt_len += len; - - to = skb_push(skb, len); - *to++ = DCCPO_ELAPSED_TIME; - *to++ = len; - - if (elapsed_time_len == 2) { - const __be16 var16 = htons((u16)elapsed_time); - memcpy(to, &var16, 2); - } else { - const __be32 var32 = htonl(elapsed_time); - memcpy(to, &var32, 4); - } - - return 0; -} - -EXPORT_SYMBOL_GPL(dccp_insert_option_elapsed_time); - static int dccp_insert_option_timestamp(struct sk_buff *skb) { __be32 now = htonl(dccp_timestamp()); diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index dd4d506ef923..4c04848953bd 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1808,6 +1808,7 @@ out: rv = (flags & MSG_PEEK) ? -sk->sk_err : sock_error(sk); if ((rv >= 0) && msg->msg_name) { + __sockaddr_check_size(sizeof(struct sockaddr_dn)); memcpy(msg->msg_name, &scp->peer, sizeof(struct sockaddr_dn)); msg->msg_namelen = sizeof(struct sockaddr_dn); } @@ -1914,7 +1915,7 @@ static int dn_sendmsg(struct kiocb *iocb, struct socket *sock, int err = 0; size_t sent = 0; int addr_len = msg->msg_namelen; - struct sockaddr_dn *addr = (struct sockaddr_dn *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_dn *, addr, msg->msg_name); struct sk_buff *skb = NULL; struct dn_skb_cb *cb; size_t len; @@ -2103,8 +2104,6 @@ static struct notifier_block dn_dev_notifier = { .notifier_call = dn_device_event, }; -extern int dn_route_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); - static struct packet_type dn_dix_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_DNA_RT), .func = dn_route_rcv, @@ -2352,9 +2351,6 @@ static const struct proto_ops dn_proto_ops = { .sendpage = sock_no_sendpage, }; -void dn_register_sysctl(void); -void dn_unregister_sysctl(void); - MODULE_DESCRIPTION("The Linux DECnet Network Protocol"); MODULE_AUTHOR("Linux DECnet Project Team"); MODULE_LICENSE("GPL"); diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index dd0dfb25f4b1..a603823a3e27 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -561,6 +561,7 @@ static const struct nla_policy dn_ifa_policy[IFA_MAX+1] = { [IFA_LOCAL] = { .type = NLA_U16 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, + [IFA_FLAGS] = { .type = NLA_U32 }, }; static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) @@ -648,7 +649,8 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) ifa->ifa_local = nla_get_le16(tb[IFA_LOCAL]); ifa->ifa_address = nla_get_le16(tb[IFA_ADDRESS]); - ifa->ifa_flags = ifm->ifa_flags; + ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : + ifm->ifa_flags; ifa->ifa_scope = ifm->ifa_scope; ifa->ifa_dev = dn_db; @@ -669,7 +671,8 @@ static inline size_t dn_ifaddr_nlmsg_size(void) return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + nla_total_size(2) /* IFA_ADDRESS */ - + nla_total_size(2); /* IFA_LOCAL */ + + nla_total_size(2) /* IFA_LOCAL */ + + nla_total_size(4); /* IFA_FLAGS */ } static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa, @@ -677,6 +680,7 @@ static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa, { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; + u32 ifa_flags = ifa->ifa_flags | IFA_F_PERMANENT; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); if (nlh == NULL) @@ -685,7 +689,7 @@ static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa, ifm = nlmsg_data(nlh); ifm->ifa_family = AF_DECnet; ifm->ifa_prefixlen = 16; - ifm->ifa_flags = ifa->ifa_flags | IFA_F_PERMANENT; + ifm->ifa_flags = ifa_flags; ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; @@ -694,7 +698,8 @@ static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa, (ifa->ifa_local && nla_put_le16(skb, IFA_LOCAL, ifa->ifa_local)) || (ifa->ifa_label[0] && - nla_put_string(skb, IFA_LABEL, ifa->ifa_label))) + nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || + nla_put_u32(skb, IFA_FLAGS, ifa_flags)) goto nla_put_failure; return nlmsg_end(skb, nlh); diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index f8637f93d318..c8121ceddb9e 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -102,19 +102,21 @@ struct neigh_table dn_neigh_table = { .id = "dn_neigh_cache", .parms ={ .tbl = &dn_neigh_table, - .base_reachable_time = 30 * HZ, - .retrans_time = 1 * HZ, - .gc_staletime = 60 * HZ, - .reachable_time = 30 * HZ, - .delay_probe_time = 5 * HZ, - .queue_len_bytes = 64*1024, - .ucast_probes = 0, - .app_probes = 0, - .mcast_probes = 0, - .anycast_delay = 0, - .proxy_delay = 0, - .proxy_qlen = 0, - .locktime = 1 * HZ, + .reachable_time = 30 * HZ, + .data = { + [NEIGH_VAR_MCAST_PROBES] = 0, + [NEIGH_VAR_UCAST_PROBES] = 0, + [NEIGH_VAR_APP_PROBES] = 0, + [NEIGH_VAR_RETRANS_TIME] = 1 * HZ, + [NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ, + [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, + [NEIGH_VAR_GC_STALETIME] = 60 * HZ, + [NEIGH_VAR_QUEUE_LEN_BYTES] = 64*1024, + [NEIGH_VAR_PROXY_QLEN] = 0, + [NEIGH_VAR_ANYCAST_DELAY] = 0, + [NEIGH_VAR_PROXY_DELAY] = 0, + [NEIGH_VAR_LOCKTIME] = 1 * HZ, + }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index fe32388ea24f..ce0cbbfe0f43 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1288,8 +1288,6 @@ int dn_route_output_sock(struct dst_entry __rcu **pprt, struct flowidn *fl, stru err = __dn_route_output_key(pprt, fl, flags & MSG_TRYHARD); if (err == 0 && fl->flowidn_proto) { - if (!(flags & MSG_DONTWAIT)) - fl->flowidn_flags |= FLOWI_FLAG_CAN_SLEEP; *pprt = xfrm_lookup(&init_net, *pprt, flowidn_to_flowi(fl), sk, 0); if (IS_ERR(*pprt)) { @@ -1668,12 +1666,8 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) if (fld.flowidn_iif) { struct net_device *dev; - if ((dev = dev_get_by_index(&init_net, fld.flowidn_iif)) == NULL) { - kfree_skb(skb); - return -ENODEV; - } - if (!dev->dn_ptr) { - dev_put(dev); + dev = __dev_get_by_index(&init_net, fld.flowidn_iif); + if (!dev || !dev->dn_ptr) { kfree_skb(skb); return -ENODEV; } @@ -1695,8 +1689,6 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) err = dn_route_output_key((struct dst_entry **)&rt, &fld, 0); } - if (skb->dev) - dev_put(skb->dev); skb->dev = NULL; if (err) goto out_free; diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index f347a2ca7d7e..bf8584339048 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -19,8 +19,7 @@ * the GNU Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this library; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/module.h> #include <linux/moduleparam.h> diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c index c32be292c7e3..e7b6d53eef88 100644 --- a/net/dns_resolver/dns_query.c +++ b/net/dns_resolver/dns_query.c @@ -32,8 +32,7 @@ * the GNU Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this library; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/module.h> diff --git a/net/dns_resolver/internal.h b/net/dns_resolver/internal.h index 17c7886b5b3a..7af1ed39c009 100644 --- a/net/dns_resolver/internal.h +++ b/net/dns_resolver/internal.h @@ -15,8 +15,7 @@ * the GNU Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this library; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/compiler.h> diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 29d684ebca6a..02c0e1716f64 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -156,7 +156,7 @@ static int dsa_slave_set_mac_address(struct net_device *dev, void *a) dev_uc_del(master, dev->dev_addr); out: - memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); + ether_addr_copy(dev->dev_addr, addr->sa_data); return 0; } diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 8f032bae60ad..5dc638cad2e1 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -156,7 +156,9 @@ EXPORT_SYMBOL(eth_rebuild_header); */ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) { - struct ethhdr *eth; + unsigned short _service_access_point; + const unsigned short *sap; + const struct ethhdr *eth; skb->dev = dev; skb_reset_mac_header(skb); @@ -194,7 +196,8 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) * layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This * won't work for fault tolerant netware but does for the rest. */ - if (unlikely(skb->len >= 2 && *(unsigned short *)(skb->data) == 0xFFFF)) + sap = skb_header_pointer(skb, 0, sizeof(*sap), &_service_access_point); + if (sap && *sap == 0xFFFF) return htons(ETH_P_802_3); /* diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 4bdab1521878..327060c6c874 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -127,11 +127,6 @@ int hsr_create_self_node(struct list_head *self_node_db, return 0; } -static void node_entry_reclaim(struct rcu_head *rh) -{ - kfree(container_of(rh, struct node_entry, rcu_head)); -} - /* Add/merge node to the database of nodes. 'skb' must contain an HSR * supervision frame. @@ -175,7 +170,7 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv, if (node && !ether_addr_equal(node->MacAddressA, hsr_sp->MacAddressA)) { /* Node has changed its AddrA, frame was received from SlaveB */ list_del_rcu(&node->mac_list); - call_rcu(&node->rcu_head, node_entry_reclaim); + kfree_rcu(node, rcu_head); node = NULL; } @@ -183,7 +178,7 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv, !ether_addr_equal(node->MacAddressB, hsr_ethsup->ethhdr.h_source)) { /* Cables have been swapped */ list_del_rcu(&node->mac_list); - call_rcu(&node->rcu_head, node_entry_reclaim); + kfree_rcu(node, rcu_head); node = NULL; } @@ -192,7 +187,7 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv, !ether_addr_equal(node->MacAddressA, hsr_ethsup->ethhdr.h_source)) { /* Cables have been swapped */ list_del_rcu(&node->mac_list); - call_rcu(&node->rcu_head, node_entry_reclaim); + kfree_rcu(node, rcu_head); node = NULL; } @@ -417,7 +412,7 @@ void hsr_prune_nodes(struct hsr_priv *hsr_priv) hsr_nl_nodedown(hsr_priv, node->MacAddressA); list_del_rcu(&node->mac_list); /* Note that we need to free this entry later: */ - call_rcu(&node->rcu_head, node_entry_reclaim); + kfree_rcu(node, rcu_head); } } rcu_read_unlock(); diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index a2d2456a557a..8edfea5da572 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -62,9 +62,6 @@ #include "6lowpan.h" -/* TTL uncompression values */ -static const u8 lowpan_ttl_values[] = {0, 1, 64, 255}; - static LIST_HEAD(lowpan_devices); /* private device info */ @@ -104,378 +101,13 @@ static inline void lowpan_address_flip(u8 *src, u8 *dest) (dest)[IEEE802154_ADDR_LEN - i - 1] = (src)[i]; } -/* list of all 6lowpan devices, uses for package delivering */ -/* print data in line */ -static inline void lowpan_raw_dump_inline(const char *caller, char *msg, - unsigned char *buf, int len) -{ -#ifdef DEBUG - if (msg) - pr_debug("(%s) %s: ", caller, msg); - print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE, - 16, 1, buf, len, false); -#endif /* DEBUG */ -} - -/* - * print data in a table format: - * - * addr: xx xx xx xx xx xx - * addr: xx xx xx xx xx xx - * ... - */ -static inline void lowpan_raw_dump_table(const char *caller, char *msg, - unsigned char *buf, int len) -{ -#ifdef DEBUG - if (msg) - pr_debug("(%s) %s:\n", caller, msg); - print_hex_dump(KERN_DEBUG, "\t", DUMP_PREFIX_OFFSET, - 16, 1, buf, len, false); -#endif /* DEBUG */ -} - -static u8 -lowpan_compress_addr_64(u8 **hc06_ptr, u8 shift, const struct in6_addr *ipaddr, - const unsigned char *lladdr) -{ - u8 val = 0; - - if (is_addr_mac_addr_based(ipaddr, lladdr)) - val = 3; /* 0-bits */ - else if (lowpan_is_iid_16_bit_compressable(ipaddr)) { - /* compress IID to 16 bits xxxx::XXXX */ - memcpy(*hc06_ptr, &ipaddr->s6_addr16[7], 2); - *hc06_ptr += 2; - val = 2; /* 16-bits */ - } else { - /* do not compress IID => xxxx::IID */ - memcpy(*hc06_ptr, &ipaddr->s6_addr16[4], 8); - *hc06_ptr += 8; - val = 1; /* 64-bits */ - } - - return rol8(val, shift); -} - -/* - * Uncompress address function for source and - * destination address(non-multicast). - * - * address_mode is sam value or dam value. - */ -static int -lowpan_uncompress_addr(struct sk_buff *skb, - struct in6_addr *ipaddr, - const u8 address_mode, - const struct ieee802154_addr *lladdr) -{ - bool fail; - - switch (address_mode) { - case LOWPAN_IPHC_ADDR_00: - /* for global link addresses */ - fail = lowpan_fetch_skb(skb, ipaddr->s6_addr, 16); - break; - case LOWPAN_IPHC_ADDR_01: - /* fe:80::XXXX:XXXX:XXXX:XXXX */ - ipaddr->s6_addr[0] = 0xFE; - ipaddr->s6_addr[1] = 0x80; - fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[8], 8); - break; - case LOWPAN_IPHC_ADDR_02: - /* fe:80::ff:fe00:XXXX */ - ipaddr->s6_addr[0] = 0xFE; - ipaddr->s6_addr[1] = 0x80; - ipaddr->s6_addr[11] = 0xFF; - ipaddr->s6_addr[12] = 0xFE; - fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[14], 2); - break; - case LOWPAN_IPHC_ADDR_03: - fail = false; - switch (lladdr->addr_type) { - case IEEE802154_ADDR_LONG: - /* fe:80::XXXX:XXXX:XXXX:XXXX - * \_________________/ - * hwaddr - */ - ipaddr->s6_addr[0] = 0xFE; - ipaddr->s6_addr[1] = 0x80; - memcpy(&ipaddr->s6_addr[8], lladdr->hwaddr, - IEEE802154_ADDR_LEN); - /* second bit-flip (Universe/Local) - * is done according RFC2464 - */ - ipaddr->s6_addr[8] ^= 0x02; - break; - case IEEE802154_ADDR_SHORT: - /* fe:80::ff:fe00:XXXX - * \__/ - * short_addr - * - * Universe/Local bit is zero. - */ - ipaddr->s6_addr[0] = 0xFE; - ipaddr->s6_addr[1] = 0x80; - ipaddr->s6_addr[11] = 0xFF; - ipaddr->s6_addr[12] = 0xFE; - ipaddr->s6_addr16[7] = htons(lladdr->short_addr); - break; - default: - pr_debug("Invalid addr_type set\n"); - return -EINVAL; - } - break; - default: - pr_debug("Invalid address mode value: 0x%x\n", address_mode); - return -EINVAL; - } - - if (fail) { - pr_debug("Failed to fetch skb data\n"); - return -EIO; - } - - lowpan_raw_dump_inline(NULL, "Reconstructed ipv6 addr is:\n", - ipaddr->s6_addr, 16); - - return 0; -} - -/* Uncompress address function for source context - * based address(non-multicast). - */ -static int -lowpan_uncompress_context_based_src_addr(struct sk_buff *skb, - struct in6_addr *ipaddr, - const u8 sam) -{ - switch (sam) { - case LOWPAN_IPHC_ADDR_00: - /* unspec address :: - * Do nothing, address is already :: - */ - break; - case LOWPAN_IPHC_ADDR_01: - /* TODO */ - case LOWPAN_IPHC_ADDR_02: - /* TODO */ - case LOWPAN_IPHC_ADDR_03: - /* TODO */ - netdev_warn(skb->dev, "SAM value 0x%x not supported\n", sam); - return -EINVAL; - default: - pr_debug("Invalid sam value: 0x%x\n", sam); - return -EINVAL; - } - - lowpan_raw_dump_inline(NULL, - "Reconstructed context based ipv6 src addr is:\n", - ipaddr->s6_addr, 16); - - return 0; -} - -/* Uncompress function for multicast destination address, - * when M bit is set. - */ -static int -lowpan_uncompress_multicast_daddr(struct sk_buff *skb, - struct in6_addr *ipaddr, - const u8 dam) -{ - bool fail; - - switch (dam) { - case LOWPAN_IPHC_DAM_00: - /* 00: 128 bits. The full address - * is carried in-line. - */ - fail = lowpan_fetch_skb(skb, ipaddr->s6_addr, 16); - break; - case LOWPAN_IPHC_DAM_01: - /* 01: 48 bits. The address takes - * the form ffXX::00XX:XXXX:XXXX. - */ - ipaddr->s6_addr[0] = 0xFF; - fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[1], 1); - fail |= lowpan_fetch_skb(skb, &ipaddr->s6_addr[11], 5); - break; - case LOWPAN_IPHC_DAM_10: - /* 10: 32 bits. The address takes - * the form ffXX::00XX:XXXX. - */ - ipaddr->s6_addr[0] = 0xFF; - fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[1], 1); - fail |= lowpan_fetch_skb(skb, &ipaddr->s6_addr[13], 3); - break; - case LOWPAN_IPHC_DAM_11: - /* 11: 8 bits. The address takes - * the form ff02::00XX. - */ - ipaddr->s6_addr[0] = 0xFF; - ipaddr->s6_addr[1] = 0x02; - fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[15], 1); - break; - default: - pr_debug("DAM value has a wrong value: 0x%x\n", dam); - return -EINVAL; - } - - if (fail) { - pr_debug("Failed to fetch skb data\n"); - return -EIO; - } - - lowpan_raw_dump_inline(NULL, "Reconstructed ipv6 multicast addr is:\n", - ipaddr->s6_addr, 16); - - return 0; -} - -static void -lowpan_compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb) -{ - struct udphdr *uh = udp_hdr(skb); - - if (((uh->source & LOWPAN_NHC_UDP_4BIT_MASK) == - LOWPAN_NHC_UDP_4BIT_PORT) && - ((uh->dest & LOWPAN_NHC_UDP_4BIT_MASK) == - LOWPAN_NHC_UDP_4BIT_PORT)) { - pr_debug("UDP header: both ports compression to 4 bits\n"); - **hc06_ptr = LOWPAN_NHC_UDP_CS_P_11; - **(hc06_ptr + 1) = /* subtraction is faster */ - (u8)((uh->dest - LOWPAN_NHC_UDP_4BIT_PORT) + - ((uh->source & LOWPAN_NHC_UDP_4BIT_PORT) << 4)); - *hc06_ptr += 2; - } else if ((uh->dest & LOWPAN_NHC_UDP_8BIT_MASK) == - LOWPAN_NHC_UDP_8BIT_PORT) { - pr_debug("UDP header: remove 8 bits of dest\n"); - **hc06_ptr = LOWPAN_NHC_UDP_CS_P_01; - memcpy(*hc06_ptr + 1, &uh->source, 2); - **(hc06_ptr + 3) = (u8)(uh->dest - LOWPAN_NHC_UDP_8BIT_PORT); - *hc06_ptr += 4; - } else if ((uh->source & LOWPAN_NHC_UDP_8BIT_MASK) == - LOWPAN_NHC_UDP_8BIT_PORT) { - pr_debug("UDP header: remove 8 bits of source\n"); - **hc06_ptr = LOWPAN_NHC_UDP_CS_P_10; - memcpy(*hc06_ptr + 1, &uh->dest, 2); - **(hc06_ptr + 3) = (u8)(uh->source - LOWPAN_NHC_UDP_8BIT_PORT); - *hc06_ptr += 4; - } else { - pr_debug("UDP header: can't compress\n"); - **hc06_ptr = LOWPAN_NHC_UDP_CS_P_00; - memcpy(*hc06_ptr + 1, &uh->source, 2); - memcpy(*hc06_ptr + 3, &uh->dest, 2); - *hc06_ptr += 5; - } - - /* checksum is always inline */ - memcpy(*hc06_ptr, &uh->check, 2); - *hc06_ptr += 2; - - /* skip the UDP header */ - skb_pull(skb, sizeof(struct udphdr)); -} - -static inline int lowpan_fetch_skb_u8(struct sk_buff *skb, u8 *val) -{ - if (unlikely(!pskb_may_pull(skb, 1))) - return -EINVAL; - - *val = skb->data[0]; - skb_pull(skb, 1); - - return 0; -} - -static inline int lowpan_fetch_skb_u16(struct sk_buff *skb, u16 *val) -{ - if (unlikely(!pskb_may_pull(skb, 2))) - return -EINVAL; - - *val = (skb->data[0] << 8) | skb->data[1]; - skb_pull(skb, 2); - - return 0; -} - -static int -lowpan_uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh) -{ - u8 tmp; - - if (!uh) - goto err; - - if (lowpan_fetch_skb_u8(skb, &tmp)) - goto err; - - if ((tmp & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) { - pr_debug("UDP header uncompression\n"); - switch (tmp & LOWPAN_NHC_UDP_CS_P_11) { - case LOWPAN_NHC_UDP_CS_P_00: - memcpy(&uh->source, &skb->data[0], 2); - memcpy(&uh->dest, &skb->data[2], 2); - skb_pull(skb, 4); - break; - case LOWPAN_NHC_UDP_CS_P_01: - memcpy(&uh->source, &skb->data[0], 2); - uh->dest = - skb->data[2] + LOWPAN_NHC_UDP_8BIT_PORT; - skb_pull(skb, 3); - break; - case LOWPAN_NHC_UDP_CS_P_10: - uh->source = skb->data[0] + LOWPAN_NHC_UDP_8BIT_PORT; - memcpy(&uh->dest, &skb->data[1], 2); - skb_pull(skb, 3); - break; - case LOWPAN_NHC_UDP_CS_P_11: - uh->source = - LOWPAN_NHC_UDP_4BIT_PORT + (skb->data[0] >> 4); - uh->dest = - LOWPAN_NHC_UDP_4BIT_PORT + (skb->data[0] & 0x0f); - skb_pull(skb, 1); - break; - default: - pr_debug("ERROR: unknown UDP format\n"); - goto err; - } - - pr_debug("uncompressed UDP ports: src = %d, dst = %d\n", - uh->source, uh->dest); - - /* copy checksum */ - memcpy(&uh->check, &skb->data[0], 2); - skb_pull(skb, 2); - - /* - * UDP lenght needs to be infered from the lower layers - * here, we obtain the hint from the remaining size of the - * frame - */ - uh->len = htons(skb->len + sizeof(struct udphdr)); - pr_debug("uncompressed UDP length: src = %d", uh->len); - } else { - pr_debug("ERROR: unsupported NH format\n"); - goto err; - } - - return 0; -err: - return -EINVAL; -} - static int lowpan_header_create(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *_daddr, const void *_saddr, unsigned int len) { - u8 tmp, iphc0, iphc1, *hc06_ptr; - struct ipv6hdr *hdr; const u8 *saddr = _saddr; const u8 *daddr = _daddr; - u8 head[100]; struct ieee802154_addr sa, da; /* TODO: @@ -484,182 +116,13 @@ static int lowpan_header_create(struct sk_buff *skb, if (type != ETH_P_IPV6) return 0; - hdr = ipv6_hdr(skb); - hc06_ptr = head + 2; - - pr_debug("IPv6 header dump:\n\tversion = %d\n\tlength = %d\n" - "\tnexthdr = 0x%02x\n\thop_lim = %d\n", hdr->version, - ntohs(hdr->payload_len), hdr->nexthdr, hdr->hop_limit); - - lowpan_raw_dump_table(__func__, "raw skb network header dump", - skb_network_header(skb), sizeof(struct ipv6hdr)); - if (!saddr) saddr = dev->dev_addr; - lowpan_raw_dump_inline(__func__, "saddr", (unsigned char *)saddr, 8); - - /* - * As we copy some bit-length fields, in the IPHC encoding bytes, - * we sometimes use |= - * If the field is 0, and the current bit value in memory is 1, - * this does not work. We therefore reset the IPHC encoding here - */ - iphc0 = LOWPAN_DISPATCH_IPHC; - iphc1 = 0; + raw_dump_inline(__func__, "saddr", (unsigned char *)saddr, 8); + raw_dump_inline(__func__, "daddr", (unsigned char *)daddr, 8); - /* TODO: context lookup */ - - lowpan_raw_dump_inline(__func__, "daddr", (unsigned char *)daddr, 8); - - /* - * Traffic class, flow label - * If flow label is 0, compress it. If traffic class is 0, compress it - * We have to process both in the same time as the offset of traffic - * class depends on the presence of version and flow label - */ - - /* hc06 format of TC is ECN | DSCP , original one is DSCP | ECN */ - tmp = (hdr->priority << 4) | (hdr->flow_lbl[0] >> 4); - tmp = ((tmp & 0x03) << 6) | (tmp >> 2); - - if (((hdr->flow_lbl[0] & 0x0F) == 0) && - (hdr->flow_lbl[1] == 0) && (hdr->flow_lbl[2] == 0)) { - /* flow label can be compressed */ - iphc0 |= LOWPAN_IPHC_FL_C; - if ((hdr->priority == 0) && - ((hdr->flow_lbl[0] & 0xF0) == 0)) { - /* compress (elide) all */ - iphc0 |= LOWPAN_IPHC_TC_C; - } else { - /* compress only the flow label */ - *hc06_ptr = tmp; - hc06_ptr += 1; - } - } else { - /* Flow label cannot be compressed */ - if ((hdr->priority == 0) && - ((hdr->flow_lbl[0] & 0xF0) == 0)) { - /* compress only traffic class */ - iphc0 |= LOWPAN_IPHC_TC_C; - *hc06_ptr = (tmp & 0xc0) | (hdr->flow_lbl[0] & 0x0F); - memcpy(hc06_ptr + 1, &hdr->flow_lbl[1], 2); - hc06_ptr += 3; - } else { - /* compress nothing */ - memcpy(hc06_ptr, hdr, 4); - /* replace the top byte with new ECN | DSCP format */ - *hc06_ptr = tmp; - hc06_ptr += 4; - } - } - - /* NOTE: payload length is always compressed */ - - /* Next Header is compress if UDP */ - if (hdr->nexthdr == UIP_PROTO_UDP) - iphc0 |= LOWPAN_IPHC_NH_C; - - if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) { - *hc06_ptr = hdr->nexthdr; - hc06_ptr += 1; - } - - /* - * Hop limit - * if 1: compress, encoding is 01 - * if 64: compress, encoding is 10 - * if 255: compress, encoding is 11 - * else do not compress - */ - switch (hdr->hop_limit) { - case 1: - iphc0 |= LOWPAN_IPHC_TTL_1; - break; - case 64: - iphc0 |= LOWPAN_IPHC_TTL_64; - break; - case 255: - iphc0 |= LOWPAN_IPHC_TTL_255; - break; - default: - *hc06_ptr = hdr->hop_limit; - hc06_ptr += 1; - break; - } - - /* source address compression */ - if (is_addr_unspecified(&hdr->saddr)) { - pr_debug("source address is unspecified, setting SAC\n"); - iphc1 |= LOWPAN_IPHC_SAC; - /* TODO: context lookup */ - } else if (is_addr_link_local(&hdr->saddr)) { - pr_debug("source address is link-local\n"); - iphc1 |= lowpan_compress_addr_64(&hc06_ptr, - LOWPAN_IPHC_SAM_BIT, &hdr->saddr, saddr); - } else { - pr_debug("send the full source address\n"); - memcpy(hc06_ptr, &hdr->saddr.s6_addr16[0], 16); - hc06_ptr += 16; - } - - /* destination address compression */ - if (is_addr_mcast(&hdr->daddr)) { - pr_debug("destination address is multicast: "); - iphc1 |= LOWPAN_IPHC_M; - if (lowpan_is_mcast_addr_compressable8(&hdr->daddr)) { - pr_debug("compressed to 1 octet\n"); - iphc1 |= LOWPAN_IPHC_DAM_11; - /* use last byte */ - *hc06_ptr = hdr->daddr.s6_addr[15]; - hc06_ptr += 1; - } else if (lowpan_is_mcast_addr_compressable32(&hdr->daddr)) { - pr_debug("compressed to 4 octets\n"); - iphc1 |= LOWPAN_IPHC_DAM_10; - /* second byte + the last three */ - *hc06_ptr = hdr->daddr.s6_addr[1]; - memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[13], 3); - hc06_ptr += 4; - } else if (lowpan_is_mcast_addr_compressable48(&hdr->daddr)) { - pr_debug("compressed to 6 octets\n"); - iphc1 |= LOWPAN_IPHC_DAM_01; - /* second byte + the last five */ - *hc06_ptr = hdr->daddr.s6_addr[1]; - memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[11], 5); - hc06_ptr += 6; - } else { - pr_debug("using full address\n"); - iphc1 |= LOWPAN_IPHC_DAM_00; - memcpy(hc06_ptr, &hdr->daddr.s6_addr[0], 16); - hc06_ptr += 16; - } - } else { - /* TODO: context lookup */ - if (is_addr_link_local(&hdr->daddr)) { - pr_debug("dest address is unicast and link-local\n"); - iphc1 |= lowpan_compress_addr_64(&hc06_ptr, - LOWPAN_IPHC_DAM_BIT, &hdr->daddr, daddr); - } else { - pr_debug("dest address is unicast: using full one\n"); - memcpy(hc06_ptr, &hdr->daddr.s6_addr16[0], 16); - hc06_ptr += 16; - } - } - - /* UDP header compression */ - if (hdr->nexthdr == UIP_PROTO_UDP) - lowpan_compress_udp_header(&hc06_ptr, skb); - - head[0] = iphc0; - head[1] = iphc1; - - skb_pull(skb, sizeof(struct ipv6hdr)); - skb_reset_transport_header(skb); - memcpy(skb_push(skb, hc06_ptr - head), head, hc06_ptr - head); - skb_reset_network_header(skb); - - lowpan_raw_dump_table(__func__, "raw skb data dump", skb->data, - skb->len); + lowpan_header_compress(skb, dev, type, daddr, saddr, len); /* * NOTE1: I'm still unsure about the fact that compression and WPAN @@ -671,39 +134,38 @@ static int lowpan_header_create(struct sk_buff *skb, * from MAC subif of the 'dev' and 'real_dev' network devices, but * this isn't implemented in mainline yet, so currently we assign 0xff */ - { - mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA; - mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev); + mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA; + mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev); - /* prepare wpan address data */ - sa.addr_type = IEEE802154_ADDR_LONG; - sa.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + /* prepare wpan address data */ + sa.addr_type = IEEE802154_ADDR_LONG; + sa.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); - memcpy(&(sa.hwaddr), saddr, 8); - /* intra-PAN communications */ - da.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + memcpy(&(sa.hwaddr), saddr, 8); + /* intra-PAN communications */ + da.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); - /* - * if the destination address is the broadcast address, use the - * corresponding short address - */ - if (lowpan_is_addr_broadcast(daddr)) { - da.addr_type = IEEE802154_ADDR_SHORT; - da.short_addr = IEEE802154_ADDR_BROADCAST; - } else { - da.addr_type = IEEE802154_ADDR_LONG; - memcpy(&(da.hwaddr), daddr, IEEE802154_ADDR_LEN); - - /* request acknowledgment */ - mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ; - } + /* + * if the destination address is the broadcast address, use the + * corresponding short address + */ + if (lowpan_is_addr_broadcast(daddr)) { + da.addr_type = IEEE802154_ADDR_SHORT; + da.short_addr = IEEE802154_ADDR_BROADCAST; + } else { + da.addr_type = IEEE802154_ADDR_LONG; + memcpy(&(da.hwaddr), daddr, IEEE802154_ADDR_LEN); - return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev, - type, (void *)&da, (void *)&sa, skb->len); + /* request acknowledgment */ + mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ; } + + return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev, + type, (void *)&da, (void *)&sa, skb->len); } -static int lowpan_give_skb_to_devices(struct sk_buff *skb) +static int lowpan_give_skb_to_devices(struct sk_buff *skb, + struct net_device *dev) { struct lowpan_dev_record *entry; struct sk_buff *skb_cp; @@ -726,31 +188,6 @@ static int lowpan_give_skb_to_devices(struct sk_buff *skb) return stat; } -static int lowpan_skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr) -{ - struct sk_buff *new; - int stat = NET_RX_SUCCESS; - - new = skb_copy_expand(skb, sizeof(struct ipv6hdr), skb_tailroom(skb), - GFP_ATOMIC); - kfree_skb(skb); - - if (!new) - return -ENOMEM; - - skb_push(new, sizeof(struct ipv6hdr)); - skb_copy_to_linear_data(new, hdr, sizeof(struct ipv6hdr)); - - new->protocol = htons(ETH_P_IPV6); - new->pkt_type = PACKET_HOST; - - stat = lowpan_give_skb_to_devices(new); - - kfree_skb(new); - - return stat; -} - static void lowpan_fragment_timer_expired(unsigned long entry_addr) { struct lowpan_fragment *entry = (struct lowpan_fragment *)entry_addr; @@ -814,16 +251,12 @@ frame_err: return NULL; } -static int -lowpan_process_data(struct sk_buff *skb) +static int process_data(struct sk_buff *skb) { - struct ipv6hdr hdr = {}; - u8 tmp, iphc0, iphc1, num_context = 0; + u8 iphc0, iphc1; const struct ieee802154_addr *_saddr, *_daddr; - int err; - lowpan_raw_dump_table(__func__, "raw skb data dump", skb->data, - skb->len); + raw_dump_table(__func__, "raw skb data dump", skb->data, skb->len); /* at least two bytes will be used for the encoding */ if (skb->len < 2) goto drop; @@ -925,162 +358,11 @@ lowpan_process_data(struct sk_buff *skb) _saddr = &mac_cb(skb)->sa; _daddr = &mac_cb(skb)->da; - pr_debug("iphc0 = %02x, iphc1 = %02x\n", iphc0, iphc1); - - /* another if the CID flag is set */ - if (iphc1 & LOWPAN_IPHC_CID) { - pr_debug("CID flag is set, increase header with one\n"); - if (lowpan_fetch_skb_u8(skb, &num_context)) - goto drop; - } - - hdr.version = 6; - - /* Traffic Class and Flow Label */ - switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) { - /* - * Traffic Class and FLow Label carried in-line - * ECN + DSCP + 4-bit Pad + Flow Label (4 bytes) - */ - case 0: /* 00b */ - if (lowpan_fetch_skb_u8(skb, &tmp)) - goto drop; - - memcpy(&hdr.flow_lbl, &skb->data[0], 3); - skb_pull(skb, 3); - hdr.priority = ((tmp >> 2) & 0x0f); - hdr.flow_lbl[0] = ((tmp >> 2) & 0x30) | (tmp << 6) | - (hdr.flow_lbl[0] & 0x0f); - break; - /* - * Traffic class carried in-line - * ECN + DSCP (1 byte), Flow Label is elided - */ - case 2: /* 10b */ - if (lowpan_fetch_skb_u8(skb, &tmp)) - goto drop; - - hdr.priority = ((tmp >> 2) & 0x0f); - hdr.flow_lbl[0] = ((tmp << 6) & 0xC0) | ((tmp >> 2) & 0x30); - break; - /* - * Flow Label carried in-line - * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided - */ - case 1: /* 01b */ - if (lowpan_fetch_skb_u8(skb, &tmp)) - goto drop; - - hdr.flow_lbl[0] = (skb->data[0] & 0x0F) | ((tmp >> 2) & 0x30); - memcpy(&hdr.flow_lbl[1], &skb->data[0], 2); - skb_pull(skb, 2); - break; - /* Traffic Class and Flow Label are elided */ - case 3: /* 11b */ - break; - default: - break; - } - - /* Next Header */ - if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) { - /* Next header is carried inline */ - if (lowpan_fetch_skb_u8(skb, &(hdr.nexthdr))) - goto drop; - - pr_debug("NH flag is set, next header carried inline: %02x\n", - hdr.nexthdr); - } - - /* Hop Limit */ - if ((iphc0 & 0x03) != LOWPAN_IPHC_TTL_I) - hdr.hop_limit = lowpan_ttl_values[iphc0 & 0x03]; - else { - if (lowpan_fetch_skb_u8(skb, &(hdr.hop_limit))) - goto drop; - } - - /* Extract SAM to the tmp variable */ - tmp = ((iphc1 & LOWPAN_IPHC_SAM) >> LOWPAN_IPHC_SAM_BIT) & 0x03; - - if (iphc1 & LOWPAN_IPHC_SAC) { - /* Source address context based uncompression */ - pr_debug("SAC bit is set. Handle context based source address.\n"); - err = lowpan_uncompress_context_based_src_addr( - skb, &hdr.saddr, tmp); - } else { - /* Source address uncompression */ - pr_debug("source address stateless compression\n"); - err = lowpan_uncompress_addr(skb, &hdr.saddr, tmp, _saddr); - } - - /* Check on error of previous branch */ - if (err) - goto drop; - - /* Extract DAM to the tmp variable */ - tmp = ((iphc1 & LOWPAN_IPHC_DAM_11) >> LOWPAN_IPHC_DAM_BIT) & 0x03; - - /* check for Multicast Compression */ - if (iphc1 & LOWPAN_IPHC_M) { - if (iphc1 & LOWPAN_IPHC_DAC) { - pr_debug("dest: context-based mcast compression\n"); - /* TODO: implement this */ - } else { - err = lowpan_uncompress_multicast_daddr( - skb, &hdr.daddr, tmp); - if (err) - goto drop; - } - } else { - pr_debug("dest: stateless compression\n"); - err = lowpan_uncompress_addr(skb, &hdr.daddr, tmp, _daddr); - if (err) - goto drop; - } - - /* UDP data uncompression */ - if (iphc0 & LOWPAN_IPHC_NH_C) { - struct udphdr uh; - struct sk_buff *new; - if (lowpan_uncompress_udp_header(skb, &uh)) - goto drop; - - /* - * replace the compressed UDP head by the uncompressed UDP - * header - */ - new = skb_copy_expand(skb, sizeof(struct udphdr), - skb_tailroom(skb), GFP_ATOMIC); - kfree_skb(skb); - - if (!new) - return -ENOMEM; - - skb = new; - - skb_push(skb, sizeof(struct udphdr)); - skb_copy_to_linear_data(skb, &uh, sizeof(struct udphdr)); - - lowpan_raw_dump_table(__func__, "raw UDP header dump", - (u8 *)&uh, sizeof(uh)); - - hdr.nexthdr = UIP_PROTO_UDP; - } - - /* Not fragmented package */ - hdr.payload_len = htons(skb->len); - - pr_debug("skb headroom size = %d, data length = %d\n", - skb_headroom(skb), skb->len); - - pr_debug("IPv6 header dump:\n\tversion = %d\n\tlength = %d\n\t" - "nexthdr = 0x%02x\n\thop_lim = %d\n", hdr.version, - ntohs(hdr.payload_len), hdr.nexthdr, hdr.hop_limit); - - lowpan_raw_dump_table(__func__, "raw header dump", (u8 *)&hdr, - sizeof(hdr)); - return lowpan_skb_deliver(skb, &hdr); + return lowpan_process_data(skb, skb->dev, (u8 *)_saddr->hwaddr, + _saddr->addr_type, IEEE802154_ADDR_LEN, + (u8 *)_daddr->hwaddr, _daddr->addr_type, + IEEE802154_ADDR_LEN, iphc0, iphc1, + lowpan_give_skb_to_devices); unlock_and_drop: spin_unlock_bh(&flist_lock); @@ -1112,7 +394,7 @@ lowpan_fragment_xmit(struct sk_buff *skb, u8 *head, hlen = (type == LOWPAN_DISPATCH_FRAG1) ? LOWPAN_FRAG1_HEAD_SIZE : LOWPAN_FRAGN_HEAD_SIZE; - lowpan_raw_dump_inline(__func__, "6lowpan fragment header", head, hlen); + raw_dump_inline(__func__, "6lowpan fragment header", head, hlen); frag = netdev_alloc_skb(skb->dev, hlen + mlen + plen + IEEE802154_MFR_SIZE); @@ -1132,8 +414,7 @@ lowpan_fragment_xmit(struct sk_buff *skb, u8 *head, skb_copy_to_linear_data_offset(frag, mlen + hlen, skb_network_header(skb) + offset, plen); - lowpan_raw_dump_table(__func__, " raw fragment dump", frag->data, - frag->len); + raw_dump_table(__func__, " raw fragment dump", frag->data, frag->len); return dev_queue_xmit(frag); } @@ -1249,7 +530,27 @@ 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, }; @@ -1316,7 +617,7 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, /* Pull off the 1-byte of 6lowpan header. */ skb_pull(local_skb, 1); - lowpan_give_skb_to_devices(local_skb); + lowpan_give_skb_to_devices(local_skb, NULL); kfree_skb(local_skb); kfree_skb(skb); @@ -1328,7 +629,7 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, local_skb = skb_clone(skb, GFP_ATOMIC); if (!local_skb) goto drop; - lowpan_process_data(local_skb); + process_data(local_skb); kfree_skb(skb); break; diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h index 2869c0526dad..2b835db3bda8 100644 --- a/net/ieee802154/6lowpan.h +++ b/net/ieee802154/6lowpan.h @@ -231,6 +231,61 @@ #define LOWPAN_NHC_UDP_CS_P_10 0xF2 /* source = 0xF0 + 8bit inline, dest = 16 bit inline */ #define LOWPAN_NHC_UDP_CS_P_11 0xF3 /* source & dest = 0xF0B + 4bit inline */ +#define LOWPAN_NHC_UDP_CS_C 0x04 /* checksum elided */ + +#ifdef DEBUG +/* print data in line */ +static inline void raw_dump_inline(const char *caller, char *msg, + unsigned char *buf, int len) +{ + if (msg) + pr_debug("%s():%s: ", caller, msg); + + print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, buf, len, false); +} + +/* print data in a table format: + * + * addr: xx xx xx xx xx xx + * addr: xx xx xx xx xx xx + * ... + */ +static inline void raw_dump_table(const char *caller, char *msg, + unsigned char *buf, int len) +{ + if (msg) + pr_debug("%s():%s:\n", caller, msg); + + print_hex_dump_debug("\t", DUMP_PREFIX_OFFSET, 16, 1, buf, len, false); +} +#else +static inline void raw_dump_table(const char *caller, char *msg, + unsigned char *buf, int len) { } +static inline void raw_dump_inline(const char *caller, char *msg, + unsigned char *buf, int len) { } +#endif + +static inline int lowpan_fetch_skb_u8(struct sk_buff *skb, u8 *val) +{ + if (unlikely(!pskb_may_pull(skb, 1))) + return -EINVAL; + + *val = skb->data[0]; + skb_pull(skb, 1); + + return 0; +} + +static inline int lowpan_fetch_skb_u16(struct sk_buff *skb, u16 *val) +{ + if (unlikely(!pskb_may_pull(skb, 2))) + return -EINVAL; + + *val = (skb->data[0] << 8) | skb->data[1]; + skb_pull(skb, 2); + + return 0; +} static inline bool lowpan_fetch_skb(struct sk_buff *skb, void *data, const unsigned int len) @@ -244,4 +299,21 @@ static inline bool lowpan_fetch_skb(struct sk_buff *skb, return false; } +static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, + const size_t len) +{ + memcpy(*hc_ptr, data, len); + *hc_ptr += len; +} + +typedef int (*skb_delivery_cb)(struct sk_buff *skb, struct net_device *dev); + +int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, + const u8 *saddr, const u8 saddr_type, const u8 saddr_len, + const u8 *daddr, const u8 daddr_type, const u8 daddr_len, + u8 iphc0, u8 iphc1, skb_delivery_cb skb_deliver); +int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, + unsigned short type, const void *_daddr, + const void *_saddr, unsigned int len); + #endif /* __6LOWPAN_H__ */ diff --git a/net/ieee802154/6lowpan_iphc.c b/net/ieee802154/6lowpan_iphc.c new file mode 100644 index 000000000000..860aa2d445ba --- /dev/null +++ b/net/ieee802154/6lowpan_iphc.c @@ -0,0 +1,802 @@ +/* + * Copyright 2011, Siemens AG + * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> + */ + +/* + * Based on patches from Jon Smirl <jonsmirl@gmail.com> + * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + */ + +/* Jon's code is based on 6lowpan implementation for Contiki which is: + * Copyright (c) 2008, Swedish Institute of Computer Science. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the Institute nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#include <linux/bitops.h> +#include <linux/if_arp.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <net/ipv6.h> +#include <net/af_ieee802154.h> + +#include "6lowpan.h" + +/* + * Uncompress address function for source and + * destination address(non-multicast). + * + * address_mode is sam value or dam value. + */ +static int uncompress_addr(struct sk_buff *skb, + struct in6_addr *ipaddr, const u8 address_mode, + const u8 *lladdr, const u8 addr_type, + const u8 addr_len) +{ + bool fail; + + switch (address_mode) { + case LOWPAN_IPHC_ADDR_00: + /* for global link addresses */ + fail = lowpan_fetch_skb(skb, ipaddr->s6_addr, 16); + break; + case LOWPAN_IPHC_ADDR_01: + /* fe:80::XXXX:XXXX:XXXX:XXXX */ + ipaddr->s6_addr[0] = 0xFE; + ipaddr->s6_addr[1] = 0x80; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[8], 8); + break; + case LOWPAN_IPHC_ADDR_02: + /* fe:80::ff:fe00:XXXX */ + ipaddr->s6_addr[0] = 0xFE; + ipaddr->s6_addr[1] = 0x80; + ipaddr->s6_addr[11] = 0xFF; + ipaddr->s6_addr[12] = 0xFE; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[14], 2); + break; + case LOWPAN_IPHC_ADDR_03: + fail = false; + switch (addr_type) { + case IEEE802154_ADDR_LONG: + /* fe:80::XXXX:XXXX:XXXX:XXXX + * \_________________/ + * hwaddr + */ + ipaddr->s6_addr[0] = 0xFE; + ipaddr->s6_addr[1] = 0x80; + memcpy(&ipaddr->s6_addr[8], lladdr, addr_len); + /* second bit-flip (Universe/Local) + * is done according RFC2464 + */ + ipaddr->s6_addr[8] ^= 0x02; + break; + case IEEE802154_ADDR_SHORT: + /* fe:80::ff:fe00:XXXX + * \__/ + * short_addr + * + * Universe/Local bit is zero. + */ + ipaddr->s6_addr[0] = 0xFE; + ipaddr->s6_addr[1] = 0x80; + ipaddr->s6_addr[11] = 0xFF; + ipaddr->s6_addr[12] = 0xFE; + ipaddr->s6_addr16[7] = htons(*((u16 *)lladdr)); + break; + default: + pr_debug("Invalid addr_type set\n"); + return -EINVAL; + } + break; + default: + pr_debug("Invalid address mode value: 0x%x\n", address_mode); + return -EINVAL; + } + + if (fail) { + pr_debug("Failed to fetch skb data\n"); + return -EIO; + } + + raw_dump_inline(NULL, "Reconstructed ipv6 addr is", + ipaddr->s6_addr, 16); + + return 0; +} + +/* + * Uncompress address function for source context + * based address(non-multicast). + */ +static int uncompress_context_based_src_addr(struct sk_buff *skb, + struct in6_addr *ipaddr, + const u8 sam) +{ + switch (sam) { + case LOWPAN_IPHC_ADDR_00: + /* unspec address :: + * Do nothing, address is already :: + */ + break; + case LOWPAN_IPHC_ADDR_01: + /* TODO */ + case LOWPAN_IPHC_ADDR_02: + /* TODO */ + case LOWPAN_IPHC_ADDR_03: + /* TODO */ + netdev_warn(skb->dev, "SAM value 0x%x not supported\n", sam); + return -EINVAL; + default: + pr_debug("Invalid sam value: 0x%x\n", sam); + return -EINVAL; + } + + raw_dump_inline(NULL, + "Reconstructed context based ipv6 src addr is", + ipaddr->s6_addr, 16); + + return 0; +} + +static int skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr, + struct net_device *dev, skb_delivery_cb deliver_skb) +{ + struct sk_buff *new; + int stat; + + new = skb_copy_expand(skb, sizeof(struct ipv6hdr), skb_tailroom(skb), + GFP_ATOMIC); + kfree_skb(skb); + + if (!new) + return -ENOMEM; + + skb_push(new, sizeof(struct ipv6hdr)); + skb_reset_network_header(new); + skb_copy_to_linear_data(new, hdr, sizeof(struct ipv6hdr)); + + new->protocol = htons(ETH_P_IPV6); + new->pkt_type = PACKET_HOST; + new->dev = dev; + + raw_dump_table(__func__, "raw skb data dump before receiving", + new->data, new->len); + + stat = deliver_skb(new, dev); + + kfree_skb(new); + + return stat; +} + +/* Uncompress function for multicast destination address, + * when M bit is set. + */ +static int +lowpan_uncompress_multicast_daddr(struct sk_buff *skb, + struct in6_addr *ipaddr, + const u8 dam) +{ + bool fail; + + switch (dam) { + case LOWPAN_IPHC_DAM_00: + /* 00: 128 bits. The full address + * is carried in-line. + */ + fail = lowpan_fetch_skb(skb, ipaddr->s6_addr, 16); + break; + case LOWPAN_IPHC_DAM_01: + /* 01: 48 bits. The address takes + * the form ffXX::00XX:XXXX:XXXX. + */ + ipaddr->s6_addr[0] = 0xFF; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[1], 1); + fail |= lowpan_fetch_skb(skb, &ipaddr->s6_addr[11], 5); + break; + case LOWPAN_IPHC_DAM_10: + /* 10: 32 bits. The address takes + * the form ffXX::00XX:XXXX. + */ + ipaddr->s6_addr[0] = 0xFF; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[1], 1); + fail |= lowpan_fetch_skb(skb, &ipaddr->s6_addr[13], 3); + break; + case LOWPAN_IPHC_DAM_11: + /* 11: 8 bits. The address takes + * the form ff02::00XX. + */ + ipaddr->s6_addr[0] = 0xFF; + ipaddr->s6_addr[1] = 0x02; + fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[15], 1); + break; + default: + pr_debug("DAM value has a wrong value: 0x%x\n", dam); + return -EINVAL; + } + + if (fail) { + pr_debug("Failed to fetch skb data\n"); + return -EIO; + } + + raw_dump_inline(NULL, "Reconstructed ipv6 multicast addr is", + ipaddr->s6_addr, 16); + + return 0; +} + +static int +uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh) +{ + bool fail; + u8 tmp = 0, val = 0; + + if (!uh) + goto err; + + fail = lowpan_fetch_skb(skb, &tmp, 1); + + if ((tmp & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) { + pr_debug("UDP header uncompression\n"); + switch (tmp & LOWPAN_NHC_UDP_CS_P_11) { + case LOWPAN_NHC_UDP_CS_P_00: + fail |= lowpan_fetch_skb(skb, &uh->source, 2); + fail |= lowpan_fetch_skb(skb, &uh->dest, 2); + break; + case LOWPAN_NHC_UDP_CS_P_01: + fail |= lowpan_fetch_skb(skb, &uh->source, 2); + fail |= lowpan_fetch_skb(skb, &val, 1); + uh->dest = htons(val + LOWPAN_NHC_UDP_8BIT_PORT); + break; + case LOWPAN_NHC_UDP_CS_P_10: + fail |= lowpan_fetch_skb(skb, &val, 1); + uh->source = htons(val + LOWPAN_NHC_UDP_8BIT_PORT); + fail |= lowpan_fetch_skb(skb, &uh->dest, 2); + break; + case LOWPAN_NHC_UDP_CS_P_11: + fail |= lowpan_fetch_skb(skb, &val, 1); + uh->source = htons(LOWPAN_NHC_UDP_4BIT_PORT + + (val >> 4)); + uh->dest = htons(LOWPAN_NHC_UDP_4BIT_PORT + + (val & 0x0f)); + break; + default: + pr_debug("ERROR: unknown UDP format\n"); + goto err; + break; + } + + pr_debug("uncompressed UDP ports: src = %d, dst = %d\n", + ntohs(uh->source), ntohs(uh->dest)); + + /* checksum */ + if (tmp & LOWPAN_NHC_UDP_CS_C) { + pr_debug_ratelimited("checksum elided currently not supported\n"); + goto err; + } else { + fail |= lowpan_fetch_skb(skb, &uh->check, 2); + } + + /* + * UDP lenght needs to be infered from the lower layers + * here, we obtain the hint from the remaining size of the + * frame + */ + uh->len = htons(skb->len + sizeof(struct udphdr)); + pr_debug("uncompressed UDP length: src = %d", ntohs(uh->len)); + } else { + pr_debug("ERROR: unsupported NH format\n"); + goto err; + } + + if (fail) + goto err; + + return 0; +err: + return -EINVAL; +} + +/* TTL uncompression values */ +static const u8 lowpan_ttl_values[] = { 0, 1, 64, 255 }; + +int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, + const u8 *saddr, const u8 saddr_type, const u8 saddr_len, + const u8 *daddr, const u8 daddr_type, const u8 daddr_len, + u8 iphc0, u8 iphc1, skb_delivery_cb deliver_skb) +{ + struct ipv6hdr hdr = {}; + u8 tmp, num_context = 0; + int err; + + raw_dump_table(__func__, "raw skb data dump uncompressed", + skb->data, skb->len); + + /* another if the CID flag is set */ + if (iphc1 & LOWPAN_IPHC_CID) { + pr_debug("CID flag is set, increase header with one\n"); + if (lowpan_fetch_skb_u8(skb, &num_context)) + goto drop; + } + + hdr.version = 6; + + /* Traffic Class and Flow Label */ + switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) { + /* + * Traffic Class and FLow Label carried in-line + * ECN + DSCP + 4-bit Pad + Flow Label (4 bytes) + */ + case 0: /* 00b */ + if (lowpan_fetch_skb_u8(skb, &tmp)) + goto drop; + + memcpy(&hdr.flow_lbl, &skb->data[0], 3); + skb_pull(skb, 3); + hdr.priority = ((tmp >> 2) & 0x0f); + hdr.flow_lbl[0] = ((tmp >> 2) & 0x30) | (tmp << 6) | + (hdr.flow_lbl[0] & 0x0f); + break; + /* + * Traffic class carried in-line + * ECN + DSCP (1 byte), Flow Label is elided + */ + case 2: /* 10b */ + if (lowpan_fetch_skb_u8(skb, &tmp)) + goto drop; + + hdr.priority = ((tmp >> 2) & 0x0f); + hdr.flow_lbl[0] = ((tmp << 6) & 0xC0) | ((tmp >> 2) & 0x30); + break; + /* + * Flow Label carried in-line + * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided + */ + case 1: /* 01b */ + if (lowpan_fetch_skb_u8(skb, &tmp)) + goto drop; + + hdr.flow_lbl[0] = (skb->data[0] & 0x0F) | ((tmp >> 2) & 0x30); + memcpy(&hdr.flow_lbl[1], &skb->data[0], 2); + skb_pull(skb, 2); + break; + /* Traffic Class and Flow Label are elided */ + case 3: /* 11b */ + break; + default: + break; + } + + /* Next Header */ + if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) { + /* Next header is carried inline */ + if (lowpan_fetch_skb_u8(skb, &(hdr.nexthdr))) + goto drop; + + pr_debug("NH flag is set, next header carried inline: %02x\n", + hdr.nexthdr); + } + + /* Hop Limit */ + if ((iphc0 & 0x03) != LOWPAN_IPHC_TTL_I) + hdr.hop_limit = lowpan_ttl_values[iphc0 & 0x03]; + else { + if (lowpan_fetch_skb_u8(skb, &(hdr.hop_limit))) + goto drop; + } + + /* Extract SAM to the tmp variable */ + tmp = ((iphc1 & LOWPAN_IPHC_SAM) >> LOWPAN_IPHC_SAM_BIT) & 0x03; + + if (iphc1 & LOWPAN_IPHC_SAC) { + /* Source address context based uncompression */ + pr_debug("SAC bit is set. Handle context based source address.\n"); + err = uncompress_context_based_src_addr( + skb, &hdr.saddr, tmp); + } else { + /* Source address uncompression */ + pr_debug("source address stateless compression\n"); + err = uncompress_addr(skb, &hdr.saddr, tmp, saddr, + saddr_type, saddr_len); + } + + /* Check on error of previous branch */ + if (err) + goto drop; + + /* Extract DAM to the tmp variable */ + tmp = ((iphc1 & LOWPAN_IPHC_DAM_11) >> LOWPAN_IPHC_DAM_BIT) & 0x03; + + /* check for Multicast Compression */ + if (iphc1 & LOWPAN_IPHC_M) { + if (iphc1 & LOWPAN_IPHC_DAC) { + pr_debug("dest: context-based mcast compression\n"); + /* TODO: implement this */ + } else { + err = lowpan_uncompress_multicast_daddr( + skb, &hdr.daddr, tmp); + if (err) + goto drop; + } + } else { + err = uncompress_addr(skb, &hdr.daddr, tmp, daddr, + daddr_type, daddr_len); + pr_debug("dest: stateless compression mode %d dest %pI6c\n", + tmp, &hdr.daddr); + if (err) + goto drop; + } + + /* UDP data uncompression */ + if (iphc0 & LOWPAN_IPHC_NH_C) { + struct udphdr uh; + struct sk_buff *new; + if (uncompress_udp_header(skb, &uh)) + goto drop; + + /* + * replace the compressed UDP head by the uncompressed UDP + * header + */ + new = skb_copy_expand(skb, sizeof(struct udphdr), + skb_tailroom(skb), GFP_ATOMIC); + kfree_skb(skb); + + if (!new) + return -ENOMEM; + + skb = new; + + skb_push(skb, sizeof(struct udphdr)); + skb_reset_transport_header(skb); + skb_copy_to_linear_data(skb, &uh, sizeof(struct udphdr)); + + raw_dump_table(__func__, "raw UDP header dump", + (u8 *)&uh, sizeof(uh)); + + hdr.nexthdr = UIP_PROTO_UDP; + } + + hdr.payload_len = htons(skb->len); + + pr_debug("skb headroom size = %d, data length = %d\n", + skb_headroom(skb), skb->len); + + pr_debug("IPv6 header dump:\n\tversion = %d\n\tlength = %d\n\t" + "nexthdr = 0x%02x\n\thop_lim = %d\n\tdest = %pI6c\n", + hdr.version, ntohs(hdr.payload_len), hdr.nexthdr, + hdr.hop_limit, &hdr.daddr); + + raw_dump_table(__func__, "raw header dump", (u8 *)&hdr, + sizeof(hdr)); + + return skb_deliver(skb, &hdr, dev, deliver_skb); + +drop: + kfree_skb(skb); + return -EINVAL; +} +EXPORT_SYMBOL_GPL(lowpan_process_data); + +static u8 lowpan_compress_addr_64(u8 **hc06_ptr, u8 shift, + const struct in6_addr *ipaddr, + const unsigned char *lladdr) +{ + u8 val = 0; + + if (is_addr_mac_addr_based(ipaddr, lladdr)) { + val = 3; /* 0-bits */ + pr_debug("address compression 0 bits\n"); + } else if (lowpan_is_iid_16_bit_compressable(ipaddr)) { + /* compress IID to 16 bits xxxx::XXXX */ + memcpy(*hc06_ptr, &ipaddr->s6_addr16[7], 2); + *hc06_ptr += 2; + val = 2; /* 16-bits */ + raw_dump_inline(NULL, "Compressed ipv6 addr is (16 bits)", + *hc06_ptr - 2, 2); + } else { + /* do not compress IID => xxxx::IID */ + memcpy(*hc06_ptr, &ipaddr->s6_addr16[4], 8); + *hc06_ptr += 8; + val = 1; /* 64-bits */ + raw_dump_inline(NULL, "Compressed ipv6 addr is (64 bits)", + *hc06_ptr - 8, 8); + } + + return rol8(val, shift); +} + +static void compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb) +{ + struct udphdr *uh = udp_hdr(skb); + u8 tmp; + + if (((ntohs(uh->source) & LOWPAN_NHC_UDP_4BIT_MASK) == + LOWPAN_NHC_UDP_4BIT_PORT) && + ((ntohs(uh->dest) & LOWPAN_NHC_UDP_4BIT_MASK) == + LOWPAN_NHC_UDP_4BIT_PORT)) { + pr_debug("UDP header: both ports compression to 4 bits\n"); + /* compression value */ + tmp = LOWPAN_NHC_UDP_CS_P_11; + lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + /* source and destination port */ + tmp = ntohs(uh->dest) - LOWPAN_NHC_UDP_4BIT_PORT + + ((ntohs(uh->source) - LOWPAN_NHC_UDP_4BIT_PORT) << 4); + lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + } else if ((ntohs(uh->dest) & LOWPAN_NHC_UDP_8BIT_MASK) == + LOWPAN_NHC_UDP_8BIT_PORT) { + pr_debug("UDP header: remove 8 bits of dest\n"); + /* compression value */ + tmp = LOWPAN_NHC_UDP_CS_P_01; + lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + /* source port */ + lowpan_push_hc_data(hc06_ptr, &uh->source, sizeof(uh->source)); + /* destination port */ + tmp = ntohs(uh->dest) - LOWPAN_NHC_UDP_8BIT_PORT; + lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + } else if ((ntohs(uh->source) & LOWPAN_NHC_UDP_8BIT_MASK) == + LOWPAN_NHC_UDP_8BIT_PORT) { + pr_debug("UDP header: remove 8 bits of source\n"); + /* compression value */ + tmp = LOWPAN_NHC_UDP_CS_P_10; + lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + /* source port */ + tmp = ntohs(uh->source) - LOWPAN_NHC_UDP_8BIT_PORT; + lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + /* destination port */ + lowpan_push_hc_data(hc06_ptr, &uh->dest, sizeof(uh->dest)); + } else { + pr_debug("UDP header: can't compress\n"); + /* compression value */ + tmp = LOWPAN_NHC_UDP_CS_P_00; + lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp)); + /* source port */ + lowpan_push_hc_data(hc06_ptr, &uh->source, sizeof(uh->source)); + /* destination port */ + lowpan_push_hc_data(hc06_ptr, &uh->dest, sizeof(uh->dest)); + } + + /* checksum is always inline */ + lowpan_push_hc_data(hc06_ptr, &uh->check, sizeof(uh->check)); + + /* skip the UDP header */ + skb_pull(skb, sizeof(struct udphdr)); +} + +int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, + unsigned short type, const void *_daddr, + const void *_saddr, unsigned int len) +{ + u8 tmp, iphc0, iphc1, *hc06_ptr; + struct ipv6hdr *hdr; + u8 head[100] = {}; + + if (type != ETH_P_IPV6) + return -EINVAL; + + hdr = ipv6_hdr(skb); + hc06_ptr = head + 2; + + pr_debug("IPv6 header dump:\n\tversion = %d\n\tlength = %d\n" + "\tnexthdr = 0x%02x\n\thop_lim = %d\n\tdest = %pI6c\n", + hdr->version, ntohs(hdr->payload_len), hdr->nexthdr, + hdr->hop_limit, &hdr->daddr); + + raw_dump_table(__func__, "raw skb network header dump", + skb_network_header(skb), sizeof(struct ipv6hdr)); + + /* + * As we copy some bit-length fields, in the IPHC encoding bytes, + * we sometimes use |= + * If the field is 0, and the current bit value in memory is 1, + * this does not work. We therefore reset the IPHC encoding here + */ + iphc0 = LOWPAN_DISPATCH_IPHC; + iphc1 = 0; + + /* TODO: context lookup */ + + raw_dump_inline(__func__, "saddr", + (unsigned char *)_saddr, IEEE802154_ADDR_LEN); + raw_dump_inline(__func__, "daddr", + (unsigned char *)_daddr, IEEE802154_ADDR_LEN); + + raw_dump_table(__func__, + "sending raw skb network uncompressed packet", + skb->data, skb->len); + + /* + * Traffic class, flow label + * If flow label is 0, compress it. If traffic class is 0, compress it + * We have to process both in the same time as the offset of traffic + * class depends on the presence of version and flow label + */ + + /* hc06 format of TC is ECN | DSCP , original one is DSCP | ECN */ + tmp = (hdr->priority << 4) | (hdr->flow_lbl[0] >> 4); + tmp = ((tmp & 0x03) << 6) | (tmp >> 2); + + if (((hdr->flow_lbl[0] & 0x0F) == 0) && + (hdr->flow_lbl[1] == 0) && (hdr->flow_lbl[2] == 0)) { + /* flow label can be compressed */ + iphc0 |= LOWPAN_IPHC_FL_C; + if ((hdr->priority == 0) && + ((hdr->flow_lbl[0] & 0xF0) == 0)) { + /* compress (elide) all */ + iphc0 |= LOWPAN_IPHC_TC_C; + } else { + /* compress only the flow label */ + *hc06_ptr = tmp; + hc06_ptr += 1; + } + } else { + /* Flow label cannot be compressed */ + if ((hdr->priority == 0) && + ((hdr->flow_lbl[0] & 0xF0) == 0)) { + /* compress only traffic class */ + iphc0 |= LOWPAN_IPHC_TC_C; + *hc06_ptr = (tmp & 0xc0) | (hdr->flow_lbl[0] & 0x0F); + memcpy(hc06_ptr + 1, &hdr->flow_lbl[1], 2); + hc06_ptr += 3; + } else { + /* compress nothing */ + memcpy(hc06_ptr, hdr, 4); + /* replace the top byte with new ECN | DSCP format */ + *hc06_ptr = tmp; + hc06_ptr += 4; + } + } + + /* NOTE: payload length is always compressed */ + + /* Next Header is compress if UDP */ + if (hdr->nexthdr == UIP_PROTO_UDP) + iphc0 |= LOWPAN_IPHC_NH_C; + + if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) { + *hc06_ptr = hdr->nexthdr; + hc06_ptr += 1; + } + + /* + * Hop limit + * if 1: compress, encoding is 01 + * if 64: compress, encoding is 10 + * if 255: compress, encoding is 11 + * else do not compress + */ + switch (hdr->hop_limit) { + case 1: + iphc0 |= LOWPAN_IPHC_TTL_1; + break; + case 64: + iphc0 |= LOWPAN_IPHC_TTL_64; + break; + case 255: + iphc0 |= LOWPAN_IPHC_TTL_255; + break; + default: + *hc06_ptr = hdr->hop_limit; + hc06_ptr += 1; + break; + } + + /* source address compression */ + if (is_addr_unspecified(&hdr->saddr)) { + pr_debug("source address is unspecified, setting SAC\n"); + iphc1 |= LOWPAN_IPHC_SAC; + /* TODO: context lookup */ + } else if (is_addr_link_local(&hdr->saddr)) { + iphc1 |= lowpan_compress_addr_64(&hc06_ptr, + LOWPAN_IPHC_SAM_BIT, &hdr->saddr, _saddr); + pr_debug("source address unicast link-local %pI6c " + "iphc1 0x%02x\n", &hdr->saddr, iphc1); + } else { + pr_debug("send the full source address\n"); + memcpy(hc06_ptr, &hdr->saddr.s6_addr16[0], 16); + hc06_ptr += 16; + } + + /* destination address compression */ + if (is_addr_mcast(&hdr->daddr)) { + pr_debug("destination address is multicast: "); + iphc1 |= LOWPAN_IPHC_M; + if (lowpan_is_mcast_addr_compressable8(&hdr->daddr)) { + pr_debug("compressed to 1 octet\n"); + iphc1 |= LOWPAN_IPHC_DAM_11; + /* use last byte */ + *hc06_ptr = hdr->daddr.s6_addr[15]; + hc06_ptr += 1; + } else if (lowpan_is_mcast_addr_compressable32(&hdr->daddr)) { + pr_debug("compressed to 4 octets\n"); + iphc1 |= LOWPAN_IPHC_DAM_10; + /* second byte + the last three */ + *hc06_ptr = hdr->daddr.s6_addr[1]; + memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[13], 3); + hc06_ptr += 4; + } else if (lowpan_is_mcast_addr_compressable48(&hdr->daddr)) { + pr_debug("compressed to 6 octets\n"); + iphc1 |= LOWPAN_IPHC_DAM_01; + /* second byte + the last five */ + *hc06_ptr = hdr->daddr.s6_addr[1]; + memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[11], 5); + hc06_ptr += 6; + } else { + pr_debug("using full address\n"); + iphc1 |= LOWPAN_IPHC_DAM_00; + memcpy(hc06_ptr, &hdr->daddr.s6_addr[0], 16); + hc06_ptr += 16; + } + } else { + /* TODO: context lookup */ + if (is_addr_link_local(&hdr->daddr)) { + iphc1 |= lowpan_compress_addr_64(&hc06_ptr, + LOWPAN_IPHC_DAM_BIT, &hdr->daddr, _daddr); + pr_debug("dest address unicast link-local %pI6c " + "iphc1 0x%02x\n", &hdr->daddr, iphc1); + } else { + pr_debug("dest address unicast %pI6c\n", &hdr->daddr); + memcpy(hc06_ptr, &hdr->daddr.s6_addr16[0], 16); + hc06_ptr += 16; + } + } + + /* UDP header compression */ + if (hdr->nexthdr == UIP_PROTO_UDP) + compress_udp_header(&hc06_ptr, skb); + + head[0] = iphc0; + head[1] = iphc1; + + skb_pull(skb, sizeof(struct ipv6hdr)); + skb_reset_transport_header(skb); + memcpy(skb_push(skb, hc06_ptr - head), head, hc06_ptr - head); + skb_reset_network_header(skb); + + pr_debug("header len %d skb %u\n", (int)(hc06_ptr - head), skb->len); + + raw_dump_table(__func__, "raw skb data dump compressed", + skb->data, skb->len); + return 0; +} +EXPORT_SYMBOL_GPL(lowpan_header_compress); + +MODULE_LICENSE("GPL"); diff --git a/net/ieee802154/Kconfig b/net/ieee802154/Kconfig index b2e06df0076c..9c9879d5ea64 100644 --- a/net/ieee802154/Kconfig +++ b/net/ieee802154/Kconfig @@ -13,5 +13,12 @@ config IEEE802154 config IEEE802154_6LOWPAN tristate "6lowpan support over IEEE 802.15.4" depends on IEEE802154 && IPV6 + select 6LOWPAN_IPHC ---help--- IPv6 compression over IEEE 802.15.4. + +config 6LOWPAN_IPHC + tristate + ---help--- + 6lowpan compression code which is shared between IEEE 802.15.4 and Bluetooth + stacks. diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index d7716d64c6bb..e8f05885ced6 100644 --- a/net/ieee802154/Makefile +++ b/net/ieee802154/Makefile @@ -1,5 +1,6 @@ obj-$(CONFIG_IEEE802154) += ieee802154.o af_802154.o obj-$(CONFIG_IEEE802154_6LOWPAN) += 6lowpan.o +obj-$(CONFIG_6LOWPAN_IPHC) += 6lowpan_iphc.o ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o af_802154-y := af_ieee802154.o raw.o dgram.o diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 1865fdf5a5a5..1846c1fe0d06 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -291,9 +291,7 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk, size_t copied = 0; int err = -EOPNOTSUPP; struct sk_buff *skb; - struct sockaddr_ieee802154 *saddr; - - saddr = (struct sockaddr_ieee802154 *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_ieee802154 *, saddr, msg->msg_name); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c index ef56ab5b35fe..4dd37615a749 100644 --- a/net/ieee802154/wpan-class.c +++ b/net/ieee802154/wpan-class.c @@ -46,7 +46,7 @@ MASTER_SHOW(current_channel, "%d"); MASTER_SHOW(current_page, "%d"); MASTER_SHOW_COMPLEX(transmit_power, "%d +- %d dB", ((signed char) (phy->transmit_power << 2)) >> 2, - (phy->transmit_power >> 6) ? (phy->transmit_power >> 6) * 3 : 1 ); + (phy->transmit_power >> 6) ? (phy->transmit_power >> 6) * 3 : 1); MASTER_SHOW(cca_mode, "%d"); static ssize_t channels_supported_show(struct device *dev, diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 4b81e91c80fe..f8c49ce5b283 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -11,7 +11,7 @@ obj-y := route.o inetpeer.o protocol.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o \ - inet_fragment.o ping.o ip_tunnel_core.o + inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o @@ -19,7 +19,7 @@ obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o obj-$(CONFIG_IP_MROUTE) += ipmr.o obj-$(CONFIG_NET_IPIP) += ipip.o -gre-y := gre_demux.o gre_offload.o +gre-y := gre_demux.o obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o obj-$(CONFIG_NET_IPGRE) += ip_gre.o obj-$(CONFIG_NET_IPVTI) += ip_vti.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 70011e029ac1..ecd2c3f245ce 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -126,9 +126,6 @@ static struct list_head inetsw[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw_lock); -struct ipv4_config ipv4_config; -EXPORT_SYMBOL(ipv4_config); - /* New destruction routine */ void inet_sock_destruct(struct sock *sk) @@ -342,7 +339,7 @@ lookup_protocol: inet->hdrincl = 1; } - if (ipv4_config.no_pmtu_disc) + if (net->ipv4.sysctl_ip_no_pmtu_disc) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; @@ -1133,7 +1130,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, daddr, 0, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, sk->sk_protocol, - inet->inet_sport, inet->inet_dport, sk, false); + inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -1377,8 +1374,12 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, if (!NAPI_GRO_CB(p)->same_flow) continue; - iph2 = ip_hdr(p); - + iph2 = (struct iphdr *)(p->data + off); + /* The above works because, with the exception of the top + * (inner most) layer, we only aggregate pkts with the same + * hdr length so all the hdrs we'll need to verify will start + * at the same offset. + */ if ((iph->protocol ^ iph2->protocol) | ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) | ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) { @@ -1390,13 +1391,24 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, NAPI_GRO_CB(p)->flush |= (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | - (__force int)((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)) | - ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id); + ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)); + /* Save the IP ID check to be included later when we get to + * the transport layer so only the inner most IP ID is checked. + * This is because some GSO/TSO implementations do not + * correctly increment the IP ID for the outer hdrs. + */ + NAPI_GRO_CB(p)->flush_id = + ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id); NAPI_GRO_CB(p)->flush |= flush; } NAPI_GRO_CB(skb)->flush |= flush; + skb_set_network_header(skb, off); + /* The above will be needed by the transport layer if there is one + * immediately following this IP hdr. + */ + skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); @@ -1411,10 +1423,10 @@ out: return pp; } -static int inet_gro_complete(struct sk_buff *skb) +static int inet_gro_complete(struct sk_buff *skb, int nhoff) { - __be16 newlen = htons(skb->len - skb_network_offset(skb)); - struct iphdr *iph = ip_hdr(skb); + __be16 newlen = htons(skb->len - nhoff); + struct iphdr *iph = (struct iphdr *)(skb->data + nhoff); const struct net_offload *ops; int proto = iph->protocol; int err = -ENOSYS; @@ -1427,7 +1439,11 @@ static int inet_gro_complete(struct sk_buff *skb) if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out_unlock; - err = ops->callbacks.gro_complete(skb); + /* Only need to add sizeof(*iph) to get to the next hdr below + * because any hdr with option will have been flushed in + * inet_gro_receive(). + */ + err = ops->callbacks.gro_complete(skb, nhoff + sizeof(*iph)); out_unlock: rcu_read_unlock(); @@ -1529,6 +1545,7 @@ static const struct net_protocol tcp_protocol = { .err_handler = tcp_v4_err, .no_policy = 1, .netns_ok = 1, + .icmp_strict_tag_validation = 1, }; static const struct net_protocol udp_protocol = { diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 7808093cede6..1a9b99e04465 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -166,18 +166,20 @@ struct neigh_table arp_tbl = { .id = "arp_cache", .parms = { .tbl = &arp_tbl, - .base_reachable_time = 30 * HZ, - .retrans_time = 1 * HZ, - .gc_staletime = 60 * HZ, .reachable_time = 30 * HZ, - .delay_probe_time = 5 * HZ, - .queue_len_bytes = 64*1024, - .ucast_probes = 3, - .mcast_probes = 3, - .anycast_delay = 1 * HZ, - .proxy_delay = (8 * HZ) / 10, - .proxy_qlen = 64, - .locktime = 1 * HZ, + .data = { + [NEIGH_VAR_MCAST_PROBES] = 3, + [NEIGH_VAR_UCAST_PROBES] = 3, + [NEIGH_VAR_RETRANS_TIME] = 1 * HZ, + [NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ, + [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, + [NEIGH_VAR_GC_STALETIME] = 60 * HZ, + [NEIGH_VAR_QUEUE_LEN_BYTES] = 64 * 1024, + [NEIGH_VAR_PROXY_QLEN] = 64, + [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, + [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, + [NEIGH_VAR_LOCKTIME] = 1 * HZ, + }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, @@ -359,14 +361,14 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) if (!saddr) saddr = inet_select_addr(dev, target, RT_SCOPE_LINK); - probes -= neigh->parms->ucast_probes; + probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); if (probes < 0) { if (!(neigh->nud_state & NUD_VALID)) pr_debug("trying to ucast probe in NUD_INVALID\n"); neigh_ha_snapshot(dst_ha, neigh, dev); dst_hw = dst_ha; } else { - probes -= neigh->parms->app_probes; + probes -= NEIGH_VAR(neigh->parms, APP_PROBES); if (probes < 0) { neigh_app_ns(neigh); return; @@ -379,6 +381,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) { + struct net *net = dev_net(in_dev->dev); int scope; switch (IN_DEV_ARP_IGNORE(in_dev)) { @@ -397,6 +400,7 @@ static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) case 3: /* Do not reply for scope host addresses */ sip = 0; scope = RT_SCOPE_LINK; + in_dev = NULL; break; case 4: /* Reserved */ case 5: @@ -408,7 +412,7 @@ static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) default: return 0; } - return !inet_confirm_addr(in_dev, sip, tip, scope); + return !inet_confirm_addr(net, in_dev, sip, tip, scope); } static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) @@ -728,6 +732,7 @@ static int arp_process(struct sk_buff *skb) int addr_type; struct neighbour *n; struct net *net = dev_net(dev); + bool is_garp = false; /* arp_rcv below verifies the ARP header and verifies the device * is ARP'able. @@ -871,7 +876,7 @@ static int arp_process(struct sk_buff *skb) if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED || skb->pkt_type == PACKET_HOST || - in_dev->arp_parms->proxy_delay == 0) { + NEIGH_VAR(in_dev->arp_parms, PROXY_DELAY) == 0) { arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha); @@ -894,10 +899,12 @@ static int arp_process(struct sk_buff *skb) It is possible, that this option should be enabled for some devices (strip is candidate) */ + is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip && + inet_addr_type(net, sip) == RTN_UNICAST; + if (n == NULL && - (arp->ar_op == htons(ARPOP_REPLY) || - (arp->ar_op == htons(ARPOP_REQUEST) && tip == sip)) && - inet_addr_type(net, sip) == RTN_UNICAST) + ((arp->ar_op == htons(ARPOP_REPLY) && + inet_addr_type(net, sip) == RTN_UNICAST) || is_garp)) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } @@ -910,7 +917,10 @@ static int arp_process(struct sk_buff *skb) agents are active. Taking the first reply prevents arp trashing and chooses the fastest router. */ - override = time_after(jiffies, n->updated + n->parms->locktime); + override = time_after(jiffies, + n->updated + + NEIGH_VAR(n->parms, LOCKTIME)) || + is_garp; /* Broadcast replies and request packets do not assert neighbour reachability. @@ -1107,7 +1117,7 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) return err; } -int arp_invalidate(struct net_device *dev, __be32 ip) +static int arp_invalidate(struct net_device *dev, __be32 ip) { struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev); int err = -ENXIO; @@ -1122,7 +1132,6 @@ int arp_invalidate(struct net_device *dev, __be32 ip) return err; } -EXPORT_SYMBOL(arp_invalidate); static int arp_req_delete_public(struct net *net, struct arpreq *r, struct net_device *dev) @@ -1284,7 +1293,7 @@ void __init arp_init(void) dev_add_pack(&arp_packet_type); arp_proc_init(); #ifdef CONFIG_SYSCTL - neigh_sysctl_register(NULL, &arp_tbl.parms, "ipv4", NULL); + neigh_sysctl_register(NULL, &arp_tbl.parms, NULL); #endif register_netdevice_notifier(&arp_netdev_notifier); } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 667c1d4ca984..69e77c8ff285 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -31,8 +31,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ @@ -1336,8 +1335,7 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def, secattr->flags |= NETLBL_SECATTR_MLS_LVL; if (tag_len > 4) { - secattr->attr.mls.cat = - netlbl_secattr_catmap_alloc(GFP_ATOMIC); + secattr->attr.mls.cat = netlbl_secattr_catmap_alloc(GFP_ATOMIC); if (secattr->attr.mls.cat == NULL) return -ENOMEM; @@ -1432,8 +1430,7 @@ static int cipso_v4_parsetag_enum(const struct cipso_v4_doi *doi_def, secattr->flags |= NETLBL_SECATTR_MLS_LVL; if (tag_len > 4) { - secattr->attr.mls.cat = - netlbl_secattr_catmap_alloc(GFP_ATOMIC); + secattr->attr.mls.cat = netlbl_secattr_catmap_alloc(GFP_ATOMIC); if (secattr->attr.mls.cat == NULL) return -ENOMEM; @@ -1527,8 +1524,7 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def, secattr->flags |= NETLBL_SECATTR_MLS_LVL; if (tag_len > 4) { - secattr->attr.mls.cat = - netlbl_secattr_catmap_alloc(GFP_ATOMIC); + secattr->attr.mls.cat = netlbl_secattr_catmap_alloc(GFP_ATOMIC); if (secattr->attr.mls.cat == NULL) return -ENOMEM; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 19e36376d2a0..8b5134c582f1 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -53,7 +53,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr, RT_CONN_FLAGS(sk), oif, sk->sk_protocol, - inet->inet_sport, usin->sin_port, sk, true); + inet->inet_sport, usin->sin_port, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a1b5bcbd04ae..bdbf68bb2e2d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -99,6 +99,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, + [IFA_FLAGS] = { .type = NLA_U32 }, }; #define IN4_ADDR_HSIZE_SHIFT 8 @@ -463,7 +464,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, } if (!(ifa->ifa_flags & IFA_F_SECONDARY)) { - net_srandom(ifa->ifa_local); + prandom_seed((__force u32) ifa->ifa_local); ifap = last_primary; } @@ -473,7 +474,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, inet_hash_insert(dev_net(in_dev->dev), ifa); cancel_delayed_work(&check_lifetime_work); - schedule_delayed_work(&check_lifetime_work, 0); + queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0); /* Send message first, then call notifier. Notifier will trigger FIB update, so that @@ -500,6 +501,7 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) return -ENOBUFS; } ipv4_devconf_setall(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); if (ifa->ifa_dev != in_dev) { WARN_ON(ifa->ifa_dev); in_dev_hold(in_dev); @@ -682,7 +684,8 @@ static void check_lifetime(struct work_struct *work) if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = now + ADDRCONF_TIMER_FUZZ_MAX; - schedule_delayed_work(&check_lifetime_work, next_sched - now); + queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, + next_sched - now); } static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, @@ -747,6 +750,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, goto errout; ipv4_devconf_setall(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); in_dev_hold(in_dev); if (tb[IFA_ADDRESS] == NULL) @@ -755,7 +759,8 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, INIT_HLIST_NODE(&ifa->hash); ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); - ifa->ifa_flags = ifm->ifa_flags; + ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : + ifm->ifa_flags; ifa->ifa_scope = ifm->ifa_scope; ifa->ifa_dev = in_dev; @@ -838,7 +843,8 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) ifa = ifa_existing; set_ifa_lifetime(ifa, valid_lft, prefered_lft); cancel_delayed_work(&check_lifetime_work); - schedule_delayed_work(&check_lifetime_work, 0); + queue_delayed_work(system_power_efficient_wq, + &check_lifetime_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); } @@ -1236,22 +1242,21 @@ static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, /* * Confirm that local IP address exists using wildcards: - * - in_dev: only on this interface, 0=any interface + * - net: netns to check, cannot be NULL + * - in_dev: only on this interface, NULL=any interface * - dst: only in the same subnet as dst, 0=any dst * - local: address, 0=autoselect the local address * - scope: maximum allowed scope value for the local address */ -__be32 inet_confirm_addr(struct in_device *in_dev, +__be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope) { __be32 addr = 0; struct net_device *dev; - struct net *net; - if (scope != RT_SCOPE_LINK) + if (in_dev != NULL) return confirm_addr_indev(in_dev, dst, local, scope); - net = dev_net(in_dev->dev); rcu_read_lock(); for_each_netdev_rcu(net, dev) { in_dev = __in_dev_get_rcu(dev); @@ -1382,6 +1387,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + ipv4_devconf_setall(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); inet_insert_ifa(ifa); } } @@ -1435,7 +1442,9 @@ 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(4) /* IFA_FLAGS */ + + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } static inline u32 cstamp_delta(unsigned long cstamp) @@ -1503,6 +1512,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || + nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) || put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp, preferred, valid)) goto nla_put_failure; @@ -1691,6 +1701,8 @@ static int inet_netconf_msgsize_devconf(int type) size += nla_total_size(4); if (type == -1 || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); + if (type == -1 || type == NETCONFA_PROXY_NEIGH) + size += nla_total_size(4); return size; } @@ -1727,6 +1739,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nla_put_s32(skb, NETCONFA_MC_FORWARDING, IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0) goto nla_put_failure; + if ((type == -1 || type == NETCONFA_PROXY_NEIGH) && + nla_put_s32(skb, NETCONFA_PROXY_NEIGH, + IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0) + goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -1764,6 +1780,7 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_RP_FILTER] = { .len = sizeof(int) }, + [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, }; static int inet_netconf_get_devconf(struct sk_buff *in_skb, @@ -1945,6 +1962,19 @@ static void inet_forward_change(struct net *net) } } +static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf) +{ + if (cnf == net->ipv4.devconf_dflt) + return NETCONFA_IFINDEX_DEFAULT; + else if (cnf == net->ipv4.devconf_all) + return NETCONFA_IFINDEX_ALL; + else { + struct in_device *idev + = container_of(cnf, struct in_device, cnf); + return idev->dev->ifindex; + } +} + static int devinet_conf_proc(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -1957,6 +1987,7 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, struct ipv4_devconf *cnf = ctl->extra1; struct net *net = ctl->extra2; int i = (int *)ctl->data - cnf->data; + int ifindex; set_bit(i, cnf->state); @@ -1966,23 +1997,19 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net); + if (i == IPV4_DEVCONF_RP_FILTER - 1 && new_value != old_value) { - int ifindex; - - if (cnf == net->ipv4.devconf_dflt) - ifindex = NETCONFA_IFINDEX_DEFAULT; - else if (cnf == net->ipv4.devconf_all) - ifindex = NETCONFA_IFINDEX_ALL; - else { - struct in_device *idev = - container_of(cnf, struct in_device, - cnf); - ifindex = idev->dev->ifindex; - } + ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER, ifindex, cnf); } + if (i == IPV4_DEVCONF_PROXY_ARP - 1 && + new_value != old_value) { + ifindex = devinet_conf_ifindex(net, cnf); + inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, + ifindex, cnf); + } } return ret; @@ -2160,7 +2187,7 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf) static void devinet_sysctl_register(struct in_device *idev) { - neigh_sysctl_register(idev->dev, idev->arp_parms, "ipv4", NULL); + neigh_sysctl_register(idev->dev, idev->arp_parms, NULL); __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, &idev->cnf); } @@ -2298,7 +2325,7 @@ void __init devinet_init(void) register_gifconf(PF_INET, inet_gifconf); register_netdevice_notifier(&ip_netdev_notifier); - schedule_delayed_work(&check_lifetime_work, 0); + queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0); rtnl_af_register(&inet_af_ops); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index d846304b7b89..c7539e22868b 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1047,6 +1047,8 @@ 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_lookup.h b/net/ipv4/fib_lookup.h index 388d113fd289..1e4f6600b31d 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -33,8 +33,6 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id, void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags); struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio); -int fib_detect_death(struct fib_info *fi, int order, - struct fib_info **last_resort, int *last_idx, int dflt); static inline void fib_result_assign(struct fib_result *res, struct fib_info *fi) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e63f47a4e651..b53f0bf84dca 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -426,8 +426,9 @@ struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio) return NULL; } -int fib_detect_death(struct fib_info *fi, int order, - struct fib_info **last_resort, int *last_idx, int dflt) +static int fib_detect_death(struct fib_info *fi, int order, + struct fib_info **last_resort, int *last_idx, + int dflt) { struct neighbour *n; int state = NUD_NONE; diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 5893e99e8299..1863422fb7d5 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -355,14 +355,7 @@ static int __init gre_init(void) goto err_gre; } - if (gre_offload_init()) { - pr_err("can't add protocol offload\n"); - goto err_gso; - } - return 0; -err_gso: - gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); err_gre: inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); err: @@ -371,8 +364,6 @@ err: static void __exit gre_exit(void) { - gre_offload_exit(); - gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 2cd02f32f99f..f1d32280cb54 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -11,6 +11,7 @@ */ #include <linux/skbuff.h> +#include <linux/init.h> #include <net/protocol.h> #include <net/gre.h> @@ -26,7 +27,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, { struct sk_buff *segs = ERR_PTR(-EINVAL); netdev_features_t enc_features; - int ghl = GRE_HEADER_SECTION; + int ghl; struct gre_base_hdr *greh; u16 mac_offset = skb->mac_header; int mac_len = skb->mac_len; @@ -49,15 +50,11 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); - if (greh->flags & GRE_KEY) - ghl += GRE_HEADER_SECTION; - if (greh->flags & GRE_SEQ) - ghl += GRE_HEADER_SECTION; - if (greh->flags & GRE_CSUM) { - ghl += GRE_HEADER_SECTION; - csum = true; - } else - csum = false; + ghl = skb_inner_network_header(skb) - skb_transport_header(skb); + if (unlikely(ghl < sizeof(*greh))) + goto out; + + csum = !!(greh->flags & GRE_CSUM); if (unlikely(!pskb_may_pull(skb, ghl))) goto out; @@ -116,19 +113,175 @@ out: return segs; } +/* Compute the whole skb csum in s/w and store it, then verify GRO csum + * starting from gro_offset. + */ +static __sum16 gro_skb_checksum(struct sk_buff *skb) +{ + __sum16 sum; + + skb->csum = skb_checksum(skb, 0, skb->len, 0); + NAPI_GRO_CB(skb)->csum = csum_sub(skb->csum, + csum_partial(skb->data, skb_gro_offset(skb), 0)); + sum = csum_fold(NAPI_GRO_CB(skb)->csum); + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) { + if (unlikely(!sum)) + netdev_rx_csum_fault(skb->dev); + } else + skb->ip_summed = CHECKSUM_COMPLETE; + + return sum; +} + +static struct sk_buff **gre_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + struct sk_buff **pp = NULL; + struct sk_buff *p; + const struct gre_base_hdr *greh; + unsigned int hlen, grehlen; + unsigned int off; + int flush = 1; + struct packet_offload *ptype; + __be16 type; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*greh); + greh = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + greh = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!greh)) + goto out; + } + + /* Only support version 0 and K (key), C (csum) flags. Note that + * although the support for the S (seq#) flag can be added easily + * for GRO, this is problematic for GSO hence can not be enabled + * here because a GRO pkt may end up in the forwarding path, thus + * requiring GSO support to break it up correctly. + */ + if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0) + goto out; + + type = greh->protocol; + + rcu_read_lock(); + ptype = gro_find_receive_by_type(type); + if (ptype == NULL) + goto out_unlock; + + grehlen = GRE_HEADER_SECTION; + + if (greh->flags & GRE_KEY) + grehlen += GRE_HEADER_SECTION; + + if (greh->flags & GRE_CSUM) + grehlen += GRE_HEADER_SECTION; + + hlen = off + grehlen; + if (skb_gro_header_hard(skb, hlen)) { + greh = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!greh)) + goto out_unlock; + } + if (greh->flags & GRE_CSUM) { /* Need to verify GRE csum first */ + __sum16 csum = 0; + + if (skb->ip_summed == CHECKSUM_COMPLETE) + csum = csum_fold(NAPI_GRO_CB(skb)->csum); + /* Don't trust csum error calculated/reported by h/w */ + if (skb->ip_summed == CHECKSUM_NONE || csum != 0) + csum = gro_skb_checksum(skb); + + /* GRE CSUM is the 1's complement of the 1's complement sum + * of the GRE hdr plus payload so it should add up to 0xffff + * (and 0 after csum_fold()) just like the IPv4 hdr csum. + */ + if (csum) + goto out_unlock; + } + flush = 0; + + for (p = *head; p; p = p->next) { + const struct gre_base_hdr *greh2; + + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + /* The following checks are needed to ensure only pkts + * from the same tunnel are considered for aggregation. + * The criteria for "the same tunnel" includes: + * 1) same version (we only support version 0 here) + * 2) same protocol (we only support ETH_P_IP for now) + * 3) same set of flags + * 4) same key if the key field is present. + */ + greh2 = (struct gre_base_hdr *)(p->data + off); + + if (greh2->flags != greh->flags || + greh2->protocol != greh->protocol) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + if (greh->flags & GRE_KEY) { + /* compare keys */ + if (*(__be32 *)(greh2+1) != *(__be32 *)(greh+1)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + } + } + + skb_gro_pull(skb, grehlen); + + /* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/ + skb_gro_postpull_rcsum(skb, greh, grehlen); + + pp = ptype->callbacks.gro_receive(head, skb); + +out_unlock: + rcu_read_unlock(); +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +static int gre_gro_complete(struct sk_buff *skb, int nhoff) +{ + struct gre_base_hdr *greh = (struct gre_base_hdr *)(skb->data + nhoff); + struct packet_offload *ptype; + unsigned int grehlen = sizeof(*greh); + int err = -ENOENT; + __be16 type; + + type = greh->protocol; + if (greh->flags & GRE_KEY) + grehlen += GRE_HEADER_SECTION; + + if (greh->flags & GRE_CSUM) + grehlen += GRE_HEADER_SECTION; + + rcu_read_lock(); + ptype = gro_find_complete_by_type(type); + if (ptype != NULL) + err = ptype->callbacks.gro_complete(skb, nhoff + grehlen); + + rcu_read_unlock(); + return err; +} + static const struct net_offload gre_offload = { .callbacks = { .gso_send_check = gre_gso_send_check, .gso_segment = gre_gso_segment, + .gro_receive = gre_gro_receive, + .gro_complete = gre_gro_complete, }, }; -int __init gre_offload_init(void) +static int __init gre_offload_init(void) { return inet_add_offload(&gre_offload, IPPROTO_GRE); } - -void __exit gre_offload_exit(void) -{ - inet_del_offload(&gre_offload, IPPROTO_GRE); -} +device_initcall(gre_offload_init); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 5c0e8bc6e5ba..0134663fdbce 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -668,6 +668,16 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info) rcu_read_unlock(); } +static bool icmp_tag_validation(int proto) +{ + bool ok; + + rcu_read_lock(); + ok = rcu_dereference(inet_protos[proto])->icmp_strict_tag_validation; + rcu_read_unlock(); + return ok; +} + /* * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and * ICMP_PARAMETERPROB. @@ -705,10 +715,22 @@ static void icmp_unreach(struct sk_buff *skb) case ICMP_PORT_UNREACH: break; case ICMP_FRAG_NEEDED: - if (ipv4_config.no_pmtu_disc) { + /* for documentation of the ip_no_pmtu_disc + * values please see + * Documentation/networking/ip-sysctl.txt + */ + switch (net->ipv4.sysctl_ip_no_pmtu_disc) { + default: LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"), &iph->daddr); - } else { + break; + case 2: + goto out; + case 3: + if (!icmp_tag_validation(iph->protocol)) + goto out; + /* fall through */ + case 0: info = ntohs(icmph->un.frag.mtu); if (!info) goto out; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 7defdc9ba167..97e4d1655d26 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -211,7 +211,7 @@ static void igmp_stop_timer(struct ip_mc_list *im) /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { - int tv = net_random() % max_delay; + int tv = prandom_u32() % max_delay; im->tm_running = 1; if (!mod_timer(&im->timer, jiffies+tv+2)) @@ -220,7 +220,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) static void igmp_gq_start_timer(struct in_device *in_dev) { - int tv = net_random() % in_dev->mr_maxdelay; + int tv = prandom_u32() % in_dev->mr_maxdelay; in_dev->mr_gq_running = 1; if (!mod_timer(&in_dev->mr_gq_timer, jiffies+tv+2)) @@ -229,7 +229,7 @@ static void igmp_gq_start_timer(struct in_device *in_dev) static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { - int tv = net_random() % delay; + int tv = prandom_u32() % delay; if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); @@ -310,7 +310,7 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) struct ip_sf_list *psf; int scount = 0; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; @@ -463,7 +463,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, } first = 1; psf_prev = NULL; - for (psf=*psf_list; psf; psf=psf_next) { + for (psf = *psf_list; psf; psf = psf_next) { __be32 *psrc; psf_next = psf->sf_next; @@ -520,7 +520,7 @@ empty_source: return skb; if (pmc->crcount || isquery) { /* make sure we have room for group header */ - if (skb && AVAILABLE(skb)<sizeof(struct igmpv3_grec)) { + if (skb && AVAILABLE(skb) < sizeof(struct igmpv3_grec)) { igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } @@ -576,7 +576,7 @@ static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; - for (psf=*ppsf; psf; psf = psf_next) { + for (psf = *ppsf; psf; psf = psf_next) { psf_next = psf->sf_next; if (psf->sf_crcount == 0) { if (psf_prev) @@ -600,7 +600,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) /* deleted MCA's */ pmc_prev = NULL; - for (pmc=in_dev->mc_tomb; pmc; pmc=pmc_next) { + for (pmc = in_dev->mc_tomb; pmc; pmc = pmc_next) { pmc_next = pmc->next; if (pmc->sfmode == MCAST_INCLUDE) { type = IGMPV3_BLOCK_OLD_SOURCES; @@ -764,7 +764,7 @@ static void igmp_ifc_event(struct in_device *in_dev) static void igmp_timer_expire(unsigned long data) { - struct ip_mc_list *im=(struct ip_mc_list *)data; + struct ip_mc_list *im = (struct ip_mc_list *)data; struct in_device *in_dev = im->interface; spin_lock(&im->lock); @@ -794,10 +794,10 @@ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) int i, scount; scount = 0; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; - for (i=0; i<nsrcs; i++) { + for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != @@ -825,10 +825,10 @@ static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) /* mark INCLUDE-mode sources */ scount = 0; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; - for (i=0; i<nsrcs; i++) + for (i = 0; i < nsrcs; i++) if (srcs[i] == psf->sf_inaddr) { psf->sf_gsresp = 1; scount++; @@ -1103,7 +1103,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) pmc->tomb = im->tomb; pmc->sources = im->sources; im->tomb = im->sources = NULL; - for (psf=pmc->sources; psf; psf=psf->sf_next) + for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = pmc->crcount; } spin_unlock_bh(&im->lock); @@ -1121,7 +1121,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr) spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; - for (pmc=in_dev->mc_tomb; pmc; pmc=pmc->next) { + for (pmc = in_dev->mc_tomb; pmc; pmc = pmc->next) { if (pmc->multiaddr == multiaddr) break; pmc_prev = pmc; @@ -1134,7 +1134,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr) } spin_unlock_bh(&in_dev->mc_tomb_lock); if (pmc) { - for (psf=pmc->tomb; psf; psf=psf_next) { + for (psf = pmc->tomb; psf; psf = psf_next) { psf_next = psf->sf_next; kfree(psf); } @@ -1167,7 +1167,7 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) psf = pmc->tomb; pmc->tomb = NULL; spin_unlock_bh(&pmc->lock); - for (; psf; psf=psf_next) { + for (; psf; psf = psf_next) { psf_next = psf->sf_next; kfree(psf); } @@ -1557,7 +1557,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, int rv = 0; psf_prev = NULL; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -1630,7 +1630,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfcount[sfmode]--; } err = 0; - for (i=0; i<sfcount; i++) { + for (i = 0; i < sfcount; i++) { int rv = ip_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; @@ -1650,7 +1650,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : IGMP_Unsolicited_Report_Count; in_dev->mr_ifc_count = pmc->crcount; - for (psf=pmc->sources; psf; psf = psf->sf_next) + for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { @@ -1671,7 +1671,7 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -1699,7 +1699,7 @@ static void sf_markstate(struct ip_mc_list *pmc) struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; - for (psf=pmc->sources; psf; psf=psf->sf_next) + for (psf = pmc->sources; psf; psf = psf->sf_next) if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && @@ -1716,7 +1716,7 @@ static int sf_setstate(struct ip_mc_list *pmc) int new_in, rv; rv = 0; - for (psf=pmc->sources; psf; psf=psf->sf_next) { + for (psf = pmc->sources; psf; psf = psf->sf_next) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; @@ -1726,7 +1726,7 @@ static int sf_setstate(struct ip_mc_list *pmc) if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; - for (dpsf=pmc->tomb; dpsf; dpsf=dpsf->sf_next) { + for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; @@ -1748,7 +1748,7 @@ static int sf_setstate(struct ip_mc_list *pmc) * add or update "delete" records if an active filter * is now inactive */ - for (dpsf=pmc->tomb; dpsf; dpsf=dpsf->sf_next) + for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) if (dpsf->sf_inaddr == psf->sf_inaddr) break; if (!dpsf) { @@ -1800,7 +1800,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (!delta) pmc->sfcount[sfmode]++; err = 0; - for (i=0; i<sfcount; i++) { + for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; @@ -1810,7 +1810,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (!delta) pmc->sfcount[sfmode]--; - for (j=0; j<i; j++) + for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST @@ -1829,7 +1829,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : IGMP_Unsolicited_Report_Count; in_dev->mr_ifc_count = pmc->crcount; - for (psf=pmc->sources; psf; psf = psf->sf_next) + for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { @@ -1844,12 +1844,12 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) { struct ip_sf_list *psf, *nextpsf; - for (psf=pmc->tomb; psf; psf=nextpsf) { + for (psf = pmc->tomb; psf; psf = nextpsf) { nextpsf = psf->sf_next; kfree(psf); } pmc->tomb = NULL; - for (psf=pmc->sources; psf; psf=nextpsf) { + for (psf = pmc->sources; psf; psf = nextpsf) { nextpsf = psf->sf_next; kfree(psf); } @@ -2043,7 +2043,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; - for (i=0; i<psl->sl_count; i++) { + for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) @@ -2062,7 +2062,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); - for (j=i+1; j<psl->sl_count; j++) + for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; @@ -2088,7 +2088,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct newpsl->sl_max = count; newpsl->sl_count = count - IP_SFBLOCK; if (psl) { - for (i=0; i<psl->sl_count; i++) + for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); @@ -2098,7 +2098,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ - for (i=0; i<psl->sl_count; i++) { + for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) @@ -2106,7 +2106,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct } if (rv == 0) /* address already there is an error */ goto done; - for (j=psl->sl_count-1; j>=i; j--) + for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = mreqs->imr_sourceaddr; psl->sl_count++; @@ -2305,7 +2305,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, copy_to_user(optval, gsf, GROUP_FILTER_SIZE(0))) { return -EFAULT; } - for (i=0; i<copycount; i++) { + for (i = 0; i < copycount; i++) { struct sockaddr_storage ss; psin = (struct sockaddr_in *)&ss; @@ -2350,7 +2350,7 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) if (!psl) goto unlock; - for (i=0; i<psl->sl_count; i++) { + for (i = 0; i < psl->sl_count; i++) { if (psl->sl_addr[i] == rmt_addr) break; } @@ -2423,7 +2423,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { - for (psf=im->sources; psf; psf=psf->sf_next) { + for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; } @@ -2762,6 +2762,7 @@ static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, }; +#endif static int igmp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) @@ -2785,8 +2786,9 @@ static struct notifier_block igmp_notifier = { .notifier_call = igmp_netdev_event, }; -int __init igmp_mc_proc_init(void) +int __init igmp_mc_init(void) { +#if defined(CONFIG_PROC_FS) int err; err = register_pernet_subsys(&igmp_net_ops); @@ -2800,5 +2802,7 @@ int __init igmp_mc_proc_init(void) reg_notif_fail: unregister_pernet_subsys(&igmp_net_ops); return err; -} +#else + return register_netdevice_notifier(&igmp_notifier); #endif +} diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index fc0e649cc002..0d1e2cb877ec 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -109,7 +109,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) again: inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - smallest_rover = rover = net_random() % remaining + low; + smallest_rover = rover = prandom_u32() % remaining + low; smallest_size = -1; do { diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index 1975f52933c5..f17ea49b28fb 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -230,29 +230,6 @@ static void lro_add_packet(struct net_lro_desc *lro_desc, struct sk_buff *skb, lro_desc->last_skb = skb; } -static void lro_add_frags(struct net_lro_desc *lro_desc, - int len, int hlen, int truesize, - struct skb_frag_struct *skb_frags, - struct iphdr *iph, struct tcphdr *tcph) -{ - struct sk_buff *skb = lro_desc->parent; - int tcp_data_len = TCP_PAYLOAD_LENGTH(iph, tcph); - - lro_add_common(lro_desc, iph, tcph, tcp_data_len); - - skb->truesize += truesize; - - skb_frags[0].page_offset += hlen; - skb_frag_size_sub(&skb_frags[0], hlen); - - while (tcp_data_len > 0) { - *(lro_desc->next_frag) = *skb_frags; - tcp_data_len -= skb_frag_size(skb_frags); - lro_desc->next_frag++; - skb_frags++; - skb_shinfo(skb)->nr_frags++; - } -} static int lro_check_tcp_conn(struct net_lro_desc *lro_desc, struct iphdr *iph, @@ -371,128 +348,6 @@ out: return 1; } - -static struct sk_buff *lro_gen_skb(struct net_lro_mgr *lro_mgr, - struct skb_frag_struct *frags, - int len, int true_size, - void *mac_hdr, - int hlen, __wsum sum, - u32 ip_summed) -{ - struct sk_buff *skb; - struct skb_frag_struct *skb_frags; - int data_len = len; - int hdr_len = min(len, hlen); - - skb = netdev_alloc_skb(lro_mgr->dev, hlen + lro_mgr->frag_align_pad); - if (!skb) - return NULL; - - skb_reserve(skb, lro_mgr->frag_align_pad); - skb->len = len; - skb->data_len = len - hdr_len; - skb->truesize += true_size; - skb->tail += hdr_len; - - memcpy(skb->data, mac_hdr, hdr_len); - - skb_frags = skb_shinfo(skb)->frags; - while (data_len > 0) { - *skb_frags = *frags; - data_len -= skb_frag_size(frags); - skb_frags++; - frags++; - skb_shinfo(skb)->nr_frags++; - } - - skb_shinfo(skb)->frags[0].page_offset += hdr_len; - skb_frag_size_sub(&skb_shinfo(skb)->frags[0], hdr_len); - - skb->ip_summed = ip_summed; - skb->csum = sum; - skb->protocol = eth_type_trans(skb, lro_mgr->dev); - return skb; -} - -static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, - struct skb_frag_struct *frags, - int len, int true_size, - void *priv, __wsum sum) -{ - struct net_lro_desc *lro_desc; - struct iphdr *iph; - struct tcphdr *tcph; - struct sk_buff *skb; - u64 flags; - void *mac_hdr; - int mac_hdr_len; - int hdr_len = LRO_MAX_PG_HLEN; - int vlan_hdr_len = 0; - - if (!lro_mgr->get_frag_header || - lro_mgr->get_frag_header(frags, (void *)&mac_hdr, (void *)&iph, - (void *)&tcph, &flags, priv)) { - mac_hdr = skb_frag_address(frags); - goto out1; - } - - if (!(flags & LRO_IPV4) || !(flags & LRO_TCP)) - goto out1; - - hdr_len = (int)((void *)(tcph) + TCP_HDR_LEN(tcph) - mac_hdr); - mac_hdr_len = (int)((void *)(iph) - mac_hdr); - - lro_desc = lro_get_desc(lro_mgr, lro_mgr->lro_arr, iph, tcph); - if (!lro_desc) - goto out1; - - if (!lro_desc->active) { /* start new lro session */ - if (lro_tcp_ip_check(iph, tcph, len - mac_hdr_len, NULL)) - goto out1; - - skb = lro_gen_skb(lro_mgr, frags, len, true_size, mac_hdr, - hdr_len, 0, lro_mgr->ip_summed_aggr); - if (!skb) - goto out; - - if ((skb->protocol == htons(ETH_P_8021Q)) && - !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID)) - vlan_hdr_len = VLAN_HLEN; - - iph = (void *)(skb->data + vlan_hdr_len); - tcph = (void *)((u8 *)skb->data + vlan_hdr_len - + IP_HDR_LEN(iph)); - - lro_init_desc(lro_desc, skb, iph, tcph); - LRO_INC_STATS(lro_mgr, aggregated); - return NULL; - } - - if (lro_desc->tcp_next_seq != ntohl(tcph->seq)) - goto out2; - - if (lro_tcp_ip_check(iph, tcph, len - mac_hdr_len, lro_desc)) - goto out2; - - lro_add_frags(lro_desc, len, hdr_len, true_size, frags, iph, tcph); - LRO_INC_STATS(lro_mgr, aggregated); - - if ((skb_shinfo(lro_desc->parent)->nr_frags >= lro_mgr->max_aggr) || - lro_desc->parent->len > (0xFFFF - lro_mgr->dev->mtu)) - lro_flush(lro_mgr, lro_desc); - - return NULL; - -out2: /* send aggregated packets to the stack */ - lro_flush(lro_mgr, lro_desc); - -out1: /* Original packet has to be posted to the stack */ - skb = lro_gen_skb(lro_mgr, frags, len, true_size, mac_hdr, - hdr_len, sum, lro_mgr->ip_summed); -out: - return skb; -} - void lro_receive_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, void *priv) @@ -506,23 +361,6 @@ void lro_receive_skb(struct net_lro_mgr *lro_mgr, } EXPORT_SYMBOL(lro_receive_skb); -void lro_receive_frags(struct net_lro_mgr *lro_mgr, - struct skb_frag_struct *frags, - int len, int true_size, void *priv, __wsum sum) -{ - struct sk_buff *skb; - - skb = __lro_proc_segment(lro_mgr, frags, len, true_size, priv, sum); - if (!skb) - return; - - if (lro_mgr->features & LRO_F_NAPI) - netif_receive_skb(skb); - else - netif_rx(skb); -} -EXPORT_SYMBOL(lro_receive_frags); - void lro_flush_all(struct net_lro_mgr *lro_mgr) { int i; @@ -534,14 +372,3 @@ void lro_flush_all(struct net_lro_mgr *lro_mgr) } } EXPORT_SYMBOL(lro_flush_all); - -void lro_flush_pkt(struct net_lro_mgr *lro_mgr, - struct iphdr *iph, struct tcphdr *tcph) -{ - struct net_lro_desc *lro_desc; - - lro_desc = lro_get_desc(lro_mgr, lro_mgr->lro_arr, iph, tcph); - if (lro_desc->active) - lro_flush(lro_mgr, lro_desc); -} -EXPORT_SYMBOL(lro_flush_pkt); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 33d5537881ed..48f424465112 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -109,13 +109,6 @@ static inline void flush_check(struct inet_peer_base *base, int family) } } -void inetpeer_invalidate_family(int family) -{ - atomic_t *fp = inetpeer_seq_ptr(family); - - atomic_inc(fp); -} - #define PEER_MAXDEPTH 40 /* sufficient for about 2^27 nodes */ /* Exported for sysctl_net_ipv4. */ @@ -227,7 +220,7 @@ static int addr_compare(const struct inetpeer_addr *a, stackptr = _stack; \ *stackptr++ = &_base->root; \ for (u = rcu_deref_locked(_base->root, _base); \ - u != peer_avl_empty; ) { \ + u != peer_avl_empty;) { \ int cmp = addr_compare(_daddr, &u->daddr); \ if (cmp == 0) \ break; \ @@ -282,7 +275,7 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, *stackptr++ = &start->avl_left; \ v = &start->avl_left; \ for (u = rcu_deref_locked(*v, base); \ - u->avl_right != peer_avl_empty_rcu; ) { \ + u->avl_right != peer_avl_empty_rcu;) { \ v = &u->avl_right; \ *stackptr++ = v; \ u = rcu_deref_locked(*v, base); \ diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 694de3b7aebf..f3869c186d97 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 || skb->local_df) + 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 = ip_dst_mtu_maybe_forward(skb_dst(skb), true); + + /* 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); @@ -49,11 +114,15 @@ 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); } int ip_forward(struct sk_buff *skb) { + u32 mtu; struct iphdr *iph; /* Our header */ struct rtable *rt; /* Route we use */ struct ip_options *opt = &(IPCB(skb)->opt); @@ -88,11 +157,12 @@ 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) { + IPCB(skb)->flags |= IPSKB_FORWARDED; + mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); + if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) { 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))); + htonl(mtu)); goto drop; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 2481993a4970..c10a3ce5cbff 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -704,7 +704,7 @@ struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user) memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(skb, user)) return NULL; - skb->rxhash = 0; + skb_clear_hash(skb); } } return skb; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index e560ef34cf4b..ec4f762efda5 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -178,7 +178,7 @@ static int ipgre_err(struct sk_buff *skb, u32 info, else itn = net_generic(net, ipgre_net_id); - iph = (const struct iphdr *)skb->data; + iph = (const struct iphdr *)(icmp_hdr(skb) + 1); t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->daddr, iph->saddr, tpi->key); @@ -278,7 +278,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, return NETDEV_TX_OK; free_skb: - dev_kfree_skb(skb); + kfree_skb(skb); out: dev->stats.tx_dropped++; return NETDEV_TX_OK; @@ -301,7 +301,7 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, return NETDEV_TX_OK; free_skb: - dev_kfree_skb(skb); + kfree_skb(skb); out: dev->stats.tx_dropped++; return NETDEV_TX_OK; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 054a3e97d822..3d4da2c16b6a 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -314,7 +314,7 @@ 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; diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ec7264514a82..f4ab72e19af9 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -167,7 +167,7 @@ int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb) soffset -= 4; if (soffset > 3) { memcpy(&faddr, &start[soffset-1], 4); - for (soffset-=4, doffset=4; soffset > 3; soffset-=4, doffset+=4) + for (soffset -= 4, doffset = 4; soffset > 3; soffset -= 4, doffset += 4) memcpy(&dptr[doffset-1], &start[soffset-1], 4); /* * RFC1812 requires to fix illegal source routes. @@ -227,7 +227,7 @@ void ip_options_fragment(struct sk_buff *skb) continue; } optlen = optptr[1]; - if (optlen<2 || optlen>l) + if (optlen < 2 || optlen > l) return; if (!IPOPT_COPIED(*optptr)) memset(optptr, IPOPT_NOOP, optlen); @@ -275,27 +275,27 @@ int ip_options_compile(struct net *net, for (l = opt->optlen; l > 0; ) { switch (*optptr) { - case IPOPT_END: - for (optptr++, l--; l>0; optptr++, l--) { + case IPOPT_END: + for (optptr++, l--; l > 0; optptr++, l--) { if (*optptr != IPOPT_END) { *optptr = IPOPT_END; opt->is_changed = 1; } } goto eol; - case IPOPT_NOOP: + case IPOPT_NOOP: l--; optptr++; continue; } optlen = optptr[1]; - if (optlen<2 || optlen>l) { + if (optlen < 2 || optlen > l) { pp_ptr = optptr; goto error; } switch (*optptr) { - case IPOPT_SSRR: - case IPOPT_LSRR: + case IPOPT_SSRR: + case IPOPT_LSRR: if (optlen < 3) { pp_ptr = optptr + 1; goto error; @@ -321,7 +321,7 @@ int ip_options_compile(struct net *net, opt->is_strictroute = (optptr[0] == IPOPT_SSRR); opt->srr = optptr - iph; break; - case IPOPT_RR: + case IPOPT_RR: if (opt->rr) { pp_ptr = optptr; goto error; @@ -349,7 +349,7 @@ int ip_options_compile(struct net *net, } opt->rr = optptr - iph; break; - case IPOPT_TIMESTAMP: + case IPOPT_TIMESTAMP: if (opt->ts) { pp_ptr = optptr; goto error; @@ -369,13 +369,13 @@ int ip_options_compile(struct net *net, goto error; } switch (optptr[3]&0xF) { - case IPOPT_TS_TSONLY: + case IPOPT_TS_TSONLY: if (skb) timeptr = &optptr[optptr[2]-1]; opt->ts_needtime = 1; optptr[2] += 4; break; - case IPOPT_TS_TSANDADDR: + case IPOPT_TS_TSANDADDR: if (optptr[2]+7 > optptr[1]) { pp_ptr = optptr + 2; goto error; @@ -389,7 +389,7 @@ int ip_options_compile(struct net *net, opt->ts_needtime = 1; optptr[2] += 8; break; - case IPOPT_TS_PRESPEC: + case IPOPT_TS_PRESPEC: if (optptr[2]+7 > optptr[1]) { pp_ptr = optptr + 2; goto error; @@ -405,7 +405,7 @@ int ip_options_compile(struct net *net, opt->ts_needtime = 1; optptr[2] += 8; break; - default: + default: if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) { pp_ptr = optptr + 3; goto error; @@ -433,7 +433,7 @@ int ip_options_compile(struct net *net, } opt->ts = optptr - iph; break; - case IPOPT_RA: + case IPOPT_RA: if (optlen < 4) { pp_ptr = optptr + 1; goto error; @@ -441,7 +441,7 @@ int ip_options_compile(struct net *net, if (optptr[2] == 0 && optptr[3] == 0) opt->router_alert = optptr - iph; break; - case IPOPT_CIPSO: + case IPOPT_CIPSO: if ((!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) || opt->cipso) { pp_ptr = optptr; goto error; @@ -452,9 +452,9 @@ int ip_options_compile(struct net *net, goto error; } break; - case IPOPT_SEC: - case IPOPT_SID: - default: + case IPOPT_SEC: + case IPOPT_SID: + default: if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) { pp_ptr = optptr; goto error; @@ -572,7 +572,7 @@ void ip_forward_options(struct sk_buff *skb) optptr = raw + opt->srr; - for ( srrptr=optptr[2], srrspace = optptr[1]; + for ( srrptr = optptr[2], srrspace = optptr[1]; srrptr <= srrspace; srrptr += 4 ) { @@ -628,7 +628,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) if (rt->rt_type != RTN_LOCAL) return -EINVAL; - for (srrptr=optptr[2], srrspace = optptr[1]; srrptr <= srrspace; srrptr += 4) { + for (srrptr = optptr[2], srrspace = optptr[1]; srrptr <= srrspace; srrptr += 4) { if (srrptr + 3 > srrspace) { icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((opt->srr+2)<<24)); return -EINVAL; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index df184616493f..8971780aec7c 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -449,6 +449,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) __be16 not_last_frag; struct rtable *rt = skb_rtable(skb); int err = 0; + bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; dev = rt->dst.dev; @@ -458,12 +459,13 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) iph = ip_hdr(skb); + mtu = ip_dst_mtu_maybe_forward(&rt->dst, forwarding); if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) || (IPCB(skb)->frag_max_size && - IPCB(skb)->frag_max_size > dst_mtu(&rt->dst)))) { + IPCB(skb)->frag_max_size > mtu))) { IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(ip_skb_dst_mtu(skb))); + htonl(mtu)); kfree_skb(skb); return -EMSGSIZE; } @@ -473,7 +475,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) */ hlen = iph->ihl * 4; - mtu = dst_mtu(&rt->dst) - hlen; /* Size of data space */ + mtu = mtu - hlen; /* Size of data space */ #ifdef CONFIG_BRIDGE_NETFILTER if (skb->nf_bridge) mtu -= nf_bridge_mtu_reduction(skb); @@ -1551,7 +1553,7 @@ void __init ip_init(void) ip_rt_init(); inet_initpeers(); -#if defined(CONFIG_IP_MULTICAST) && defined(CONFIG_PROC_FS) - igmp_mc_proc_init(); +#if defined(CONFIG_IP_MULTICAST) + igmp_mc_init(); #endif } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ddf32a6bc415..580dd96666e0 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -56,7 +56,6 @@ /* * SOL_IP control messages. */ -#define PKTINFO_SKB_CB(__skb) ((struct in_pktinfo *)((__skb)->cb)) static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { @@ -390,7 +389,7 @@ 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; - struct sockaddr_in *sin; + DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct { struct sock_extended_err ee; struct sockaddr_in offender; @@ -416,7 +415,6 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) serr = SKB_EXT_ERR(skb); - sin = (struct sockaddr_in *)msg->msg_name; if (sin) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) + @@ -1051,14 +1049,15 @@ e_inval: * * To support IP_CMSG_PKTINFO option, we store rt_iif and specific * destination in skb->cb[] before dst drop. - * This way, receiver doesnt make cache line misses to read rtable. + * This way, receiver doesn't make cache line misses to read rtable. */ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); + bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) || + ipv6_sk_rxinfo(sk); - if ((inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) && - skb_rtable(skb)) { + if (prepare && skb_rtable(skb)) { pktinfo->ipi_ifindex = inet_iif(skb); pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb); } else { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 90ff9570d7d4..50228be5c17b 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -40,6 +40,7 @@ #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/rculist.h> +#include <linux/err.h> #include <net/sock.h> #include <net/ip.h> @@ -61,13 +62,63 @@ #include <net/ip6_route.h> #endif -static unsigned int ip_tunnel_hash(struct ip_tunnel_net *itn, - __be32 key, __be32 remote) +static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) { return hash_32((__force u32)key ^ (__force u32)remote, IP_TNL_HASH_BITS); } +static void __tunnel_dst_set(struct ip_tunnel_dst *idst, + struct dst_entry *dst) +{ + struct dst_entry *old_dst; + + if (dst) { + if (dst->flags & DST_NOCACHE) + dst = NULL; + else + dst_clone(dst); + } + old_dst = xchg((__force struct dst_entry **)&idst->dst, dst); + dst_release(old_dst); +} + +static void tunnel_dst_set(struct ip_tunnel *t, struct dst_entry *dst) +{ + __tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst); +} + +static void tunnel_dst_reset(struct ip_tunnel *t) +{ + tunnel_dst_set(t, NULL); +} + +static void tunnel_dst_reset_all(struct ip_tunnel *t) +{ + int i; + + for_each_possible_cpu(i) + __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); +} + +static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) +{ + struct dst_entry *dst; + + rcu_read_lock(); + dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst); + if (dst) { + if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + rcu_read_unlock(); + tunnel_dst_reset(t); + return NULL; + } + dst_hold(dst); + } + rcu_read_unlock(); + return (struct rtable *)dst; +} + /* Often modified stats are per cpu, other are shared (netdev->stats) */ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) @@ -75,7 +126,8 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, int i; for_each_possible_cpu(i) { - const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); u64 rx_packets, rx_bytes, tx_packets, tx_bytes; unsigned int start; @@ -146,7 +198,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, struct ip_tunnel *t, *cand = NULL; struct hlist_head *head; - hash = ip_tunnel_hash(itn, key, remote); + hash = ip_tunnel_hash(key, remote); head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { @@ -178,7 +230,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, cand = t; } - hash = ip_tunnel_hash(itn, key, 0); + hash = ip_tunnel_hash(key, 0); head = &itn->tunnels[hash]; hlist_for_each_entry_rcu(t, head, hash_node) { @@ -234,7 +286,7 @@ static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, else remote = 0; - h = ip_tunnel_hash(itn, parms->i_key, remote); + h = ip_tunnel_hash(parms->i_key, remote); return &itn->tunnels[h]; } @@ -318,11 +370,10 @@ failed: return ERR_PTR(err); } -static inline struct rtable *ip_route_output_tunnel(struct net *net, - struct flowi4 *fl4, - int proto, - __be32 daddr, __be32 saddr, - __be32 key, __u8 tos, int oif) +static inline void init_tunnel_flow(struct flowi4 *fl4, + int proto, + __be32 daddr, __be32 saddr, + __be32 key, __u8 tos, int oif) { memset(fl4, 0, sizeof(*fl4)); fl4->flowi4_oif = oif; @@ -331,7 +382,6 @@ static inline struct rtable *ip_route_output_tunnel(struct net *net, fl4->flowi4_tos = tos; fl4->flowi4_proto = proto; fl4->fl4_gre_key = key; - return ip_route_output_key(net, fl4); } static int ip_tunnel_bind_dev(struct net_device *dev) @@ -350,14 +400,14 @@ static int ip_tunnel_bind_dev(struct net_device *dev) struct flowi4 fl4; struct rtable *rt; - rt = ip_route_output_tunnel(tunnel->net, &fl4, - tunnel->parms.iph.protocol, - iph->daddr, iph->saddr, - tunnel->parms.o_key, - RT_TOS(iph->tos), - tunnel->parms.link); + init_tunnel_flow(&fl4, iph->protocol, iph->daddr, + iph->saddr, tunnel->parms.o_key, + RT_TOS(iph->tos), tunnel->parms.link); + rt = ip_route_output_key(tunnel->net, &fl4); + if (!IS_ERR(rt)) { tdev = rt->dst.dev; + tunnel_dst_set(tunnel, &rt->dst); ip_rt_put(rt); } if (dev->type != ARPHRD_ETHER) @@ -405,7 +455,7 @@ 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) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; const struct iphdr *iph = ip_hdr(skb); int err; @@ -532,6 +582,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, unsigned int max_headroom; /* The extra header space needed */ __be32 dst; int err; + bool connected = true; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); @@ -581,27 +632,38 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, #endif else goto tx_error; + + connected = false; } tos = tnl_params->tos; if (tos & 0x1) { tos &= ~0x1; - if (skb->protocol == htons(ETH_P_IP)) + if (skb->protocol == htons(ETH_P_IP)) { tos = inner_iph->tos; - else if (skb->protocol == htons(ETH_P_IPV6)) + connected = false; + } else if (skb->protocol == htons(ETH_P_IPV6)) { tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); + connected = false; + } } - rt = ip_route_output_tunnel(tunnel->net, &fl4, - protocol, - dst, tnl_params->saddr, - tunnel->parms.o_key, - RT_TOS(tos), - tunnel->parms.link); - if (IS_ERR(rt)) { - dev->stats.tx_carrier_errors++; - goto tx_error; + init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, + tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link); + + rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL; + + if (!rt) { + rt = ip_route_output_key(tunnel->net, &fl4); + + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error; + } + if (connected) + tunnel_dst_set(tunnel, &rt->dst); } + if (rt->dst.dev == dev) { ip_rt_put(rt); dev->stats.collisions++; @@ -618,6 +680,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, 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; @@ -647,7 +710,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, if (skb_cow_head(skb, dev->needed_headroom)) { dev->stats.tx_dropped++; - dev_kfree_skb(skb); + kfree_skb(skb); return; } @@ -663,7 +726,7 @@ tx_error_icmp: #endif tx_error: dev->stats.tx_errors++; - dev_kfree_skb(skb); + kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_tunnel_xmit); @@ -696,6 +759,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, if (set_mtu) dev->mtu = mtu; } + tunnel_dst_reset_all(t); netdev_state_change(dev); } @@ -811,6 +875,7 @@ static void ip_tunnel_dev_free(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); gro_cells_destroy(&tunnel->gro_cells); + free_percpu(tunnel->dst_cache); free_percpu(dev->tstats); free_netdev(dev); } @@ -859,7 +924,7 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, } rtnl_unlock(); - return PTR_RET(itn->fb_tunnel_dev); + return PTR_ERR_OR_ZERO(itn->fb_tunnel_dev); } EXPORT_SYMBOL_GPL(ip_tunnel_init_net); @@ -979,18 +1044,25 @@ int ip_tunnel_init(struct net_device *dev) int i, err; dev->destructor = ip_tunnel_dev_free; - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ipt_stats; + struct pcpu_sw_netstats *ipt_stats; ipt_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ipt_stats->syncp); } + tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); + if (!tunnel->dst_cache) { + free_percpu(dev->tstats); + return -ENOMEM; + } + err = gro_cells_init(&tunnel->gro_cells, dev); if (err) { + free_percpu(tunnel->dst_cache); free_percpu(dev->tstats); return err; } @@ -1015,6 +1087,8 @@ void ip_tunnel_uninit(struct net_device *dev) /* fb_tunnel_dev will be unregisted in net-exit call. */ if (itn->fb_tunnel_dev != dev) ip_tunnel_del(netdev_priv(dev)); + + tunnel_dst_reset_all(tunnel); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 42ffbc8d65c6..6156f4ef5e91 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -56,7 +56,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb, skb_scrub_packet(skb, xnet); - skb->rxhash = 0; + skb_clear_hash(skb); skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); @@ -107,8 +107,7 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) nf_reset(skb); secpath_reset(skb); - if (!skb->l4_rxhash) - skb->rxhash = 0; + skb_clear_hash_if_not_l4(skb); skb_dst_drop(skb); skb->vlan_tci = 0; skb_set_queue_mapping(skb, 0); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 52b802a0cd8c..48eafae51769 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -60,7 +60,7 @@ static int vti_rcv(struct sk_buff *skb) tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); if (tunnel != NULL) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; u32 oldmark = skb->mark; int ret; @@ -162,7 +162,7 @@ tx_error_icmp: dst_link_failure(skb); tx_error: dev->stats.tx_errors++; - dev_kfree_skb(skb); + kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index efa1138fa523..b3e86ea7b71b 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -273,7 +273,7 @@ static int __init ic_open_devs(void) msleep(1); - if time_before(jiffies, next_msg) + if (time_before(jiffies, next_msg)) continue; elapsed = jiffies_to_msecs(jiffies - start); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index fe3e9f7f1f0b..812b18351462 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -228,7 +228,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; tx_error: - dev_kfree_skb(skb); + kfree_skb(skb); out: dev->stats.tx_errors++; return NETDEV_TX_OK; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 1672409f5ba5..b9b3472975ba 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -428,6 +428,7 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) goto failure; ipv4_devconf_setall(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); IPV4_DEVCONF(in_dev->cnf, RP_FILTER) = 0; if (dev_open(dev)) @@ -520,6 +521,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) } ipv4_devconf_setall(in_dev); + neigh_parms_data_state_setall(in_dev->arp_parms); IPV4_DEVCONF(in_dev->cnf, RP_FILTER) = 0; rcu_read_unlock(); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 40d56073cd19..a26ce035e3fa 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -39,23 +39,38 @@ config NF_CONNTRACK_PROC_COMPAT config NF_TABLES_IPV4 depends on NF_TABLES tristate "IPv4 nf_tables support" - -config NFT_REJECT_IPV4 - depends on NF_TABLES_IPV4 - tristate "nf_tables IPv4 reject support" + help + This option enables the IPv4 support for nf_tables. config NFT_CHAIN_ROUTE_IPV4 depends on NF_TABLES_IPV4 tristate "IPv4 nf_tables route chain support" + help + This option enables the "route" chain for IPv4 in nf_tables. This + chain type is used to force packet re-routing after mangling header + fields such as the source, destination, type of service and + the packet mark. config NFT_CHAIN_NAT_IPV4 depends on NF_TABLES_IPV4 depends on NF_NAT_IPV4 && NFT_NAT tristate "IPv4 nf_tables nat chain support" + help + This option enables the "nat" chain for IPv4 in nf_tables. This + chain type is used to perform Network Address Translation (NAT) + packet transformations such as the source, destination address and + source and destination ports. + +config NFT_REJECT_IPV4 + depends on NF_TABLES_IPV4 + default NFT_REJECT + tristate config NF_TABLES_ARP depends on NF_TABLES tristate "ARP nf_tables support" + help + This option enables the ARP support for nf_tables. config IP_NF_IPTABLES tristate "IP tables support (required for filtering/masq/NAT)" diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 19df72b7ba88..90b82405331e 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -28,9 +28,9 @@ obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o -obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o +obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o # generic IP tables diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index b969131ad1c1..5b6e0df4ccff 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -17,10 +17,6 @@ #include <linux/udp.h> #include <linux/icmp.h> #include <net/icmp.h> -#include <net/ip.h> -#include <net/tcp.h> -#include <net/route.h> -#include <net/dst.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ipt_REJECT.h> @@ -28,128 +24,12 @@ #include <linux/netfilter_bridge.h> #endif +#include <net/netfilter/ipv4/nf_reject.h> + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv4"); -/* Send RST reply */ -static void send_reset(struct sk_buff *oldskb, int hook) -{ - struct sk_buff *nskb; - const struct iphdr *oiph; - struct iphdr *niph; - const struct tcphdr *oth; - struct tcphdr _otcph, *tcph; - - /* IP header checks: fragment. */ - if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) - return; - - oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb), - sizeof(_otcph), &_otcph); - if (oth == NULL) - return; - - /* No RST for RST. */ - if (oth->rst) - return; - - if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) - return; - - /* Check checksum */ - if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP)) - return; - oiph = ip_hdr(oldskb); - - nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + - LL_MAX_HEADER, GFP_ATOMIC); - if (!nskb) - return; - - skb_reserve(nskb, LL_MAX_HEADER); - - skb_reset_network_header(nskb); - niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr)); - niph->version = 4; - niph->ihl = sizeof(struct iphdr) / 4; - niph->tos = 0; - niph->id = 0; - niph->frag_off = htons(IP_DF); - niph->protocol = IPPROTO_TCP; - niph->check = 0; - niph->saddr = oiph->daddr; - niph->daddr = oiph->saddr; - - skb_reset_transport_header(nskb); - tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); - memset(tcph, 0, sizeof(*tcph)); - tcph->source = oth->dest; - tcph->dest = oth->source; - tcph->doff = sizeof(struct tcphdr) / 4; - - if (oth->ack) - tcph->seq = oth->ack_seq; - else { - tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin + - oldskb->len - ip_hdrlen(oldskb) - - (oth->doff << 2)); - tcph->ack = 1; - } - - tcph->rst = 1; - tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr, - niph->daddr, 0); - nskb->ip_summed = CHECKSUM_PARTIAL; - nskb->csum_start = (unsigned char *)tcph - nskb->head; - nskb->csum_offset = offsetof(struct tcphdr, check); - - /* ip_route_me_harder expects skb->dst to be set */ - skb_dst_set_noref(nskb, skb_dst(oldskb)); - - nskb->protocol = htons(ETH_P_IP); - if (ip_route_me_harder(nskb, RTN_UNSPEC)) - goto free_nskb; - - niph->ttl = ip4_dst_hoplimit(skb_dst(nskb)); - - /* "Never happens" */ - if (nskb->len > dst_mtu(skb_dst(nskb))) - goto free_nskb; - - nf_ct_attach(nskb, oldskb); - -#ifdef CONFIG_BRIDGE_NETFILTER - /* If we use ip_local_out for bridged traffic, the MAC source on - * the RST will be ours, instead of the destination's. This confuses - * some routers/firewalls, and they drop the packet. So we need to - * build the eth header using the original destination's MAC as the - * source, and send the RST packet directly. - */ - if (oldskb->nf_bridge) { - struct ethhdr *oeth = eth_hdr(oldskb); - nskb->dev = oldskb->nf_bridge->physindev; - niph->tot_len = htons(nskb->len); - ip_send_check(niph); - if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol), - oeth->h_source, oeth->h_dest, nskb->len) < 0) - goto free_nskb; - dev_queue_xmit(nskb); - } else -#endif - ip_local_out(nskb); - - return; - - free_nskb: - kfree_skb(nskb); -} - -static inline void send_unreach(struct sk_buff *skb_in, int code) -{ - icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); -} - static unsigned int reject_tg(struct sk_buff *skb, const struct xt_action_param *par) { @@ -157,28 +37,28 @@ reject_tg(struct sk_buff *skb, const struct xt_action_param *par) switch (reject->with) { case IPT_ICMP_NET_UNREACHABLE: - send_unreach(skb, ICMP_NET_UNREACH); + nf_send_unreach(skb, ICMP_NET_UNREACH); break; case IPT_ICMP_HOST_UNREACHABLE: - send_unreach(skb, ICMP_HOST_UNREACH); + nf_send_unreach(skb, ICMP_HOST_UNREACH); break; case IPT_ICMP_PROT_UNREACHABLE: - send_unreach(skb, ICMP_PROT_UNREACH); + nf_send_unreach(skb, ICMP_PROT_UNREACH); break; case IPT_ICMP_PORT_UNREACHABLE: - send_unreach(skb, ICMP_PORT_UNREACH); + nf_send_unreach(skb, ICMP_PORT_UNREACH); break; case IPT_ICMP_NET_PROHIBITED: - send_unreach(skb, ICMP_NET_ANO); + nf_send_unreach(skb, ICMP_NET_ANO); break; case IPT_ICMP_HOST_PROHIBITED: - send_unreach(skb, ICMP_HOST_ANO); + nf_send_unreach(skb, ICMP_HOST_ANO); break; case IPT_ICMP_ADMIN_PROHIBITED: - send_unreach(skb, ICMP_PKT_FILTERED); + nf_send_unreach(skb, ICMP_PKT_FILTERED); break; case IPT_TCP_RESET: - send_reset(skb, par->hooknum); + nf_send_reset(skb, par->hooknum); case IPT_ICMP_ECHOREPLY: /* Doesn't happen. */ break; diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index ecd8bec411c9..8127dc802865 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -548,9 +548,3 @@ static void __exit nf_conntrack_l3proto_ipv4_fini(void) module_init(nf_conntrack_l3proto_ipv4_init); module_exit(nf_conntrack_l3proto_ipv4_fini); - -void need_ipv4_conntrack(void) -{ - return; -} -EXPORT_SYMBOL_GPL(need_ipv4_conntrack); diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 9eea059dd621..574f7ebba0b6 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -229,7 +229,10 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, ret = nf_ct_expect_related(rtcp_exp); if (ret == 0) break; - else if (ret != -EBUSY) { + else if (ret == -EBUSY) { + nf_ct_unexpect_related(rtp_exp); + continue; + } else if (ret < 0) { nf_ct_unexpect_related(rtp_exp); nated_port = 0; break; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 5f011cc89cd9..d551e31b416e 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -34,8 +34,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * * Author: James Morris <jmorris@intercode.com.au> * @@ -462,14 +461,14 @@ static unsigned char asn1_oid_decode(struct asn1_ctx *ctx, } if (subid < 40) { - optr [0] = 0; - optr [1] = subid; + optr[0] = 0; + optr[1] = subid; } else if (subid < 80) { - optr [0] = 1; - optr [1] = subid - 40; + optr[0] = 1; + optr[1] = subid - 40; } else { - optr [0] = 2; - optr [1] = subid - 80; + optr[0] = 2; + optr[1] = subid - 80; } *len = 2; diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c index 3e67ef1c676f..19412a4063fb 100644 --- a/net/ipv4/netfilter/nf_tables_arp.c +++ b/net/ipv4/netfilter/nf_tables_arp.c @@ -14,10 +14,30 @@ #include <linux/netfilter_arp.h> #include <net/netfilter/nf_tables.h> +static unsigned int +nft_do_chain_arp(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nft_pktinfo pkt; + + nft_set_pktinfo(&pkt, ops, skb, in, out); + + return nft_do_chain(&pkt, ops); +} + static struct nft_af_info nft_af_arp __read_mostly = { .family = NFPROTO_ARP, .nhooks = NF_ARP_NUMHOOKS, .owner = THIS_MODULE, + .nops = 1, + .hooks = { + [NF_ARP_IN] = nft_do_chain_arp, + [NF_ARP_OUT] = nft_do_chain_arp, + [NF_ARP_FORWARD] = nft_do_chain_arp, + }, }; static int nf_tables_arp_init_net(struct net *net) @@ -48,32 +68,14 @@ static struct pernet_operations nf_tables_arp_net_ops = { .exit = nf_tables_arp_exit_net, }; -static unsigned int -nft_do_chain_arp(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct nft_pktinfo pkt; - - nft_set_pktinfo(&pkt, ops, skb, in, out); - - return nft_do_chain_pktinfo(&pkt, ops); -} - -static struct nf_chain_type filter_arp = { - .family = NFPROTO_ARP, +static const struct nf_chain_type filter_arp = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, + .family = NFPROTO_ARP, + .owner = THIS_MODULE, .hook_mask = (1 << NF_ARP_IN) | (1 << NF_ARP_OUT) | (1 << NF_ARP_FORWARD), - .fn = { - [NF_ARP_IN] = nft_do_chain_arp, - [NF_ARP_OUT] = nft_do_chain_arp, - [NF_ARP_FORWARD] = nft_do_chain_arp, - }, }; static int __init nf_tables_arp_init(void) diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c index 0f4cbfeb19bd..6820c8c40842 100644 --- a/net/ipv4/netfilter/nf_tables_ipv4.c +++ b/net/ipv4/netfilter/nf_tables_ipv4.c @@ -18,14 +18,25 @@ #include <net/ip.h> #include <net/netfilter/nf_tables_ipv4.h> +static unsigned int nft_do_chain_ipv4(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nft_pktinfo pkt; + + nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out); + + return nft_do_chain(&pkt, ops); +} + static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct nft_pktinfo pkt; - if (unlikely(skb->len < sizeof(struct iphdr) || ip_hdr(skb)->ihl < sizeof(struct iphdr) / 4)) { if (net_ratelimit()) @@ -33,19 +44,24 @@ static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops, "packet\n"); return NF_ACCEPT; } - nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out); - return nft_do_chain_pktinfo(&pkt, ops); + return nft_do_chain_ipv4(ops, skb, in, out, okfn); } -static struct nft_af_info nft_af_ipv4 __read_mostly = { +struct nft_af_info nft_af_ipv4 __read_mostly = { .family = NFPROTO_IPV4, .nhooks = NF_INET_NUMHOOKS, .owner = THIS_MODULE, + .nops = 1, .hooks = { + [NF_INET_LOCAL_IN] = nft_do_chain_ipv4, [NF_INET_LOCAL_OUT] = nft_ipv4_output, + [NF_INET_FORWARD] = nft_do_chain_ipv4, + [NF_INET_PRE_ROUTING] = nft_do_chain_ipv4, + [NF_INET_POST_ROUTING] = nft_do_chain_ipv4, }, }; +EXPORT_SYMBOL_GPL(nft_af_ipv4); static int nf_tables_ipv4_init_net(struct net *net) { @@ -75,42 +91,28 @@ static struct pernet_operations nf_tables_ipv4_net_ops = { .exit = nf_tables_ipv4_exit_net, }; -static unsigned int -nft_do_chain_ipv4(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct nft_pktinfo pkt; - - nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out); - - return nft_do_chain_pktinfo(&pkt, ops); -} - -static struct nf_chain_type filter_ipv4 = { - .family = NFPROTO_IPV4, +static const struct nf_chain_type filter_ipv4 = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, + .family = NFPROTO_IPV4, + .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING), - .fn = { - [NF_INET_LOCAL_IN] = nft_do_chain_ipv4, - [NF_INET_LOCAL_OUT] = nft_ipv4_output, - [NF_INET_FORWARD] = nft_do_chain_ipv4, - [NF_INET_PRE_ROUTING] = nft_do_chain_ipv4, - [NF_INET_POST_ROUTING] = nft_do_chain_ipv4, - }, }; static int __init nf_tables_ipv4_init(void) { + int ret; + nft_register_chain_type(&filter_ipv4); - return register_pernet_subsys(&nf_tables_ipv4_net_ops); + ret = register_pernet_subsys(&nf_tables_ipv4_net_ops); + if (ret < 0) + nft_unregister_chain_type(&filter_ipv4); + + return ret; } static void __exit nf_tables_ipv4_exit(void) diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c index cf2c792cd971..b5b256d45e67 100644 --- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c @@ -75,7 +75,7 @@ static unsigned int nf_nat_fn(const struct nf_hook_ops *ops, nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out); - ret = nft_do_chain_pktinfo(&pkt, ops); + ret = nft_do_chain(&pkt, ops); if (ret != NF_ACCEPT) return ret; if (!nf_nat_initialized(ct, maniptype)) { @@ -164,21 +164,21 @@ static unsigned int nf_nat_output(const struct nf_hook_ops *ops, return ret; } -static struct nf_chain_type nft_chain_nat_ipv4 = { - .family = NFPROTO_IPV4, +static const struct nf_chain_type nft_chain_nat_ipv4 = { .name = "nat", .type = NFT_CHAIN_T_NAT, + .family = NFPROTO_IPV4, + .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), - .fn = { + .hooks = { [NF_INET_PRE_ROUTING] = nf_nat_prerouting, [NF_INET_POST_ROUTING] = nf_nat_postrouting, [NF_INET_LOCAL_OUT] = nf_nat_output, [NF_INET_LOCAL_IN] = nf_nat_fn, }, - .me = THIS_MODULE, }; static int __init nft_chain_nat_init(void) diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c index 4e6bf9a3d7aa..125b66766c0a 100644 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c @@ -47,7 +47,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, daddr = iph->daddr; tos = iph->tos; - ret = nft_do_chain_pktinfo(&pkt, ops); + ret = nft_do_chain(&pkt, ops); if (ret != NF_DROP && ret != NF_QUEUE) { iph = ip_hdr(skb); @@ -61,15 +61,15 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, return ret; } -static struct nf_chain_type nft_chain_route_ipv4 = { - .family = NFPROTO_IPV4, +static const struct nf_chain_type nft_chain_route_ipv4 = { .name = "route", .type = NFT_CHAIN_T_ROUTE, + .family = NFPROTO_IPV4, + .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_LOCAL_OUT), - .fn = { + .hooks = { [NF_INET_LOCAL_OUT] = nf_route_table_hook, }, - .me = THIS_MODULE, }; static int __init nft_chain_route_init(void) diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index 4a5e94ac314a..e79718a382f2 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -1,5 +1,6 @@ /* * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2013 Eric Leblond <eric@regit.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -16,108 +17,59 @@ #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/icmp.h> +#include <net/netfilter/ipv4/nf_reject.h> +#include <net/netfilter/nft_reject.h> -struct nft_reject { - enum nft_reject_types type:8; - u8 icmp_code; -}; - -static void nft_reject_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], - const struct nft_pktinfo *pkt) +void nft_reject_ipv4_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) { struct nft_reject *priv = nft_expr_priv(expr); switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - icmp_send(pkt->skb, ICMP_DEST_UNREACH, priv->icmp_code, 0); + nf_send_unreach(pkt->skb, priv->icmp_code); break; case NFT_REJECT_TCP_RST: + nf_send_reset(pkt->skb, pkt->ops->hooknum); break; } data[NFT_REG_VERDICT].verdict = NF_DROP; } +EXPORT_SYMBOL_GPL(nft_reject_ipv4_eval); -static const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = { - [NFTA_REJECT_TYPE] = { .type = NLA_U32 }, - [NFTA_REJECT_ICMP_CODE] = { .type = NLA_U8 }, -}; - -static int nft_reject_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_reject *priv = nft_expr_priv(expr); - - if (tb[NFTA_REJECT_TYPE] == NULL) - return -EINVAL; - - priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE])); - switch (priv->type) { - case NFT_REJECT_ICMP_UNREACH: - if (tb[NFTA_REJECT_ICMP_CODE] == NULL) - return -EINVAL; - priv->icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]); - case NFT_REJECT_TCP_RST: - break; - default: - return -EINVAL; - } - - return 0; -} - -static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) -{ - const struct nft_reject *priv = nft_expr_priv(expr); - - if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type))) - goto nla_put_failure; - - switch (priv->type) { - case NFT_REJECT_ICMP_UNREACH: - if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) - goto nla_put_failure; - break; - } - - return 0; - -nla_put_failure: - return -1; -} - -static struct nft_expr_type nft_reject_type; -static const struct nft_expr_ops nft_reject_ops = { - .type = &nft_reject_type, +static struct nft_expr_type nft_reject_ipv4_type; +static const struct nft_expr_ops nft_reject_ipv4_ops = { + .type = &nft_reject_ipv4_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), - .eval = nft_reject_eval, + .eval = nft_reject_ipv4_eval, .init = nft_reject_init, .dump = nft_reject_dump, }; -static struct nft_expr_type nft_reject_type __read_mostly = { +static struct nft_expr_type nft_reject_ipv4_type __read_mostly = { + .family = NFPROTO_IPV4, .name = "reject", - .ops = &nft_reject_ops, + .ops = &nft_reject_ipv4_ops, .policy = nft_reject_policy, .maxattr = NFTA_REJECT_MAX, .owner = THIS_MODULE, }; -static int __init nft_reject_module_init(void) +static int __init nft_reject_ipv4_module_init(void) { - return nft_register_expr(&nft_reject_type); + return nft_register_expr(&nft_reject_ipv4_type); } -static void __exit nft_reject_module_exit(void) +static void __exit nft_reject_ipv4_module_exit(void) { - nft_unregister_expr(&nft_reject_type); + nft_unregister_expr(&nft_reject_ipv4_type); } -module_init(nft_reject_module_init); -module_exit(nft_reject_module_exit); +module_init(nft_reject_ipv4_module_init); +module_exit(nft_reject_ipv4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_EXPR("reject"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "reject"); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 242e7f4ed6f4..2d11c094296e 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -53,8 +53,12 @@ #include <net/transp_v6.h> #endif +struct ping_table { + struct hlist_nulls_head hash[PING_HTABLE_SIZE]; + rwlock_t lock; +}; -struct ping_table ping_table; +static struct ping_table ping_table; struct pingv6_ops pingv6_ops; EXPORT_SYMBOL_GPL(pingv6_ops); @@ -316,6 +320,9 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, if (addr_len < sizeof(*addr)) return -EINVAL; + if (addr->sin6_family != AF_INET6) + return -EINVAL; + pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n", sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port)); @@ -668,8 +675,8 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, } EXPORT_SYMBOL_GPL(ping_common_sendmsg); -int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len) +static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t len) { struct net *net = sock_net(sk); struct flowi4 fl4; @@ -696,7 +703,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, */ if (msg->msg_name) { - struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) @@ -869,7 +876,7 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, /* Copy the address and add cmsg data. */ if (family == AF_INET) { - struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); if (sin) { sin->sin_family = AF_INET; @@ -886,8 +893,7 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } else if (family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6hdr *ip6 = ipv6_hdr(skb); - struct sockaddr_in6 *sin6 = - (struct sockaddr_in6 *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); if (sin6) { sin6->sin6_family = AF_INET6; @@ -903,7 +909,12 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } if (inet6_sk(sk)->rxopt.all) - pingv6_ops.ip6_datagram_recv_ctl(sk, msg, skb); + pingv6_ops.ip6_datagram_recv_common_ctl(sk, msg, skb); + if (skb->protocol == htons(ETH_P_IPV6) && + inet6_sk(sk)->rxopt.all) + pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb); + else if (skb->protocol == htons(ETH_P_IP) && isk->cmsg_flags) + ip_cmsg_recv(msg, skb); #endif } else { BUG(); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 4a0335854b89..a6c8a80ec9d6 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -279,6 +279,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD), SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES), SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS), + SNMP_MIB_ITEM("TCPAutoCorking", LINUX_MIB_TCPAUTOCORKING), SNMP_MIB_SENTINEL }; @@ -332,22 +333,22 @@ static void icmp_put(struct seq_file *seq) atomic_long_t *ptr = net->mib.icmpmsg_statistics->mibs; seq_puts(seq, "\nIcmp: InMsgs InErrors InCsumErrors"); - for (i=0; icmpmibmap[i].name != NULL; i++) + for (i = 0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " In%s", icmpmibmap[i].name); seq_printf(seq, " OutMsgs OutErrors"); - for (i=0; icmpmibmap[i].name != NULL; i++) + for (i = 0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " Out%s", icmpmibmap[i].name); seq_printf(seq, "\nIcmp: %lu %lu %lu", snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INMSGS), snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INERRORS), snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_CSUMERRORS)); - for (i=0; icmpmibmap[i].name != NULL; i++) + for (i = 0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " %lu", atomic_long_read(ptr + icmpmibmap[i].index)); seq_printf(seq, " %lu %lu", snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTMSGS), snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTERRORS)); - for (i=0; icmpmibmap[i].name != NULL; i++) + for (i = 0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " %lu", atomic_long_read(ptr + (icmpmibmap[i].index | 0x100))); } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 23c3e5b5bb53..c04518f4850a 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -493,7 +493,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, */ if (msg->msg_namelen) { - struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); err = -EINVAL; if (msg->msg_namelen < sizeof(*usin)) goto out; @@ -575,7 +575,7 @@ 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) | (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0); @@ -690,7 +690,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct inet_sock *inet = inet_sk(sk); size_t copied = 0; int err = -EOPNOTSUPP; - struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; if (flags & MSG_OOB) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f8da28278014..4c011ec69ed4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -112,9 +112,6 @@ #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) -/* IPv4 datagram length is stored into 16bit field (tot_len) */ -#define IP_MAX_MTU 0xFFFF - #define RT_GC_TIMEOUT (300*HZ) static int ip_rt_max_size; @@ -1600,6 +1597,7 @@ 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; @@ -1698,10 +1696,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; err = fib_lookup(net, &fl4, &res); - if (err != 0) + if (err != 0) { + if (!IN_DEV_FORWARD(in_dev)) + err = -EHOSTUNREACH; goto no_route; - - RT_CACHE_STAT_INC(in_slow_tot); + } if (res.type == RTN_BROADCAST) goto brd_input; @@ -1715,8 +1714,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto local_input; } - if (!IN_DEV_FORWARD(in_dev)) + if (!IN_DEV_FORWARD(in_dev)) { + err = -EHOSTUNREACH; goto no_route; + } if (res.type != RTN_UNICAST) goto martian_destination; @@ -1771,6 +1772,7 @@ 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; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index b95331e6c077..f2ed13c2125f 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -121,7 +121,7 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr, cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq; /* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */ - diff = (count - (cookie >> COOKIEBITS)) & ((__u32) - 1 >> COOKIEBITS); + diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS); if (diff >= MAX_SYNCOOKIE_AGE) return (__u32)-1; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 3d69ec8dac57..44eba052b43d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -286,13 +286,6 @@ static struct ctl_table ipv4_table[] = { .extra2 = &ip_ttl_max, }, { - .procname = "ip_no_pmtu_disc", - .data = &ipv4_config.no_pmtu_disc, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "ip_nonlocal_bind", .data = &sysctl_ip_nonlocal_bind, .maxlen = sizeof(int), @@ -707,7 +700,7 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { + { .procname = "tcp_thin_dupack", .data = &sysctl_tcp_thin_dupack, .maxlen = sizeof(int), @@ -733,6 +726,15 @@ static struct ctl_table ipv4_table[] = { .extra2 = &gso_max_segs, }, { + .procname = "tcp_autocorking", + .data = &sysctl_tcp_autocorking, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), @@ -822,6 +824,20 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = ipv4_local_port_range, }, + { + .procname = "ip_no_pmtu_disc", + .data = &init_net.ipv4.sysctl_ip_no_pmtu_disc, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "ip_forward_use_pmtu", + .data = &init_net.ipv4.sysctl_ip_fwd_use_pmtu, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 82de78603686..9f3a2db9109e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -285,6 +285,8 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; int sysctl_tcp_min_tso_segs __read_mostly = 2; +int sysctl_tcp_autocorking __read_mostly = 1; + struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); @@ -379,7 +381,7 @@ void tcp_init_sock(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - skb_queue_head_init(&tp->out_of_order_queue); + __skb_queue_head_init(&tp->out_of_order_queue); tcp_init_xmit_timers(sk); tcp_prequeue_init(tp); INIT_LIST_HEAD(&tp->tsq_node); @@ -619,19 +621,58 @@ static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) tp->snd_up = tp->write_seq; } -static inline void tcp_push(struct sock *sk, int flags, int mss_now, - int nonagle) +/* If a not yet filled skb is pushed, do not send it if + * we have data packets in Qdisc or NIC queues : + * Because TX completion will happen shortly, it gives a chance + * to coalesce future sendmsg() payload into this skb, without + * need for a timer, and with no latency trade off. + * As packets containing data payload have a bigger truesize + * than pure acks (dataless) packets, the last checks prevent + * autocorking if we only have an ACK in Qdisc/NIC queues, + * or if TX completion was delayed after we processed ACK packet. + */ +static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, + int size_goal) { - if (tcp_send_head(sk)) { - struct tcp_sock *tp = tcp_sk(sk); + return skb->len < size_goal && + sysctl_tcp_autocorking && + skb != tcp_write_queue_head(sk) && + atomic_read(&sk->sk_wmem_alloc) > skb->truesize; +} + +static void tcp_push(struct sock *sk, int flags, int mss_now, + int nonagle, int size_goal) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; - if (!(flags & MSG_MORE) || forced_push(tp)) - tcp_mark_push(tp, tcp_write_queue_tail(sk)); + if (!tcp_send_head(sk)) + return; + + skb = tcp_write_queue_tail(sk); + if (!(flags & MSG_MORE) || forced_push(tp)) + tcp_mark_push(tp, skb); + + tcp_mark_urg(tp, flags); + + if (tcp_should_autocork(sk, skb, size_goal)) { - tcp_mark_urg(tp, flags); - __tcp_push_pending_frames(sk, mss_now, - (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle); + /* avoid atomic op if TSQ_THROTTLED bit is already set */ + if (!test_bit(TSQ_THROTTLED, &tp->tsq_flags)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); + set_bit(TSQ_THROTTLED, &tp->tsq_flags); + } + /* It is possible TX completion already happened + * before we set TSQ_THROTTLED. + */ + if (atomic_read(&sk->sk_wmem_alloc) > skb->truesize) + return; } + + if (flags & MSG_MORE) + nonagle = TCP_NAGLE_CORK; + + __tcp_push_pending_frames(sk, mss_now, nonagle); } static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, @@ -934,7 +975,8 @@ new_segment: wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: - tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); + tcp_push(sk, flags & ~MSG_MORE, mss_now, + TCP_NAGLE_PUSH, size_goal); if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) goto do_error; @@ -944,7 +986,7 @@ wait_for_memory: out: if (copied && !(flags & MSG_SENDPAGE_NOTLAST)) - tcp_push(sk, flags, mss_now, tp->nonagle); + tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); return copied; do_error: @@ -1225,7 +1267,8 @@ wait_for_sndbuf: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); wait_for_memory: if (copied) - tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH); + tcp_push(sk, flags & ~MSG_MORE, mss_now, + TCP_NAGLE_PUSH, size_goal); if ((err = sk_stream_wait_memory(sk, &timeo)) != 0) goto do_error; @@ -1236,7 +1279,7 @@ wait_for_memory: out: if (copied) - tcp_push(sk, flags, mss_now, tp->nonagle); + tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); release_sock(sk); return copied + copied_syn; @@ -2186,7 +2229,7 @@ adjudge_to_death: /* This is a (useful) BSD violating of the RFC. There is a * problem with TCP as specified in that the other end could * keep a socket open forever with no application left this end. - * We use a 3 minute timeout (about the same as BSD) then kill + * We use a 1 minute timeout (about the same as BSD) then kill * our end. If they send after that then tough - BUT: long enough * that we won't make the old 4*rto = almost no time - whoops * reset mistake. diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 8a520996f3d2..e498a62b8f97 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 c53b7f35c51d..227cba79fa6b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -671,6 +671,7 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) { struct tcp_sock *tp = tcp_sk(sk); long m = mrtt; /* RTT */ + u32 srtt = tp->srtt; /* The following amusing code comes from Jacobson's * article in SIGCOMM '88. Note that rtt and mdev @@ -688,11 +689,9 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) * does not matter how to _calculate_ it. Seems, it was trap * that VJ failed to avoid. 8) */ - if (m == 0) - m = 1; - if (tp->srtt != 0) { - m -= (tp->srtt >> 3); /* m is now error in rtt est */ - tp->srtt += m; /* rtt = 7/8 rtt + 1/8 new */ + if (srtt != 0) { + m -= (srtt >> 3); /* m is now error in rtt est */ + srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) { m = -m; /* m is now abs(error) */ m -= (tp->mdev >> 2); /* similar update on mdev */ @@ -723,11 +722,12 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) } } else { /* no previous measure. */ - tp->srtt = m << 3; /* take the measured time to be rtt */ + srtt = m << 3; /* take the measured time to be rtt */ tp->mdev = m << 1; /* make sure rto = 3*rtt */ tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); tp->rtt_seq = tp->snd_nxt; } + tp->srtt = max(1U, srtt); } /* Set the sk_pacing_rate to allow proper sizing of TSO packets. @@ -746,8 +746,10 @@ static void tcp_update_pacing_rate(struct sock *sk) 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) + /* Correction for small srtt and scheduling constraints. + * For small rtt, consider noise is too high, and use + * the minimal value (srtt = 1 -> 125 us for HZ=1000) + * * 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. @@ -766,7 +768,7 @@ static void tcp_update_pacing_rate(struct sock *sk) /* Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ -void tcp_set_rto(struct sock *sk) +static void tcp_set_rto(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); /* Old crap is replaced with new one. 8) @@ -3686,7 +3688,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) int opcode = *ptr++; int opsize; - switch(opcode) { + switch (opcode) { case TCPOPT_EOL: return NULL; case TCPOPT_NOP: @@ -4046,7 +4048,7 @@ static void tcp_sack_remove(struct tcp_sock *tp) WARN_ON(before(tp->rcv_nxt, sp->end_seq)); /* Zap this SACK, by moving forward any other SACKS. */ - for (i=this_sack+1; i < num_sacks; i++) + for (i = this_sack+1; i < num_sacks; i++) tp->selective_acks[i-1] = tp->selective_acks[i]; num_sacks--; continue; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 067213924751..3cf976510497 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -173,7 +173,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_TCP, - orig_sport, orig_dport, sk, true); + orig_sport, orig_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) @@ -827,7 +827,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; int err = -1; - struct sk_buff * skb; + struct sk_buff *skb; /* First, grab a route. */ if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) @@ -1668,7 +1668,6 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } sk_setup_caps(newsk, dst); - tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric_advmss(dst); if (tcp_sk(sk)->rx_opt.user_mss && diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 098b3a29f6f3..d547075d8300 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -22,7 +22,8 @@ int sysctl_tcp_nometrics_save __read_mostly; -static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr, +static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *saddr, + const struct inetpeer_addr *daddr, struct net *net, unsigned int hash); struct tcp_fastopen_metrics { @@ -34,7 +35,8 @@ struct tcp_fastopen_metrics { struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; - struct inetpeer_addr tcpm_addr; + struct inetpeer_addr tcpm_saddr; + struct inetpeer_addr tcpm_daddr; unsigned long tcpm_stamp; u32 tcpm_ts; u32 tcpm_ts_stamp; @@ -145,7 +147,8 @@ static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst #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, + struct inetpeer_addr *saddr, + struct inetpeer_addr *daddr, unsigned int hash) { struct tcp_metrics_block *tm; @@ -158,7 +161,7 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, /* 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); + tm = __tcp_get_metrics(saddr, daddr, net, hash); if (tm == TCP_METRICS_RECLAIM_PTR) { reclaim = true; tm = NULL; @@ -183,7 +186,8 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, if (!tm) goto out_unlock; } - tm->tcpm_addr = *addr; + tm->tcpm_saddr = *saddr; + tm->tcpm_daddr = *daddr; tcpm_suck_dst(tm, dst, true); @@ -206,7 +210,8 @@ static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, in return NULL; } -static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr, +static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *saddr, + const struct inetpeer_addr *daddr, struct net *net, unsigned int hash) { struct tcp_metrics_block *tm; @@ -214,7 +219,8 @@ static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *a for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; tm = rcu_dereference(tm->tcpm_next)) { - if (addr_same(&tm->tcpm_addr, addr)) + if (addr_same(&tm->tcpm_saddr, saddr) && + addr_same(&tm->tcpm_daddr, daddr)) break; depth++; } @@ -225,19 +231,22 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, struct dst_entry *dst) { struct tcp_metrics_block *tm; - struct inetpeer_addr addr; + struct inetpeer_addr saddr, daddr; unsigned int hash; struct net *net; - addr.family = req->rsk_ops->family; - switch (addr.family) { + saddr.family = req->rsk_ops->family; + daddr.family = req->rsk_ops->family; + switch (daddr.family) { case AF_INET: - addr.addr.a4 = inet_rsk(req)->ir_rmt_addr; - hash = (__force unsigned int) addr.addr.a4; + saddr.addr.a4 = inet_rsk(req)->ir_loc_addr; + daddr.addr.a4 = inet_rsk(req)->ir_rmt_addr; + hash = (__force unsigned int) daddr.addr.a4; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: - *(struct in6_addr *)addr.addr.a6 = inet_rsk(req)->ir_v6_rmt_addr; + *(struct in6_addr *)saddr.addr.a6 = inet_rsk(req)->ir_v6_loc_addr; + *(struct in6_addr *)daddr.addr.a6 = inet_rsk(req)->ir_v6_rmt_addr; hash = ipv6_addr_hash(&inet_rsk(req)->ir_v6_rmt_addr); break; #endif @@ -250,7 +259,8 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; tm = rcu_dereference(tm->tcpm_next)) { - if (addr_same(&tm->tcpm_addr, &addr)) + if (addr_same(&tm->tcpm_saddr, &saddr) && + addr_same(&tm->tcpm_daddr, &daddr)) break; } tcpm_check_stamp(tm, dst); @@ -260,32 +270,44 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw) { struct tcp_metrics_block *tm; - struct inetpeer_addr addr; + struct inetpeer_addr saddr, daddr; unsigned int hash; struct net *net; - addr.family = tw->tw_family; - switch (addr.family) { - case AF_INET: - addr.addr.a4 = tw->tw_daddr; - hash = (__force unsigned int) addr.addr.a4; - break; + if (tw->tw_family == AF_INET) { + saddr.family = AF_INET; + saddr.addr.a4 = tw->tw_rcv_saddr; + daddr.family = AF_INET; + daddr.addr.a4 = tw->tw_daddr; + hash = (__force unsigned int) daddr.addr.a4; + } #if IS_ENABLED(CONFIG_IPV6) - case AF_INET6: - *(struct in6_addr *)addr.addr.a6 = tw->tw_v6_daddr; - hash = ipv6_addr_hash(&tw->tw_v6_daddr); - break; + else if (tw->tw_family == AF_INET6) { + if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) { + saddr.family = AF_INET; + saddr.addr.a4 = tw->tw_rcv_saddr; + daddr.family = AF_INET; + daddr.addr.a4 = tw->tw_daddr; + hash = (__force unsigned int) daddr.addr.a4; + } else { + saddr.family = AF_INET6; + *(struct in6_addr *)saddr.addr.a6 = tw->tw_v6_rcv_saddr; + daddr.family = AF_INET6; + *(struct in6_addr *)daddr.addr.a6 = tw->tw_v6_daddr; + hash = ipv6_addr_hash(&tw->tw_v6_daddr); + } + } #endif - default: + else return NULL; - } net = twsk_net(tw); hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; tm = rcu_dereference(tm->tcpm_next)) { - if (addr_same(&tm->tcpm_addr, &addr)) + if (addr_same(&tm->tcpm_saddr, &saddr) && + addr_same(&tm->tcpm_daddr, &daddr)) break; } return tm; @@ -296,34 +318,45 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, bool create) { struct tcp_metrics_block *tm; - struct inetpeer_addr addr; + struct inetpeer_addr saddr, daddr; unsigned int hash; struct net *net; - addr.family = sk->sk_family; - switch (addr.family) { - case AF_INET: - addr.addr.a4 = inet_sk(sk)->inet_daddr; - hash = (__force unsigned int) addr.addr.a4; - break; + if (sk->sk_family == AF_INET) { + saddr.family = AF_INET; + saddr.addr.a4 = inet_sk(sk)->inet_saddr; + daddr.family = AF_INET; + daddr.addr.a4 = inet_sk(sk)->inet_daddr; + hash = (__force unsigned int) daddr.addr.a4; + } #if IS_ENABLED(CONFIG_IPV6) - case AF_INET6: - *(struct in6_addr *)addr.addr.a6 = sk->sk_v6_daddr; - hash = ipv6_addr_hash(&sk->sk_v6_daddr); - break; + else if (sk->sk_family == AF_INET6) { + if (ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { + saddr.family = AF_INET; + saddr.addr.a4 = inet_sk(sk)->inet_saddr; + daddr.family = AF_INET; + daddr.addr.a4 = inet_sk(sk)->inet_daddr; + hash = (__force unsigned int) daddr.addr.a4; + } else { + saddr.family = AF_INET6; + *(struct in6_addr *)saddr.addr.a6 = sk->sk_v6_rcv_saddr; + daddr.family = AF_INET6; + *(struct in6_addr *)daddr.addr.a6 = sk->sk_v6_daddr; + hash = ipv6_addr_hash(&sk->sk_v6_daddr); + } + } #endif - default: + else return NULL; - } net = dev_net(dst->dev); hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); - tm = __tcp_get_metrics(&addr, net, hash); + tm = __tcp_get_metrics(&saddr, &daddr, net, hash); if (tm == TCP_METRICS_RECLAIM_PTR) tm = NULL; if (!tm && create) - tm = tcpm_new(dst, &addr, hash); + tm = tcpm_new(dst, &saddr, &daddr, hash); else tcpm_check_stamp(tm, dst); @@ -737,15 +770,21 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, struct nlattr *nest; int i; - switch (tm->tcpm_addr.family) { + switch (tm->tcpm_daddr.family) { case AF_INET: if (nla_put_be32(msg, TCP_METRICS_ATTR_ADDR_IPV4, - tm->tcpm_addr.addr.a4) < 0) + tm->tcpm_daddr.addr.a4) < 0) + goto nla_put_failure; + if (nla_put_be32(msg, TCP_METRICS_ATTR_SADDR_IPV4, + tm->tcpm_saddr.addr.a4) < 0) goto nla_put_failure; break; case AF_INET6: if (nla_put(msg, TCP_METRICS_ATTR_ADDR_IPV6, 16, - tm->tcpm_addr.addr.a6) < 0) + tm->tcpm_daddr.addr.a6) < 0) + goto nla_put_failure; + if (nla_put(msg, TCP_METRICS_ATTR_SADDR_IPV6, 16, + tm->tcpm_saddr.addr.a6) < 0) goto nla_put_failure; break; default: @@ -868,44 +907,66 @@ done: return skb->len; } -static int parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, - unsigned int *hash, int optional) +static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, + unsigned int *hash, int optional, int v4, int v6) { struct nlattr *a; - a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV4]; + a = info->attrs[v4]; if (a) { addr->family = AF_INET; addr->addr.a4 = nla_get_be32(a); - *hash = (__force unsigned int) addr->addr.a4; + if (hash) + *hash = (__force unsigned int) addr->addr.a4; return 0; } - a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV6]; + a = info->attrs[v6]; if (a) { if (nla_len(a) != sizeof(struct in6_addr)) return -EINVAL; addr->family = AF_INET6; memcpy(addr->addr.a6, nla_data(a), sizeof(addr->addr.a6)); - *hash = ipv6_addr_hash((struct in6_addr *) addr->addr.a6); + if (hash) + *hash = ipv6_addr_hash((struct in6_addr *) addr->addr.a6); return 0; } return optional ? 1 : -EAFNOSUPPORT; } +static int parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, + unsigned int *hash, int optional) +{ + return __parse_nl_addr(info, addr, hash, optional, + TCP_METRICS_ATTR_ADDR_IPV4, + TCP_METRICS_ATTR_ADDR_IPV6); +} + +static int parse_nl_saddr(struct genl_info *info, struct inetpeer_addr *addr) +{ + return __parse_nl_addr(info, addr, NULL, 0, + TCP_METRICS_ATTR_SADDR_IPV4, + TCP_METRICS_ATTR_SADDR_IPV6); +} + static int tcp_metrics_nl_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct tcp_metrics_block *tm; - struct inetpeer_addr addr; + struct inetpeer_addr saddr, daddr; unsigned int hash; struct sk_buff *msg; struct net *net = genl_info_net(info); void *reply; int ret; + bool src = true; - ret = parse_nl_addr(info, &addr, &hash, 0); + ret = parse_nl_addr(info, &daddr, &hash, 0); if (ret < 0) return ret; + ret = parse_nl_saddr(info, &saddr); + if (ret < 0) + src = false; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -920,7 +981,8 @@ static int tcp_metrics_nl_cmd_get(struct sk_buff *skb, struct genl_info *info) rcu_read_lock(); for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; tm = rcu_dereference(tm->tcpm_next)) { - if (addr_same(&tm->tcpm_addr, &addr)) { + if (addr_same(&tm->tcpm_daddr, &daddr) && + (!src || addr_same(&tm->tcpm_saddr, &saddr))) { ret = tcp_metrics_fill_info(msg, tm); break; } @@ -975,32 +1037,38 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info) struct tcpm_hash_bucket *hb; struct tcp_metrics_block *tm; struct tcp_metrics_block __rcu **pp; - struct inetpeer_addr addr; + struct inetpeer_addr saddr, daddr; unsigned int hash; struct net *net = genl_info_net(info); int ret; + bool src = true, found = false; - ret = parse_nl_addr(info, &addr, &hash, 1); + ret = parse_nl_addr(info, &daddr, &hash, 1); if (ret < 0) return ret; if (ret > 0) return tcp_metrics_flush_all(net); + ret = parse_nl_saddr(info, &saddr); + if (ret < 0) + src = false; hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); hb = net->ipv4.tcp_metrics_hash + hash; pp = &hb->chain; spin_lock_bh(&tcp_metrics_lock); - for (tm = deref_locked_genl(*pp); tm; - pp = &tm->tcpm_next, tm = deref_locked_genl(*pp)) { - if (addr_same(&tm->tcpm_addr, &addr)) { + for (tm = deref_locked_genl(*pp); tm; tm = deref_locked_genl(*pp)) { + if (addr_same(&tm->tcpm_daddr, &daddr) && + (!src || addr_same(&tm->tcpm_saddr, &saddr))) { *pp = tm->tcpm_next; - break; + kfree_rcu(tm, rcu_head); + found = true; + } else { + pp = &tm->tcpm_next; } } spin_unlock_bh(&tcp_metrics_lock); - if (!tm) + if (!found) return -ESRCH; - kfree_rcu(tm, rcu_head); return 0; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 97b684159861..7a436c517e44 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -297,6 +297,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_v6_daddr = sk->sk_v6_daddr; tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr; tw->tw_tclass = np->tclass; + tw->tw_flowlabel = np->flow_label >> 12; tw->tw_ipv6only = np->ipv6only; } #endif @@ -425,7 +426,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, tcp_set_ca_state(newsk, TCP_CA_Open); tcp_init_xmit_timers(newsk); - skb_queue_head_init(&newtp->out_of_order_queue); + __skb_queue_head_init(&newtp->out_of_order_queue); newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; newtp->rx_opt.saw_tstamp = 0; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 05606353c7e7..b92b81718ca4 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -138,7 +138,6 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, out: return segs; } -EXPORT_SYMBOL(tcp_gso_segment); struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) { @@ -197,7 +196,8 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) goto out_check_final; found: - flush = NAPI_GRO_CB(p)->flush; + /* Include the IP ID check below from the inner most IP hdr */ + flush = NAPI_GRO_CB(p)->flush | NAPI_GRO_CB(p)->flush_id; flush |= (__force int)(flags & TCP_FLAG_CWR); flush |= (__force int)((flags ^ tcp_flag_word(th2)) & ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH)); @@ -230,17 +230,16 @@ out_check_final: pp = head; out: - NAPI_GRO_CB(skb)->flush |= flush; + NAPI_GRO_CB(skb)->flush |= (flush != 0); return pp; } -EXPORT_SYMBOL(tcp_gro_receive); int tcp_gro_complete(struct sk_buff *skb) { struct tcphdr *th = tcp_hdr(skb); - skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_start = (unsigned char *)th - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; @@ -272,6 +271,7 @@ static int tcp_v4_gso_send_check(struct sk_buff *skb) static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) { + /* Use the IP hdr immediately proceeding for this transport */ const struct iphdr *iph = skb_gro_network_header(skb); __wsum wsum; @@ -279,7 +279,7 @@ static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff * if (NAPI_GRO_CB(skb)->flush) goto skip_csum; - wsum = skb->csum; + wsum = NAPI_GRO_CB(skb)->csum; switch (skb->ip_summed) { case CHECKSUM_NONE: @@ -303,13 +303,13 @@ skip_csum: return tcp_gro_receive(head, skb); } -static int tcp4_gro_complete(struct sk_buff *skb) +static int tcp4_gro_complete(struct sk_buff *skb, int thoff) { const struct iphdr *iph = ip_hdr(skb); struct tcphdr *th = tcp_hdr(skb); - th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb), - iph->saddr, iph->daddr, 0); + th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, + iph->daddr, 0); skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; return tcp_gro_complete(skb); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7820f3a7dd70..3be16727f058 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -363,15 +363,17 @@ static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb, */ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; TCP_SKB_CB(skb)->tcp_flags = flags; TCP_SKB_CB(skb)->sacked = 0; - skb_shinfo(skb)->gso_segs = 1; - skb_shinfo(skb)->gso_size = 0; - skb_shinfo(skb)->gso_type = 0; + shinfo->gso_segs = 1; + shinfo->gso_size = 0; + shinfo->gso_type = 0; TCP_SKB_CB(skb)->seq = seq; if (flags & (TCPHDR_SYN | TCPHDR_FIN)) @@ -406,7 +408,7 @@ struct tcp_out_options { * Beware: Something in the Internet is very sensitive to the ordering of * TCP options, we learned this through the hard way, so be careful here. * Luckily we can at least blame others for their non-compliance but from - * inter-operatibility perspective it seems that we're somewhat stuck with + * inter-operability perspective it seems that we're somewhat stuck with * the ordering which we have been using if we want to keep working with * those broken things (not that it currently hurts anybody as there isn't * particular reason why the ordering would need to be changed). @@ -679,7 +681,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb * * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb * needs to be reallocated in a driver. - * The invariant being skb->truesize substracted from sk->sk_wmem_alloc + * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc * * Since transmit from skb destructor is forbidden, we use a tasklet * to process all sockets that eventually need to send more skbs. @@ -696,12 +698,13 @@ 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. + * One tasklet per cpu tries to send more skbs. * We run in tasklet context but need to disable irqs when - * transfering tsq->head because tcp_wfree() might + * transferring tsq->head because tcp_wfree() might * interrupt us (non NAPI drivers) */ static void tcp_tasklet_func(unsigned long data) @@ -795,7 +798,7 @@ void __init tcp_tasklet_init(void) /* * Write buffer destructor automatically called from kfree_skb. - * We cant xmit new skbs from this context, as we might already + * We can't xmit new skbs from this context, as we might already * hold qdisc lock. */ void tcp_wfree(struct sk_buff *skb) @@ -986,6 +989,8 @@ 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) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* Make sure we own this skb before messing gso_size/gso_segs */ WARN_ON_ONCE(skb_cloned(skb)); @@ -993,13 +998,13 @@ static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, /* Avoid the costly divide in the normal * non-TSO case. */ - skb_shinfo(skb)->gso_segs = 1; - skb_shinfo(skb)->gso_size = 0; - skb_shinfo(skb)->gso_type = 0; + shinfo->gso_segs = 1; + shinfo->gso_size = 0; + shinfo->gso_type = 0; } else { - skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss_now); - skb_shinfo(skb)->gso_size = mss_now; - skb_shinfo(skb)->gso_type = sk->sk_gso_type; + shinfo->gso_segs = DIV_ROUND_UP(skb->len, mss_now); + shinfo->gso_size = mss_now; + shinfo->gso_type = sk->sk_gso_type; } } @@ -1146,6 +1151,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, */ static void __pskb_trim_head(struct sk_buff *skb, int len) { + struct skb_shared_info *shinfo; int i, k, eat; eat = min_t(int, len, skb_headlen(skb)); @@ -1157,23 +1163,24 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) } eat = len; k = 0; - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); + shinfo = skb_shinfo(skb); + for (i = 0; i < shinfo->nr_frags; i++) { + int size = skb_frag_size(&shinfo->frags[i]); if (size <= eat) { skb_frag_unref(skb, i); eat -= size; } else { - skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; + shinfo->frags[k] = shinfo->frags[i]; if (eat) { - skb_shinfo(skb)->frags[k].page_offset += eat; - skb_frag_size_sub(&skb_shinfo(skb)->frags[k], eat); + shinfo->frags[k].page_offset += eat; + skb_frag_size_sub(&shinfo->frags[k], eat); eat = 0; } k++; } } - skb_shinfo(skb)->nr_frags = k; + shinfo->nr_frags = k; skb_reset_tail_pointer(skb); skb->data_len -= len; @@ -1378,23 +1385,51 @@ static void tcp_cwnd_validate(struct sock *sk) } } -/* Returns the portion of skb which can be sent right away without - * introducing MSS oddities to segment boundaries. In rare cases where - * mss_now != mss_cache, we will request caller to create a small skb - * per input skb which could be mostly avoided here (if desired). - * - * We explicitly want to create a request for splitting write queue tail - * to a small skb for Nagle purposes while avoiding unnecessary modulos, - * thus all the complexity (cwnd_len is always MSS multiple which we - * return whenever allowed by the other factors). Basically we need the - * modulo only when the receiver window alone is the limiting factor or - * when we would be allowed to send the split-due-to-Nagle skb fully. +/* Minshall's variant of the Nagle send check. */ +static bool tcp_minshall_check(const struct tcp_sock *tp) +{ + return after(tp->snd_sml, tp->snd_una) && + !after(tp->snd_sml, tp->snd_nxt); +} + +/* Update snd_sml if this skb is under mss + * Note that a TSO packet might end with a sub-mss segment + * The test is really : + * if ((skb->len % mss) != 0) + * tp->snd_sml = TCP_SKB_CB(skb)->end_seq; + * But we can avoid doing the divide again given we already have + * skb_pcount = skb->len / mss_now */ -static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb, - unsigned int mss_now, unsigned int max_segs) +static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now, + const struct sk_buff *skb) +{ + if (skb->len < tcp_skb_pcount(skb) * mss_now) + tp->snd_sml = TCP_SKB_CB(skb)->end_seq; +} + +/* Return false, if packet can be sent now without violation Nagle's rules: + * 1. It is full sized. (provided by caller in %partial bool) + * 2. Or it contains FIN. (already checked by caller) + * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. + * 4. Or TCP_CORK is not set, and all sent packets are ACKed. + * With Minshall's modification: all sent small packets are ACKed. + */ +static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, + unsigned int mss_now, int nonagle) +{ + return partial && + ((nonagle & TCP_NAGLE_CORK) || + (!nonagle && tp->packets_out && tcp_minshall_check(tp))); +} +/* Returns the portion of skb which can be sent right away */ +static unsigned int tcp_mss_split_point(const struct sock *sk, + const struct sk_buff *skb, + unsigned int mss_now, + unsigned int max_segs, + int nonagle) { const struct tcp_sock *tp = tcp_sk(sk); - u32 needed, window, max_len; + u32 partial, needed, window, max_len; window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; max_len = mss_now * max_segs; @@ -1407,7 +1442,15 @@ static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_b if (max_len <= needed) return max_len; - return needed - needed % mss_now; + partial = needed % mss_now; + /* If last segment is not a full MSS, check if Nagle rules allow us + * to include this last segment in this skb. + * Otherwise, we'll split the skb at last MSS boundary + */ + if (tcp_nagle_check(partial != 0, tp, mss_now, nonagle)) + return needed - partial; + + return needed; } /* Can at least one segment of SKB be sent right now, according to the @@ -1447,28 +1490,6 @@ static int tcp_init_tso_segs(const struct sock *sk, struct sk_buff *skb, return tso_segs; } -/* Minshall's variant of the Nagle send check. */ -static inline bool tcp_minshall_check(const struct tcp_sock *tp) -{ - return after(tp->snd_sml, tp->snd_una) && - !after(tp->snd_sml, tp->snd_nxt); -} - -/* Return false, if packet can be sent now without violation Nagle's rules: - * 1. It is full sized. - * 2. Or it contains FIN. (already checked by caller) - * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. - * 4. Or TCP_CORK is not set, and all sent packets are ACKed. - * With Minshall's modification: all sent small packets are ACKed. - */ -static inline bool tcp_nagle_check(const struct tcp_sock *tp, - const struct sk_buff *skb, - unsigned int mss_now, int nonagle) -{ - return skb->len < mss_now && - ((nonagle & TCP_NAGLE_CORK) || - (!nonagle && tp->packets_out && tcp_minshall_check(tp))); -} /* Return true if the Nagle test allows this packet to be * sent now. @@ -1489,7 +1510,7 @@ static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buf if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) return true; - if (!tcp_nagle_check(tp, skb, cur_mss, nonagle)) + if (!tcp_nagle_check(skb->len < cur_mss, tp, cur_mss, nonagle)) return true; return false; @@ -1884,7 +1905,15 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, 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; @@ -1892,7 +1921,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, limit = tcp_mss_split_point(sk, skb, mss_now, min_t(unsigned int, cwnd_quota, - sk->sk_gso_max_segs)); + sk->sk_gso_max_segs), + nonagle); if (skb->len > limit && unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) @@ -1956,7 +1986,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) /* Schedule a loss probe in 2*RTT for SACK capable connections * in Open state, that are either limited by cwnd or application. */ - if (sysctl_tcp_early_retrans < 3 || !rtt || !tp->packets_out || + if (sysctl_tcp_early_retrans < 3 || !tp->srtt || !tp->packets_out || !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open) return false; @@ -2756,7 +2786,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, EXPORT_SYMBOL(tcp_make_synack); /* Do all connect socket setups that can be done AF independent. */ -void tcp_connect_init(struct sock *sk) +static void tcp_connect_init(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 8b97d71e193b..1f2d37613c9e 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -38,7 +38,7 @@ MODULE_DESCRIPTION("TCP cwnd snooper"); MODULE_LICENSE("GPL"); MODULE_VERSION("1.1"); -static int port __read_mostly = 0; +static int port __read_mostly; MODULE_PARM_DESC(port, "Port to match (0=all)"); module_param(port, int, 0); @@ -46,7 +46,7 @@ static unsigned int bufsize __read_mostly = 4096; MODULE_PARM_DESC(bufsize, "Log buffer size in packets (4096)"); module_param(bufsize, uint, 0); -static unsigned int fwmark __read_mostly = 0; +static unsigned int fwmark __read_mostly; MODULE_PARM_DESC(fwmark, "skb mark to match (0=no mark)"); module_param(fwmark, uint, 0); diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index a347a078ee07..1a8d271f994d 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -3,7 +3,7 @@ * YeAH TCP * * For further details look at: - * http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf + * https://web.archive.org/web/20080316215752/http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf * */ #include <linux/mm.h> @@ -15,13 +15,13 @@ #include "tcp_vegas.h" -#define TCP_YEAH_ALPHA 80 //lin number of packets queued at the bottleneck -#define TCP_YEAH_GAMMA 1 //lin fraction of queue to be removed per rtt -#define TCP_YEAH_DELTA 3 //log minimum fraction of cwnd to be removed on loss -#define TCP_YEAH_EPSILON 1 //log maximum fraction to be removed on early decongestion -#define TCP_YEAH_PHY 8 //lin maximum delta from base -#define TCP_YEAH_RHO 16 //lin minimum number of consecutive rtt to consider competition on loss -#define TCP_YEAH_ZETA 50 //lin minimum number of state switchs to reset reno_count +#define TCP_YEAH_ALPHA 80 /* number of packets queued at the bottleneck */ +#define TCP_YEAH_GAMMA 1 /* fraction of queue to be removed per rtt */ +#define TCP_YEAH_DELTA 3 /* log minimum fraction of cwnd to be removed on loss */ +#define TCP_YEAH_EPSILON 1 /* log maximum fraction to be removed on early decongestion */ +#define TCP_YEAH_PHY 8 /* maximum delta from base */ +#define TCP_YEAH_RHO 16 /* minimum number of consecutive rtt to consider competition on loss */ +#define TCP_YEAH_ZETA 50 /* minimum number of state switches to reset reno_count */ #define TCP_SCALABLE_AI_CNT 100U @@ -214,9 +214,9 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) { if (yeah->doing_reno_now < TCP_YEAH_RHO) { reduction = yeah->lastQ; - reduction = min( reduction, max(tp->snd_cwnd>>1, 2U) ); + reduction = min(reduction, max(tp->snd_cwnd>>1, 2U)); - reduction = max( reduction, tp->snd_cwnd >> TCP_YEAH_DELTA); + reduction = max(reduction, tp->snd_cwnd >> TCP_YEAH_DELTA); } else reduction = max(tp->snd_cwnd>>1, 2U); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a7e4729e974b..77bd16fa9f34 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -223,7 +223,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - rand = net_random(); + rand = prandom_u32(); first = (((u64)rand * remaining) >> 32) + low; /* * force rand to be an odd multiple of UDP_HTABLE_SIZE @@ -902,7 +902,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, * Get and verify the address. */ if (msg->msg_name) { - struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) { @@ -986,7 +986,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, fl4 = &fl4_stack; flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, - inet_sk_flowi_flags(sk)|FLOWI_FLAG_CAN_SLEEP, + inet_sk_flowi_flags(sk), faddr, saddr, dport, inet->inet_sport); security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); @@ -1226,7 +1226,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); - struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; unsigned int ulen, copied; int peeked, off = 0; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 79c62bdcd3c5..88b4023ecfcf 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -14,6 +14,17 @@ #include <net/udp.h> #include <net/protocol.h> +static DEFINE_SPINLOCK(udp_offload_lock); +static struct udp_offload_priv __rcu *udp_offload_base __read_mostly; + +#define udp_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&udp_offload_lock)) + +struct udp_offload_priv { + struct udp_offload *offload; + struct rcu_head rcu; + struct udp_offload_priv __rcu *next; +}; + static int udp4_ufo_send_check(struct sk_buff *skb) { if (!pskb_may_pull(skb, sizeof(struct udphdr))) @@ -89,10 +100,143 @@ out: return segs; } +int udp_add_offload(struct udp_offload *uo) +{ + struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_ATOMIC); + + if (!new_offload) + return -ENOMEM; + + new_offload->offload = uo; + + spin_lock(&udp_offload_lock); + new_offload->next = udp_offload_base; + rcu_assign_pointer(udp_offload_base, new_offload); + spin_unlock(&udp_offload_lock); + + return 0; +} +EXPORT_SYMBOL(udp_add_offload); + +static void udp_offload_free_routine(struct rcu_head *head) +{ + struct udp_offload_priv *ou_priv = container_of(head, struct udp_offload_priv, rcu); + kfree(ou_priv); +} + +void udp_del_offload(struct udp_offload *uo) +{ + struct udp_offload_priv __rcu **head = &udp_offload_base; + struct udp_offload_priv *uo_priv; + + spin_lock(&udp_offload_lock); + + uo_priv = udp_deref_protected(*head); + for (; uo_priv != NULL; + uo_priv = udp_deref_protected(*head)) { + if (uo_priv->offload == uo) { + rcu_assign_pointer(*head, + udp_deref_protected(uo_priv->next)); + goto unlock; + } + head = &uo_priv->next; + } + pr_warn("udp_del_offload: didn't find offload for port %d\n", ntohs(uo->port)); +unlock: + spin_unlock(&udp_offload_lock); + if (uo_priv != NULL) + call_rcu(&uo_priv->rcu, udp_offload_free_routine); +} +EXPORT_SYMBOL(udp_del_offload); + +static struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb) +{ + struct udp_offload_priv *uo_priv; + struct sk_buff *p, **pp = NULL; + struct udphdr *uh, *uh2; + unsigned int hlen, off; + int flush = 1; + + if (NAPI_GRO_CB(skb)->udp_mark || + (!skb->encapsulation && skb->ip_summed != CHECKSUM_COMPLETE)) + goto out; + + /* mark that this skb passed once through the udp gro layer */ + NAPI_GRO_CB(skb)->udp_mark = 1; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*uh); + uh = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) { + uh = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!uh)) + goto out; + } + + rcu_read_lock(); + uo_priv = rcu_dereference(udp_offload_base); + for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) { + if (uo_priv->offload->port == uh->dest && + uo_priv->offload->callbacks.gro_receive) + goto unflush; + } + goto out_unlock; + +unflush: + flush = 0; + + for (p = *head; p; p = p->next) { + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + uh2 = (struct udphdr *)(p->data + off); + if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + } + + skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ + pp = uo_priv->offload->callbacks.gro_receive(head, skb); + +out_unlock: + rcu_read_unlock(); +out: + NAPI_GRO_CB(skb)->flush |= flush; + return pp; +} + +static int udp_gro_complete(struct sk_buff *skb, int nhoff) +{ + struct udp_offload_priv *uo_priv; + __be16 newlen = htons(skb->len - nhoff); + struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); + int err = -ENOSYS; + + uh->len = newlen; + + rcu_read_lock(); + + uo_priv = rcu_dereference(udp_offload_base); + for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) { + if (uo_priv->offload->port == uh->dest && + uo_priv->offload->callbacks.gro_complete) + break; + } + + if (uo_priv != NULL) + err = uo_priv->offload->callbacks.gro_complete(skb, nhoff + sizeof(struct udphdr)); + + rcu_read_unlock(); + return err; +} + static const struct net_offload udpv4_offload = { .callbacks = { .gso_send_check = udp4_ufo_send_check, .gso_segment = udp4_ufo_fragment, + .gro_receive = udp_gro_receive, + .gro_complete = udp_gro_complete, }, }; diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index e3db3f915114..71acd0014f2d 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -48,7 +48,7 @@ static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4); skb_set_network_header(skb, -x->props.header_len - - hdrlen + (XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph))); + hdrlen + (XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph))); if (x->sel.family != AF_INET6) skb->network_header += IPV4_BEET_PHMAXLEN; skb->mac_header = skb->network_header + diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 0b2a0641526a..542074c00c78 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -16,7 +16,7 @@ static int xfrm4_init_flags(struct xfrm_state *x) { - if (ipv4_config.no_pmtu_disc) + if (xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc) x->props.flags |= XFRM_STATE_NOPMTUDISC; return 0; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4b6b720971b9..fdbfeca36d63 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -442,6 +442,8 @@ static int inet6_netconf_msgsize_devconf(int type) if (type == -1 || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); #endif + if (type == -1 || type == NETCONFA_PROXY_NEIGH) + size += nla_total_size(4); return size; } @@ -475,6 +477,10 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, devconf->mc_forwarding) < 0) goto nla_put_failure; #endif + if ((type == -1 || type == NETCONFA_PROXY_NEIGH) && + nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0) + goto nla_put_failure; + return nlmsg_end(skb, nlh); nla_put_failure: @@ -509,6 +515,7 @@ errout: static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, + [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, }; static int inet6_netconf_get_devconf(struct sk_buff *in_skb, @@ -834,6 +841,8 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, goto out; } + neigh_parms_data_state_setall(idev->nd_parms); + ifa->addr = *addr; if (peer_addr) ifa->peer_addr = *peer_addr; @@ -891,15 +900,95 @@ out: goto out2; } +enum cleanup_prefix_rt_t { + CLEANUP_PREFIX_RT_NOP, /* no cleanup action for prefix route */ + CLEANUP_PREFIX_RT_DEL, /* delete the prefix route */ + CLEANUP_PREFIX_RT_EXPIRE, /* update the lifetime of the prefix route */ +}; + +/* + * Check, whether the prefix for ifp would still need a prefix route + * after deleting ifp. The function returns one of the CLEANUP_PREFIX_RT_* + * constants. + * + * 1) we don't purge prefix if address was not permanent. + * prefix is managed by its own lifetime. + * 2) we also don't purge, if the address was IFA_F_NOPREFIXROUTE. + * 3) if there are no addresses, delete prefix. + * 4) if there are still other permanent address(es), + * corresponding prefix is still permanent. + * 5) if there are still other addresses with IFA_F_NOPREFIXROUTE, + * don't purge the prefix, assume user space is managing it. + * 6) otherwise, update prefix lifetime to the + * longest valid lifetime among the corresponding + * addresses on the device. + * Note: subsequent RA will update lifetime. + **/ +static enum cleanup_prefix_rt_t +check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) +{ + struct inet6_ifaddr *ifa; + struct inet6_dev *idev = ifp->idev; + unsigned long lifetime; + enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_DEL; + + *expires = jiffies; + + list_for_each_entry(ifa, &idev->addr_list, if_list) { + if (ifa == ifp) + continue; + if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr, + ifp->prefix_len)) + continue; + if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE)) + return CLEANUP_PREFIX_RT_NOP; + + action = CLEANUP_PREFIX_RT_EXPIRE; + + spin_lock(&ifa->lock); + + lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ); + /* + * Note: Because this address is + * not permanent, lifetime < + * LONG_MAX / HZ here. + */ + if (time_before(*expires, ifa->tstamp + lifetime * HZ)) + *expires = ifa->tstamp + lifetime * HZ; + spin_unlock(&ifa->lock); + } + + return action; +} + +static void +cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt) +{ + struct rt6_info *rt; + + rt = addrconf_get_prefix_route(&ifp->addr, + ifp->prefix_len, + ifp->idev->dev, + 0, RTF_GATEWAY | RTF_DEFAULT); + if (rt) { + if (del_rt) + ip6_del_rt(rt); + else { + if (!(rt->rt6i_flags & RTF_EXPIRES)) + rt6_set_expires(rt, expires); + ip6_rt_put(rt); + } + } +} + + /* This function wants to get referenced ifp and releases it before return */ static void ipv6_del_addr(struct inet6_ifaddr *ifp) { - struct inet6_ifaddr *ifa, *ifn; - struct inet6_dev *idev = ifp->idev; int state; - int deleted = 0, onlink = 0; - unsigned long expires = jiffies; + enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP; + unsigned long expires; spin_lock_bh(&ifp->state_lock); state = ifp->state; @@ -913,7 +1002,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) hlist_del_init_rcu(&ifp->addr_lst); spin_unlock_bh(&addrconf_hash_lock); - write_lock_bh(&idev->lock); + write_lock_bh(&ifp->idev->lock); if (ifp->flags&IFA_F_TEMPORARY) { list_del(&ifp->tmp_list); @@ -924,45 +1013,13 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) __in6_ifa_put(ifp); } - list_for_each_entry_safe(ifa, ifn, &idev->addr_list, if_list) { - if (ifa == ifp) { - list_del_init(&ifp->if_list); - __in6_ifa_put(ifp); + if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE)) + action = check_cleanup_prefix_route(ifp, &expires); - if (!(ifp->flags & IFA_F_PERMANENT) || onlink > 0) - break; - deleted = 1; - continue; - } else if (ifp->flags & IFA_F_PERMANENT) { - if (ipv6_prefix_equal(&ifa->addr, &ifp->addr, - ifp->prefix_len)) { - if (ifa->flags & IFA_F_PERMANENT) { - onlink = 1; - if (deleted) - break; - } else { - unsigned long lifetime; - - if (!onlink) - onlink = -1; - - spin_lock(&ifa->lock); - - lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ); - /* - * Note: Because this address is - * not permanent, lifetime < - * LONG_MAX / HZ here. - */ - if (time_before(expires, - ifa->tstamp + lifetime * HZ)) - expires = ifa->tstamp + lifetime * HZ; - spin_unlock(&ifa->lock); - } - } - } - } - write_unlock_bh(&idev->lock); + list_del_init(&ifp->if_list); + __in6_ifa_put(ifp); + + write_unlock_bh(&ifp->idev->lock); addrconf_del_dad_timer(ifp); @@ -970,41 +1027,9 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) inet6addr_notifier_call_chain(NETDEV_DOWN, ifp); - /* - * Purge or update corresponding prefix - * - * 1) we don't purge prefix here if address was not permanent. - * prefix is managed by its own lifetime. - * 2) if there're no addresses, delete prefix. - * 3) if there're still other permanent address(es), - * corresponding prefix is still permanent. - * 4) otherwise, update prefix lifetime to the - * longest valid lifetime among the corresponding - * addresses on the device. - * Note: subsequent RA will update lifetime. - * - * --yoshfuji - */ - if ((ifp->flags & IFA_F_PERMANENT) && onlink < 1) { - struct in6_addr prefix; - struct rt6_info *rt; - - ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len); - - rt = addrconf_get_prefix_route(&prefix, - ifp->prefix_len, - ifp->idev->dev, - 0, RTF_GATEWAY | RTF_DEFAULT); - - if (rt) { - if (onlink == 0) { - ip6_del_rt(rt); - rt = NULL; - } else if (!(rt->rt6i_flags & RTF_EXPIRES)) { - rt6_set_expires(rt, expires); - } - } - ip6_rt_put(rt); + if (action != CLEANUP_PREFIX_RT_NOP) { + cleanup_prefix_route(ifp, expires, + action == CLEANUP_PREFIX_RT_DEL); } /* clean up prefsrc entries */ @@ -1024,7 +1049,7 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i u32 addr_flags; unsigned long now = jiffies; - write_lock(&idev->lock); + write_lock_bh(&idev->lock); if (ift) { spin_lock_bh(&ift->lock); memcpy(&addr.s6_addr[8], &ift->addr.s6_addr[8], 8); @@ -1036,7 +1061,7 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i retry: in6_dev_hold(idev); if (idev->cnf.use_tempaddr <= 0) { - write_unlock(&idev->lock); + write_unlock_bh(&idev->lock); pr_info("%s: use_tempaddr is disabled\n", __func__); in6_dev_put(idev); ret = -1; @@ -1046,7 +1071,7 @@ retry: if (ifp->regen_count++ >= idev->cnf.regen_max_retry) { idev->cnf.use_tempaddr = -1; /*XXX*/ spin_unlock_bh(&ifp->lock); - write_unlock(&idev->lock); + write_unlock_bh(&idev->lock); pr_warn("%s: regeneration time exceeded - disabled temporary address support\n", __func__); in6_dev_put(idev); @@ -1071,8 +1096,8 @@ retry: regen_advance = idev->cnf.regen_max_retry * idev->cnf.dad_transmits * - idev->nd_parms->retrans_time / HZ; - write_unlock(&idev->lock); + NEIGH_VAR(idev->nd_parms, RETRANS_TIME) / HZ; + write_unlock_bh(&idev->lock); /* A temporary address is created only if this calculated Preferred * Lifetime is greater than REGEN_ADVANCE time units. In particular, @@ -1099,7 +1124,7 @@ retry: in6_dev_put(idev); pr_info("%s: retry temporary address regeneration\n", __func__); tmpaddr = &addr; - write_lock(&idev->lock); + write_lock_bh(&idev->lock); goto retry; } @@ -1200,7 +1225,7 @@ static int ipv6_get_saddr_eval(struct net *net, * | d is scope of the destination. * B-d | \ * | \ <- smaller scope is better if - * B-15 | \ if scope is enough for destinaion. + * B-15 | \ if scope is enough for destination. * | ret = B - scope (-1 <= scope >= d <= 15). * d-C-1 | / * |/ <- greater is better @@ -1407,12 +1432,14 @@ try_nextdev: EXPORT_SYMBOL(ipv6_dev_get_saddr); int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, - unsigned char banned_flags) + u32 banned_flags) { struct inet6_ifaddr *ifp; int err = -EADDRNOTAVAIL; - list_for_each_entry(ifp, &idev->addr_list, if_list) { + list_for_each_entry_reverse(ifp, &idev->addr_list, if_list) { + if (ifp->scope > IFA_LINK) + break; if (ifp->scope == IFA_LINK && !(ifp->flags & banned_flags)) { *addr = ifp->addr; @@ -1424,7 +1451,7 @@ int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, } int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, - unsigned char banned_flags) + u32 banned_flags) { struct inet6_dev *idev; int err = -EADDRNOTAVAIL; @@ -1816,6 +1843,7 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) return addrconf_ifid_sit(eui, dev); case ARPHRD_IPGRE: return addrconf_ifid_gre(eui, dev); + case ARPHRD_6LOWPAN: case ARPHRD_IEEE802154: return addrconf_ifid_eui64(eui, dev); case ARPHRD_IEEE1394: @@ -1832,7 +1860,9 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - list_for_each_entry(ifp, &idev->addr_list, if_list) { + list_for_each_entry_reverse(ifp, &idev->addr_list, if_list) { + if (ifp->scope > IFA_LINK) + break; if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) { memcpy(eui, ifp->addr.s6_addr+8, 8); err = 0; @@ -1888,7 +1918,8 @@ static void ipv6_regen_rndid(unsigned long data) expires = jiffies + idev->cnf.temp_prefered_lft * HZ - - idev->cnf.regen_max_retry * idev->cnf.dad_transmits * idev->nd_parms->retrans_time - + idev->cnf.regen_max_retry * idev->cnf.dad_transmits * + NEIGH_VAR(idev->nd_parms, RETRANS_TIME) - idev->cnf.max_desync_factor * HZ; if (time_before(expires, jiffies)) { pr_warn("%s: too short regeneration interval; timer disabled for %s\n", @@ -2016,6 +2047,73 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev) return idev; } +static void manage_tempaddrs(struct inet6_dev *idev, + struct inet6_ifaddr *ifp, + __u32 valid_lft, __u32 prefered_lft, + bool create, unsigned long now) +{ + u32 flags; + struct inet6_ifaddr *ift; + + read_lock_bh(&idev->lock); + /* update all temporary addresses in the list */ + list_for_each_entry(ift, &idev->tempaddr_list, tmp_list) { + int age, max_valid, max_prefered; + + if (ifp != ift->ifpub) + continue; + + /* RFC 4941 section 3.3: + * If a received option will extend the lifetime of a public + * address, the lifetimes of temporary addresses should + * be extended, subject to the overall constraint that no + * temporary addresses should ever remain "valid" or "preferred" + * for a time longer than (TEMP_VALID_LIFETIME) or + * (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR), respectively. + */ + age = (now - ift->cstamp) / HZ; + max_valid = idev->cnf.temp_valid_lft - age; + if (max_valid < 0) + max_valid = 0; + + max_prefered = idev->cnf.temp_prefered_lft - + idev->cnf.max_desync_factor - age; + if (max_prefered < 0) + max_prefered = 0; + + if (valid_lft > max_valid) + valid_lft = max_valid; + + if (prefered_lft > max_prefered) + prefered_lft = max_prefered; + + spin_lock(&ift->lock); + flags = ift->flags; + ift->valid_lft = valid_lft; + ift->prefered_lft = prefered_lft; + ift->tstamp = now; + if (prefered_lft > 0) + ift->flags &= ~IFA_F_DEPRECATED; + + spin_unlock(&ift->lock); + if (!(flags&IFA_F_TENTATIVE)) + ipv6_ifa_notify(0, ift); + } + + if ((create || list_empty(&idev->tempaddr_list)) && + idev->cnf.use_tempaddr > 0) { + /* When a new public address is created as described + * in [ADDRCONF], also create a new temporary address. + * Also create a temporary address if it's enabled but + * no temporary address currently exists. + */ + read_unlock_bh(&idev->lock); + ipv6_create_tempaddr(ifp, NULL); + } else { + read_unlock_bh(&idev->lock); + } +} + void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) { struct prefix_info *pinfo; @@ -2170,6 +2268,7 @@ ok: return; } + ifp->flags |= IFA_F_MANAGETEMPADDR; update_lft = 0; create = 1; ifp->cstamp = jiffies; @@ -2178,9 +2277,8 @@ ok: } if (ifp) { - int flags; + u32 flags; unsigned long now; - struct inet6_ifaddr *ift; u32 stored_lft; /* update lifetime (RFC2462 5.5.3 e) */ @@ -2221,70 +2319,8 @@ ok: } else spin_unlock(&ifp->lock); - read_lock_bh(&in6_dev->lock); - /* update all temporary addresses in the list */ - list_for_each_entry(ift, &in6_dev->tempaddr_list, - tmp_list) { - int age, max_valid, max_prefered; - - if (ifp != ift->ifpub) - continue; - - /* - * RFC 4941 section 3.3: - * If a received option will extend the lifetime - * of a public address, the lifetimes of - * temporary addresses should be extended, - * subject to the overall constraint that no - * temporary addresses should ever remain - * "valid" or "preferred" for a time longer than - * (TEMP_VALID_LIFETIME) or - * (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR), - * respectively. - */ - age = (now - ift->cstamp) / HZ; - max_valid = in6_dev->cnf.temp_valid_lft - age; - if (max_valid < 0) - max_valid = 0; - - max_prefered = in6_dev->cnf.temp_prefered_lft - - in6_dev->cnf.max_desync_factor - - age; - if (max_prefered < 0) - max_prefered = 0; - - if (valid_lft > max_valid) - valid_lft = max_valid; - - if (prefered_lft > max_prefered) - prefered_lft = max_prefered; - - spin_lock(&ift->lock); - flags = ift->flags; - ift->valid_lft = valid_lft; - ift->prefered_lft = prefered_lft; - ift->tstamp = now; - if (prefered_lft > 0) - ift->flags &= ~IFA_F_DEPRECATED; - - spin_unlock(&ift->lock); - if (!(flags&IFA_F_TENTATIVE)) - ipv6_ifa_notify(0, ift); - } - - if ((create || list_empty(&in6_dev->tempaddr_list)) && in6_dev->cnf.use_tempaddr > 0) { - /* - * When a new public address is created as - * described in [ADDRCONF], also create a new - * temporary address. Also create a temporary - * address if it's enabled but no temporary - * address currently exists. - */ - read_unlock_bh(&in6_dev->lock); - ipv6_create_tempaddr(ifp, NULL); - } else { - read_unlock_bh(&in6_dev->lock); - } + manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft, + create, now); in6_ifa_put(ifp); addrconf_verify(0); @@ -2363,10 +2399,11 @@ err_exit: /* * Manual configuration of address on an interface */ -static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *pfx, +static int inet6_addr_add(struct net *net, int ifindex, + const struct in6_addr *pfx, const struct in6_addr *peer_pfx, - unsigned int plen, __u8 ifa_flags, __u32 prefered_lft, - __u32 valid_lft) + unsigned int plen, __u32 ifa_flags, + __u32 prefered_lft, __u32 valid_lft) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; @@ -2385,6 +2422,9 @@ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *p if (!valid_lft || prefered_lft > valid_lft) return -EINVAL; + if (ifa_flags & IFA_F_MANAGETEMPADDR && plen != 64) + return -EINVAL; + dev = __dev_get_by_index(net, ifindex); if (!dev) return -ENODEV; @@ -2417,14 +2457,20 @@ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *p valid_lft, prefered_lft); if (!IS_ERR(ifp)) { - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev, - expires, flags); + if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) { + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev, + expires, flags); + } + /* * Note that section 3.1 of RFC 4429 indicates * that the Optimistic flag should not be set for * manually configured addresses */ addrconf_dad_start(ifp); + if (ifa_flags & IFA_F_MANAGETEMPADDR) + manage_tempaddrs(idev, ifp, valid_lft, prefered_lft, + true, jiffies); in6_ifa_put(ifp); addrconf_verify(0); return 0; @@ -2611,8 +2657,18 @@ 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, false); @@ -2660,7 +2716,8 @@ static void addrconf_dev_config(struct net_device *dev) (dev->type != ARPHRD_INFINIBAND) && (dev->type != ARPHRD_IEEE802154) && (dev->type != ARPHRD_IEEE1394) && - (dev->type != ARPHRD_TUNNEL6)) { + (dev->type != ARPHRD_TUNNEL6) && + (dev->type != ARPHRD_6LOWPAN)) { /* Alas, we support only Ethernet autoconfiguration. */ return; } @@ -2726,6 +2783,8 @@ static void addrconf_gre_config(struct net_device *dev) ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) addrconf_add_linklocal(idev, &addr); + else + addrconf_prefix_route(&addr, 64, dev, 0, 0); } #endif @@ -2857,7 +2916,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, } /* - * MTU falled under IPV6_MIN_MTU. + * if MTU under IPV6_MIN_MTU. * Stop IPv6 on this interface. */ @@ -3083,7 +3142,7 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) if (ifp->flags & IFA_F_OPTIMISTIC) rand_num = 0; else - rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1); + rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1); ifp->dad_probes = idev->cnf.dad_transmits; addrconf_mod_dad_timer(ifp, rand_num); @@ -3096,7 +3155,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp) addrconf_join_solict(dev, &ifp->addr); - net_srandom(ifp->addr.s6_addr32[3]); + prandom_seed((__force u32) ifp->addr.s6_addr32[3]); read_lock_bh(&idev->lock); spin_lock(&ifp->lock); @@ -3178,7 +3237,8 @@ static void addrconf_dad_timer(unsigned long data) } ifp->dad_probes--; - addrconf_mod_dad_timer(ifp, ifp->idev->nd_parms->retrans_time); + addrconf_mod_dad_timer(ifp, + NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME)); spin_unlock(&ifp->lock); write_unlock(&idev->lock); @@ -3195,7 +3255,9 @@ static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp) struct inet6_ifaddr *ifpiter; struct inet6_dev *idev = ifp->idev; - list_for_each_entry(ifpiter, &idev->addr_list, if_list) { + list_for_each_entry_reverse(ifpiter, &idev->addr_list, if_list) { + if (ifpiter->scope > IFA_LINK) + break; if (ifp != ifpiter && ifpiter->scope == IFA_LINK && (ifpiter->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE| IFA_F_OPTIMISTIC|IFA_F_DADFAILED)) == @@ -3371,7 +3433,7 @@ static int if6_seq_show(struct seq_file *seq, void *v) ifp->idev->dev->ifindex, ifp->prefix_len, ifp->scope, - ifp->flags, + (u8) ifp->flags, ifp->idev->dev->name); return 0; } @@ -3518,7 +3580,7 @@ restart: !(ifp->flags&IFA_F_TENTATIVE)) { unsigned long regen_advance = ifp->idev->cnf.regen_max_retry * ifp->idev->cnf.dad_transmits * - ifp->idev->nd_parms->retrans_time / HZ; + NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME) / HZ; if (age >= ifp->prefered_lft - regen_advance) { struct inet6_ifaddr *ifpub = ifp->ifpub; @@ -3593,6 +3655,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = { [IFA_ADDRESS] = { .len = sizeof(struct in6_addr) }, [IFA_LOCAL] = { .len = sizeof(struct in6_addr) }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, + [IFA_FLAGS] = { .len = sizeof(u32) }, }; static int @@ -3616,16 +3679,22 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) return inet6_addr_del(net, ifm->ifa_index, pfx, ifm->ifa_prefixlen); } -static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, +static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, u32 prefered_lft, u32 valid_lft) { u32 flags; clock_t expires; unsigned long timeout; + bool was_managetempaddr; + bool had_prefixroute; if (!valid_lft || (prefered_lft > valid_lft)) return -EINVAL; + if (ifa_flags & IFA_F_MANAGETEMPADDR && + (ifp->flags & IFA_F_TEMPORARY || ifp->prefix_len != 64)) + return -EINVAL; + timeout = addrconf_timeout_fixup(valid_lft, HZ); if (addrconf_finite_timeout(timeout)) { expires = jiffies_to_clock_t(timeout * HZ); @@ -3645,7 +3714,13 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, } spin_lock_bh(&ifp->lock); - ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS)) | ifa_flags; + was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR; + had_prefixroute = ifp->flags & IFA_F_PERMANENT && + !(ifp->flags & IFA_F_NOPREFIXROUTE); + ifp->flags &= ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | + IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | + IFA_F_NOPREFIXROUTE); + ifp->flags |= ifa_flags; ifp->tstamp = jiffies; ifp->valid_lft = valid_lft; ifp->prefered_lft = prefered_lft; @@ -3654,8 +3729,30 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, if (!(ifp->flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev, - expires, flags); + if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) { + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev, + expires, flags); + } else if (had_prefixroute) { + enum cleanup_prefix_rt_t action; + unsigned long rt_expires; + + write_lock_bh(&ifp->idev->lock); + action = check_cleanup_prefix_route(ifp, &rt_expires); + write_unlock_bh(&ifp->idev->lock); + + if (action != CLEANUP_PREFIX_RT_NOP) { + cleanup_prefix_route(ifp, rt_expires, + action == CLEANUP_PREFIX_RT_DEL); + } + } + + if (was_managetempaddr || ifp->flags & IFA_F_MANAGETEMPADDR) { + if (was_managetempaddr && !(ifp->flags & IFA_F_MANAGETEMPADDR)) + valid_lft = prefered_lft = 0; + manage_tempaddrs(ifp->idev, ifp, valid_lft, prefered_lft, + !was_managetempaddr, jiffies); + } + addrconf_verify(0); return 0; @@ -3671,7 +3768,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) struct inet6_ifaddr *ifa; struct net_device *dev; u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME; - u8 ifa_flags; + u32 ifa_flags; int err; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy); @@ -3698,14 +3795,17 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) if (dev == NULL) return -ENODEV; + ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; + /* We ignore other flags so far. */ - ifa_flags = ifm->ifa_flags & (IFA_F_NODAD | IFA_F_HOMEADDRESS); + ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | + IFA_F_NOPREFIXROUTE; ifa = ipv6_get_ifaddr(net, pfx, dev, 1); if (ifa == NULL) { /* * It would be best to check for !NLM_F_CREATE here but - * userspace alreay relies on not having to provide this. + * userspace already relies on not having to provide this. */ return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx, ifm->ifa_prefixlen, ifa_flags, @@ -3723,7 +3823,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) return err; } -static void put_ifaddrmsg(struct nlmsghdr *nlh, u8 prefixlen, u8 flags, +static void put_ifaddrmsg(struct nlmsghdr *nlh, u8 prefixlen, u32 flags, u8 scope, int ifindex) { struct ifaddrmsg *ifm; @@ -3766,7 +3866,8 @@ static inline int inet6_ifaddr_msgsize(void) return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(16) /* IFA_LOCAL */ + nla_total_size(16) /* IFA_ADDRESS */ - + nla_total_size(sizeof(struct ifa_cacheinfo)); + + nla_total_size(sizeof(struct ifa_cacheinfo)) + + nla_total_size(4) /* IFA_FLAGS */; } static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, @@ -3815,6 +3916,9 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) goto error; + if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0) + goto error; + return nlmsg_end(skb, nlh); error: @@ -4218,7 +4322,7 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev) ci.max_reasm_len = IPV6_MAXPLEN; ci.tstamp = cstamp_delta(idev->tstamp); ci.reachable_time = jiffies_to_msecs(idev->nd_parms->reachable_time); - ci.retrans_time = jiffies_to_msecs(idev->nd_parms->retrans_time); + ci.retrans_time = jiffies_to_msecs(NEIGH_VAR(idev->nd_parms, RETRANS_TIME)); if (nla_put(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; nla = nla_reserve(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(s32)); @@ -4694,6 +4798,46 @@ int addrconf_sysctl_disable(struct ctl_table *ctl, int write, return ret; } +static +int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int *valp = ctl->data; + int ret; + int old, new; + + old = *valp; + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + new = *valp; + + if (write && old != new) { + struct net *net = ctl->extra2; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (valp == &net->ipv6.devconf_dflt->proxy_ndp) + inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, + NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt); + else if (valp == &net->ipv6.devconf_all->proxy_ndp) + inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); + else { + struct inet6_dev *idev = ctl->extra1; + + inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, + idev->dev->ifindex, + &idev->cnf); + } + rtnl_unlock(); + } + + return ret; +} + + static struct addrconf_sysctl_table { struct ctl_table_header *sysctl_header; @@ -4880,7 +5024,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.proxy_ndp, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = addrconf_sysctl_proxy_ndp, }, { .procname = "accept_source_route", @@ -4996,7 +5140,7 @@ static void __addrconf_sysctl_unregister(struct ipv6_devconf *p) static void addrconf_sysctl_register(struct inet6_dev *idev) { - neigh_sysctl_register(idev->dev, idev->nd_parms, "ipv6", + neigh_sysctl_register(idev->dev, idev->nd_parms, &ndisc_ifinfo_sysctl_change); __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, idev, &idev->cnf); @@ -5129,9 +5273,7 @@ int __init addrconf_init(void) addrconf_verify(0); - err = rtnl_af_register(&inet6_ops); - if (err < 0) - goto errout_af; + rtnl_af_register(&inet6_ops); err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo, NULL); @@ -5155,7 +5297,6 @@ int __init addrconf_init(void) return 0; errout: rtnl_af_unregister(&inet6_ops); -errout_af: unregister_netdevice_notifier(&ipv6_dev_notf); errlo: unregister_pernet_subsys(&addrconf_ops); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 4fbdb7046d28..d935889f1008 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -213,7 +213,7 @@ lookup_protocol: inet->mc_list = NULL; inet->rcv_tos = 0; - if (ipv4_config.no_pmtu_disc) + if (net->ipv4.sysctl_ip_no_pmtu_disc) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; @@ -661,7 +661,7 @@ int inet6_sk_rebuild_header(struct sock *sk) final_p = fl6_update_dst(&fl6, np->opt, &final); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { sk->sk_route_caps = 0; sk->sk_err_soft = -PTR_ERR(dst); @@ -683,8 +683,7 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb) if (np->rxopt.all) { if ((opt->hop && (np->rxopt.bits.hopopts || np->rxopt.bits.ohopopts)) || - ((IPV6_FLOWINFO_MASK & - *(__be32 *)skb_network_header(skb)) && + (ip6_flowinfo((struct ipv6hdr *) skb_network_header(skb)) && np->rxopt.bits.rxflow) || (opt->srcrt && (np->rxopt.bits.srcrt || np->rxopt.bits.osrcrt)) || @@ -776,6 +775,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.bindv6only = 0; net->ipv6.sysctl.icmpv6_time = 1*HZ; + net->ipv6.sysctl.flowlabel_consistency = 1; atomic_set(&net->ipv6.rt_genid, 0); err = ipv6_init_mibs(net); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 82e1da3a40b9..81e496a2e008 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -12,8 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * * Authors * diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 5a80f15a9de2..210183244689 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -383,6 +383,17 @@ bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, return found; } +/* check if this anycast address is link-local on given interface or + * is global + */ +bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, + const struct in6_addr *addr) +{ + return ipv6_chk_acast_addr(net, + (ipv6_addr_type(addr) & IPV6_ADDR_LINKLOCAL ? + dev : NULL), + addr); +} #ifdef CONFIG_PROC_FS struct ac6_iter_state { diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 93b1aa34c432..c3bf2d2e519e 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -170,7 +170,7 @@ ipv4_connected: opt = flowlabel ? flowlabel->opt : np->opt; final_p = fl6_update_dst(&fl6, opt, &final); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); err = 0; if (IS_ERR(dst)) { err = PTR_ERR(dst); @@ -205,6 +205,16 @@ out: } EXPORT_SYMBOL_GPL(ip6_datagram_connect); +int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr, + int addr_len) +{ + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, uaddr); + if (sin6->sin6_family != AF_INET6) + return -EAFNOSUPPORT; + return ip6_datagram_connect(sk, uaddr, addr_len); +} +EXPORT_SYMBOL_GPL(ip6_datagram_connect_v6_only); + void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { @@ -322,7 +332,7 @@ 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; struct sk_buff *skb, *skb2; - struct sockaddr_in6 *sin; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name); struct { struct sock_extended_err ee; struct sockaddr_in6 offender; @@ -348,7 +358,6 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) serr = SKB_EXT_ERR(skb); - sin = (struct sockaddr_in6 *)msg->msg_name; if (sin) { const unsigned char *nh = skb_network_header(skb); sin->sin6_family = AF_INET6; @@ -378,10 +387,12 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_port = 0; + if (np->rxopt.all) + ip6_datagram_recv_common_ctl(sk, msg, skb); if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) - ip6_datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_specific_ctl(sk, msg, skb); sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); @@ -429,8 +440,8 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; - struct sockaddr_in6 *sin; struct ip6_mtuinfo mtu_info; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name); int err; int copied; @@ -452,7 +463,6 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info)); - sin = (struct sockaddr_in6 *)msg->msg_name; if (sin) { sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; @@ -473,20 +483,34 @@ out: } -int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, - struct sk_buff *skb) +void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); - struct inet6_skb_parm *opt = IP6CB(skb); - unsigned char *nh = skb_network_header(skb); + bool is_ipv6 = skb->protocol == htons(ETH_P_IPV6); if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; - src_info.ipi6_ifindex = opt->iif; - src_info.ipi6_addr = ipv6_hdr(skb)->daddr; + if (is_ipv6) { + src_info.ipi6_ifindex = IP6CB(skb)->iif; + src_info.ipi6_addr = ipv6_hdr(skb)->daddr; + } else { + src_info.ipi6_ifindex = + PKTINFO_SKB_CB(skb)->ipi_ifindex; + ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr, + &src_info.ipi6_addr); + } put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } +} + +void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct inet6_skb_parm *opt = IP6CB(skb); + unsigned char *nh = skb_network_header(skb); if (np->rxopt.bits.rxhlim) { int hlim = ipv6_hdr(skb)->hop_limit; @@ -604,7 +628,13 @@ int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6); } } - return 0; +} + +void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) +{ + ip6_datagram_recv_common_ctl(sk, msg, skb); + ip6_datagram_recv_specific_ctl(sk, msg, skb); } EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl); @@ -669,7 +699,9 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) && !ipv6_chk_addr(net, &src_info->ipi6_addr, - strict ? dev : NULL, 0)) + strict ? dev : NULL, 0) && + !ipv6_chk_acast_addr_src(net, dev, + &src_info->ipi6_addr)) err = -EINVAL; else fl6->saddr = src_info->ipi6_addr; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index b8719df0366e..6eef8a7e35f2 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -12,8 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * * Authors * diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 3fd0a578329e..b4d5e1d97c1b 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -169,7 +169,7 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) return 0; } - if (r->tclass && r->tclass != ((ntohl(fl6->flowlabel) >> 20) & 0xff)) + if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel)) return 0; return 1; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index eef8d945b362..f2610e157660 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -67,6 +67,7 @@ #include <net/icmp.h> #include <net/xfrm.h> #include <net/inet_common.h> +#include <net/dsfield.h> #include <asm/uaccess.h> @@ -315,8 +316,10 @@ static void mip6_addr_swap(struct sk_buff *skb) static inline void mip6_addr_swap(struct sk_buff *skb) {} #endif -struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb, - struct sock *sk, struct flowi6 *fl6) +static struct dst_entry *icmpv6_route_lookup(struct net *net, + struct sk_buff *skb, + struct sock *sk, + struct flowi6 *fl6) { struct dst_entry *dst, *dst2; struct flowi6 fl2; @@ -410,7 +413,8 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) */ addr_type = ipv6_addr_type(&hdr->daddr); - if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0)) + if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) || + ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr)) saddr = &hdr->daddr; /* @@ -551,10 +555,13 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct dst_entry *dst; int err = 0; int hlimit; + u8 tclass; saddr = &ipv6_hdr(skb)->daddr; - if (!ipv6_unicast_destination(skb)) + if (!ipv6_unicast_destination(skb) && + !(net->ipv6.sysctl.anycast_src_echo_reply && + ipv6_anycast_destination(skb))) saddr = NULL; memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr)); @@ -599,8 +606,9 @@ static void icmpv6_echo_reply(struct sk_buff *skb) msg.offset = 0; msg.type = ICMPV6_ECHO_REPLY; + tclass = ipv6_get_dsfield(ipv6_hdr(skb)); err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl6, + sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl6, (struct rt6_info *)dst, MSG_DONTWAIT, np->dontfrag); @@ -984,7 +992,7 @@ int icmpv6_err_convert(u8 type, u8 code, int *err) EXPORT_SYMBOL(icmpv6_err_convert); #ifdef CONFIG_SYSCTL -struct ctl_table ipv6_icmp_table_template[] = { +static struct ctl_table ipv6_icmp_table_template[] = { { .procname = "ratelimit", .data = &init_net.ipv6.sysctl.icmpv6_time, diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 77bb8afb141d..c9138189415a 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -86,7 +86,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, fl6->fl6_sport = htons(ireq->ir_num); security_req_classify_flow(req, flowi6_to_flowi(fl6)); - dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); + dst = ip6_dst_lookup_flow(sk, fl6, final_p); if (IS_ERR(dst)) return NULL; @@ -216,7 +216,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, dst = __inet6_csk_dst_check(sk, np->dst_cookie); if (!dst) { - dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); + dst = ip6_dst_lookup_flow(sk, fl6, final_p); if (!IS_ERR(dst)) __inet6_csk_dst_store(sk, dst, NULL, NULL); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5550a8113a6d..075602fc6b6a 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1530,7 +1530,7 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root, } void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), - int prune, void *arg) + void *arg) { struct fib6_table *table; struct hlist_head *head; @@ -1542,7 +1542,7 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), hlist_for_each_entry_rcu(table, head, tb6_hlist) { write_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, - func, prune, arg); + func, 0, arg); write_unlock_bh(&table->tb6_lock); } } @@ -1636,7 +1636,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) gc_args.more = icmp6_dst_gc(); - fib6_clean_all(net, fib6_age, 0, NULL); + fib6_clean_all(net, fib6_age, NULL); now = jiffies; net->ipv6.ip6_rt_last_gc = now; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index e7fb7106550f..dfa41bb4e0dc 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -210,7 +210,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net, spin_lock_bh(&ip6_fl_lock); if (label == 0) { for (;;) { - fl->label = htonl(net_random())&IPV6_FLOWLABEL_MASK; + fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK; if (fl->label) { lfl = __fl_lookup(net, fl->label); if (lfl == NULL) @@ -481,11 +481,22 @@ static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, spin_unlock_bh(&ip6_sk_fl_lock); } -int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq) +int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, + int flags) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_fl_socklist *sfl; + if (flags & IPV6_FL_F_REMOTE) { + freq->flr_label = np->rcv_flowinfo & IPV6_FLOWLABEL_MASK; + return 0; + } + + if (np->repflow) { + freq->flr_label = np->flow_label; + return 0; + } + rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) { @@ -527,6 +538,15 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) switch (freq.flr_action) { case IPV6_FL_A_PUT: + if (freq.flr_flags & IPV6_FL_F_REFLECT) { + if (sk->sk_protocol != IPPROTO_TCP) + return -ENOPROTOOPT; + if (!np->repflow) + return -ESRCH; + np->flow_label = 0; + np->repflow = 0; + return 0; + } spin_lock_bh(&ip6_sk_fl_lock); for (sflp = &np->ipv6_fl_list; (sfl = rcu_dereference(*sflp))!=NULL; @@ -567,6 +587,20 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) return -ESRCH; case IPV6_FL_A_GET: + if (freq.flr_flags & IPV6_FL_F_REFLECT) { + struct net *net = sock_net(sk); + if (net->ipv6.sysctl.flowlabel_consistency) { + net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n"); + return -EPERM; + } + + if (sk->sk_protocol != IPPROTO_TCP) + return -ENOPROTOOPT; + + np->repflow = 1; + return 0; + } + if (freq.flr_label & ~IPV6_FLOWLABEL_MASK) return -EINVAL; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 8acb28621f9c..f3ffb43f59c0 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -61,9 +61,6 @@ static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); -#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) -#define IPV6_TCLASS_SHIFT 20 - #define HASH_SIZE_SHIFT 5 #define HASH_SIZE (1 << HASH_SIZE_SHIFT) @@ -499,7 +496,7 @@ static int ip6gre_rcv(struct sk_buff *skb) &ipv6h->saddr, &ipv6h->daddr, key, gre_proto); if (tunnel) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; @@ -846,7 +843,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) - fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK); + fl6.flowlabel |= ip6_flowlabel(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) fl6.flowi6_mark = skb->mark; @@ -1266,12 +1263,12 @@ static int ip6gre_tunnel_init(struct net_device *dev) if (ipv6_addr_any(&tunnel->parms.raddr)) dev->header_ops = &ip6gre_header_ops; - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ip6gre_tunnel_stats; + struct pcpu_sw_netstats *ip6gre_tunnel_stats; ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ip6gre_tunnel_stats->syncp); } @@ -1467,12 +1464,12 @@ static int ip6gre_tap_init(struct net_device *dev) ip6gre_tnl_link_config(tunnel, 1); - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ip6gre_tap_stats; + struct pcpu_sw_netstats *ip6gre_tap_stats; ip6gre_tap_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ip6gre_tap_stats->syncp); } diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 302d6fb1ff2b..51d54dc376f3 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_offload.c b/net/ipv6/ip6_offload.c index 4b851692b1f6..1e8683b135bb 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -154,6 +154,32 @@ out: return segs; } +/* Return the total length of all the extension hdrs, following the same + * logic in ipv6_gso_pull_exthdrs() when parsing ext-hdrs. + */ +static int ipv6_exthdrs_len(struct ipv6hdr *iph, + const struct net_offload **opps) +{ + struct ipv6_opt_hdr *opth = (void *)iph; + int len = 0, proto, optlen = sizeof(*iph); + + proto = iph->nexthdr; + for (;;) { + if (proto != NEXTHDR_HOP) { + *opps = rcu_dereference(inet6_offloads[proto]); + if (unlikely(!(*opps))) + break; + if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR)) + break; + } + opth = (void *)opth + optlen; + optlen = ipv6_optlen(opth); + len += optlen; + proto = opth->nexthdr; + } + return len; +} + static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, struct sk_buff *skb) { @@ -164,7 +190,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, unsigned int nlen; unsigned int hlen; unsigned int off; - int flush = 1; + u16 flush = 1; int proto; __wsum csum; @@ -177,6 +203,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, goto out; } + skb_set_network_header(skb, off); skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); @@ -211,12 +238,16 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, if (!NAPI_GRO_CB(p)->same_flow) continue; - iph2 = ipv6_hdr(p); + iph2 = (struct ipv6hdr *)(p->data + off); first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ; - /* All fields must match except length and Traffic Class. */ - if (nlen != skb_network_header_len(p) || - (first_word & htonl(0xF00FFFFF)) || + /* All fields must match except length and Traffic Class. + * XXX skbs on the gro_list have all been parsed and pulled + * already so we don't need to compare nlen + * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops))) + * memcmp() alone below is suffcient, right? + */ + if ((first_word & htonl(0xF00FFFFF)) || memcmp(&iph->nexthdr, &iph2->nexthdr, nlen - offsetof(struct ipv6hdr, nexthdr))) { NAPI_GRO_CB(p)->same_flow = 0; @@ -245,21 +276,21 @@ out: return pp; } -static int ipv6_gro_complete(struct sk_buff *skb) +static int ipv6_gro_complete(struct sk_buff *skb, int nhoff) { const struct net_offload *ops; - struct ipv6hdr *iph = ipv6_hdr(skb); + struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff); int err = -ENOSYS; - iph->payload_len = htons(skb->len - skb_network_offset(skb) - - sizeof(*iph)); + iph->payload_len = htons(skb->len - nhoff - sizeof(*iph)); rcu_read_lock(); - ops = rcu_dereference(inet6_offloads[NAPI_GRO_CB(skb)->proto]); + + nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out_unlock; - err = ops->callbacks.gro_complete(skb); + err = ops->callbacks.gro_complete(skb, nhoff); out_unlock: rcu_read_unlock(); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e6f931997996..070a2fae2375 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -321,6 +321,41 @@ static inline int ip6_forward_finish(struct sk_buff *skb) return dst_output(skb); } +static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) +{ + unsigned int mtu; + struct inet6_dev *idev; + + if (dst_metric_locked(dst, RTAX_MTU)) { + mtu = dst_metric_raw(dst, RTAX_MTU); + if (mtu) + return mtu; + } + + mtu = IPV6_MIN_MTU; + rcu_read_lock(); + idev = __in6_dev_get(dst->dev); + if (idev) + mtu = idev->cnf.mtu6; + rcu_read_unlock(); + + return mtu; +} + +static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) + return true; + + 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); @@ -336,7 +371,8 @@ int ip6_forward(struct sk_buff *skb) goto drop; if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { - IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_INDISCARDS); goto drop; } @@ -370,8 +406,8 @@ int ip6_forward(struct sk_buff *skb) /* Force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); - IP6_INC_STATS_BH(net, - ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -ETIMEDOUT; @@ -384,14 +420,15 @@ int ip6_forward(struct sk_buff *skb) if (proxied > 0) return ip6_input(skb); else if (proxied < 0) { - IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_INDISCARDS); goto drop; } } if (!xfrm6_route_forward(skb)) { - IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_INDISCARDS); goto drop; } dst = skb_dst(skb); @@ -439,25 +476,25 @@ int ip6_forward(struct sk_buff *skb) } } - mtu = dst_mtu(dst); + mtu = ip6_dst_mtu_forward(dst); 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); - IP6_INC_STATS_BH(net, - ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS); - IP6_INC_STATS_BH(net, - ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_INTOOBIGERRORS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } if (skb_cow(skb, dst->dev->hard_header_len)) { - IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS_BH(net, ip6_dst_idev(dst), + IPSTATS_MIB_OUTDISCARDS); goto drop; } @@ -938,7 +975,6 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup); * @sk: socket which provides route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup - * @can_sleep: we are in a sleepable context * * This function performs a route lookup on the given flow. * @@ -946,8 +982,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup); * error code. */ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, - const struct in6_addr *final_dst, - bool can_sleep) + const struct in6_addr *final_dst) { struct dst_entry *dst = NULL; int err; @@ -957,8 +992,6 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; - if (can_sleep) - fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP; return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } @@ -969,7 +1002,6 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); * @sk: socket which provides the dst cache and route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup - * @can_sleep: we are in a sleepable context * * This function performs a route lookup on the given flow with the * possibility of using the cached route in the socket if it is valid. @@ -980,8 +1012,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); * error code. */ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, - const struct in6_addr *final_dst, - bool can_sleep) + const struct in6_addr *final_dst) { struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie); int err; @@ -993,8 +1024,6 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; - if (can_sleep) - fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP; return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } @@ -1162,10 +1191,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, np->cork.hop_limit = hlimit; np->cork.tclass = tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) - mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? + mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? rt->dst.dev->mtu : dst_mtu(&rt->dst); else - mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? + mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? rt->dst.dev->mtu : dst_mtu(rt->dst.path); if (np->frag_size < mtu) { if (np->frag_size) @@ -1285,7 +1314,7 @@ alloc_new_skb: if (skb == NULL || skb_prev == NULL) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, - np->pmtudisc == + np->pmtudisc >= IPV6_PMTUDISC_PROBE); skb_prev = skb; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 7881965a8248..5db8d310f9c0 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -29,7 +29,6 @@ #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> -#include <linux/if_tunnel.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> @@ -70,9 +69,6 @@ MODULE_ALIAS_NETDEV("ip6tnl0"); #define IP6_TNL_TRACE(x...) do {;} while(0) #endif -#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) -#define IPV6_TCLASS_SHIFT 20 - #define HASH_SIZE_SHIFT 5 #define HASH_SIZE (1 << HASH_SIZE_SHIFT) @@ -103,12 +99,13 @@ struct ip6_tnl_net { static struct net_device_stats *ip6_get_stats(struct net_device *dev) { - struct pcpu_tstats tmp, sum = { 0 }; + struct pcpu_sw_netstats tmp, sum = { 0 }; int i; for_each_possible_cpu(i) { unsigned int start; - const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); do { start = u64_stats_fetch_begin_bh(&tstats->syncp); @@ -794,7 +791,7 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; if (t->parms.proto != ipproto && t->parms.proto != 0) { rcu_read_unlock(); @@ -1142,7 +1139,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) - fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK); + fl6.flowlabel |= ip6_flowlabel(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) fl6.flowi6_mark = skb->mark; @@ -1509,12 +1506,12 @@ ip6_tnl_dev_init_gen(struct net_device *dev) t->dev = dev; t->net = dev_net(dev); - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ip6_tnl_stats; + struct pcpu_sw_netstats *ip6_tnl_stats; ip6_tnl_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ip6_tnl_stats->syncp); } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 7b42d5ef868d..2d19272b8cee 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -24,7 +24,6 @@ #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> -#include <linux/if_tunnel.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> @@ -292,7 +291,7 @@ static int vti6_rcv(struct sk_buff *skb) if ((t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) { rcu_read_unlock(); @@ -736,11 +735,11 @@ static inline int vti6_dev_init_gen(struct net_device *dev) t->dev = dev; t->net = dev_net(dev); - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *stats; + struct pcpu_sw_netstats *stats; stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&stats->syncp); } diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index ce507d9e1c90..da9becb42e81 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -16,8 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ /* * [Memo] diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 1c6ce3119ff8..0a00f449de5e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -722,7 +722,7 @@ done: case IPV6_MTU_DISCOVER: if (optlen < sizeof(int)) goto e_inval; - if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE) + if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_INTERFACE) goto e_inval; np->pmtudisc = val; retv = 0; @@ -1002,10 +1002,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, release_sock(sk); if (skb) { - int err = ip6_datagram_recv_ctl(sk, &msg, skb); + ip6_datagram_recv_ctl(sk, &msg, skb); kfree_skb(skb); - if (err) - return err; } else { if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; @@ -1019,7 +1017,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.rxtclass) { - int tclass = np->rcv_tclass; + int tclass = (int)ip6_tclass(np->rcv_flowinfo); + put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); } if (np->rxopt.bits.rxoinfo) { @@ -1034,6 +1033,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, int hlim = np->mcast_hops; put_cmsg(&msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim); } + if (np->rxopt.bits.rxflow) { + __be32 flowinfo = np->rcv_flowinfo; + + put_cmsg(&msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); + } } len -= msg.msg_controllen; return put_user(len, optlen); @@ -1215,6 +1219,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, case IPV6_FLOWLABEL_MGR: { struct in6_flowlabel_req freq; + int flags; if (len < sizeof(freq)) return -EINVAL; @@ -1226,9 +1231,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, return -EINVAL; len = sizeof(freq); + flags = freq.flr_flags; + memset(&freq, 0, sizeof(freq)); - val = ipv6_flowlabel_opt_get(sk, &freq); + val = ipv6_flowlabel_opt_get(sk, &freq, flags); if (val < 0) return val; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index d18f9f903db6..e1e47350784b 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -999,7 +999,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, static void mld_gq_start_timer(struct inet6_dev *idev) { - unsigned long tv = net_random() % idev->mc_maxdelay; + unsigned long tv = prandom_u32() % idev->mc_maxdelay; idev->mc_gq_running = 1; if (!mod_timer(&idev->mc_gq_timer, jiffies+tv+2)) @@ -1015,7 +1015,7 @@ static void mld_gq_stop_timer(struct inet6_dev *idev) static void mld_ifc_start_timer(struct inet6_dev *idev, unsigned long delay) { - unsigned long tv = net_random() % delay; + unsigned long tv = prandom_u32() % delay; if (!mod_timer(&idev->mc_ifc_timer, jiffies+tv+2)) in6_dev_hold(idev); @@ -1030,7 +1030,7 @@ static void mld_ifc_stop_timer(struct inet6_dev *idev) static void mld_dad_start_timer(struct inet6_dev *idev, unsigned long delay) { - unsigned long tv = net_random() % delay; + unsigned long tv = prandom_u32() % delay; if (!mod_timer(&idev->mc_dad_timer, jiffies+tv+2)) in6_dev_hold(idev); @@ -1061,7 +1061,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) } if (delay >= resptime) - delay = net_random() % resptime; + delay = prandom_u32() % resptime; ma->mca_timer.expires = jiffies + delay; if (!mod_timer(&ma->mca_timer, jiffies + delay)) @@ -1665,7 +1665,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, skb_tailroom(skb)) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, - int type, int gdeleted, int sdeleted) + int type, int gdeleted, int sdeleted, int crsend) { struct inet6_dev *idev = pmc->idev; struct net_device *dev = idev->dev; @@ -1757,7 +1757,7 @@ empty_source: if (type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) return skb; - if (pmc->mca_crcount || isquery) { + if (pmc->mca_crcount || isquery || crsend) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)) { mld_sendpack(skb); @@ -1789,7 +1789,7 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; - skb = add_grec(skb, pmc, type, 0, 0); + skb = add_grec(skb, pmc, type, 0, 0, 0); spin_unlock_bh(&pmc->mca_lock); } } else { @@ -1798,7 +1798,7 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; - skb = add_grec(skb, pmc, type, 0, 0); + skb = add_grec(skb, pmc, type, 0, 0, 0); spin_unlock_bh(&pmc->mca_lock); } read_unlock_bh(&idev->lock); @@ -1843,13 +1843,13 @@ static void mld_send_cr(struct inet6_dev *idev) if (pmc->mca_sfmode == MCAST_INCLUDE) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; - skb = add_grec(skb, pmc, type, 1, 0); - skb = add_grec(skb, pmc, dtype, 1, 1); + skb = add_grec(skb, pmc, type, 1, 0, 0); + skb = add_grec(skb, pmc, dtype, 1, 1, 0); } if (pmc->mca_crcount) { if (pmc->mca_sfmode == MCAST_EXCLUDE) { type = MLD2_CHANGE_TO_INCLUDE; - skb = add_grec(skb, pmc, type, 1, 0); + skb = add_grec(skb, pmc, type, 1, 0, 0); } pmc->mca_crcount--; if (pmc->mca_crcount == 0) { @@ -1880,8 +1880,8 @@ static void mld_send_cr(struct inet6_dev *idev) type = MLD2_ALLOW_NEW_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; } - skb = add_grec(skb, pmc, type, 0, 0); - skb = add_grec(skb, pmc, dtype, 0, 1); /* deleted sources */ + skb = add_grec(skb, pmc, type, 0, 0, 0); + skb = add_grec(skb, pmc, dtype, 0, 1, 0); /* deleted sources */ /* filter mode changes */ if (pmc->mca_crcount) { @@ -1889,7 +1889,7 @@ static void mld_send_cr(struct inet6_dev *idev) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_CHANGE_TO_INCLUDE; - skb = add_grec(skb, pmc, type, 0, 0); + skb = add_grec(skb, pmc, type, 0, 0, 0); pmc->mca_crcount--; } spin_unlock_bh(&pmc->mca_lock); @@ -1997,27 +1997,36 @@ err_out: goto out; } -static void mld_resend_report(struct inet6_dev *idev) +static void mld_send_initial_cr(struct inet6_dev *idev) { - if (mld_in_v1_mode(idev)) { - struct ifmcaddr6 *mcaddr; - read_lock_bh(&idev->lock); - for (mcaddr = idev->mc_list; mcaddr; mcaddr = mcaddr->next) { - if (!(mcaddr->mca_flags & MAF_NOREPORT)) - igmp6_send(&mcaddr->mca_addr, idev->dev, - ICMPV6_MGM_REPORT); - } - read_unlock_bh(&idev->lock); - } else { - mld_send_report(idev, NULL); + struct sk_buff *skb; + struct ifmcaddr6 *pmc; + int type; + + if (mld_in_v1_mode(idev)) + return; + + skb = NULL; + read_lock_bh(&idev->lock); + for (pmc=idev->mc_list; pmc; pmc=pmc->next) { + spin_lock_bh(&pmc->mca_lock); + if (pmc->mca_sfcount[MCAST_EXCLUDE]) + type = MLD2_CHANGE_TO_EXCLUDE; + else + type = MLD2_CHANGE_TO_INCLUDE; + skb = add_grec(skb, pmc, type, 0, 0, 1); + spin_unlock_bh(&pmc->mca_lock); } + read_unlock_bh(&idev->lock); + if (skb) + mld_sendpack(skb); } void ipv6_mc_dad_complete(struct inet6_dev *idev) { idev->mc_dad_count = idev->mc_qrv; if (idev->mc_dad_count) { - mld_resend_report(idev); + mld_send_initial_cr(idev); idev->mc_dad_count--; if (idev->mc_dad_count) mld_dad_start_timer(idev, idev->mc_maxdelay); @@ -2028,7 +2037,7 @@ static void mld_dad_timer_expire(unsigned long data) { struct inet6_dev *idev = (struct inet6_dev *)data; - mld_resend_report(idev); + mld_send_initial_cr(idev); if (idev->mc_dad_count) { idev->mc_dad_count--; if (idev->mc_dad_count) @@ -2328,7 +2337,7 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = net_random() % unsolicited_report_interval(ma->idev); + delay = prandom_u32() % unsolicited_report_interval(ma->idev); spin_lock_bh(&ma->mca_lock); if (del_timer(&ma->mca_timer)) { diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 9ac01dc9402e..db9b6cbc9db3 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -13,8 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ /* * Authors: diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 300865171394..09a22f4f36c9 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -125,17 +125,19 @@ struct neigh_table nd_tbl = { .id = "ndisc_cache", .parms = { .tbl = &nd_tbl, - .base_reachable_time = ND_REACHABLE_TIME, - .retrans_time = ND_RETRANS_TIMER, - .gc_staletime = 60 * HZ, .reachable_time = ND_REACHABLE_TIME, - .delay_probe_time = 5 * HZ, - .queue_len_bytes = 64*1024, - .ucast_probes = 3, - .mcast_probes = 3, - .anycast_delay = 1 * HZ, - .proxy_delay = (8 * HZ) / 10, - .proxy_qlen = 64, + .data = { + [NEIGH_VAR_MCAST_PROBES] = 3, + [NEIGH_VAR_UCAST_PROBES] = 3, + [NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER, + [NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME, + [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, + [NEIGH_VAR_GC_STALETIME] = 60 * HZ, + [NEIGH_VAR_QUEUE_LEN_BYTES] = 64 * 1024, + [NEIGH_VAR_PROXY_QLEN] = 64, + [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, + [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, + }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, @@ -656,14 +658,14 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) if (skb && ipv6_chk_addr(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, 1)) saddr = &ipv6_hdr(skb)->saddr; - if ((probes -= neigh->parms->ucast_probes) < 0) { + if ((probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES)) < 0) { if (!(neigh->nud_state & NUD_VALID)) { ND_PRINTK(1, dbg, "%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); } ndisc_send_ns(dev, neigh, target, target, saddr); - } else if ((probes -= neigh->parms->app_probes) < 0) { + } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); } else { addrconf_addr_solict_mult(target, &mcaddr); @@ -790,7 +792,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && inc && - idev->nd_parms->proxy_delay != 0) { + NEIGH_VAR(idev->nd_parms, PROXY_DELAY) != 0) { /* * for anycast or proxy, * sender should delay its response @@ -1210,7 +1212,7 @@ skip_defrtr: rtime = (rtime*HZ)/1000; if (rtime < HZ/10) rtime = HZ/10; - in6_dev->nd_parms->retrans_time = rtime; + NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime); in6_dev->tstamp = jiffies; inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); } @@ -1222,9 +1224,11 @@ skip_defrtr: if (rtime < HZ/10) rtime = HZ/10; - if (rtime != in6_dev->nd_parms->base_reachable_time) { - in6_dev->nd_parms->base_reachable_time = rtime; - in6_dev->nd_parms->gc_staletime = 3 * rtime; + if (rtime != NEIGH_VAR(in6_dev->nd_parms, BASE_REACHABLE_TIME)) { + NEIGH_VAR_SET(in6_dev->nd_parms, + BASE_REACHABLE_TIME, rtime); + NEIGH_VAR_SET(in6_dev->nd_parms, + GC_STALETIME, 3 * rtime); in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime); in6_dev->tstamp = jiffies; inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); @@ -1651,22 +1655,23 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *bu ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default"); if (strcmp(ctl->procname, "retrans_time") == 0) - ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + ret = neigh_proc_dointvec(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time") == 0) - ret = proc_dointvec_jiffies(ctl, write, - buffer, lenp, ppos); + ret = neigh_proc_dointvec_jiffies(ctl, write, + buffer, lenp, ppos); else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) || (strcmp(ctl->procname, "base_reachable_time_ms") == 0)) - ret = proc_dointvec_ms_jiffies(ctl, write, - buffer, lenp, ppos); + ret = neigh_proc_dointvec_ms_jiffies(ctl, write, + buffer, lenp, ppos); else ret = -1; if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) { - if (ctl->data == &idev->nd_parms->base_reachable_time) - idev->nd_parms->reachable_time = neigh_rand_reach_time(idev->nd_parms->base_reachable_time); + if (ctl->data == &NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)) + idev->nd_parms->reachable_time = + neigh_rand_reach_time(NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)); idev->tstamp = jiffies; inet6_ifinfo_notify(RTM_NEWLINK, idev); in6_dev_put(idev); @@ -1725,7 +1730,7 @@ int __init ndisc_init(void) neigh_table_init(&nd_tbl); #ifdef CONFIG_SYSCTL - err = neigh_sysctl_register(NULL, &nd_tbl.parms, "ipv6", + err = neigh_sysctl_register(NULL, &nd_tbl.parms, &ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 7702f9e90a04..4bff1f297e39 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -28,15 +28,32 @@ config NF_CONNTRACK_IPV6 config NF_TABLES_IPV6 depends on NF_TABLES tristate "IPv6 nf_tables support" + help + This option enables the IPv6 support for nf_tables. config NFT_CHAIN_ROUTE_IPV6 depends on NF_TABLES_IPV6 tristate "IPv6 nf_tables route chain support" + help + This option enables the "route" chain for IPv6 in nf_tables. This + chain type is used to force packet re-routing after mangling header + fields such as the source, destination, flowlabel, hop-limit and + the packet mark. config NFT_CHAIN_NAT_IPV6 depends on NF_TABLES_IPV6 depends on NF_NAT_IPV6 && NFT_NAT tristate "IPv6 nf_tables nat chain support" + help + This option enables the "nat" chain for IPv6 in nf_tables. This + chain type is used to perform Network Address Translation (NAT) + packet transformations such as the source, destination address and + source and destination ports. + +config NFT_REJECT_IPV6 + depends on NF_TABLES_IPV6 + default NFT_REJECT + tristate config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering)" diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index d1b4928f34f7..70d3dd66f2cd 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o +obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o # matches obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index da00a2ecde55..544b0a9da1b5 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -23,181 +23,18 @@ #include <linux/skbuff.h> #include <linux/icmpv6.h> #include <linux/netdevice.h> -#include <net/ipv6.h> -#include <net/tcp.h> #include <net/icmp.h> -#include <net/ip6_checksum.h> -#include <net/ip6_fib.h> -#include <net/ip6_route.h> #include <net/flow.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_ipv6/ip6t_REJECT.h> +#include <net/netfilter/ipv6/nf_reject.h> + MODULE_AUTHOR("Yasuyuki KOZAKAI <yasuyuki.kozakai@toshiba.co.jp>"); MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6"); MODULE_LICENSE("GPL"); -/* Send RST reply */ -static void send_reset(struct net *net, struct sk_buff *oldskb, int hook) -{ - struct sk_buff *nskb; - struct tcphdr otcph, *tcph; - unsigned int otcplen, hh_len; - int tcphoff, needs_ack; - const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); - struct ipv6hdr *ip6h; -#define DEFAULT_TOS_VALUE 0x0U - const __u8 tclass = DEFAULT_TOS_VALUE; - struct dst_entry *dst = NULL; - u8 proto; - __be16 frag_off; - struct flowi6 fl6; - - if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) || - (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) { - pr_debug("addr is not unicast.\n"); - return; - } - - proto = oip6h->nexthdr; - tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off); - - if ((tcphoff < 0) || (tcphoff > oldskb->len)) { - pr_debug("Cannot get TCP header.\n"); - return; - } - - otcplen = oldskb->len - tcphoff; - - /* IP header checks: fragment, too short. */ - if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) { - pr_debug("proto(%d) != IPPROTO_TCP, " - "or too short. otcplen = %d\n", - proto, otcplen); - return; - } - - if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr))) - BUG(); - - /* No RST for RST. */ - if (otcph.rst) { - pr_debug("RST is set\n"); - return; - } - - /* Check checksum. */ - if (nf_ip6_checksum(oldskb, hook, tcphoff, IPPROTO_TCP)) { - pr_debug("TCP checksum is invalid\n"); - return; - } - - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_TCP; - fl6.saddr = oip6h->daddr; - fl6.daddr = oip6h->saddr; - fl6.fl6_sport = otcph.dest; - fl6.fl6_dport = otcph.source; - security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); - dst = ip6_route_output(net, NULL, &fl6); - if (dst == NULL || dst->error) { - dst_release(dst); - return; - } - dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); - if (IS_ERR(dst)) - return; - - hh_len = (dst->dev->hard_header_len + 15)&~15; - nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr) - + sizeof(struct tcphdr) + dst->trailer_len, - GFP_ATOMIC); - - if (!nskb) { - net_dbg_ratelimited("cannot alloc skb\n"); - dst_release(dst); - return; - } - - skb_dst_set(nskb, dst); - - skb_reserve(nskb, hh_len + dst->header_len); - - skb_put(nskb, sizeof(struct ipv6hdr)); - skb_reset_network_header(nskb); - ip6h = ipv6_hdr(nskb); - ip6_flow_hdr(ip6h, tclass, 0); - ip6h->hop_limit = ip6_dst_hoplimit(dst); - ip6h->nexthdr = IPPROTO_TCP; - ip6h->saddr = oip6h->daddr; - ip6h->daddr = oip6h->saddr; - - skb_reset_transport_header(nskb); - tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); - /* Truncate to length (no data) */ - tcph->doff = sizeof(struct tcphdr)/4; - tcph->source = otcph.dest; - tcph->dest = otcph.source; - - if (otcph.ack) { - needs_ack = 0; - tcph->seq = otcph.ack_seq; - tcph->ack_seq = 0; - } else { - needs_ack = 1; - tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin - + otcplen - (otcph.doff<<2)); - tcph->seq = 0; - } - - /* Reset flags */ - ((u_int8_t *)tcph)[13] = 0; - tcph->rst = 1; - tcph->ack = needs_ack; - tcph->window = 0; - tcph->urg_ptr = 0; - tcph->check = 0; - - /* Adjust TCP checksum */ - tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr, - &ipv6_hdr(nskb)->daddr, - sizeof(struct tcphdr), IPPROTO_TCP, - csum_partial(tcph, - sizeof(struct tcphdr), 0)); - - nf_ct_attach(nskb, oldskb); - -#ifdef CONFIG_BRIDGE_NETFILTER - /* If we use ip6_local_out for bridged traffic, the MAC source on - * the RST will be ours, instead of the destination's. This confuses - * some routers/firewalls, and they drop the packet. So we need to - * build the eth header using the original destination's MAC as the - * source, and send the RST packet directly. - */ - if (oldskb->nf_bridge) { - struct ethhdr *oeth = eth_hdr(oldskb); - nskb->dev = oldskb->nf_bridge->physindev; - nskb->protocol = htons(ETH_P_IPV6); - ip6h->payload_len = htons(sizeof(struct tcphdr)); - if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol), - oeth->h_source, oeth->h_dest, nskb->len) < 0) - return; - dev_queue_xmit(nskb); - } else -#endif - ip6_local_out(nskb); -} - -static inline void -send_unreach(struct net *net, struct sk_buff *skb_in, unsigned char code, - unsigned int hooknum) -{ - if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) - skb_in->dev = net->loopback_dev; - - icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); -} static unsigned int reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) @@ -208,25 +45,25 @@ reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) pr_debug("%s: medium point\n", __func__); switch (reject->with) { case IP6T_ICMP6_NO_ROUTE: - send_unreach(net, skb, ICMPV6_NOROUTE, par->hooknum); + nf_send_unreach6(net, skb, ICMPV6_NOROUTE, par->hooknum); break; case IP6T_ICMP6_ADM_PROHIBITED: - send_unreach(net, skb, ICMPV6_ADM_PROHIBITED, par->hooknum); + nf_send_unreach6(net, skb, ICMPV6_ADM_PROHIBITED, par->hooknum); break; case IP6T_ICMP6_NOT_NEIGHBOUR: - send_unreach(net, skb, ICMPV6_NOT_NEIGHBOUR, par->hooknum); + nf_send_unreach6(net, skb, ICMPV6_NOT_NEIGHBOUR, par->hooknum); break; case IP6T_ICMP6_ADDR_UNREACH: - send_unreach(net, skb, ICMPV6_ADDR_UNREACH, par->hooknum); + nf_send_unreach6(net, skb, ICMPV6_ADDR_UNREACH, par->hooknum); break; case IP6T_ICMP6_PORT_UNREACH: - send_unreach(net, skb, ICMPV6_PORT_UNREACH, par->hooknum); + nf_send_unreach6(net, skb, ICMPV6_PORT_UNREACH, par->hooknum); break; case IP6T_ICMP6_ECHOREPLY: /* Do nothing */ break; case IP6T_TCP_RESET: - send_reset(net, skb, par->hooknum); + nf_send_reset6(net, skb, par->hooknum); break; default: net_info_ratelimited("case %u not handled yet\n", reject->with); diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c index d77db8a13505..0d812b31277d 100644 --- a/net/ipv6/netfilter/nf_tables_ipv6.c +++ b/net/ipv6/netfilter/nf_tables_ipv6.c @@ -16,34 +16,51 @@ #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_ipv6.h> +static unsigned int nft_do_chain_ipv6(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nft_pktinfo pkt; + + /* malformed packet, drop it */ + if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0) + return NF_DROP; + + return nft_do_chain(&pkt, ops); +} + static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - struct nft_pktinfo pkt; - if (unlikely(skb->len < sizeof(struct ipv6hdr))) { if (net_ratelimit()) pr_info("nf_tables_ipv6: ignoring short SOCK_RAW " "packet\n"); return NF_ACCEPT; } - if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0) - return NF_DROP; - return nft_do_chain_pktinfo(&pkt, ops); + return nft_do_chain_ipv6(ops, skb, in, out, okfn); } -static struct nft_af_info nft_af_ipv6 __read_mostly = { +struct nft_af_info nft_af_ipv6 __read_mostly = { .family = NFPROTO_IPV6, .nhooks = NF_INET_NUMHOOKS, .owner = THIS_MODULE, + .nops = 1, .hooks = { + [NF_INET_LOCAL_IN] = nft_do_chain_ipv6, [NF_INET_LOCAL_OUT] = nft_ipv6_output, + [NF_INET_FORWARD] = nft_do_chain_ipv6, + [NF_INET_PRE_ROUTING] = nft_do_chain_ipv6, + [NF_INET_POST_ROUTING] = nft_do_chain_ipv6, }, }; +EXPORT_SYMBOL_GPL(nft_af_ipv6); static int nf_tables_ipv6_init_net(struct net *net) { @@ -73,44 +90,28 @@ static struct pernet_operations nf_tables_ipv6_net_ops = { .exit = nf_tables_ipv6_exit_net, }; -static unsigned int -nft_do_chain_ipv6(const struct nf_hook_ops *ops, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct nft_pktinfo pkt; - - /* malformed packet, drop it */ - if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0) - return NF_DROP; - - return nft_do_chain_pktinfo(&pkt, ops); -} - -static struct nf_chain_type filter_ipv6 = { - .family = NFPROTO_IPV6, +static const struct nf_chain_type filter_ipv6 = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, + .family = NFPROTO_IPV6, + .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING), - .fn = { - [NF_INET_LOCAL_IN] = nft_do_chain_ipv6, - [NF_INET_LOCAL_OUT] = nft_ipv6_output, - [NF_INET_FORWARD] = nft_do_chain_ipv6, - [NF_INET_PRE_ROUTING] = nft_do_chain_ipv6, - [NF_INET_POST_ROUTING] = nft_do_chain_ipv6, - }, }; static int __init nf_tables_ipv6_init(void) { + int ret; + nft_register_chain_type(&filter_ipv6); - return register_pernet_subsys(&nf_tables_ipv6_net_ops); + ret = register_pernet_subsys(&nf_tables_ipv6_net_ops); + if (ret < 0) + nft_unregister_chain_type(&filter_ipv6); + + return ret; } static void __exit nf_tables_ipv6_exit(void) diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c index e86dcd70dc76..9c3297a768fd 100644 --- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -79,7 +79,7 @@ static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out); - ret = nft_do_chain_pktinfo(&pkt, ops); + ret = nft_do_chain(&pkt, ops); if (ret != NF_ACCEPT) return ret; if (!nf_nat_initialized(ct, maniptype)) { @@ -170,21 +170,21 @@ static unsigned int nf_nat_ipv6_output(const struct nf_hook_ops *ops, return ret; } -static struct nf_chain_type nft_chain_nat_ipv6 = { - .family = NFPROTO_IPV6, +static const struct nf_chain_type nft_chain_nat_ipv6 = { .name = "nat", .type = NFT_CHAIN_T_NAT, + .family = NFPROTO_IPV6, + .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), - .fn = { + .hooks = { [NF_INET_PRE_ROUTING] = nf_nat_ipv6_prerouting, [NF_INET_POST_ROUTING] = nf_nat_ipv6_postrouting, [NF_INET_LOCAL_OUT] = nf_nat_ipv6_output, [NF_INET_LOCAL_IN] = nf_nat_ipv6_fn, }, - .me = THIS_MODULE, }; static int __init nft_chain_nat_ipv6_init(void) diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c index 3fe40f0456ad..42031299585e 100644 --- a/net/ipv6/netfilter/nft_chain_route_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -47,7 +47,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u32 *)ipv6_hdr(skb)); - ret = nft_do_chain_pktinfo(&pkt, ops); + ret = nft_do_chain(&pkt, ops); if (ret != NF_DROP && ret != NF_QUEUE && (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || @@ -59,15 +59,15 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, return ret; } -static struct nf_chain_type nft_chain_route_ipv6 = { - .family = NFPROTO_IPV6, +static const struct nf_chain_type nft_chain_route_ipv6 = { .name = "route", .type = NFT_CHAIN_T_ROUTE, + .family = NFPROTO_IPV6, + .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_LOCAL_OUT), - .fn = { + .hooks = { [NF_INET_LOCAL_OUT] = nf_route_table_hook, }, - .me = THIS_MODULE, }; static int __init nft_chain_route_init(void) diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c new file mode 100644 index 000000000000..0bc19fa87821 --- /dev/null +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -0,0 +1,76 @@ +/* + * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2013 Eric Leblond <eric@regit.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_reject.h> +#include <net/netfilter/ipv6/nf_reject.h> + +void nft_reject_ipv6_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + struct nft_reject *priv = nft_expr_priv(expr); + struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out); + + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + nf_send_unreach6(net, pkt->skb, priv->icmp_code, + pkt->ops->hooknum); + break; + case NFT_REJECT_TCP_RST: + nf_send_reset6(net, pkt->skb, pkt->ops->hooknum); + break; + } + + data[NFT_REG_VERDICT].verdict = NF_DROP; +} +EXPORT_SYMBOL_GPL(nft_reject_ipv6_eval); + +static struct nft_expr_type nft_reject_ipv6_type; +static const struct nft_expr_ops nft_reject_ipv6_ops = { + .type = &nft_reject_ipv6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), + .eval = nft_reject_ipv6_eval, + .init = nft_reject_init, + .dump = nft_reject_dump, +}; + +static struct nft_expr_type nft_reject_ipv6_type __read_mostly = { + .family = NFPROTO_IPV6, + .name = "reject", + .ops = &nft_reject_ipv6_ops, + .policy = nft_reject_policy, + .maxattr = NFTA_REJECT_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_reject_ipv6_module_init(void) +{ + return nft_register_expr(&nft_reject_ipv6_type); +} + +static void __exit nft_reject_ipv6_module_exit(void) +{ + nft_unregister_expr(&nft_reject_ipv6_type); +} + +module_init(nft_reject_ipv6_module_init); +module_exit(nft_reject_ipv6_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "reject"); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index a83243c3d656..fb9beb78f00b 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -31,7 +31,7 @@ struct proto pingv6_prot = { .owner = THIS_MODULE, .init = ping_init_sock, .close = ping_close, - .connect = ip6_datagram_connect, + .connect = ip6_datagram_connect_v6_only, .disconnect = udp_disconnect, .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, @@ -62,10 +62,9 @@ static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, { return -EAFNOSUPPORT; } -static int dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, +static void dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { - return -EAFNOSUPPORT; } static int dummy_icmpv6_err_convert(u8 type, u8 code, int *err) { @@ -103,7 +102,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, return err; if (msg->msg_name) { - struct sockaddr_in6 *u = (struct sockaddr_in6 *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name); if (msg->msg_namelen < sizeof(struct sockaddr_in6) || u->sin6_family != AF_INET6) { return -EINVAL; @@ -145,7 +144,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; - dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, 1); + dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr); if (IS_ERR(dst)) return PTR_ERR(dst); rt = (struct rt6_info *) dst; @@ -254,7 +253,9 @@ int __init pingv6_init(void) return ret; #endif pingv6_ops.ipv6_recv_error = ipv6_recv_error; - pingv6_ops.ip6_datagram_recv_ctl = ip6_datagram_recv_ctl; + pingv6_ops.ip6_datagram_recv_common_ctl = ip6_datagram_recv_common_ctl; + pingv6_ops.ip6_datagram_recv_specific_ctl = + ip6_datagram_recv_specific_ctl; pingv6_ops.icmpv6_err_convert = icmpv6_err_convert; pingv6_ops.ipv6_icmp_error = ipv6_icmp_error; pingv6_ops.ipv6_chk_addr = ipv6_chk_addr; @@ -267,7 +268,8 @@ int __init pingv6_init(void) void pingv6_exit(void) { pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error; - pingv6_ops.ip6_datagram_recv_ctl = dummy_ip6_datagram_recv_ctl; + pingv6_ops.ip6_datagram_recv_common_ctl = dummy_ip6_datagram_recv_ctl; + pingv6_ops.ip6_datagram_recv_specific_ctl = dummy_ip6_datagram_recv_ctl; pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert; pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error; pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index b6bb87e55805..1f29996e368a 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -250,6 +250,10 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; + + if (addr->sin6_family != AF_INET6) + return -EINVAL; + addr_type = ipv6_addr_type(&addr->sin6_addr); /* Raw sockets are IPv6 only */ @@ -457,7 +461,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); - struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct sk_buff *skb; size_t copied; int err; @@ -734,7 +738,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; - struct sockaddr_in6 * sin6 = (struct sockaddr_in6 *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -864,7 +868,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; @@ -1209,7 +1213,7 @@ struct proto rawv6_prot = { .owner = THIS_MODULE, .close = rawv6_close, .destroy = raw6_destroy, - .connect = ip6_datagram_connect, + .connect = ip6_datagram_connect_v6_only, .disconnect = udp_disconnect, .ioctl = rawv6_ioctl, .init = rawv6_init_sk, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4b4944c3e4c4..11dac21e6586 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -66,8 +66,9 @@ #endif enum rt6_nud_state { - RT6_NUD_FAIL_HARD = -2, - RT6_NUD_FAIL_SOFT = -1, + RT6_NUD_FAIL_HARD = -3, + RT6_NUD_FAIL_PROBE = -2, + RT6_NUD_FAIL_DO_RR = -1, RT6_NUD_SUCCEED = 1 }; @@ -103,6 +104,36 @@ static struct rt6_info *rt6_get_route_info(struct net *net, const struct in6_addr *gwaddr, int ifindex); #endif +static void rt6_bind_peer(struct rt6_info *rt, int create) +{ + struct inet_peer_base *base; + struct inet_peer *peer; + + base = inetpeer_base_ptr(rt->_rt6i_peer); + if (!base) + return; + + peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create); + if (peer) { + if (!rt6_set_peer(rt, peer)) + inet_putpeer(peer); + } +} + +static struct inet_peer *__rt6_get_peer(struct rt6_info *rt, int create) +{ + if (rt6_has_peer(rt)) + return rt6_peer_ptr(rt); + + rt6_bind_peer(rt, create); + return (rt6_has_peer(rt) ? rt6_peer_ptr(rt) : NULL); +} + +static struct inet_peer *rt6_get_peer_create(struct rt6_info *rt) +{ + return __rt6_get_peer(rt, 1); +} + static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) { struct rt6_info *rt = (struct rt6_info *) dst; @@ -311,22 +342,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) } } -void rt6_bind_peer(struct rt6_info *rt, int create) -{ - struct inet_peer_base *base; - struct inet_peer *peer; - - base = inetpeer_base_ptr(rt->_rt6i_peer); - if (!base) - return; - - peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create); - if (peer) { - if (!rt6_set_peer(rt, peer)) - inet_putpeer(peer); - } -} - static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int how) { @@ -521,7 +536,7 @@ static void rt6_probe(struct rt6_info *rt) work = kmalloc(sizeof(*work), GFP_ATOMIC); if (neigh && work) - neigh->updated = jiffies; + __neigh_set_probe_once(neigh); if (neigh) write_unlock(&neigh->lock); @@ -577,11 +592,13 @@ static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt) #ifdef CONFIG_IPV6_ROUTER_PREF else if (!(neigh->nud_state & NUD_FAILED)) ret = RT6_NUD_SUCCEED; + else + ret = RT6_NUD_FAIL_PROBE; #endif read_unlock(&neigh->lock); } else { ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? - RT6_NUD_SUCCEED : RT6_NUD_FAIL_SOFT; + RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR; } rcu_read_unlock_bh(); @@ -618,16 +635,17 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, goto out; m = rt6_score_route(rt, oif, strict); - if (m == RT6_NUD_FAIL_SOFT) { + if (m == RT6_NUD_FAIL_DO_RR) { match_do_rr = true; m = 0; /* lowest valid score */ - } else if (m < 0) { + } else if (m == RT6_NUD_FAIL_HARD) { goto out; } if (strict & RT6_LOOKUP_F_REACHABLE) rt6_probe(rt); + /* note that m can be RT6_NUD_FAIL_PROBE at this point */ if (m > *mpri) { *do_rr = match_do_rr; *mpri = m; @@ -2238,7 +2256,7 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) .net = net, .addr = &ifp->addr, }; - fib6_clean_all(net, fib6_remove_prefsrc, 0, &adni); + fib6_clean_all(net, fib6_remove_prefsrc, &adni); } struct arg_dev_net { @@ -2265,7 +2283,7 @@ void rt6_ifdown(struct net *net, struct net_device *dev) .net = net, }; - fib6_clean_all(net, fib6_ifdown, 0, &adn); + fib6_clean_all(net, fib6_ifdown, &adn); icmp6_clean_all(fib6_ifdown, &adn); } @@ -2320,7 +2338,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu) .mtu = mtu, }; - fib6_clean_all(dev_net(dev), rt6_mtu_change_route, 0, &arg); + fib6_clean_all(dev_net(dev), rt6_mtu_change_route, &arg); } static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index d3005b34476a..3dfbcf1dcb1c 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -671,7 +671,7 @@ static int ipip6_rcv(struct sk_buff *skb) tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { - struct pcpu_tstats *tstats; + struct pcpu_sw_netstats *tstats; if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && tunnel->parms.iph.protocol != 0) @@ -1365,12 +1365,12 @@ static int ipip6_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip6_tunnel_bind_dev(dev); - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ipip6_tunnel_stats; + struct pcpu_sw_netstats *ipip6_tunnel_stats; ipip6_tunnel_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ipip6_tunnel_stats->syncp); } @@ -1395,12 +1395,12 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; iph->ttl = 64; - dev->tstats = alloc_percpu(struct pcpu_tstats); + dev->tstats = alloc_percpu(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; for_each_possible_cpu(i) { - struct pcpu_tstats *ipip6_fb_stats; + struct pcpu_sw_netstats *ipip6_fb_stats; ipip6_fb_stats = per_cpu_ptr(dev->tstats, i); u64_stats_init(&ipip6_fb_stats->syncp); } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 535a3ad262f1..bb53a5e73c1a 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -247,7 +247,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) fl6.fl6_sport = inet_sk(sk)->inet_sport; security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false); + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) goto out_free; } diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 107b2f1d90ae..7f405a168822 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -24,6 +24,20 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "anycast_src_echo_reply", + .data = &init_net.ipv6.sysctl.anycast_src_echo_reply, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "flowlabel_consistency", + .data = &init_net.ipv6.sysctl.flowlabel_consistency, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; @@ -51,6 +65,8 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) if (!ipv6_table) goto out; ipv6_table[0].data = &net->ipv6.sysctl.bindv6only; + ipv6_table[1].data = &net->ipv6.sysctl.anycast_src_echo_reply; + ipv6_table[2].data = &net->ipv6.sysctl.flowlabel_consistency; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f67033b4bb66..889079b2ea85 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -164,12 +164,12 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, * connect() to INADDR_ANY means loopback (BSD'ism). */ - if(ipv6_addr_any(&usin->sin6_addr)) + if (ipv6_addr_any(&usin->sin6_addr)) usin->sin6_addr.s6_addr[15] = 0x1; addr_type = ipv6_addr_type(&usin->sin6_addr); - if(addr_type & IPV6_ADDR_MULTICAST) + if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type&IPV6_ADDR_LINKLOCAL) { @@ -257,7 +257,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; @@ -336,7 +336,7 @@ static void tcp_v6_mtu_reduced(struct sock *sk) static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - const struct ipv6hdr *hdr = (const struct ipv6hdr*)skb->data; + const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct ipv6_pinfo *np; struct sock *sk; @@ -397,6 +397,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (sk->sk_state == TCP_LISTEN) goto out; + if (!ip6_sk_accept_pmtu(sk)) + goto out; + tp->mtu_info = ntohl(info); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); @@ -466,7 +469,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); - struct sk_buff * skb; + struct sk_buff *skb; int err = -ENOMEM; /* First, grab a route. */ @@ -480,6 +483,9 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, &ireq->ir_v6_rmt_addr); fl6->daddr = ireq->ir_v6_rmt_addr; + if (np->repflow && (ireq->pktopts != NULL)) + fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); + skb_set_queue_mapping(skb, queue_mapping); err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass); err = net_xmit_eval(err); @@ -721,7 +727,8 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, - struct tcp_md5sig_key *key, int rst, u8 tclass) + struct tcp_md5sig_key *key, int rst, u8 tclass, + u32 label) { const struct tcphdr *th = tcp_hdr(skb); struct tcphdr *t1; @@ -783,6 +790,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, memset(&fl6, 0, sizeof(fl6)); fl6.daddr = ipv6_hdr(skb)->saddr; fl6.saddr = ipv6_hdr(skb)->daddr; + fl6.flowlabel = label; buff->ip_summed = CHECKSUM_PARTIAL; buff->csum = 0; @@ -800,7 +808,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, * Underlying function will use this to retrieve the network * namespace */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false); + dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass); @@ -868,7 +876,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); - tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, key, 1, 0); + tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, key, 1, 0, 0); #ifdef CONFIG_TCP_MD5SIG release_sk1: @@ -881,9 +889,11 @@ release_sk1: static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, - struct tcp_md5sig_key *key, u8 tclass) + struct tcp_md5sig_key *key, u8 tclass, + u32 label) { - tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, key, 0, tclass); + tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, key, 0, tclass, + label); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) @@ -895,7 +905,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw), - tw->tw_tclass); + tw->tw_tclass, (tw->tw_flowlabel << 12)); inet_twsk_put(tw); } @@ -905,11 +915,12 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, { tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, tcp_time_stamp, req->ts_recent, - tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0); + tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), + 0, 0); } -static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) +static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) { struct request_sock *req, **prev; const struct tcphdr *th = tcp_hdr(skb); @@ -1010,7 +1021,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!isn) { if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || - np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { + np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || + np->repflow) { atomic_inc(&skb->users); ireq->pktopts = skb; } @@ -1082,9 +1094,9 @@ drop: return 0; /* don't send reset */ } -static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct dst_entry *dst) +static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst) { struct inet_request_sock *ireq; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); @@ -1134,7 +1146,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; - newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); + if (np->repflow) + newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count @@ -1214,7 +1228,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; - newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); + if (np->repflow) + newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* Clone native IPv6 options from listening socket (if any) @@ -1230,7 +1246,6 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + newnp->opt->opt_flen); - tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric_advmss(dst); if (tcp_sk(sk)->rx_opt.user_mss && @@ -1379,7 +1394,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) * otherwise we just shortcircuit this and continue with * the new socket.. */ - if(nsk != sk) { + if (nsk != sk) { sock_rps_save_rxhash(nsk, skb); if (tcp_child_process(sk, nsk, skb)) goto reset; @@ -1424,8 +1439,10 @@ ipv6_pktoptions: np->mcast_oif = inet6_iif(opt_skb); 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(opt_skb)); + if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) + np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); + if (np->repflow) + np->flow_label = ip6_flowlabel(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); @@ -1739,7 +1756,7 @@ static void get_openreq6(struct seq_file *seq, dest->s6_addr32[2], dest->s6_addr32[3], ntohs(inet_rsk(req)->ir_rmt_port), TCP_SYN_RECV, - 0,0, /* could print option size, but that is af dependent. */ + 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), req->num_timeout, @@ -1798,7 +1815,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) atomic_read(&sp->sk_refcnt), sp, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), - (icsk->icsk_ack.quick << 1 ) | icsk->icsk_ack.pingpong, + (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh ); diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 6d18157dc32c..0d78132ff18a 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -66,13 +66,13 @@ skip_csum: return tcp_gro_receive(head, skb); } -static int tcp6_gro_complete(struct sk_buff *skb) +static int tcp6_gro_complete(struct sk_buff *skb, int thoff) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); - th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb), - &iph->saddr, &iph->daddr, 0); + th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr, + &iph->daddr, 0); skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; return tcp_gro_complete(skb); diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 4b0f50d9a962..2c4e4c5c7614 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -12,8 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * * Authors Mitsuru KANDA <mk@linux-ipv6.org> * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 089c741a3992..1e586d92260e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -460,9 +460,7 @@ try_again: /* Copy the address. */ if (msg->msg_name) { - struct sockaddr_in6 *sin6; - - sin6 = (struct sockaddr_in6 *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); sin6->sin6_family = AF_INET6; sin6->sin6_port = udp_hdr(skb)->source; sin6->sin6_flowinfo = 0; @@ -479,12 +477,16 @@ try_again: } *addr_len = sizeof(*sin6); } + + if (np->rxopt.all) + ip6_datagram_recv_common_ctl(sk, msg, skb); + if (is_udp4) { if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); } else { if (np->rxopt.all) - ip6_datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_specific_ctl(sk, msg, skb); } err = copied; @@ -538,8 +540,11 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (sk == NULL) return; - if (type == ICMPV6_PKT_TOOBIG) + if (type == ICMPV6_PKT_TOOBIG) { + if (!ip6_sk_accept_pmtu(sk)) + goto out; ip6_sk_update_pmtu(skb, sk, info); + } if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); goto out; @@ -1038,7 +1043,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; @@ -1220,7 +1225,7 @@ do_udp_sendmsg: security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, true); + dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c index 63d5d493098a..0e015906f9ca 100644 --- a/net/ipv6/xfrm6_mode_ro.c +++ b/net/ipv6/xfrm6_mode_ro.c @@ -15,8 +15,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ /* * Authors: diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index de2bcfaaf759..1c66465a42dd 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -12,8 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * * Authors Mitsuru KANDA <mk@linux-ipv6.org> * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index e096025b477f..00b2a6d1c009 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -52,18 +52,12 @@ #include <net/p8022.h> #include <net/psnap.h> #include <net/sock.h> +#include <net/datalink.h> #include <net/tcp_states.h> +#include <net/net_namespace.h> #include <asm/uaccess.h> -#ifdef CONFIG_SYSCTL -extern void ipx_register_sysctl(void); -extern void ipx_unregister_sysctl(void); -#else -#define ipx_register_sysctl() -#define ipx_unregister_sysctl() -#endif - /* Configuration Variables */ static unsigned char ipxcfg_max_hops = 16; static char ipxcfg_auto_select_primary; @@ -84,15 +78,6 @@ DEFINE_SPINLOCK(ipx_interfaces_lock); struct ipx_interface *ipx_primary_net; struct ipx_interface *ipx_internal_net; -extern int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc, - unsigned char *node); -extern void ipxrtr_del_routes(struct ipx_interface *intrfc); -extern int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx, - struct iovec *iov, size_t len, int noblock); -extern int ipxrtr_route_skb(struct sk_buff *skb); -extern struct ipx_route *ipxrtr_lookup(__be32 net); -extern int ipxrtr_ioctl(unsigned int cmd, void __user *arg); - struct ipx_interface *ipx_interfaces_head(void) { struct ipx_interface *rc = NULL; @@ -1707,7 +1692,7 @@ static int ipx_sendmsg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct ipx_sock *ipxs = ipx_sk(sk); - struct sockaddr_ipx *usipx = (struct sockaddr_ipx *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_ipx *, usipx, msg->msg_name); struct sockaddr_ipx local_sipx; int rc = -EINVAL; int flags = msg->msg_flags; @@ -1774,7 +1759,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct ipx_sock *ipxs = ipx_sk(sk); - struct sockaddr_ipx *sipx = (struct sockaddr_ipx *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_ipx *, sipx, msg->msg_name); struct ipxhdr *ipx = NULL; struct sk_buff *skb; int copied, rc; @@ -1986,9 +1971,6 @@ static struct notifier_block ipx_dev_notifier = { .notifier_call = ipxitf_device_event, }; -extern struct datalink_proto *make_EII_client(void); -extern void destroy_EII_client(struct datalink_proto *); - static const unsigned char ipx_8022_type = 0xE0; static const unsigned char ipx_snap_id[5] = { 0x0, 0x0, 0x0, 0x81, 0x37 }; static const char ipx_EII_err_msg[] __initconst = diff --git a/net/ipx/ipx_route.c b/net/ipx/ipx_route.c index 30f4519b092f..c1f03185c5e1 100644 --- a/net/ipx/ipx_route.c +++ b/net/ipx/ipx_route.c @@ -20,15 +20,11 @@ DEFINE_RWLOCK(ipx_routes_lock); extern struct ipx_interface *ipx_internal_net; -extern __be16 ipx_cksum(struct ipxhdr *packet, int length); extern struct ipx_interface *ipxitf_find_using_net(__be32 net); extern int ipxitf_demux_socket(struct ipx_interface *intrfc, struct sk_buff *skb, int copy); extern int ipxitf_demux_socket(struct ipx_interface *intrfc, struct sk_buff *skb, int copy); -extern int ipxitf_send(struct ipx_interface *intrfc, struct sk_buff *skb, - char *node); -extern struct ipx_interface *ipxitf_find_using_net(__be32 net); struct ipx_route *ipxrtr_lookup(__be32 net) { diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index de7db23049f1..54747c25c86c 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -25,9 +25,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * * Linux-IrDA now supports four different types of IrDA sockets: * @@ -1654,7 +1652,7 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock, /* Check if an address was specified with sendto. Jean II */ if (msg->msg_name) { - struct sockaddr_irda *addr = (struct sockaddr_irda *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_irda *, addr, msg->msg_name); err = -EINVAL; /* Check address, extract pid. Jean II */ if (msg->msg_namelen < sizeof(*addr)) diff --git a/net/irda/discovery.c b/net/irda/discovery.c index b0b56a339a83..6786e7f193d2 100644 --- a/net/irda/discovery.c +++ b/net/irda/discovery.c @@ -24,9 +24,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/ircomm/ircomm_core.c b/net/irda/ircomm/ircomm_core.c index b797daac063c..4490a675b1bb 100644 --- a/net/irda/ircomm/ircomm_core.c +++ b/net/irda/ircomm/ircomm_core.c @@ -23,9 +23,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/ircomm/ircomm_event.c b/net/irda/ircomm/ircomm_event.c index d78554fedbac..b172c6522328 100644 --- a/net/irda/ircomm/ircomm_event.c +++ b/net/irda/ircomm/ircomm_event.c @@ -22,9 +22,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/ircomm/ircomm_lmp.c b/net/irda/ircomm/ircomm_lmp.c index 3b8095c771d4..6536114adf37 100644 --- a/net/irda/ircomm/ircomm_lmp.c +++ b/net/irda/ircomm/ircomm_lmp.c @@ -24,9 +24,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/ircomm/ircomm_param.c b/net/irda/ircomm/ircomm_param.c index 308939128359..f80b1a6a244b 100644 --- a/net/irda/ircomm/ircomm_param.c +++ b/net/irda/ircomm/ircomm_param.c @@ -22,9 +22,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/ircomm/ircomm_ttp.c b/net/irda/ircomm/ircomm_ttp.c index 6e6509f22f60..d362d711b79c 100644 --- a/net/irda/ircomm/ircomm_ttp.c +++ b/net/irda/ircomm/ircomm_ttp.c @@ -23,9 +23,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 41ac7938268b..2ba8b9705bb7 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -24,9 +24,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/ircomm/ircomm_tty_attach.c b/net/irda/ircomm/ircomm_tty_attach.c index a2a508f5f268..2ee87bf387cc 100644 --- a/net/irda/ircomm/ircomm_tty_attach.c +++ b/net/irda/ircomm/ircomm_tty_attach.c @@ -23,9 +23,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/ircomm/ircomm_tty_ioctl.c b/net/irda/ircomm/ircomm_tty_ioctl.c index b343f50dc8d7..ce943853c38d 100644 --- a/net/irda/ircomm/ircomm_tty_ioctl.c +++ b/net/irda/ircomm/ircomm_tty_ioctl.c @@ -22,9 +22,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/irda_device.c b/net/irda/irda_device.c index 14653b8d664d..365b895da84b 100644 --- a/net/irda/irda_device.c +++ b/net/irda/irda_device.c @@ -23,9 +23,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/irlap.c b/net/irda/irlap.c index 005b424494a0..a778df55f5d6 100644 --- a/net/irda/irlap.c +++ b/net/irda/irlap.c @@ -23,9 +23,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/parameters.c b/net/irda/parameters.c index 71cd38c1a67f..6d0869716bf6 100644 --- a/net/irda/parameters.c +++ b/net/irda/parameters.c @@ -22,9 +22,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/irda/qos.c b/net/irda/qos.c index 798ffd9a705e..11a7cc0cbc28 100644 --- a/net/irda/qos.c +++ b/net/irda/qos.c @@ -24,9 +24,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, - * MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * ********************************************************************/ diff --git a/net/key/af_key.c b/net/key/af_key.c index 545f047868ad..1a04c1329362 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1340,6 +1340,12 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_ max_spi = range->sadb_spirange_max; } + err = verify_spi_info(x->id.proto, min_spi, max_spi); + if (err) { + xfrm_state_put(x); + return err; + } + err = xfrm_alloc_spi(x, min_spi, max_spi); resp_skb = err ? ERR_PTR(err) : pfkey_xfrm_state2msg(x); @@ -1380,10 +1386,9 @@ static int pfkey_acquire(struct sock *sk, struct sk_buff *skb, const struct sadb return 0; spin_lock_bh(&x->lock); - if (x->km.state == XFRM_STATE_ACQ) { + if (x->km.state == XFRM_STATE_ACQ) x->km.state = XFRM_STATE_ERROR; - wake_up(&net->xfrm.km_waitq); - } + spin_unlock_bh(&x->lock); xfrm_state_put(x); return 0; @@ -1785,7 +1790,9 @@ static int pfkey_dump_sa(struct pfkey_sock *pfk) static void pfkey_dump_sa_done(struct pfkey_sock *pfk) { - xfrm_state_walk_done(&pfk->dump.u.state); + struct net *net = sock_net(&pfk->sk); + + xfrm_state_walk_done(&pfk->dump.u.state, net); } static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) @@ -1861,7 +1868,7 @@ static u32 gen_reqid(struct net *net) reqid = IPSEC_MANUAL_REQID_MAX+1; xfrm_policy_walk_init(&walk, XFRM_POLICY_TYPE_MAIN); rc = xfrm_policy_walk(net, &walk, check_reqid, (void*)&reqid); - xfrm_policy_walk_done(&walk); + xfrm_policy_walk_done(&walk, net); if (rc != -EEXIST) return reqid; } while (reqid != start); @@ -2485,6 +2492,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, struct xfrm_selector sel; struct xfrm_migrate m[XFRM_MAX_DEPTH]; struct xfrm_kmaddress k; + struct net *net = sock_net(sk); if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC - 1], ext_hdrs[SADB_EXT_ADDRESS_DST - 1]) || @@ -2558,7 +2566,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, } return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i, - kma ? &k : NULL); + kma ? &k : NULL, net); out: return err; @@ -2659,7 +2667,9 @@ static int pfkey_dump_sp(struct pfkey_sock *pfk) static void pfkey_dump_sp_done(struct pfkey_sock *pfk) { - xfrm_policy_walk_done(&pfk->dump.u.policy); + struct net *net = sock_net((struct sock *)pfk); + + xfrm_policy_walk_done(&pfk->dump.u.policy, net); } static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) @@ -3569,6 +3579,7 @@ static int pfkey_sendmsg(struct kiocb *kiocb, struct sk_buff *skb = NULL; struct sadb_msg *hdr = NULL; int err; + struct net *net = sock_net(sk); err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) @@ -3591,9 +3602,9 @@ static int pfkey_sendmsg(struct kiocb *kiocb, if (!hdr) goto out; - mutex_lock(&xfrm_cfg_mutex); + mutex_lock(&net->xfrm.xfrm_cfg_mutex); err = pfkey_process(sk, skb, hdr); - mutex_unlock(&xfrm_cfg_mutex); + mutex_unlock(&net->xfrm.xfrm_cfg_mutex); out: if (err && hdr && pfkey_error(hdr, err, sk) == 0) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 9af77d9c0ec9..735d0f60c83a 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -176,7 +176,7 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) * owned by userspace. A struct sock returned from this function must be * released using l2tp_tunnel_sock_put once you're done with it. */ -struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) +static struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) { int err = 0; struct socket *sock = NULL; @@ -202,10 +202,9 @@ struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) out: return sk; } -EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_lookup); /* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */ -void l2tp_tunnel_sock_put(struct sock *sk) +static void l2tp_tunnel_sock_put(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); if (tunnel) { @@ -217,7 +216,6 @@ void l2tp_tunnel_sock_put(struct sock *sk) } sock_put(sk); } -EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_put); /* Lookup a session by id in the global session list */ diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 1ee9f6965d68..1f01ba3435bc 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -238,8 +238,6 @@ out: return tunnel; } -struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel); -void l2tp_tunnel_sock_put(struct sock *sk); struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index da1a1cee1a08..0b44d855269c 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -403,7 +403,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m /* Get and verify the address. */ if (msg->msg_name) { - struct sockaddr_l2tpip *lip = (struct sockaddr_l2tpip *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_l2tpip *, lip, msg->msg_name); rc = -EINVAL; if (msg->msg_namelen < sizeof(*lip)) goto out; @@ -512,7 +512,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m struct inet_sock *inet = inet_sk(sk); size_t copied = 0; int err = -EOPNOTSUPP; - struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; if (flags & MSG_OOB) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index bb6e206ea70b..7704ea9502fd 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -371,6 +371,9 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, if (addr_len < sizeof(*lsa)) return -EINVAL; + if (usin->sin6_family != AF_INET6) + return -EINVAL; + addr_type = ipv6_addr_type(&usin->sin6_addr); if (addr_type & IPV6_ADDR_MULTICAST) return -EINVAL; @@ -481,8 +484,7 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; - struct sockaddr_l2tpip6 *lsa = - (struct sockaddr_l2tpip6 *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_txoptions *opt = NULL; @@ -597,7 +599,7 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk, security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; @@ -652,7 +654,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); - struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name); size_t copied = 0; int err = -EOPNOTSUPP; struct sk_buff *skb; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index c71b699eb555..0080d2b0a8ae 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -707,7 +707,7 @@ out: static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags) { - struct sockaddr_llc *uaddr = (struct sockaddr_llc *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_llc *, uaddr, msg->msg_name); const int nonblock = flags & MSG_DONTWAIT; struct sk_buff *skb = NULL; struct sock *sk = sock->sk; @@ -884,7 +884,7 @@ static int llc_ui_sendmsg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); - struct sockaddr_llc *addr = (struct sockaddr_llc *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; struct sk_buff *skb; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index cd8724177965..42dc2e45c921 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -753,7 +753,7 @@ void llc_sap_remove_socket(struct llc_sap *sap, struct sock *sk) * * Sends received pdus to the connection state machine. */ -static int llc_conn_rcv(struct sock* sk, struct sk_buff *skb) +static int llc_conn_rcv(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); @@ -891,7 +891,7 @@ out_kfree_skb: * * Initializes a socket with default llc values. */ -static void llc_sk_init(struct sock* sk) +static void llc_sk_init(struct sock *sk) { struct llc_sock *llc = llc_sk(sk); diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 2bb0ddff8c0f..842851cef698 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -23,7 +23,7 @@ #include <net/llc.h> LIST_HEAD(llc_sap_list); -DEFINE_SPINLOCK(llc_sap_list_lock); +static DEFINE_SPINLOCK(llc_sap_list_lock); /** * llc_sap_alloc - allocates and initializes sap. @@ -48,7 +48,7 @@ static struct llc_sap *llc_sap_alloc(void) static struct llc_sap *__llc_sap_find(unsigned char sap_value) { - struct llc_sap* sap; + struct llc_sap *sap; list_for_each_entry(sap, &llc_sap_list, node) if (sap->laddr.lsap == sap_value) @@ -159,7 +159,6 @@ module_init(llc_init); module_exit(llc_exit); EXPORT_SYMBOL(llc_sap_list); -EXPORT_SYMBOL(llc_sap_list_lock); EXPORT_SYMBOL(llc_sap_find); EXPORT_SYMBOL(llc_sap_open); EXPORT_SYMBOL(llc_sap_close); diff --git a/net/llc/llc_output.c b/net/llc/llc_output.c index 2dae8a5df23f..94425e421213 100644 --- a/net/llc/llc_output.c +++ b/net/llc/llc_output.c @@ -43,7 +43,7 @@ int llc_mac_hdr_init(struct sk_buff *skb, rc = 0; break; default: - WARN(1, "device type not supported: %d\n", skb->dev->type); + break; } return rc; } diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index e5850699098e..06033f6c845f 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -66,7 +66,7 @@ struct sk_buff *llc_alloc_frame(struct sock *sk, struct net_device *dev, return skb; } -void llc_save_primitive(struct sock *sk, struct sk_buff* skb, u8 prim) +void llc_save_primitive(struct sock *sk, struct sk_buff *skb, u8 prim) { struct sockaddr_llc *addr; @@ -114,7 +114,7 @@ void llc_sap_rtn_pdu(struct llc_sap *sap, struct sk_buff *skb) * failure. */ static struct llc_sap_state_trans *llc_find_sap_trans(struct llc_sap *sap, - struct sk_buff* skb) + struct sk_buff *skb) { int i = 0; struct llc_sap_state_trans *rc = NULL; diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c index 537488cbf941..9b9009f99551 100644 --- a/net/mac80211/aes_cmac.c +++ b/net/mac80211/aes_cmac.c @@ -111,7 +111,7 @@ void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad, } -struct crypto_cipher * ieee80211_aes_cmac_key_setup(const u8 key[]) +struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[]) { struct crypto_cipher *tfm; diff --git a/net/mac80211/aes_cmac.h b/net/mac80211/aes_cmac.h index 20785a647254..0ce6487af795 100644 --- a/net/mac80211/aes_cmac.h +++ b/net/mac80211/aes_cmac.h @@ -11,7 +11,7 @@ #include <linux/crypto.h> -struct crypto_cipher * ieee80211_aes_cmac_key_setup(const u8 key[]); +struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[]); void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad, const u8 *data, size_t data_len, u8 *mic); void ieee80211_aes_cmac_key_free(struct crypto_cipher *tfm); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 364ce0c5962f..453e974287d1 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -133,7 +133,9 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, struct key_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; struct sta_info *sta = NULL; + const struct ieee80211_cipher_scheme *cs = NULL; struct ieee80211_key *key; int err; @@ -145,22 +147,28 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_WEP104: - if (IS_ERR(sdata->local->wep_tx_tfm)) + if (IS_ERR(local->wep_tx_tfm)) return -EINVAL; break; + case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_GCMP: + break; default: + cs = ieee80211_cs_get(local, params->cipher, sdata->vif.type); break; } key = ieee80211_key_alloc(params->cipher, key_idx, params->key_len, - params->key, params->seq_len, params->seq); + params->key, params->seq_len, params->seq, + cs); if (IS_ERR(key)) return PTR_ERR(key); if (pairwise) key->conf.flags |= IEEE80211_KEY_FLAG_PAIRWISE; - mutex_lock(&sdata->local->sta_mtx); + mutex_lock(&local->sta_mtx); if (mac_addr) { if (ieee80211_vif_is_mesh(&sdata->vif)) @@ -216,10 +224,13 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, break; } + if (sta) + sta->cipher_scheme = cs; + err = ieee80211_key_link(key, sdata, sta); out_unlock: - mutex_unlock(&sdata->local->sta_mtx); + mutex_unlock(&local->sta_mtx); return err; } @@ -244,7 +255,7 @@ static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev, goto out_unlock; if (pairwise) - key = key_mtx_dereference(local, sta->ptk); + key = key_mtx_dereference(local, sta->ptk[key_idx]); else key = key_mtx_dereference(local, sta->gtk[key_idx]); } else @@ -290,9 +301,10 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, if (!sta) goto out; - if (pairwise) - key = rcu_dereference(sta->ptk); - else if (key_idx < NUM_DEFAULT_KEYS) + if (pairwise && key_idx < NUM_DEFAULT_KEYS) + key = rcu_dereference(sta->ptk[key_idx]); + else if (!pairwise && + key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) key = rcu_dereference(sta->gtk[key_idx]); } else key = rcu_dereference(sdata->keys[key_idx]); @@ -521,8 +533,8 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) STATION_INFO_PEER_PM | STATION_INFO_NONPEER_PM; - sinfo->llid = le16_to_cpu(sta->llid); - sinfo->plid = le16_to_cpu(sta->plid); + sinfo->llid = sta->llid; + sinfo->plid = sta->plid; sinfo->plink_state = sta->plink_state; if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { sinfo->filled |= STATION_INFO_T_OFFSET; @@ -816,6 +828,7 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy, if (cfg80211_chandef_identical(&local->monitor_chandef, chandef)) return 0; + mutex_lock(&local->mtx); mutex_lock(&local->iflist_mtx); if (local->use_chanctx) { sdata = rcu_dereference_protected( @@ -834,6 +847,7 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy, if (ret == 0) local->monitor_chandef = *chandef; mutex_unlock(&local->iflist_mtx); + mutex_unlock(&local->mtx); return ret; } @@ -846,7 +860,7 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, if (!resp || !resp_len) return 1; - old = rtnl_dereference(sdata->u.ap.probe_resp); + old = sdata_dereference(sdata->u.ap.probe_resp, sdata); new = kzalloc(sizeof(struct probe_resp) + resp_len, GFP_KERNEL); if (!new) @@ -862,15 +876,16 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, return 0; } -int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, - struct cfg80211_beacon_data *params) +static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, + struct cfg80211_beacon_data *params) { struct beacon_data *new, *old; int new_head_len, new_tail_len; int size, err; u32 changed = BSS_CHANGED_BEACON; - old = rtnl_dereference(sdata->u.ap.beacon); + old = sdata_dereference(sdata->u.ap.beacon, sdata); + /* Need to have a beacon head if we don't have one yet */ if (!params->head && !old) @@ -938,6 +953,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; struct beacon_data *old; struct ieee80211_sub_if_data *vlan; u32 changed = BSS_CHANGED_BEACON_INT | @@ -947,7 +963,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_P2P_PS; int err; - old = rtnl_dereference(sdata->u.ap.beacon); + old = sdata_dereference(sdata->u.ap.beacon, sdata); if (old) return -EALREADY; @@ -956,8 +972,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->needed_rx_chains = sdata->local->rx_chains; sdata->radar_required = params->radar_required; + mutex_lock(&local->mtx); err = ieee80211_vif_use_channel(sdata, ¶ms->chandef, IEEE80211_CHANCTX_SHARED); + mutex_unlock(&local->mtx); if (err) return err; ieee80211_vif_copy_chanctx_to_vlans(sdata, false); @@ -968,11 +986,19 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, */ sdata->control_port_protocol = params->crypto.control_port_ethertype; sdata->control_port_no_encrypt = params->crypto.control_port_no_encrypt; + sdata->encrypt_headroom = ieee80211_cs_headroom(sdata->local, + ¶ms->crypto, + sdata->vif.type); + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { vlan->control_port_protocol = params->crypto.control_port_ethertype; vlan->control_port_no_encrypt = params->crypto.control_port_no_encrypt; + vlan->encrypt_headroom = + ieee80211_cs_headroom(sdata->local, + ¶ms->crypto, + vlan->vif.type); } sdata->vif.bss_conf.beacon_int = params->beacon_interval; @@ -995,19 +1021,24 @@ 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); if (err) { - old = rtnl_dereference(sdata->u.ap.beacon); + old = sdata_dereference(sdata->u.ap.beacon, sdata); + if (old) kfree_rcu(old, rcu_head); RCU_INIT_POINTER(sdata->u.ap.beacon, NULL); + ieee80211_vif_release_channel(sdata); return err; } + ieee80211_recalc_dtim(local, sdata); ieee80211_bss_info_change_notify(sdata, changed); netif_carrier_on(dev); @@ -1032,7 +1063,7 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, if (sdata->vif.csa_active) return -EBUSY; - old = rtnl_dereference(sdata->u.ap.beacon); + old = sdata_dereference(sdata->u.ap.beacon, sdata); if (!old) return -ENOENT; @@ -1050,16 +1081,17 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) struct ieee80211_local *local = sdata->local; struct beacon_data *old_beacon; struct probe_resp *old_probe_resp; + struct cfg80211_chan_def chandef; - old_beacon = rtnl_dereference(sdata->u.ap.beacon); + old_beacon = sdata_dereference(sdata->u.ap.beacon, sdata); if (!old_beacon) return -ENOENT; - old_probe_resp = rtnl_dereference(sdata->u.ap.probe_resp); + old_probe_resp = sdata_dereference(sdata->u.ap.probe_resp, sdata); /* abort any running channel switch */ sdata->vif.csa_active = false; - cancel_work_sync(&sdata->csa_finalize_work); - cancel_work_sync(&sdata->u.ap.request_smps_work); + kfree(sdata->u.ap.next_beacon); + sdata->u.ap.next_beacon = NULL; /* turn off carrier for this interface and dependent VLANs */ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) @@ -1072,18 +1104,10 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) kfree_rcu(old_beacon, rcu_head); if (old_probe_resp) kfree_rcu(old_probe_resp, rcu_head); + sdata->u.ap.driver_smps_mode = IEEE80211_SMPS_OFF; - list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) - sta_info_flush_defer(vlan); - sta_info_flush_defer(sdata); - synchronize_net(); - rcu_barrier(); - list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { - sta_info_flush_cleanup(vlan); - ieee80211_free_keys(vlan); - } - sta_info_flush_cleanup(sdata); - ieee80211_free_keys(sdata); + __sta_info_flush(sdata, true); + ieee80211_free_keys(sdata, true); sdata->vif.bss_conf.enable_beacon = false; sdata->vif.bss_conf.ssid_len = 0; @@ -1091,8 +1115,10 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); if (sdata->wdev.cac_started) { + chandef = sdata->vif.bss_conf.chandef; cancel_delayed_work_sync(&sdata->dfs_cac_timer_work); - cfg80211_cac_event(sdata->dev, NL80211_RADAR_CAC_ABORTED, + cfg80211_cac_event(sdata->dev, &chandef, + NL80211_RADAR_CAC_ABORTED, GFP_KERNEL); } @@ -1103,7 +1129,9 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) skb_queue_purge(&sdata->u.ap.ps.bc_buf); ieee80211_vif_copy_chanctx_to_vlans(sdata, true); + mutex_lock(&local->mtx); ieee80211_vif_release_channel(sdata); + mutex_unlock(&local->mtx); return 0; } @@ -1926,8 +1954,10 @@ static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev, sdata->smps_mode = IEEE80211_SMPS_OFF; sdata->needed_rx_chains = sdata->local->rx_chains; + mutex_lock(&sdata->local->mtx); err = ieee80211_vif_use_channel(sdata, &setup->chandef, IEEE80211_CHANCTX_SHARED); + mutex_unlock(&sdata->local->mtx); if (err) return err; @@ -1939,7 +1969,9 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); ieee80211_stop_mesh(sdata); + mutex_lock(&sdata->local->mtx); ieee80211_vif_release_channel(sdata); + mutex_unlock(&sdata->local->mtx); return 0; } @@ -1953,7 +1985,7 @@ static int ieee80211_change_bss(struct wiphy *wiphy, enum ieee80211_band band; u32 changed = 0; - if (!rtnl_dereference(sdata->u.ap.beacon)) + if (!sdata_dereference(sdata->u.ap.beacon, sdata)) return -ENOENT; band = ieee80211_get_sdata_band(sdata); @@ -2561,8 +2593,8 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, int j; sdata->rc_rateidx_mask[i] = mask->control[i].legacy; - memcpy(sdata->rc_rateidx_mcs_mask[i], mask->control[i].mcs, - sizeof(mask->control[i].mcs)); + memcpy(sdata->rc_rateidx_mcs_mask[i], mask->control[i].ht_mcs, + sizeof(mask->control[i].ht_mcs)); sdata->rc_has_mcs_mask[i] = false; if (!sband) @@ -2608,6 +2640,24 @@ 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) @@ -2742,24 +2792,6 @@ 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; } @@ -2877,26 +2909,29 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy, unsigned long timeout; int err; - if (!list_empty(&local->roc_list) || local->scanning) - return -EBUSY; + mutex_lock(&local->mtx); + if (!list_empty(&local->roc_list) || local->scanning) { + err = -EBUSY; + goto out_unlock; + } /* whatever, but channel contexts should not complain about that one */ sdata->smps_mode = IEEE80211_SMPS_OFF; sdata->needed_rx_chains = local->rx_chains; sdata->radar_required = true; - mutex_lock(&local->iflist_mtx); err = ieee80211_vif_use_channel(sdata, chandef, IEEE80211_CHANCTX_SHARED); - mutex_unlock(&local->iflist_mtx); if (err) - return err; + goto out_unlock; timeout = msecs_to_jiffies(IEEE80211_DFS_MIN_CAC_TIME_MS); ieee80211_queue_delayed_work(&sdata->local->hw, &sdata->dfs_cac_timer_work, timeout); - return 0; + out_unlock: + mutex_unlock(&local->mtx); + return err; } static struct cfg80211_beacon_data * @@ -2963,27 +2998,35 @@ void ieee80211_csa_finalize_work(struct work_struct *work) struct ieee80211_local *local = sdata->local; int err, changed = 0; + sdata_lock(sdata); + /* AP might have been stopped while waiting for the lock. */ + if (!sdata->vif.csa_active) + goto unlock; + if (!ieee80211_sdata_running(sdata)) - return; + goto unlock; sdata->radar_required = sdata->csa_radar_required; - err = ieee80211_vif_change_channel(sdata, &local->csa_chandef, - &changed); + mutex_lock(&local->mtx); + err = ieee80211_vif_change_channel(sdata, &changed); + mutex_unlock(&local->mtx); if (WARN_ON(err < 0)) - return; + goto unlock; if (!local->use_chanctx) { - local->_oper_chandef = local->csa_chandef; + local->_oper_chandef = sdata->csa_chandef; ieee80211_hw_config(local, 0); } ieee80211_bss_info_change_notify(sdata, changed); + sdata->vif.csa_active = false; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: err = ieee80211_assign_beacon(sdata, sdata->u.ap.next_beacon); if (err < 0) - return; + goto unlock; + changed |= err; kfree(sdata->u.ap.next_beacon); sdata->u.ap.next_beacon = NULL; @@ -2997,24 +3040,26 @@ void ieee80211_csa_finalize_work(struct work_struct *work) case NL80211_IFTYPE_MESH_POINT: err = ieee80211_mesh_finish_csa(sdata); if (err < 0) - return; + goto unlock; break; #endif default: WARN_ON(1); - return; + goto unlock; } - sdata->vif.csa_active = false; ieee80211_wake_queues_by_reason(&sdata->local->hw, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_CSA); - cfg80211_ch_switch_notify(sdata->dev, &local->csa_chandef); + cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef); + +unlock: + sdata_unlock(sdata); } -static int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, - struct cfg80211_csa_settings *params) +int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_csa_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; @@ -3023,6 +3068,8 @@ static int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_if_mesh __maybe_unused *ifmsh; int err, num_chanctx; + lockdep_assert_held(&sdata->wdev.mtx); + if (!list_empty(&local->roc_list) || local->scanning) return -EBUSY; @@ -3143,7 +3190,7 @@ static int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_CSA); - local->csa_chandef = params->chandef; + sdata->csa_chandef = params->chandef; sdata->vif.csa_active = true; ieee80211_bss_info_change_notify(sdata, err); @@ -3153,26 +3200,25 @@ static int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, } static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, - struct ieee80211_channel *chan, bool offchan, - unsigned int wait, const u8 *buf, size_t len, - bool no_cck, bool dont_wait_for_ack, u64 *cookie) + struct cfg80211_mgmt_tx_params *params, + u64 *cookie) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct sta_info *sta; - const struct ieee80211_mgmt *mgmt = (void *)buf; + const struct ieee80211_mgmt *mgmt = (void *)params->buf; bool need_offchan = false; u32 flags; int ret; - if (dont_wait_for_ack) + if (params->dont_wait_for_ack) flags = IEEE80211_TX_CTL_NO_ACK; else flags = IEEE80211_TX_INTFL_NL80211_FRAME_TX | IEEE80211_TX_CTL_REQ_TX_STATUS; - if (no_cck) + if (params->no_cck) flags |= IEEE80211_TX_CTL_NO_CCK_RATE; switch (sdata->vif.type) { @@ -3220,7 +3266,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, /* configurations requiring offchan cannot work if no channel has been * specified */ - if (need_offchan && !chan) + if (need_offchan && !params->chan) return -EINVAL; mutex_lock(&local->mtx); @@ -3233,8 +3279,10 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); if (chanctx_conf) { - need_offchan = chan && (chan != chanctx_conf->def.chan); - } else if (!chan) { + need_offchan = params->chan && + (params->chan != + chanctx_conf->def.chan); + } else if (!params->chan) { ret = -EINVAL; rcu_read_unlock(); goto out_unlock; @@ -3244,19 +3292,19 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, rcu_read_unlock(); } - if (need_offchan && !offchan) { + if (need_offchan && !params->offchan) { ret = -EBUSY; goto out_unlock; } - skb = dev_alloc_skb(local->hw.extra_tx_headroom + len); + skb = dev_alloc_skb(local->hw.extra_tx_headroom + params->len); if (!skb) { ret = -ENOMEM; goto out_unlock; } skb_reserve(skb, local->hw.extra_tx_headroom); - memcpy(skb_put(skb, len), buf, len); + memcpy(skb_put(skb, params->len), params->buf, params->len); IEEE80211_SKB_CB(skb)->flags = flags; @@ -3276,8 +3324,8 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, local->hw.offchannel_tx_hw_queue; /* This will handle all kinds of coalescing and immediate TX */ - ret = ieee80211_start_roc_work(local, sdata, chan, - wait, cookie, skb, + ret = ieee80211_start_roc_work(local, sdata, params->chan, + params->wait, cookie, skb, IEEE80211_ROC_TYPE_MGMT_TX); if (ret) kfree_skb(skb); @@ -3792,6 +3840,31 @@ static void ieee80211_set_wakeup(struct wiphy *wiphy, bool enabled) } #endif +static int ieee80211_set_qos_map(struct wiphy *wiphy, + struct net_device *dev, + struct cfg80211_qos_map *qos_map) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct mac80211_qos_map *new_qos_map, *old_qos_map; + + if (qos_map) { + new_qos_map = kzalloc(sizeof(*new_qos_map), GFP_KERNEL); + if (!new_qos_map) + return -ENOMEM; + memcpy(&new_qos_map->qos_map, qos_map, sizeof(*qos_map)); + } else { + /* A NULL qos_map was passed to disable QoS mapping */ + new_qos_map = NULL; + } + + old_qos_map = sdata_dereference(sdata->qos_map, sdata); + rcu_assign_pointer(sdata->qos_map, new_qos_map); + if (old_qos_map) + kfree_rcu(old_qos_map, rcu_head); + + return 0; +} + struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -3871,4 +3944,5 @@ struct cfg80211_ops mac80211_config_ops = { .get_channel = ieee80211_cfg_get_channel, .start_radar_detection = ieee80211_start_radar_detection, .channel_switch = ieee80211_channel_switch, + .set_qos_map = ieee80211_set_qos_map, }; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 03ba6b5c5373..f43613a97dd6 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -9,6 +9,140 @@ #include "ieee80211_i.h" #include "driver-ops.h" +static enum nl80211_chan_width ieee80211_get_sta_bw(struct ieee80211_sta *sta) +{ + switch (sta->bandwidth) { + case IEEE80211_STA_RX_BW_20: + if (sta->ht_cap.ht_supported) + return NL80211_CHAN_WIDTH_20; + else + return NL80211_CHAN_WIDTH_20_NOHT; + case IEEE80211_STA_RX_BW_40: + return NL80211_CHAN_WIDTH_40; + case IEEE80211_STA_RX_BW_80: + return NL80211_CHAN_WIDTH_80; + case IEEE80211_STA_RX_BW_160: + /* + * This applied for both 160 and 80+80. since we use + * the returned value to consider degradation of + * ctx->conf.min_def, we have to make sure to take + * the bigger one (NL80211_CHAN_WIDTH_160). + * Otherwise we might try degrading even when not + * needed, as the max required sta_bw returned (80+80) + * might be smaller than the configured bw (160). + */ + return NL80211_CHAN_WIDTH_160; + default: + WARN_ON(1); + return NL80211_CHAN_WIDTH_20; + } +} + +static enum nl80211_chan_width +ieee80211_get_max_required_bw(struct ieee80211_sub_if_data *sdata) +{ + enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; + struct sta_info *sta; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { + if (sdata != sta->sdata && + !(sta->sdata->bss && sta->sdata->bss == sdata->bss)) + continue; + + if (!sta->uploaded) + continue; + + max_bw = max(max_bw, ieee80211_get_sta_bw(&sta->sta)); + } + rcu_read_unlock(); + + return max_bw; +} + +static enum nl80211_chan_width +ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, + struct ieee80211_chanctx_conf *conf) +{ + struct ieee80211_sub_if_data *sdata; + enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; + + rcu_read_lock(); + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + struct ieee80211_vif *vif = &sdata->vif; + enum nl80211_chan_width width = NL80211_CHAN_WIDTH_20_NOHT; + + if (!ieee80211_sdata_running(sdata)) + continue; + + if (rcu_access_pointer(sdata->vif.chanctx_conf) != conf) + continue; + + switch (vif->type) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + width = ieee80211_get_max_required_bw(sdata); + break; + case NL80211_IFTYPE_P2P_DEVICE: + continue; + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_WDS: + case NL80211_IFTYPE_MESH_POINT: + width = vif->bss_conf.chandef.width; + break; + case NL80211_IFTYPE_UNSPECIFIED: + case NUM_NL80211_IFTYPES: + case NL80211_IFTYPE_MONITOR: + case NL80211_IFTYPE_P2P_CLIENT: + case NL80211_IFTYPE_P2P_GO: + WARN_ON_ONCE(1); + } + max_bw = max(max_bw, width); + } + rcu_read_unlock(); + + return max_bw; +} + +/* + * recalc the min required chan width of the channel context, which is + * the max of min required widths of all the interfaces bound to this + * channel context. + */ +void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) +{ + enum nl80211_chan_width max_bw; + struct cfg80211_chan_def min_def; + + lockdep_assert_held(&local->chanctx_mtx); + + /* don't optimize 5MHz, 10MHz, and radar_enabled confs */ + if (ctx->conf.def.width == NL80211_CHAN_WIDTH_5 || + ctx->conf.def.width == NL80211_CHAN_WIDTH_10 || + ctx->conf.radar_enabled) { + ctx->conf.min_def = ctx->conf.def; + return; + } + + max_bw = ieee80211_get_chanctx_max_required_bw(local, &ctx->conf); + + /* downgrade chandef up to max_bw */ + min_def = ctx->conf.def; + while (min_def.width > max_bw) + ieee80211_chandef_downgrade(&min_def); + + if (cfg80211_chandef_identical(&ctx->conf.min_def, &min_def)) + return; + + ctx->conf.min_def = min_def; + if (!ctx->driver_present) + return; + + drv_change_chanctx(local, ctx, IEEE80211_CHANCTX_CHANGE_MIN_WIDTH); +} + static void ieee80211_change_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, const struct cfg80211_chan_def *chandef) @@ -20,6 +154,7 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, ctx->conf.def = *chandef; drv_change_chanctx(local, ctx, IEEE80211_CHANCTX_CHANGE_WIDTH); + ieee80211_recalc_chanctx_min_def(local, ctx); if (!local->use_chanctx) { local->_oper_chandef = *chandef; @@ -93,11 +228,12 @@ ieee80211_new_chanctx(struct ieee80211_local *local, ctx->conf.rx_chains_dynamic = 1; ctx->mode = mode; ctx->conf.radar_enabled = ieee80211_is_radar_required(local); + ieee80211_recalc_chanctx_min_def(local, ctx); if (!local->use_chanctx) local->hw.conf.radar_enabled = ctx->conf.radar_enabled; - /* acquire mutex to prevent idle from changing */ - mutex_lock(&local->mtx); + /* we hold the mutex to prevent idle from changing */ + lockdep_assert_held(&local->mtx); /* turn idle off *before* setting channel -- some drivers need that */ changed = ieee80211_idle_off(local); if (changed) @@ -110,19 +246,14 @@ ieee80211_new_chanctx(struct ieee80211_local *local, err = drv_add_chanctx(local, ctx); if (err) { kfree(ctx); - ctx = ERR_PTR(err); - ieee80211_recalc_idle(local); - goto out; + return ERR_PTR(err); } } /* and keep the mutex held until the new chanctx is on the list */ list_add_rcu(&ctx->list, &local->chanctx_list); - out: - mutex_unlock(&local->mtx); - return ctx; } @@ -158,9 +289,7 @@ static void ieee80211_free_chanctx(struct ieee80211_local *local, /* throw a warning if this wasn't the only channel context. */ WARN_ON(check_single_channel && !list_empty(&local->chanctx_list)); - mutex_lock(&local->mtx); ieee80211_recalc_idle(local); - mutex_unlock(&local->mtx); } static int ieee80211_assign_vif_chanctx(struct ieee80211_sub_if_data *sdata, @@ -179,6 +308,7 @@ static int ieee80211_assign_vif_chanctx(struct ieee80211_sub_if_data *sdata, ctx->refcount++; ieee80211_recalc_txpower(sdata); + ieee80211_recalc_chanctx_min_def(local, ctx); sdata->vif.bss_conf.idle = false; if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && @@ -221,6 +351,31 @@ static void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, ieee80211_change_chanctx(local, ctx, compat); } +static void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *chanctx) +{ + bool radar_enabled; + + lockdep_assert_held(&local->chanctx_mtx); + /* for setting local->radar_detect_enabled */ + lockdep_assert_held(&local->mtx); + + radar_enabled = ieee80211_is_radar_required(local); + + if (radar_enabled == chanctx->conf.radar_enabled) + return; + + chanctx->conf.radar_enabled = radar_enabled; + local->radar_detect_enabled = chanctx->conf.radar_enabled; + + if (!local->use_chanctx) { + local->hw.conf.radar_enabled = chanctx->conf.radar_enabled; + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + } + + drv_change_chanctx(local, chanctx, IEEE80211_CHANCTX_CHANGE_RADAR); +} + static void ieee80211_unassign_vif_chanctx(struct ieee80211_sub_if_data *sdata, struct ieee80211_chanctx *ctx) { @@ -243,6 +398,7 @@ static void ieee80211_unassign_vif_chanctx(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_chanctx_chantype(sdata->local, ctx); ieee80211_recalc_smps_chanctx(local, ctx); ieee80211_recalc_radar_chanctx(local, ctx); + ieee80211_recalc_chanctx_min_def(local, ctx); } } @@ -266,29 +422,6 @@ static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata) ieee80211_free_chanctx(local, ctx); } -void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local, - struct ieee80211_chanctx *chanctx) -{ - bool radar_enabled; - - lockdep_assert_held(&local->chanctx_mtx); - - radar_enabled = ieee80211_is_radar_required(local); - - if (radar_enabled == chanctx->conf.radar_enabled) - return; - - chanctx->conf.radar_enabled = radar_enabled; - local->radar_detect_enabled = chanctx->conf.radar_enabled; - - if (!local->use_chanctx) { - local->hw.conf.radar_enabled = chanctx->conf.radar_enabled; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); - } - - drv_change_chanctx(local, chanctx, IEEE80211_CHANCTX_CHANGE_RADAR); -} - void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *chanctx) { @@ -380,6 +513,8 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata, struct ieee80211_chanctx *ctx; int ret; + lockdep_assert_held(&local->mtx); + WARN_ON(sdata->dev && netif_carrier_ok(sdata->dev)); mutex_lock(&local->chanctx_mtx); @@ -411,15 +546,17 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata, } int ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata, - const struct cfg80211_chan_def *chandef, u32 *changed) { struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *ctx; + const struct cfg80211_chan_def *chandef = &sdata->csa_chandef; int ret; u32 chanctx_changed = 0; + lockdep_assert_held(&local->mtx); + /* should never be called if not performing a channel switch. */ if (WARN_ON(!sdata->vif.csa_active)) return -EINVAL; @@ -456,6 +593,7 @@ int ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata, ieee80211_recalc_chanctx_chantype(local, ctx); ieee80211_recalc_smps_chanctx(local, ctx); ieee80211_recalc_radar_chanctx(local, ctx); + ieee80211_recalc_chanctx_min_def(local, ctx); ret = 0; out: @@ -516,6 +654,8 @@ void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata) { WARN_ON(sdata->dev && netif_carrier_ok(sdata->dev)); + lockdep_assert_held(&sdata->local->mtx); + mutex_lock(&sdata->local->chanctx_mtx); __ieee80211_vif_release_channel(sdata); mutex_unlock(&sdata->local->chanctx_mtx); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 5c090e41d9bb..fa16e54980a1 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -17,6 +17,172 @@ #define DEBUGFS_FORMAT_BUFFER_SIZE 100 +#define TX_LATENCY_BIN_DELIMTER_C ',' +#define TX_LATENCY_BIN_DELIMTER_S "," +#define TX_LATENCY_BINS_DISABLED "enable(bins disabled)\n" +#define TX_LATENCY_DISABLED "disable\n" + + +/* + * Display if Tx latency statistics & bins are enabled/disabled + */ +static ssize_t sta_tx_latency_stat_read(struct file *file, + char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct ieee80211_local *local = file->private_data; + struct ieee80211_tx_latency_bin_ranges *tx_latency; + char *buf; + int bufsz, i, ret; + int pos = 0; + + rcu_read_lock(); + + tx_latency = rcu_dereference(local->tx_latency); + + if (tx_latency && tx_latency->n_ranges) { + bufsz = tx_latency->n_ranges * 15; + buf = kzalloc(bufsz, GFP_ATOMIC); + if (!buf) + goto err; + + for (i = 0; i < tx_latency->n_ranges; i++) + pos += scnprintf(buf + pos, bufsz - pos, "%d,", + tx_latency->ranges[i]); + pos += scnprintf(buf + pos, bufsz - pos, "\n"); + } else if (tx_latency) { + bufsz = sizeof(TX_LATENCY_BINS_DISABLED) + 1; + buf = kzalloc(bufsz, GFP_ATOMIC); + if (!buf) + goto err; + + pos += scnprintf(buf + pos, bufsz - pos, "%s\n", + TX_LATENCY_BINS_DISABLED); + } else { + bufsz = sizeof(TX_LATENCY_DISABLED) + 1; + buf = kzalloc(bufsz, GFP_ATOMIC); + if (!buf) + goto err; + + pos += scnprintf(buf + pos, bufsz - pos, "%s\n", + TX_LATENCY_DISABLED); + } + + rcu_read_unlock(); + + ret = simple_read_from_buffer(userbuf, count, ppos, buf, pos); + kfree(buf); + + return ret; +err: + rcu_read_unlock(); + return -ENOMEM; +} + +/* + * Receive input from user regarding Tx latency statistics + * The input should indicate if Tx latency statistics and bins are + * enabled/disabled. + * If bins are enabled input should indicate the amount of different bins and + * their ranges. Each bin will count how many Tx frames transmitted within the + * appropriate latency. + * Legal input is: + * a) "enable(bins disabled)" - to enable only general statistics + * b) "a,b,c,d,...z" - to enable general statistics and bins, where all are + * numbers and a < b < c < d.. < z + * c) "disable" - disable all statistics + * NOTE: must configure Tx latency statistics bins before stations connected. + */ + +static ssize_t sta_tx_latency_stat_write(struct file *file, + const char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct ieee80211_local *local = file->private_data; + char buf[128] = {}; + char *bins = buf; + char *token; + int buf_size, i, alloc_size; + int prev_bin = 0; + int n_ranges = 0; + int ret = count; + struct ieee80211_tx_latency_bin_ranges *tx_latency; + + if (sizeof(buf) <= count) + return -EINVAL; + buf_size = count; + if (copy_from_user(buf, userbuf, buf_size)) + return -EFAULT; + + mutex_lock(&local->sta_mtx); + + /* cannot change config once we have stations */ + if (local->num_sta) + goto unlock; + + tx_latency = + rcu_dereference_protected(local->tx_latency, + lockdep_is_held(&local->sta_mtx)); + + /* disable Tx statistics */ + if (!strcmp(buf, TX_LATENCY_DISABLED)) { + if (!tx_latency) + goto unlock; + rcu_assign_pointer(local->tx_latency, NULL); + synchronize_rcu(); + kfree(tx_latency); + goto unlock; + } + + /* Tx latency already enabled */ + if (tx_latency) + goto unlock; + + if (strcmp(TX_LATENCY_BINS_DISABLED, buf)) { + /* check how many bins and between what ranges user requested */ + token = buf; + while (*token != '\0') { + if (*token == TX_LATENCY_BIN_DELIMTER_C) + n_ranges++; + token++; + } + n_ranges++; + } + + alloc_size = sizeof(struct ieee80211_tx_latency_bin_ranges) + + n_ranges * sizeof(u32); + tx_latency = kzalloc(alloc_size, GFP_ATOMIC); + if (!tx_latency) { + ret = -ENOMEM; + goto unlock; + } + tx_latency->n_ranges = n_ranges; + for (i = 0; i < n_ranges; i++) { /* setting bin ranges */ + token = strsep(&bins, TX_LATENCY_BIN_DELIMTER_S); + sscanf(token, "%d", &tx_latency->ranges[i]); + /* bins values should be in ascending order */ + if (prev_bin >= tx_latency->ranges[i]) { + ret = -EINVAL; + kfree(tx_latency); + goto unlock; + } + prev_bin = tx_latency->ranges[i]; + } + rcu_assign_pointer(local->tx_latency, tx_latency); + +unlock: + mutex_unlock(&local->sta_mtx); + + return ret; +} + +static const struct file_operations stats_tx_latency_ops = { + .write = sta_tx_latency_stat_write, + .read = sta_tx_latency_stat_read, + .open = simple_open, + .llseek = generic_file_llseek, +}; + int mac80211_format_buffer(char __user *userbuf, size_t count, loff_t *ppos, char *fmt, ...) { @@ -315,4 +481,6 @@ void debugfs_hw_add(struct ieee80211_local *local) DEBUGFS_DEVSTATS_ADD(dot11RTSFailureCount); DEBUGFS_DEVSTATS_ADD(dot11FCSErrorCount); DEBUGFS_DEVSTATS_ADD(dot11RTSSuccessCount); + + DEBUGFS_DEVSTATS_ADD(tx_latency); } diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 04b5a14c8a05..ebf80f3abd83 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -133,7 +133,15 @@ static ssize_t ieee80211_if_fmt_##name( \ jiffies_to_msecs(sdata->field)); \ } -#define __IEEE80211_IF_FILE(name, _write) \ +#define _IEEE80211_IF_FILE_OPS(name, _read, _write) \ +static const struct file_operations name##_ops = { \ + .read = (_read), \ + .write = (_write), \ + .open = simple_open, \ + .llseek = generic_file_llseek, \ +} + +#define _IEEE80211_IF_FILE_R_FN(name) \ static ssize_t ieee80211_if_read_##name(struct file *file, \ char __user *userbuf, \ size_t count, loff_t *ppos) \ @@ -141,28 +149,34 @@ static ssize_t ieee80211_if_read_##name(struct file *file, \ return ieee80211_if_read(file->private_data, \ userbuf, count, ppos, \ ieee80211_if_fmt_##name); \ -} \ -static const struct file_operations name##_ops = { \ - .read = ieee80211_if_read_##name, \ - .write = (_write), \ - .open = simple_open, \ - .llseek = generic_file_llseek, \ } -#define __IEEE80211_IF_FILE_W(name) \ +#define _IEEE80211_IF_FILE_W_FN(name) \ static ssize_t ieee80211_if_write_##name(struct file *file, \ const char __user *userbuf, \ size_t count, loff_t *ppos) \ { \ return ieee80211_if_write(file->private_data, userbuf, count, \ ppos, ieee80211_if_parse_##name); \ -} \ -__IEEE80211_IF_FILE(name, ieee80211_if_write_##name) +} + +#define IEEE80211_IF_FILE_R(name) \ + _IEEE80211_IF_FILE_R_FN(name) \ + _IEEE80211_IF_FILE_OPS(name, ieee80211_if_read_##name, NULL) + +#define IEEE80211_IF_FILE_W(name) \ + _IEEE80211_IF_FILE_W_FN(name) \ + _IEEE80211_IF_FILE_OPS(name, NULL, ieee80211_if_write_##name) +#define IEEE80211_IF_FILE_RW(name) \ + _IEEE80211_IF_FILE_R_FN(name) \ + _IEEE80211_IF_FILE_W_FN(name) \ + _IEEE80211_IF_FILE_OPS(name, ieee80211_if_read_##name, \ + ieee80211_if_write_##name) #define IEEE80211_IF_FILE(name, field, format) \ - IEEE80211_IF_FMT_##format(name, field) \ - __IEEE80211_IF_FILE(name, NULL) + IEEE80211_IF_FMT_##format(name, field) \ + IEEE80211_IF_FILE_R(name) /* common attributes */ IEEE80211_IF_FILE(drop_unencrypted, drop_unencrypted, DEC); @@ -199,7 +213,7 @@ ieee80211_if_fmt_hw_queues(const struct ieee80211_sub_if_data *sdata, return len; } -__IEEE80211_IF_FILE(hw_queues, NULL); +IEEE80211_IF_FILE_R(hw_queues); /* STA attributes */ IEEE80211_IF_FILE(bssid, u.mgd.bssid, MAC); @@ -275,14 +289,7 @@ static ssize_t ieee80211_if_parse_smps(struct ieee80211_sub_if_data *sdata, return -EINVAL; } - -__IEEE80211_IF_FILE_W(smps); - -static ssize_t ieee80211_if_fmt_tkip_mic_test( - const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) -{ - return -EOPNOTSUPP; -} +IEEE80211_IF_FILE_RW(smps); static ssize_t ieee80211_if_parse_tkip_mic_test( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) @@ -349,8 +356,7 @@ static ssize_t ieee80211_if_parse_tkip_mic_test( return buflen; } - -__IEEE80211_IF_FILE_W(tkip_mic_test); +IEEE80211_IF_FILE_W(tkip_mic_test); static ssize_t ieee80211_if_fmt_uapsd_queues( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) @@ -378,7 +384,7 @@ static ssize_t ieee80211_if_parse_uapsd_queues( return buflen; } -__IEEE80211_IF_FILE_W(uapsd_queues); +IEEE80211_IF_FILE_RW(uapsd_queues); static ssize_t ieee80211_if_fmt_uapsd_max_sp_len( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) @@ -406,7 +412,7 @@ static ssize_t ieee80211_if_parse_uapsd_max_sp_len( return buflen; } -__IEEE80211_IF_FILE_W(uapsd_max_sp_len); +IEEE80211_IF_FILE_RW(uapsd_max_sp_len); /* AP attributes */ IEEE80211_IF_FILE(num_mcast_sta, u.ap.num_mcast_sta, ATOMIC); @@ -419,7 +425,7 @@ static ssize_t ieee80211_if_fmt_num_buffered_multicast( return scnprintf(buf, buflen, "%u\n", skb_queue_len(&sdata->u.ap.ps.bc_buf)); } -__IEEE80211_IF_FILE(num_buffered_multicast, NULL); +IEEE80211_IF_FILE_R(num_buffered_multicast); /* IBSS attributes */ static ssize_t ieee80211_if_fmt_tsf( @@ -468,9 +474,10 @@ static ssize_t ieee80211_if_parse_tsf( } } + ieee80211_recalc_dtim(local, sdata); return buflen; } -__IEEE80211_IF_FILE_W(tsf); +IEEE80211_IF_FILE_RW(tsf); /* WDS attributes */ diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 19c54a44ed47..80194b557a0c 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -38,6 +38,13 @@ static const struct file_operations sta_ ##name## _ops = { \ .llseek = generic_file_llseek, \ } +#define STA_OPS_W(name) \ +static const struct file_operations sta_ ##name## _ops = { \ + .write = sta_##name##_write, \ + .open = simple_open, \ + .llseek = generic_file_llseek, \ +} + #define STA_OPS_RW(name) \ static const struct file_operations sta_ ##name## _ops = { \ .read = sta_##name##_read, \ @@ -388,6 +395,131 @@ static ssize_t sta_last_rx_rate_read(struct file *file, char __user *userbuf, } STA_OPS(last_rx_rate); +static int +sta_tx_latency_stat_header(struct ieee80211_tx_latency_bin_ranges *tx_latency, + char *buf, int pos, int bufsz) +{ + int i; + int range_count = tx_latency->n_ranges; + u32 *bin_ranges = tx_latency->ranges; + + pos += scnprintf(buf + pos, bufsz - pos, + "Station\t\t\tTID\tMax\tAvg"); + if (range_count) { + pos += scnprintf(buf + pos, bufsz - pos, + "\t<=%d", bin_ranges[0]); + for (i = 0; i < range_count - 1; i++) + pos += scnprintf(buf + pos, bufsz - pos, "\t%d-%d", + bin_ranges[i], bin_ranges[i+1]); + pos += scnprintf(buf + pos, bufsz - pos, + "\t%d<", bin_ranges[range_count - 1]); + } + + pos += scnprintf(buf + pos, bufsz - pos, "\n"); + + return pos; +} + +static int +sta_tx_latency_stat_table(struct ieee80211_tx_latency_bin_ranges *tx_lat_range, + struct ieee80211_tx_latency_stat *tx_lat, + char *buf, int pos, int bufsz, int tid) +{ + u32 avg = 0; + int j; + int bin_count = tx_lat->bin_count; + + pos += scnprintf(buf + pos, bufsz - pos, "\t\t\t%d", tid); + /* make sure you don't divide in 0 */ + if (tx_lat->counter) + avg = tx_lat->sum / tx_lat->counter; + + pos += scnprintf(buf + pos, bufsz - pos, "\t%d\t%d", + tx_lat->max, avg); + + if (tx_lat_range->n_ranges && tx_lat->bins) + for (j = 0; j < bin_count; j++) + pos += scnprintf(buf + pos, bufsz - pos, + "\t%d", tx_lat->bins[j]); + pos += scnprintf(buf + pos, bufsz - pos, "\n"); + + return pos; +} + +/* + * Output Tx latency statistics station && restart all statistics information + */ +static ssize_t sta_tx_latency_stat_read(struct file *file, + char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->local; + struct ieee80211_tx_latency_bin_ranges *tx_latency; + char *buf; + int bufsz, ret, i; + int pos = 0; + + bufsz = 20 * IEEE80211_NUM_TIDS * + sizeof(struct ieee80211_tx_latency_stat); + buf = kzalloc(bufsz, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + rcu_read_lock(); + + tx_latency = rcu_dereference(local->tx_latency); + + if (!sta->tx_lat) { + pos += scnprintf(buf + pos, bufsz - pos, + "Tx latency statistics are not enabled\n"); + goto unlock; + } + + pos = sta_tx_latency_stat_header(tx_latency, buf, pos, bufsz); + + pos += scnprintf(buf + pos, bufsz - pos, "%pM\n", sta->sta.addr); + for (i = 0; i < IEEE80211_NUM_TIDS; i++) + pos = sta_tx_latency_stat_table(tx_latency, &sta->tx_lat[i], + buf, pos, bufsz, i); +unlock: + rcu_read_unlock(); + + ret = simple_read_from_buffer(userbuf, count, ppos, buf, pos); + kfree(buf); + + return ret; +} +STA_OPS(tx_latency_stat); + +static ssize_t sta_tx_latency_stat_reset_write(struct file *file, + const char __user *userbuf, + size_t count, loff_t *ppos) +{ + u32 *bins; + int bin_count; + struct sta_info *sta = file->private_data; + int i; + + if (!sta->tx_lat) + return -EINVAL; + + for (i = 0; i < IEEE80211_NUM_TIDS; i++) { + bins = sta->tx_lat[i].bins; + bin_count = sta->tx_lat[i].bin_count; + + sta->tx_lat[i].max = 0; + sta->tx_lat[i].sum = 0; + sta->tx_lat[i].counter = 0; + + if (bin_count) + memset(bins, 0, bin_count * sizeof(u32)); + } + + return count; +} +STA_OPS_W(tx_latency_stat_reset); + #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ sta->debugfs.dir, sta, &sta_ ##name## _ops); @@ -441,6 +573,8 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD(last_ack_signal); DEBUGFS_ADD(current_tx_rate); DEBUGFS_ADD(last_rx_rate); + DEBUGFS_ADD(tx_latency_stat); + DEBUGFS_ADD(tx_latency_stat_reset); DEBUGFS_ADD_COUNTER(rx_packets, rx_packets); DEBUGFS_ADD_COUNTER(tx_packets, tx_packets); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 5d03c47c0a4c..ef8b385eff04 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -242,22 +242,6 @@ static inline u64 drv_prepare_multicast(struct ieee80211_local *local, return ret; } -static inline void drv_set_multicast_list(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - struct netdev_hw_addr_list *mc_list) -{ - bool allmulti = sdata->flags & IEEE80211_SDATA_ALLMULTI; - - trace_drv_set_multicast_list(local, sdata, mc_list->count); - - check_sdata_in_driver(sdata); - - if (local->ops->set_multicast_list) - local->ops->set_multicast_list(&local->hw, &sdata->vif, - allmulti, mc_list); - trace_drv_return_void(local); -} - static inline void drv_configure_filter(struct ieee80211_local *local, unsigned int changed_flags, unsigned int *total_flags, @@ -550,6 +534,22 @@ static inline void drv_sta_remove_debugfs(struct ieee80211_local *local, } #endif +static inline void drv_sta_pre_rcu_remove(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct sta_info *sta) +{ + might_sleep(); + + sdata = get_bss_sdata(sdata); + check_sdata_in_driver(sdata); + + trace_drv_sta_pre_rcu_remove(local, sdata, &sta->sta); + if (local->ops->sta_pre_rcu_remove) + local->ops->sta_pre_rcu_remove(&local->hw, &sdata->vif, + &sta->sta); + trace_drv_return_void(local); +} + static inline __must_check int drv_sta_state(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 9a8be8f69224..70dd013de836 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -466,7 +466,9 @@ void ieee80211_request_smps_ap_work(struct work_struct *work) u.ap.request_smps_work); sdata_lock(sdata); - __ieee80211_request_smps_ap(sdata, sdata->u.ap.driver_smps_mode); + if (sdata_dereference(sdata->u.ap.beacon, sdata)) + __ieee80211_request_smps_ap(sdata, + sdata->u.ap.driver_smps_mode); sdata_unlock(sdata); } @@ -479,10 +481,9 @@ void ieee80211_request_smps(struct ieee80211_vif *vif, vif->type != NL80211_IFTYPE_AP)) return; - if (WARN_ON(smps_mode == IEEE80211_SMPS_OFF)) - smps_mode = IEEE80211_SMPS_AUTOMATIC; - if (vif->type == NL80211_IFTYPE_STATION) { + if (WARN_ON(smps_mode == IEEE80211_SMPS_OFF)) + smps_mode = IEEE80211_SMPS_AUTOMATIC; if (sdata->u.mgd.driver_smps_mode == smps_mode) return; sdata->u.mgd.driver_smps_mode = smps_mode; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 27a39de89679..2796a198728f 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -293,14 +293,17 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, radar_required = true; } + mutex_lock(&local->mtx); ieee80211_vif_release_channel(sdata); if (ieee80211_vif_use_channel(sdata, &chandef, ifibss->fixed_channel ? IEEE80211_CHANCTX_SHARED : IEEE80211_CHANCTX_EXCLUSIVE)) { sdata_info(sdata, "Failed to join IBSS, no channel context\n"); + mutex_unlock(&local->mtx); return; } + mutex_unlock(&local->mtx); memcpy(ifibss->bssid, bssid, ETH_ALEN); @@ -363,7 +366,9 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.ssid_len = 0; RCU_INIT_POINTER(ifibss->presp, NULL); kfree_rcu(presp, rcu_head); + mutex_lock(&local->mtx); ieee80211_vif_release_channel(sdata); + mutex_unlock(&local->mtx); sdata_info(sdata, "Failed to join IBSS, driver failure: %d\n", err); return; @@ -522,7 +527,7 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata, if (csa_settings) ieee80211_send_action_csa(sdata, csa_settings); - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON); + return BSS_CHANGED_BEACON; out: return ret; } @@ -534,7 +539,8 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata) int err; u16 capability; - sdata_lock(sdata); + sdata_assert_lock(sdata); + /* update cfg80211 bss information with the new channel */ if (!is_zero_ether_addr(ifibss->bssid)) { capability = WLAN_CAPABILITY_IBSS; @@ -550,19 +556,21 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata) capability); /* XXX: should not really modify cfg80211 data */ if (cbss) { - cbss->channel = sdata->local->csa_chandef.chan; + cbss->channel = sdata->csa_chandef.chan; cfg80211_put_bss(sdata->local->hw.wiphy, cbss); } } - ifibss->chandef = sdata->local->csa_chandef; + ifibss->chandef = sdata->csa_chandef; /* generate the beacon */ err = ieee80211_ibss_csa_beacon(sdata, NULL); - sdata_unlock(sdata); if (err < 0) return err; + if (err) + ieee80211_bss_info_change_notify(sdata, err); + return 0; } @@ -687,12 +695,9 @@ static void ieee80211_ibss_disconnect(struct ieee80211_sub_if_data *sdata) struct cfg80211_bss *cbss; struct beacon_data *presp; struct sta_info *sta; - int active_ibss; u16 capability; - active_ibss = ieee80211_sta_active_ibss(sdata); - - if (!active_ibss && !is_zero_ether_addr(ifibss->bssid)) { + if (!is_zero_ether_addr(ifibss->bssid)) { capability = WLAN_CAPABILITY_IBSS; if (ifibss->privacy) @@ -744,7 +749,9 @@ static void ieee80211_ibss_disconnect(struct ieee80211_sub_if_data *sdata) ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED | BSS_CHANGED_IBSS); drv_leave_ibss(local, sdata); + mutex_lock(&local->mtx); ieee80211_vif_release_channel(sdata); + mutex_unlock(&local->mtx); } static void ieee80211_csa_connection_drop_work(struct work_struct *work) @@ -753,12 +760,16 @@ static void ieee80211_csa_connection_drop_work(struct work_struct *work) container_of(work, struct ieee80211_sub_if_data, u.ibss.csa_connection_drop_work); + sdata_lock(sdata); + ieee80211_ibss_disconnect(sdata); synchronize_rcu(); skb_queue_purge(&sdata->skb_queue); /* trigger a scan to find another IBSS network to join */ ieee80211_queue_work(&sdata->local->hw, &sdata->work); + + sdata_unlock(sdata); } static void ieee80211_ibss_csa_mark_radar(struct ieee80211_sub_if_data *sdata) @@ -784,18 +795,10 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, struct cfg80211_csa_settings params; struct ieee80211_csa_ie csa_ie; struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; - struct ieee80211_chanctx_conf *chanctx_conf; - struct ieee80211_chanctx *chanctx; enum nl80211_channel_type ch_type; - int err, num_chanctx; + int err; u32 sta_flags; - if (sdata->vif.csa_active) - return true; - - if (!sdata->vif.bss_conf.ibss_joined) - return false; - sta_flags = IEEE80211_STA_DISABLE_VHT; switch (ifibss->chandef.width) { case NL80211_CHAN_WIDTH_5: @@ -830,9 +833,6 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, params.count = csa_ie.count; params.chandef = csa_ie.chandef; - if (ifibss->chandef.chan->band != params.chandef.chan->band) - goto disconnect; - switch (ifibss->chandef.width) { case NL80211_CHAN_WIDTH_20_NOHT: case NL80211_CHAN_WIDTH_20: @@ -888,28 +888,12 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, params.radar_required = true; } - rcu_read_lock(); - chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); - if (!chanctx_conf) { - rcu_read_unlock(); - goto disconnect; - } - - /* don't handle for multi-VIF cases */ - chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); - if (chanctx->refcount > 1) { - rcu_read_unlock(); - goto disconnect; - } - num_chanctx = 0; - list_for_each_entry_rcu(chanctx, &sdata->local->chanctx_list, list) - num_chanctx++; - - if (num_chanctx > 1) { - rcu_read_unlock(); - goto disconnect; + if (cfg80211_chandef_identical(¶ms.chandef, + &sdata->vif.bss_conf.chandef)) { + ibss_dbg(sdata, + "received csa with an identical chandef, ignoring\n"); + return true; } - rcu_read_unlock(); /* all checks done, now perform the channel switch. */ ibss_dbg(sdata, @@ -918,19 +902,9 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, params.block_tx = !!csa_ie.mode; - ieee80211_ibss_csa_beacon(sdata, ¶ms); - sdata->csa_radar_required = params.radar_required; - - if (params.block_tx) - ieee80211_stop_queues_by_reason(&sdata->local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); - - sdata->local->csa_chandef = params.chandef; - sdata->vif.csa_active = true; - - ieee80211_bss_info_change_notify(sdata, err); - drv_channel_switch_beacon(sdata, ¶ms.chandef); + if (ieee80211_channel_switch(sdata->local->hw.wiphy, sdata->dev, + ¶ms)) + goto disconnect; ieee80211_ibss_csa_mark_radar(sdata); @@ -966,7 +940,8 @@ ieee80211_rx_mgmt_spectrum_mgmt(struct ieee80211_sub_if_data *sdata, if (len < required_len) return; - ieee80211_ibss_process_chanswitch(sdata, elems, false); + if (!sdata->vif.csa_active) + ieee80211_ibss_process_chanswitch(sdata, elems, false); } static void ieee80211_rx_mgmt_deauth_ibss(struct ieee80211_sub_if_data *sdata, @@ -1147,7 +1122,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, goto put_bss; /* process channel switch */ - if (ieee80211_ibss_process_chanswitch(sdata, elems, true)) + if (sdata->vif.csa_active || + ieee80211_ibss_process_chanswitch(sdata, elems, true)) goto put_bss; /* same BSSID */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 4aea4e791113..3701930c6649 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -232,6 +232,7 @@ struct ieee80211_rx_data { struct beacon_data { u8 *head, *tail; int head_len, tail_len; + struct ieee80211_meshconf_ie *meshconf; struct rcu_head rcu_head; }; @@ -245,7 +246,8 @@ struct ps_data { /* yes, this looks ugly, but guarantees that we can later use * bitmap_empty :) * NB: don't touch this bitmap, use sta_info_{set,clear}_tim_bit */ - u8 tim[sizeof(unsigned long) * BITS_TO_LONGS(IEEE80211_MAX_AID + 1)]; + u8 tim[sizeof(unsigned long) * BITS_TO_LONGS(IEEE80211_MAX_AID + 1)] + __aligned(__alignof__(unsigned long)); struct sk_buff_head bc_buf; atomic_t num_sta_ps; /* number of stations in PS mode */ int dtim_count; @@ -540,7 +542,10 @@ struct ieee80211_mesh_sync_ops { struct ieee80211_mgmt *mgmt, struct ieee802_11_elems *elems, struct ieee80211_rx_status *rx_status); - void (*adjust_tbtt)(struct ieee80211_sub_if_data *sdata); + + /* should be called with beacon_data under RCU read lock */ + void (*adjust_tbtt)(struct ieee80211_sub_if_data *sdata, + struct beacon_data *beacon); /* add other framework functions here */ }; @@ -614,6 +619,9 @@ struct ieee80211_if_mesh { bool chsw_init; u8 chsw_ttl; u16 pre_value; + + /* offset from skb->data while building IE */ + int meshconf_offset; }; #ifdef CONFIG_MAC80211_MESH @@ -686,6 +694,11 @@ struct ieee80211_chanctx { struct ieee80211_chanctx_conf conf; }; +struct mac80211_qos_map { + struct cfg80211_qos_map qos_map; + struct rcu_head rcu_head; +}; + struct ieee80211_sub_if_data { struct list_head list; @@ -728,13 +741,16 @@ struct ieee80211_sub_if_data { u16 sequence_number; __be16 control_port_protocol; bool control_port_no_encrypt; + int encrypt_headroom; struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS]; + struct mac80211_qos_map __rcu *qos_map; struct work_struct csa_finalize_work; int csa_counter_offset_beacon; int csa_counter_offset_presp; bool csa_radar_required; + struct cfg80211_chan_def csa_chandef; /* used to reconfigure hardware SM PS */ struct work_struct recalc_smps; @@ -774,10 +790,6 @@ struct ieee80211_sub_if_data { u32 mntr_flags; } u; - spinlock_t cleanup_stations_lock; - struct list_head cleanup_stations; - struct work_struct cleanup_stations_wk; - #ifdef CONFIG_MAC80211_DEBUGFS struct { struct dentry *subdir_stations; @@ -811,6 +823,9 @@ static inline void sdata_unlock(struct ieee80211_sub_if_data *sdata) __release(&sdata->wdev.mtx); } +#define sdata_dereference(p, sdata) \ + rcu_dereference_protected(p, lockdep_is_held(&sdata->wdev.mtx)) + static inline void sdata_assert_lock(struct ieee80211_sub_if_data *sdata) { @@ -896,6 +911,24 @@ struct tpt_led_trigger { }; #endif +/* + * struct ieee80211_tx_latency_bin_ranges - Tx latency statistics bins ranges + * + * Measuring Tx latency statistics. Counts how many Tx frames transmitted in a + * certain latency range (in Milliseconds). Each station that uses these + * ranges will have bins to count the amount of frames received in that range. + * The user can configure the ranges via debugfs. + * If ranges is NULL then Tx latency statistics bins are disabled for all + * stations. + * + * @n_ranges: number of ranges that are taken in account + * @ranges: the ranges that the user requested or NULL if disabled. + */ +struct ieee80211_tx_latency_bin_ranges { + int n_ranges; + u32 ranges[]; +}; + /** * mac80211 scan flags - currently active scan mode * @@ -1048,6 +1081,12 @@ struct ieee80211_local { struct timer_list sta_cleanup; int sta_generation; + /* + * Tx latency statistics parameters for all stations. + * Can enable via debugfs (NULL when disabled). + */ + struct ieee80211_tx_latency_bin_ranges __rcu *tx_latency; + struct sk_buff_head pending[IEEE80211_MAX_QUEUES]; struct tasklet_struct tx_pending_tasklet; @@ -1088,12 +1127,12 @@ struct ieee80211_local { struct work_struct sched_scan_stopped_work; struct ieee80211_sub_if_data __rcu *sched_scan_sdata; + struct cfg80211_sched_scan_request *sched_scan_req; unsigned long leave_oper_channel_time; enum mac80211_scan_state next_scan_state; struct delayed_work scan_work; struct ieee80211_sub_if_data __rcu *scan_sdata; - struct cfg80211_chan_def csa_chandef; /* For backward compatibility only -- do not use */ struct cfg80211_chan_def _oper_chandef; @@ -1397,6 +1436,9 @@ void ieee80211_rx_bss_put(struct ieee80211_local *local, struct ieee80211_bss *bss); /* scheduled scan handling */ +int +__ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, + struct cfg80211_sched_scan_request *req); int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req); int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata); @@ -1415,6 +1457,8 @@ void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc); /* channel switch handling */ void ieee80211_csa_finalize_work(struct work_struct *work); +int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_csa_settings *params); /* interface handling */ int ieee80211_iface_init(void); @@ -1437,8 +1481,6 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local); bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata); void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata); -int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, - struct cfg80211_beacon_data *params); static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata) { @@ -1693,6 +1735,7 @@ int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps_mode); void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata); +void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata); size_t ieee80211_ie_split(const u8 *ies, size_t ielen, const u8 *ids, int n_ids, size_t offset); @@ -1731,7 +1774,6 @@ ieee80211_vif_change_bandwidth(struct ieee80211_sub_if_data *sdata, /* NOTE: only use ieee80211_vif_change_channel() for channel switch */ int __must_check ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata, - const struct cfg80211_chan_def *chandef, u32 *changed); void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata); void ieee80211_vif_vlan_copy_chanctx(struct ieee80211_sub_if_data *sdata); @@ -1740,8 +1782,8 @@ void ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata, void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *chanctx); -void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local, - struct ieee80211_chanctx *chanctx); +void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx); void ieee80211_dfs_cac_timer(unsigned long data); void ieee80211_dfs_cac_timer_work(struct work_struct *work); @@ -1750,6 +1792,17 @@ void ieee80211_dfs_radar_detected_work(struct work_struct *work); int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, struct cfg80211_csa_settings *csa_settings); +bool ieee80211_cs_valid(const struct ieee80211_cipher_scheme *cs); +bool ieee80211_cs_list_valid(const struct ieee80211_cipher_scheme *cs, int n); +const struct ieee80211_cipher_scheme * +ieee80211_cs_get(struct ieee80211_local *local, u32 cipher, + enum nl80211_iftype iftype); +int ieee80211_cs_headroom(struct ieee80211_local *local, + struct cfg80211_crypto_settings *crypto, + enum nl80211_iftype iftype); +void ieee80211_recalc_dtim(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata); + #ifdef CONFIG_MAC80211_NOINLINE #define debug_noinline noinline #else diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index a0757913046e..ce1c44370610 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -401,6 +401,8 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) snprintf(sdata->name, IFNAMSIZ, "%s-monitor", wiphy_name(local->hw.wiphy)); + sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; + ieee80211_set_default_queues(sdata); ret = drv_add_interface(local, sdata); @@ -416,18 +418,24 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) return ret; } + mutex_lock(&local->iflist_mtx); + rcu_assign_pointer(local->monitor_sdata, sdata); + mutex_unlock(&local->iflist_mtx); + + mutex_lock(&local->mtx); ret = ieee80211_vif_use_channel(sdata, &local->monitor_chandef, IEEE80211_CHANCTX_EXCLUSIVE); + mutex_unlock(&local->mtx); if (ret) { + mutex_lock(&local->iflist_mtx); + rcu_assign_pointer(local->monitor_sdata, NULL); + mutex_unlock(&local->iflist_mtx); + synchronize_net(); drv_remove_interface(local, sdata); kfree(sdata); return ret; } - mutex_lock(&local->iflist_mtx); - rcu_assign_pointer(local->monitor_sdata, sdata); - mutex_unlock(&local->iflist_mtx); - return 0; } @@ -454,7 +462,9 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local) synchronize_net(); + mutex_lock(&local->mtx); ieee80211_vif_release_channel(sdata); + mutex_unlock(&local->mtx); drv_remove_interface(local, sdata); @@ -749,6 +759,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, u32 hw_reconf_flags = 0; int i, flushed; struct ps_data *ps; + struct cfg80211_chan_def chandef; clear_bit(SDATA_STATE_RUNNING, &sdata->state); @@ -763,12 +774,19 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_roc_purge(local, sdata); - if (sdata->vif.type == NL80211_IFTYPE_STATION) + switch (sdata->vif.type) { + case NL80211_IFTYPE_STATION: ieee80211_mgd_stop(sdata); - - if (sdata->vif.type == NL80211_IFTYPE_ADHOC) + break; + case NL80211_IFTYPE_ADHOC: ieee80211_ibss_stop(sdata); - + break; + case NL80211_IFTYPE_AP: + cancel_work_sync(&sdata->u.ap.request_smps_work); + break; + default: + break; + } /* * Remove all stations associated with this interface. @@ -783,10 +801,8 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, * This is relevant only in WDS mode, in all other modes we've * already removed all stations when disconnecting or similar, * so warn otherwise. - * - * We call sta_info_flush_cleanup() later, to combine RCU waits. */ - flushed = sta_info_flush_defer(sdata); + flushed = sta_info_flush(sdata); WARN_ON_ONCE((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) || (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1)); @@ -823,11 +839,13 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, cancel_delayed_work_sync(&sdata->dfs_cac_timer_work); if (sdata->wdev.cac_started) { + chandef = sdata->vif.bss_conf.chandef; WARN_ON(local->suspended); - mutex_lock(&local->iflist_mtx); + mutex_lock(&local->mtx); ieee80211_vif_release_channel(sdata); - mutex_unlock(&local->iflist_mtx); - cfg80211_cac_event(sdata->dev, NL80211_RADAR_CAC_ABORTED, + mutex_unlock(&local->mtx); + cfg80211_cac_event(sdata->dev, &chandef, + NL80211_RADAR_CAC_ABORTED, GFP_KERNEL); } @@ -886,23 +904,15 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, cancel_work_sync(&sdata->work); /* * When we get here, the interface is marked down. + * Free the remaining keys, if there are any + * (shouldn't be, except maybe in WDS mode?) * - * sta_info_flush_cleanup() requires rcu_barrier() - * first to wait for the station call_rcu() calls - * to complete, and we also need synchronize_rcu() - * to wait for the RX path in case it is using the - * interface and enqueuing frames at this very time on + * Force the key freeing to always synchronize_net() + * to wait for the RX path in case it is using this + * interface enqueuing frames * at this very time on * another CPU. */ - synchronize_rcu(); - rcu_barrier(); - sta_info_flush_cleanup(sdata); - - /* - * Free all remaining keys, there shouldn't be any, - * except maybe in WDS mode? - */ - ieee80211_free_keys(sdata); + ieee80211_free_keys(sdata, true); /* fall through */ case NL80211_IFTYPE_AP: @@ -1013,17 +1023,6 @@ static void ieee80211_set_multicast_list(struct net_device *dev) atomic_dec(&local->iff_promiscs); sdata->flags ^= IEEE80211_SDATA_PROMISC; } - - /* - * TODO: If somebody needs this on AP interfaces, - * it can be enabled easily but multicast - * addresses from VLANs need to be synced. - */ - if (sdata->vif.type != NL80211_IFTYPE_MONITOR && - sdata->vif.type != NL80211_IFTYPE_AP_VLAN && - sdata->vif.type != NL80211_IFTYPE_AP) - drv_set_multicast_list(local, sdata, &dev->mc); - spin_lock_bh(&local->filter_lock); __hw_addr_sync(&local->mc_list, &dev->mc, dev->addr_len); spin_unlock_bh(&local->filter_lock); @@ -1036,11 +1035,10 @@ static void ieee80211_set_multicast_list(struct net_device *dev) */ static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata) { - int flushed; int i; /* free extra data */ - ieee80211_free_keys(sdata); + ieee80211_free_keys(sdata, false); ieee80211_debugfs_remove_netdev(sdata); @@ -1050,9 +1048,6 @@ static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata) if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_rmc_free(sdata); - - flushed = sta_info_flush(sdata); - WARN_ON(flushed); } static void ieee80211_uninit(struct net_device *dev) @@ -1062,7 +1057,8 @@ static void ieee80211_uninit(struct net_device *dev) static u16 ieee80211_netdev_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb); } @@ -1080,7 +1076,8 @@ static const struct net_device_ops ieee80211_dataif_ops = { static u16 ieee80211_monitor_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; @@ -1272,6 +1269,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, sdata->control_port_protocol = cpu_to_be16(ETH_P_PAE); sdata->control_port_no_encrypt = false; + sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; sdata->noack_map = 0; @@ -1497,8 +1495,8 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local, bool used = false; list_for_each_entry(sdata, &local->interfaces, list) { - if (memcmp(local->hw.wiphy->addresses[i].addr, - sdata->vif.addr, ETH_ALEN) == 0) { + if (ether_addr_equal(local->hw.wiphy->addresses[i].addr, + sdata->vif.addr)) { used = true; break; } @@ -1558,8 +1556,7 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local, val += inc; list_for_each_entry(sdata, &local->interfaces, list) { - if (memcmp(tmp_addr, sdata->vif.addr, - ETH_ALEN) == 0) { + if (ether_addr_equal(tmp_addr, sdata->vif.addr)) { used = true; break; } @@ -1579,15 +1576,6 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local, mutex_unlock(&local->iflist_mtx); } -static void ieee80211_cleanup_sdata_stas_wk(struct work_struct *wk) -{ - struct ieee80211_sub_if_data *sdata; - - sdata = container_of(wk, struct ieee80211_sub_if_data, cleanup_stations_wk); - - ieee80211_cleanup_sdata_stas(sdata); -} - int ieee80211_if_add(struct ieee80211_local *local, const char *name, struct wireless_dev **new_wdev, enum nl80211_iftype type, struct vif_params *params) @@ -1660,9 +1648,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, INIT_LIST_HEAD(&sdata->key_list); - spin_lock_init(&sdata->cleanup_stations_lock); - INIT_LIST_HEAD(&sdata->cleanup_stations); - INIT_WORK(&sdata->cleanup_stations_wk, ieee80211_cleanup_sdata_stas_wk); INIT_DELAYED_WORK(&sdata->dfs_cac_timer_work, ieee80211_dfs_cac_timer_work); INIT_DELAYED_WORK(&sdata->dec_tailroom_needed_wk, @@ -1687,6 +1672,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL; sdata->user_power_level = local->user_power_level; + sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; + /* setup type-dependent data */ ieee80211_setup_sdata(sdata, type); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 3e51dd7d98b3..6ff65a1ebaa9 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -260,25 +260,29 @@ static void ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, int idx; bool defunikey, defmultikey, defmgmtkey; + /* caller must provide at least one old/new */ + if (WARN_ON(!new && !old)) + return; + if (new) list_add_tail(&new->list, &sdata->key_list); - if (sta && pairwise) { - rcu_assign_pointer(sta->ptk, new); - } else if (sta) { - if (old) - idx = old->conf.keyidx; - else - idx = new->conf.keyidx; - rcu_assign_pointer(sta->gtk[idx], new); - } else { - WARN_ON(new && old && new->conf.keyidx != old->conf.keyidx); + WARN_ON(new && old && new->conf.keyidx != old->conf.keyidx); - if (old) - idx = old->conf.keyidx; - else - idx = new->conf.keyidx; + if (old) + idx = old->conf.keyidx; + else + idx = new->conf.keyidx; + if (sta) { + if (pairwise) { + rcu_assign_pointer(sta->ptk[idx], new); + sta->ptk_idx = idx; + } else { + rcu_assign_pointer(sta->gtk[idx], new); + sta->gtk_idx = idx; + } + } else { defunikey = old && old == key_mtx_dereference(sdata->local, sdata->default_unicast_key); @@ -312,9 +316,11 @@ static void ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, list_del(&old->list); } -struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, - const u8 *key_data, - size_t seq_len, const u8 *seq) +struct ieee80211_key * +ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, + const u8 *key_data, + size_t seq_len, const u8 *seq, + const struct ieee80211_cipher_scheme *cs) { struct ieee80211_key *key; int i, j, err; @@ -393,6 +399,18 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, return ERR_PTR(err); } break; + default: + if (cs) { + size_t len = (seq_len > MAX_PN_LEN) ? + MAX_PN_LEN : seq_len; + + key->conf.iv_len = cs->hdr_len; + key->conf.icv_len = cs->mic_len; + for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) + for (j = 0; j < len; j++) + key->u.gen.rx_pn[i][j] = + seq[len - j - 1]; + } } memcpy(key->conf.key, key_data, key_len); INIT_LIST_HEAD(&key->list); @@ -475,7 +493,7 @@ int ieee80211_key_link(struct ieee80211_key *key, mutex_lock(&sdata->local->key_mtx); if (sta && pairwise) - old_key = key_mtx_dereference(sdata->local, sta->ptk); + old_key = key_mtx_dereference(sdata->local, sta->ptk[idx]); else if (sta) old_key = key_mtx_dereference(sdata->local, sta->gtk[idx]); else @@ -571,14 +589,10 @@ void ieee80211_iter_keys(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_iter_keys); -void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata) +static void ieee80211_free_keys_iface(struct ieee80211_sub_if_data *sdata, + struct list_head *keys) { struct ieee80211_key *key, *tmp; - LIST_HEAD(keys); - - cancel_delayed_work_sync(&sdata->dec_tailroom_needed_wk); - - mutex_lock(&sdata->local->key_mtx); sdata->crypto_tx_tailroom_needed_cnt -= sdata->crypto_tx_tailroom_pending_dec; @@ -590,28 +604,51 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata) ieee80211_key_replace(key->sdata, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); - list_add_tail(&key->list, &keys); + list_add_tail(&key->list, keys); } ieee80211_debugfs_key_update_default(sdata); +} - if (!list_empty(&keys)) { - synchronize_net(); - list_for_each_entry_safe(key, tmp, &keys, list) - __ieee80211_key_destroy(key, false); +void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, + bool force_synchronize) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_sub_if_data *vlan; + struct ieee80211_key *key, *tmp; + LIST_HEAD(keys); + + cancel_delayed_work_sync(&sdata->dec_tailroom_needed_wk); + + mutex_lock(&local->key_mtx); + + ieee80211_free_keys_iface(sdata, &keys); + + if (sdata->vif.type == NL80211_IFTYPE_AP) { + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + ieee80211_free_keys_iface(vlan, &keys); } + if (!list_empty(&keys) || force_synchronize) + synchronize_net(); + list_for_each_entry_safe(key, tmp, &keys, list) + __ieee80211_key_destroy(key, false); + WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt || sdata->crypto_tx_tailroom_pending_dec); + if (sdata->vif.type == NL80211_IFTYPE_AP) { + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt || + vlan->crypto_tx_tailroom_pending_dec); + } - mutex_unlock(&sdata->local->key_mtx); + mutex_unlock(&local->key_mtx); } void ieee80211_free_sta_keys(struct ieee80211_local *local, struct sta_info *sta) { - struct ieee80211_key *key, *tmp; - LIST_HEAD(keys); + struct ieee80211_key *key; int i; mutex_lock(&local->key_mtx); @@ -622,25 +659,18 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local, ieee80211_key_replace(key->sdata, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); - list_add(&key->list, &keys); + __ieee80211_key_destroy(key, true); } - key = key_mtx_dereference(local, sta->ptk); - if (key) { + for (i = 0; i < NUM_DEFAULT_KEYS; i++) { + key = key_mtx_dereference(local, sta->ptk[i]); + if (!key) + continue; ieee80211_key_replace(key->sdata, key->sta, key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE, key, NULL); - list_add(&key->list, &keys); - } - - /* - * NB: the station code relies on this being - * done even if there aren't any keys - */ - synchronize_net(); - - list_for_each_entry_safe(key, tmp, &keys, list) __ieee80211_key_destroy(key, true); + } mutex_unlock(&local->key_mtx); } @@ -877,7 +907,7 @@ ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, key = ieee80211_key_alloc(keyconf->cipher, keyconf->keyidx, keyconf->keylen, keyconf->key, - 0, NULL); + 0, NULL, NULL); if (IS_ERR(key)) return ERR_CAST(key); diff --git a/net/mac80211/key.h b/net/mac80211/key.h index aaae0ed37004..19db68663d75 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -18,6 +18,7 @@ #define NUM_DEFAULT_KEYS 4 #define NUM_DEFAULT_MGMT_KEYS 2 +#define MAX_PN_LEN 16 struct ieee80211_local; struct ieee80211_sub_if_data; @@ -93,6 +94,10 @@ struct ieee80211_key { u32 replays; /* dot11RSNAStatsCMACReplays */ u32 icverrors; /* dot11RSNAStatsCMACICVErrors */ } aes_cmac; + struct { + /* generic cipher scheme */ + u8 rx_pn[IEEE80211_NUM_TIDS + 1][MAX_PN_LEN]; + } gen; } u; /* number of times this key has been used */ @@ -113,9 +118,11 @@ struct ieee80211_key { struct ieee80211_key_conf conf; }; -struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, - const u8 *key_data, - size_t seq_len, const u8 *seq); +struct ieee80211_key * +ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, + const u8 *key_data, + size_t seq_len, const u8 *seq, + const struct ieee80211_cipher_scheme *cs); /* * Insert a key into data structures (sdata, sta if necessary) * to make it used, free old key. On failure, also free the new key. @@ -129,7 +136,8 @@ void ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, int idx, bool uni, bool multi); void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata, int idx); -void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata); +void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, + bool force_synchronize); void ieee80211_free_sta_keys(struct ieee80211_local *local, struct sta_info *sta); void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 7d1c3ac48ed9..d767cfb9b45f 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -250,12 +250,8 @@ static void ieee80211_restart_work(struct work_struct *work) /* wait for scan work complete */ flush_workqueue(local->workqueue); - mutex_lock(&local->mtx); - WARN(test_bit(SCAN_HW_SCANNING, &local->scanning) || - rcu_dereference_protected(local->sched_scan_sdata, - lockdep_is_held(&local->mtx)), - "%s called with hardware scan in progress\n", __func__); - mutex_unlock(&local->mtx); + WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), + "%s called with hardware scan in progress\n", __func__); rtnl_lock(); ieee80211_scan_cancel(local); @@ -651,15 +647,14 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, } EXPORT_SYMBOL(ieee80211_alloc_hw); -int ieee80211_register_hw(struct ieee80211_hw *hw) +static int ieee80211_init_cipher_suites(struct ieee80211_local *local) { - struct ieee80211_local *local = hw_to_local(hw); - int result, i; - enum ieee80211_band band; - int channels, max_bitrates; - bool supp_ht, supp_vht; - netdev_features_t feature_whitelist; - struct cfg80211_chan_def dflt_chandef = {}; + bool have_wep = !(IS_ERR(local->wep_tx_tfm) || + IS_ERR(local->wep_rx_tfm)); + bool have_mfp = local->hw.flags & IEEE80211_HW_MFP_CAPABLE; + const struct ieee80211_cipher_scheme *cs = local->hw.cipher_schemes; + int n_suites = 0, r = 0, w = 0; + u32 *suites; static const u32 cipher_suites[] = { /* keep WEP first, it may be removed below */ WLAN_CIPHER_SUITE_WEP40, @@ -671,6 +666,93 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) WLAN_CIPHER_SUITE_AES_CMAC }; + /* Driver specifies the ciphers, we have nothing to do... */ + if (local->hw.wiphy->cipher_suites && have_wep) + return 0; + + /* Set up cipher suites if driver relies on mac80211 cipher defs */ + if (!local->hw.wiphy->cipher_suites && !cs) { + local->hw.wiphy->cipher_suites = cipher_suites; + local->hw.wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites); + + if (!have_mfp) + local->hw.wiphy->n_cipher_suites--; + + if (!have_wep) { + local->hw.wiphy->cipher_suites += 2; + local->hw.wiphy->n_cipher_suites -= 2; + } + + return 0; + } + + if (!local->hw.wiphy->cipher_suites) { + /* + * Driver specifies cipher schemes only + * We start counting ciphers defined by schemes, TKIP and CCMP + */ + n_suites = local->hw.n_cipher_schemes + 2; + + /* check if we have WEP40 and WEP104 */ + if (have_wep) + n_suites += 2; + + /* check if we have AES_CMAC */ + if (have_mfp) + n_suites++; + + suites = kmalloc(sizeof(u32) * n_suites, GFP_KERNEL); + if (!suites) + return -ENOMEM; + + suites[w++] = WLAN_CIPHER_SUITE_CCMP; + suites[w++] = WLAN_CIPHER_SUITE_TKIP; + + if (have_wep) { + suites[w++] = WLAN_CIPHER_SUITE_WEP40; + suites[w++] = WLAN_CIPHER_SUITE_WEP104; + } + + if (have_mfp) + suites[w++] = WLAN_CIPHER_SUITE_AES_CMAC; + + for (r = 0; r < local->hw.n_cipher_schemes; r++) + suites[w++] = cs[r].cipher; + } else { + /* Driver provides cipher suites, but we need to exclude WEP */ + suites = kmemdup(local->hw.wiphy->cipher_suites, + sizeof(u32) * local->hw.wiphy->n_cipher_suites, + GFP_KERNEL); + if (!suites) + return -ENOMEM; + + for (r = 0; r < local->hw.wiphy->n_cipher_suites; r++) { + u32 suite = local->hw.wiphy->cipher_suites[r]; + + if (suite == WLAN_CIPHER_SUITE_WEP40 || + suite == WLAN_CIPHER_SUITE_WEP104) + continue; + suites[w++] = suite; + } + } + + local->hw.wiphy->cipher_suites = suites; + local->hw.wiphy->n_cipher_suites = w; + local->wiphy_ciphers_allocated = true; + + return 0; +} + +int ieee80211_register_hw(struct ieee80211_hw *hw) +{ + struct ieee80211_local *local = hw_to_local(hw); + int result, i; + enum ieee80211_band band; + int channels, max_bitrates; + bool supp_ht, supp_vht; + netdev_features_t feature_whitelist; + struct cfg80211_chan_def dflt_chandef = {}; + if (hw->flags & IEEE80211_HW_QUEUE_CONTROL && (local->hw.offchannel_tx_hw_queue == IEEE80211_INVAL_HW_QUEUE || local->hw.offchannel_tx_hw_queue >= local->hw.queues)) @@ -764,17 +846,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) /* TODO: consider VHT for RX chains, hopefully it's the same */ } - local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) + - sizeof(void *) * channels, GFP_KERNEL); - if (!local->int_scan_req) - return -ENOMEM; - - for (band = 0; band < IEEE80211_NUM_BANDS; band++) { - if (!local->hw.wiphy->bands[band]) - continue; - local->int_scan_req->rates[band] = (u32) -1; - } - /* if low-level driver supports AP, we also support VLAN */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_AP)) { hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_AP_VLAN); @@ -798,6 +869,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) return -EINVAL; } + local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) + + sizeof(void *) * channels, GFP_KERNEL); + if (!local->int_scan_req) + return -ENOMEM; + + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { + if (!local->hw.wiphy->bands[band]) + continue; + local->int_scan_req->rates[band] = (u32) -1; + } + #ifndef CONFIG_MAC80211_MESH /* mesh depends on Kconfig, but drivers should set it if they want */ local->hw.wiphy->interface_modes &= ~BIT(NL80211_IFTYPE_MESH_POINT); @@ -851,43 +933,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (local->hw.wiphy->max_scan_ie_len) local->hw.wiphy->max_scan_ie_len -= local->scan_ies_len; - /* Set up cipher suites unless driver already did */ - if (!local->hw.wiphy->cipher_suites) { - local->hw.wiphy->cipher_suites = cipher_suites; - local->hw.wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites); - if (!(local->hw.flags & IEEE80211_HW_MFP_CAPABLE)) - local->hw.wiphy->n_cipher_suites--; - } - if (IS_ERR(local->wep_tx_tfm) || IS_ERR(local->wep_rx_tfm)) { - if (local->hw.wiphy->cipher_suites == cipher_suites) { - local->hw.wiphy->cipher_suites += 2; - local->hw.wiphy->n_cipher_suites -= 2; - } else { - u32 *suites; - int r, w = 0; - - /* Filter out WEP */ - - suites = kmemdup( - local->hw.wiphy->cipher_suites, - sizeof(u32) * local->hw.wiphy->n_cipher_suites, - GFP_KERNEL); - if (!suites) { - result = -ENOMEM; - goto fail_wiphy_register; - } - for (r = 0; r < local->hw.wiphy->n_cipher_suites; r++) { - u32 suite = local->hw.wiphy->cipher_suites[r]; - if (suite == WLAN_CIPHER_SUITE_WEP40 || - suite == WLAN_CIPHER_SUITE_WEP104) - continue; - suites[w++] = suite; - } - local->hw.wiphy->cipher_suites = suites; - local->hw.wiphy->n_cipher_suites = w; - local->wiphy_ciphers_allocated = true; - } - } + WARN_ON(!ieee80211_cs_list_valid(local->hw.cipher_schemes, + local->hw.n_cipher_schemes)); + + result = ieee80211_init_cipher_suites(local); + if (result < 0) + goto fail_wiphy_register; if (!local->ops->remain_on_channel) local->hw.wiphy->max_remain_on_channel_duration = 5000; @@ -1090,6 +1141,8 @@ void ieee80211_free_hw(struct ieee80211_hw *hw) ieee80211_free_ack_frame, NULL); idr_destroy(&local->ack_status_frames); + kfree(rcu_access_pointer(local->tx_latency)); + wiphy_free(local->hw.wiphy); } EXPORT_SYMBOL(ieee80211_free_hw); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index ba105257d03f..5b919cab1de0 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -259,6 +259,9 @@ int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata, *pos++ = WLAN_EID_MESH_CONFIG; *pos++ = meshconf_len; + /* save a pointer for quick updates in pre-tbtt */ + ifmsh->meshconf_offset = pos - skb->data; + /* Active path selection protocol ID */ *pos++ = ifmsh->mesh_pp_id; /* Active path selection metric ID */ @@ -674,8 +677,6 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) rcu_read_lock(); csa = rcu_dereference(ifmsh->csa); if (csa) { - __le16 pre_value; - pos = skb_put(skb, 13); memset(pos, 0, 13); *pos++ = WLAN_EID_CHANNEL_SWITCH; @@ -697,8 +698,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT : 0x00; put_unaligned_le16(WLAN_REASON_MESH_CHAN, pos); pos += 2; - pre_value = cpu_to_le16(ifmsh->pre_value); - memcpy(pos, &pre_value, 2); + put_unaligned_le16(ifmsh->pre_value, pos); pos += 2; } rcu_read_unlock(); @@ -726,6 +726,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) bcn->tail_len = skb->len; memcpy(bcn->tail, skb->data, bcn->tail_len); + bcn->meshconf = (struct ieee80211_meshconf_ie *) + (bcn->tail + ifmsh->meshconf_offset); dev_kfree_skb(skb); rcu_assign_pointer(ifmsh->beacon, bcn); @@ -805,6 +807,7 @@ int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata) return -ENOMEM; } + ieee80211_recalc_dtim(local, sdata); ieee80211_bss_info_change_notify(sdata, changed); netif_carrier_on(sdata->dev); @@ -964,7 +967,7 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->local->csa_chandef = params.chandef; + sdata->csa_chandef = params.chandef; sdata->vif.csa_active = true; ieee80211_bss_info_change_notify(sdata, err); diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 2bc7fd2f787d..f39a19f9090f 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -215,8 +215,6 @@ int mesh_rmc_check(struct ieee80211_sub_if_data *sdata, bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *ie); void mesh_ids_set_default(struct ieee80211_if_mesh *mesh); -void mesh_mgmt_ies_add(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb); int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_meshid_ie(struct ieee80211_sub_if_data *sdata, @@ -303,8 +301,8 @@ void mesh_mpath_table_grow(void); void mesh_mpp_table_grow(void); /* Mesh paths */ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, - u8 ttl, const u8 *target, __le32 target_sn, - __le16 target_rcode, const u8 *ra); + u8 ttl, const u8 *target, u32 target_sn, + u16 target_rcode, const u8 *ra); void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta); void mesh_path_flush_pending(struct mesh_path *mpath); void mesh_path_tx_pending(struct mesh_path *mpath); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 486819cd02cd..f9514685d45a 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -102,12 +102,11 @@ enum mpath_frame_type { static const u8 broadcast_addr[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, - const u8 *orig_addr, __le32 orig_sn, + const u8 *orig_addr, u32 orig_sn, u8 target_flags, const u8 *target, - __le32 target_sn, const u8 *da, + u32 target_sn, const u8 *da, u8 hop_count, u8 ttl, - __le32 lifetime, __le32 metric, - __le32 preq_id, + u32 lifetime, u32 metric, u32 preq_id, struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; @@ -167,33 +166,33 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, if (action == MPATH_PREP) { memcpy(pos, target, ETH_ALEN); pos += ETH_ALEN; - memcpy(pos, &target_sn, 4); + put_unaligned_le32(target_sn, pos); pos += 4; } else { if (action == MPATH_PREQ) { - memcpy(pos, &preq_id, 4); + put_unaligned_le32(preq_id, pos); pos += 4; } memcpy(pos, orig_addr, ETH_ALEN); pos += ETH_ALEN; - memcpy(pos, &orig_sn, 4); + put_unaligned_le32(orig_sn, pos); pos += 4; } - memcpy(pos, &lifetime, 4); /* interval for RANN */ + put_unaligned_le32(lifetime, pos); /* interval for RANN */ pos += 4; - memcpy(pos, &metric, 4); + put_unaligned_le32(metric, pos); pos += 4; if (action == MPATH_PREQ) { *pos++ = 1; /* destination count */ *pos++ = target_flags; memcpy(pos, target, ETH_ALEN); pos += ETH_ALEN; - memcpy(pos, &target_sn, 4); + put_unaligned_le32(target_sn, pos); pos += 4; } else if (action == MPATH_PREP) { memcpy(pos, orig_addr, ETH_ALEN); pos += ETH_ALEN; - memcpy(pos, &orig_sn, 4); + put_unaligned_le32(orig_sn, pos); pos += 4; } @@ -239,8 +238,8 @@ static void prepare_frame_for_deferred_tx(struct ieee80211_sub_if_data *sdata, * frame directly but add it to the pending queue instead. */ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, - u8 ttl, const u8 *target, __le32 target_sn, - __le16 target_rcode, const u8 *ra) + u8 ttl, const u8 *target, u32 target_sn, + u16 target_rcode, const u8 *ra) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb; @@ -254,13 +253,13 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, return -EAGAIN; skb = dev_alloc_skb(local->tx_headroom + - IEEE80211_ENCRYPT_HEADROOM + + sdata->encrypt_headroom + IEEE80211_ENCRYPT_TAILROOM + hdr_len + 2 + 15 /* PERR IE */); if (!skb) return -1; - skb_reserve(skb, local->tx_headroom + IEEE80211_ENCRYPT_HEADROOM); + skb_reserve(skb, local->tx_headroom + sdata->encrypt_headroom); mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len); memset(mgmt, 0, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | @@ -293,9 +292,9 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, pos++; memcpy(pos, target, ETH_ALEN); pos += ETH_ALEN; - memcpy(pos, &target_sn, 4); + put_unaligned_le32(target_sn, pos); pos += 4; - memcpy(pos, &target_rcode, 2); + put_unaligned_le16(target_rcode, pos); /* see note in function header */ prepare_frame_for_deferred_tx(sdata, skb); @@ -592,10 +591,9 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, if (ttl != 0) { mhwmp_dbg(sdata, "replying to the PREQ\n"); mesh_path_sel_frame_tx(MPATH_PREP, 0, orig_addr, - cpu_to_le32(orig_sn), 0, target_addr, - cpu_to_le32(target_sn), mgmt->sa, 0, ttl, - cpu_to_le32(lifetime), cpu_to_le32(metric), - 0, sdata); + orig_sn, 0, target_addr, + target_sn, mgmt->sa, 0, ttl, + lifetime, metric, 0, sdata); } else { ifmsh->mshstats.dropped_frames_ttl++; } @@ -625,11 +623,9 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, } mesh_path_sel_frame_tx(MPATH_PREQ, flags, orig_addr, - cpu_to_le32(orig_sn), target_flags, target_addr, - cpu_to_le32(target_sn), da, - hopcount, ttl, cpu_to_le32(lifetime), - cpu_to_le32(metric), cpu_to_le32(preq_id), - sdata); + orig_sn, target_flags, target_addr, + target_sn, da, hopcount, ttl, lifetime, + metric, preq_id, sdata); if (!is_multicast_ether_addr(da)) ifmsh->mshstats.fwded_unicast++; else @@ -695,11 +691,9 @@ static void hwmp_prep_frame_process(struct ieee80211_sub_if_data *sdata, target_sn = PREP_IE_TARGET_SN(prep_elem); orig_sn = PREP_IE_ORIG_SN(prep_elem); - mesh_path_sel_frame_tx(MPATH_PREP, flags, orig_addr, - cpu_to_le32(orig_sn), 0, target_addr, - cpu_to_le32(target_sn), next_hop, hopcount, - ttl, cpu_to_le32(lifetime), cpu_to_le32(metric), - 0, sdata); + mesh_path_sel_frame_tx(MPATH_PREP, flags, orig_addr, orig_sn, 0, + target_addr, target_sn, next_hop, hopcount, + ttl, lifetime, metric, 0, sdata); rcu_read_unlock(); sdata->u.mesh.mshstats.fwded_unicast++; @@ -750,8 +744,7 @@ static void hwmp_perr_frame_process(struct ieee80211_sub_if_data *sdata, if (!ifmsh->mshcfg.dot11MeshForwarding) goto endperr; mesh_path_error_tx(sdata, ttl, target_addr, - cpu_to_le32(target_sn), - cpu_to_le16(target_rcode), + target_sn, target_rcode, broadcast_addr); } else spin_unlock_bh(&mpath->state_lock); @@ -847,11 +840,9 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, if (ifmsh->mshcfg.dot11MeshForwarding) { mesh_path_sel_frame_tx(MPATH_RANN, flags, orig_addr, - cpu_to_le32(orig_sn), - 0, NULL, 0, broadcast_addr, - hopcount, ttl, cpu_to_le32(interval), - cpu_to_le32(metric + metric_txsta), - 0, sdata); + orig_sn, 0, NULL, 0, broadcast_addr, + hopcount, ttl, interval, + metric + metric_txsta, 0, sdata); } rcu_read_unlock(); @@ -1049,11 +1040,9 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) spin_unlock_bh(&mpath->state_lock); da = (mpath->is_root) ? mpath->rann_snd_addr : broadcast_addr; - mesh_path_sel_frame_tx(MPATH_PREQ, 0, sdata->vif.addr, - cpu_to_le32(ifmsh->sn), target_flags, mpath->dst, - cpu_to_le32(mpath->sn), da, 0, - ttl, cpu_to_le32(lifetime), 0, - cpu_to_le32(ifmsh->preq_id++), sdata); + mesh_path_sel_frame_tx(MPATH_PREQ, 0, sdata->vif.addr, ifmsh->sn, + target_flags, mpath->dst, mpath->sn, da, 0, + ttl, lifetime, 0, ifmsh->preq_id++, sdata); mod_timer(&mpath->timer, jiffies + mpath->discovery_timeout); enddiscovery: @@ -1212,10 +1201,9 @@ void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata) switch (ifmsh->mshcfg.dot11MeshHWMPRootMode) { case IEEE80211_PROACTIVE_RANN: mesh_path_sel_frame_tx(MPATH_RANN, flags, sdata->vif.addr, - cpu_to_le32(++ifmsh->sn), - 0, NULL, 0, broadcast_addr, - 0, ifmsh->mshcfg.element_ttl, - cpu_to_le32(interval), 0, 0, sdata); + ++ifmsh->sn, 0, NULL, 0, broadcast_addr, + 0, ifmsh->mshcfg.element_ttl, + interval, 0, 0, sdata); break; case IEEE80211_PROACTIVE_PREQ_WITH_PREP: flags |= IEEE80211_PREQ_PROACTIVE_PREP_FLAG; @@ -1224,11 +1212,10 @@ void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata) target_flags |= IEEE80211_PREQ_TO_FLAG | IEEE80211_PREQ_USN_FLAG; mesh_path_sel_frame_tx(MPATH_PREQ, flags, sdata->vif.addr, - cpu_to_le32(++ifmsh->sn), target_flags, - (u8 *) broadcast_addr, 0, broadcast_addr, - 0, ifmsh->mshcfg.element_ttl, - cpu_to_le32(interval), - 0, cpu_to_le32(ifmsh->preq_id++), sdata); + ++ifmsh->sn, target_flags, + (u8 *) broadcast_addr, 0, broadcast_addr, + 0, ifmsh->mshcfg.element_ttl, interval, + 0, ifmsh->preq_id++, sdata); break; default: mhwmp_dbg(sdata, "Proactive mechanism not supported\n"); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 89aacfd2756d..7d050ed6fe5a 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -722,7 +722,6 @@ void mesh_plink_broken(struct sta_info *sta) struct mpath_node *node; struct ieee80211_sub_if_data *sdata = sta->sdata; int i; - __le16 reason = cpu_to_le16(WLAN_REASON_MESH_PATH_DEST_UNREACHABLE); rcu_read_lock(); tbl = rcu_dereference(mesh_paths); @@ -736,9 +735,9 @@ void mesh_plink_broken(struct sta_info *sta) ++mpath->sn; spin_unlock_bh(&mpath->state_lock); mesh_path_error_tx(sdata, - sdata->u.mesh.mshcfg.element_ttl, - mpath->dst, cpu_to_le32(mpath->sn), - reason, bcast); + sdata->u.mesh.mshcfg.element_ttl, + mpath->dst, mpath->sn, + WLAN_REASON_MESH_PATH_DEST_UNREACHABLE, bcast); } } rcu_read_unlock(); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 4301aa5aa227..e8f60aa2e848 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -19,12 +19,6 @@ #define mod_plink_timer(s, t) (mod_timer(&s->plink_timer, \ jiffies + HZ * t / 1000)) -/* We only need a valid sta if user configured a minimum rssi_threshold. */ -#define rssi_threshold_check(sta, sdata) \ - (sdata->u.mesh.mshcfg.rssi_threshold == 0 ||\ - (sta && (s8) -ewma_read(&sta->avg_signal) > \ - sdata->u.mesh.mshcfg.rssi_threshold)) - enum plink_event { PLINK_UNDEFINED, OPN_ACPT, @@ -61,7 +55,17 @@ static const char * const mplevents[] = { static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, enum ieee80211_self_protected_actioncode action, - u8 *da, __le16 llid, __le16 plid, __le16 reason); + u8 *da, u16 llid, u16 plid, u16 reason); + + +/* We only need a valid sta if user configured a minimum rssi_threshold. */ +static bool rssi_threshold_check(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta) +{ + s32 rssi_threshold = sdata->u.mesh.mshcfg.rssi_threshold; + return rssi_threshold == 0 || + (sta && (s8) -ewma_read(&sta->avg_signal) > rssi_threshold); +} /** * mesh_plink_fsm_restart - restart a mesh peer link finite state machine @@ -242,7 +246,7 @@ u32 mesh_plink_deactivate(struct sta_info *sta) spin_lock_bh(&sta->lock); changed = __mesh_plink_deactivate(sta); - sta->reason = cpu_to_le16(WLAN_REASON_MESH_PEER_CANCELED); + sta->reason = WLAN_REASON_MESH_PEER_CANCELED; mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, sta->sta.addr, sta->llid, sta->plid, sta->reason); @@ -253,7 +257,7 @@ u32 mesh_plink_deactivate(struct sta_info *sta) static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, enum ieee80211_self_protected_actioncode action, - u8 *da, __le16 llid, __le16 plid, __le16 reason) + u8 *da, u16 llid, u16 plid, u16 reason) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb; @@ -279,7 +283,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, 2 + 8 + /* peering IE */ sdata->u.mesh.ie_len); if (!skb) - return -1; + return err; info = IEEE80211_SKB_CB(skb); skb_reserve(skb, local->tx_headroom); mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len); @@ -301,7 +305,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, if (action == WLAN_SP_MESH_PEERING_CONFIRM) { /* AID */ pos = skb_put(skb, 2); - memcpy(pos + 2, &plid, 2); + put_unaligned_le16(plid, pos + 2); } if (ieee80211_add_srates_ie(sdata, skb, true, band) || ieee80211_add_ext_srates_ie(sdata, skb, true, band) || @@ -343,14 +347,14 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, *pos++ = ie_len; memcpy(pos, &peering_proto, 2); pos += 2; - memcpy(pos, &llid, 2); + put_unaligned_le16(llid, pos); pos += 2; if (include_plid) { - memcpy(pos, &plid, 2); + put_unaligned_le16(plid, pos); pos += 2; } if (action == WLAN_SP_MESH_PEERING_CLOSE) { - memcpy(pos, &reason, 2); + put_unaligned_le16(reason, pos); pos += 2; } @@ -433,6 +437,7 @@ __mesh_sta_info_alloc(struct ieee80211_sub_if_data *sdata, u8 *hw_addr) sta_info_pre_move_state(sta, IEEE80211_STA_AUTHORIZED); set_sta_flag(sta, WLAN_STA_WME); + sta->sta.wme = true; return sta; } @@ -518,7 +523,7 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, sta->plink_state == NL80211_PLINK_LISTEN && sdata->u.mesh.accepting_plinks && sdata->u.mesh.mshcfg.auto_open_plinks && - rssi_threshold_check(sta, sdata)) + rssi_threshold_check(sdata, sta)) changed = mesh_plink_open(sta); ieee80211_mps_frame_release(sta, elems); @@ -530,9 +535,10 @@ out: static void mesh_plink_timer(unsigned long data) { struct sta_info *sta; - __le16 llid, plid, reason; + u16 reason = 0; struct ieee80211_sub_if_data *sdata; struct mesh_config *mshcfg; + enum ieee80211_self_protected_actioncode action = 0; /* * This STA is valid because sta_info_destroy() will @@ -553,9 +559,6 @@ static void mesh_plink_timer(unsigned long data) mpl_dbg(sta->sdata, "Mesh plink timer for %pM fired on state %s\n", sta->sta.addr, mplstates[sta->plink_state]); - reason = 0; - llid = sta->llid; - plid = sta->plid; sdata = sta->sdata; mshcfg = &sdata->u.mesh.mshcfg; @@ -574,33 +577,31 @@ static void mesh_plink_timer(unsigned long data) rand % sta->plink_timeout; ++sta->plink_retries; mod_plink_timer(sta, sta->plink_timeout); - spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_OPEN, - sta->sta.addr, llid, 0, 0); + action = WLAN_SP_MESH_PEERING_OPEN; break; } - reason = cpu_to_le16(WLAN_REASON_MESH_MAX_RETRIES); + reason = WLAN_REASON_MESH_MAX_RETRIES; /* fall through on else */ case NL80211_PLINK_CNF_RCVD: /* confirm timer */ if (!reason) - reason = cpu_to_le16(WLAN_REASON_MESH_CONFIRM_TIMEOUT); + reason = WLAN_REASON_MESH_CONFIRM_TIMEOUT; sta->plink_state = NL80211_PLINK_HOLDING; mod_plink_timer(sta, mshcfg->dot11MeshHoldingTimeout); - spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, - sta->sta.addr, llid, plid, reason); + action = WLAN_SP_MESH_PEERING_CLOSE; break; case NL80211_PLINK_HOLDING: /* holding timer */ del_timer(&sta->plink_timer); mesh_plink_fsm_restart(sta); - spin_unlock_bh(&sta->lock); break; default: - spin_unlock_bh(&sta->lock); break; } + spin_unlock_bh(&sta->lock); + if (action) + mesh_plink_frame_tx(sdata, action, sta->sta.addr, + sta->llid, sta->plid, reason); } static inline void mesh_plink_timer_set(struct sta_info *sta, int timeout) @@ -612,9 +613,40 @@ static inline void mesh_plink_timer_set(struct sta_info *sta, int timeout) add_timer(&sta->plink_timer); } +static bool llid_in_use(struct ieee80211_sub_if_data *sdata, + u16 llid) +{ + struct ieee80211_local *local = sdata->local; + bool in_use = false; + struct sta_info *sta; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &local->sta_list, list) { + if (!memcmp(&sta->llid, &llid, sizeof(llid))) { + in_use = true; + break; + } + } + rcu_read_unlock(); + + return in_use; +} + +static u16 mesh_get_new_llid(struct ieee80211_sub_if_data *sdata) +{ + u16 llid; + + do { + get_random_bytes(&llid, sizeof(llid)); + /* for mesh PS we still only have the AID range for TIM bits */ + llid = (llid % IEEE80211_MAX_AID) + 1; + } while (llid_in_use(sdata, llid)); + + return llid; +} + u32 mesh_plink_open(struct sta_info *sta) { - __le16 llid; struct ieee80211_sub_if_data *sdata = sta->sdata; u32 changed; @@ -622,8 +654,7 @@ u32 mesh_plink_open(struct sta_info *sta) return 0; spin_lock_bh(&sta->lock); - get_random_bytes(&llid, 2); - sta->llid = llid; + sta->llid = mesh_get_new_llid(sdata); if (sta->plink_state != NL80211_PLINK_LISTEN && sta->plink_state != NL80211_PLINK_BLOCKED) { spin_unlock_bh(&sta->lock); @@ -640,7 +671,7 @@ u32 mesh_plink_open(struct sta_info *sta) changed = ieee80211_mps_local_status_update(sdata); mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_OPEN, - sta->sta.addr, llid, 0, 0); + sta->sta.addr, sta->llid, 0, 0); return changed; } @@ -656,390 +687,147 @@ u32 mesh_plink_block(struct sta_info *sta) return changed; } - -void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, size_t len, - struct ieee80211_rx_status *rx_status) +static void mesh_plink_close(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + enum plink_event event) { struct mesh_config *mshcfg = &sdata->u.mesh.mshcfg; - struct ieee802_11_elems elems; - struct sta_info *sta; - enum plink_event event; - enum ieee80211_self_protected_actioncode ftype; - size_t baselen; - bool matches_local = true; - u8 ie_len; - u8 *baseaddr; - u32 changed = 0; - __le16 plid, llid, reason; - - /* need action_code, aux */ - if (len < IEEE80211_MIN_ACTION_SIZE + 3) - return; - - if (sdata->u.mesh.user_mpm) - /* userspace must register for these */ - return; - - if (is_multicast_ether_addr(mgmt->da)) { - mpl_dbg(sdata, - "Mesh plink: ignore frame from multicast address\n"); - return; - } - - baseaddr = mgmt->u.action.u.self_prot.variable; - baselen = (u8 *) mgmt->u.action.u.self_prot.variable - (u8 *) mgmt; - if (mgmt->u.action.u.self_prot.action_code == - WLAN_SP_MESH_PEERING_CONFIRM) { - baseaddr += 4; - baselen += 4; - } - ieee802_11_parse_elems(baseaddr, len - baselen, true, &elems); - - if (!elems.peering) { - mpl_dbg(sdata, - "Mesh plink: missing necessary peer link ie\n"); - return; - } - if (elems.rsn_len && - sdata->u.mesh.security == IEEE80211_MESH_SEC_NONE) { - mpl_dbg(sdata, - "Mesh plink: can't establish link with secure peer\n"); - return; - } + u16 reason = (event == CLS_ACPT) ? + WLAN_REASON_MESH_CLOSE : WLAN_REASON_MESH_CONFIG; - ftype = mgmt->u.action.u.self_prot.action_code; - ie_len = elems.peering_len; - if ((ftype == WLAN_SP_MESH_PEERING_OPEN && ie_len != 4) || - (ftype == WLAN_SP_MESH_PEERING_CONFIRM && ie_len != 6) || - (ftype == WLAN_SP_MESH_PEERING_CLOSE && ie_len != 6 - && ie_len != 8)) { - mpl_dbg(sdata, - "Mesh plink: incorrect plink ie length %d %d\n", - ftype, ie_len); - return; - } - - if (ftype != WLAN_SP_MESH_PEERING_CLOSE && - (!elems.mesh_id || !elems.mesh_config)) { - mpl_dbg(sdata, "Mesh plink: missing necessary ie\n"); - return; - } - /* Note the lines below are correct, the llid in the frame is the plid - * from the point of view of this host. - */ - memcpy(&plid, PLINK_GET_LLID(elems.peering), 2); - if (ftype == WLAN_SP_MESH_PEERING_CONFIRM || - (ftype == WLAN_SP_MESH_PEERING_CLOSE && ie_len == 8)) - memcpy(&llid, PLINK_GET_PLID(elems.peering), 2); - - /* WARNING: Only for sta pointer, is dropped & re-acquired */ - rcu_read_lock(); - - sta = sta_info_get(sdata, mgmt->sa); - if (!sta && ftype != WLAN_SP_MESH_PEERING_OPEN) { - mpl_dbg(sdata, "Mesh plink: cls or cnf from unknown peer\n"); - rcu_read_unlock(); - return; - } - - if (ftype == WLAN_SP_MESH_PEERING_OPEN && - !rssi_threshold_check(sta, sdata)) { - mpl_dbg(sdata, "Mesh plink: %pM does not meet rssi threshold\n", - mgmt->sa); - rcu_read_unlock(); - return; - } - - if (sta && !test_sta_flag(sta, WLAN_STA_AUTH)) { - mpl_dbg(sdata, "Mesh plink: Action frame from non-authed peer\n"); - rcu_read_unlock(); - return; - } + sta->reason = reason; + sta->plink_state = NL80211_PLINK_HOLDING; + mod_plink_timer(sta, mshcfg->dot11MeshHoldingTimeout); +} - if (sta && sta->plink_state == NL80211_PLINK_BLOCKED) { - rcu_read_unlock(); - return; - } +static u32 mesh_plink_establish(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta) +{ + struct mesh_config *mshcfg = &sdata->u.mesh.mshcfg; + u32 changed = 0; - /* Now we will figure out the appropriate event... */ - event = PLINK_UNDEFINED; - if (ftype != WLAN_SP_MESH_PEERING_CLOSE && - !mesh_matches_local(sdata, &elems)) { - matches_local = false; - switch (ftype) { - case WLAN_SP_MESH_PEERING_OPEN: - event = OPN_RJCT; - break; - case WLAN_SP_MESH_PEERING_CONFIRM: - event = CNF_RJCT; - break; - default: - break; - } - } + del_timer(&sta->plink_timer); + sta->plink_state = NL80211_PLINK_ESTAB; + changed |= mesh_plink_inc_estab_count(sdata); + changed |= mesh_set_ht_prot_mode(sdata); + changed |= mesh_set_short_slot_time(sdata); + mpl_dbg(sdata, "Mesh plink with %pM ESTABLISHED\n", sta->sta.addr); + ieee80211_mps_sta_status_update(sta); + changed |= ieee80211_mps_set_sta_local_pm(sta, mshcfg->power_mode); + return changed; +} - if (!sta && !matches_local) { - rcu_read_unlock(); - reason = cpu_to_le16(WLAN_REASON_MESH_CONFIG); - llid = 0; - mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, - mgmt->sa, llid, plid, reason); - return; - } else if (!sta) { - /* ftype == WLAN_SP_MESH_PEERING_OPEN */ - if (!mesh_plink_free_count(sdata)) { - mpl_dbg(sdata, "Mesh plink error: no more free plinks\n"); - rcu_read_unlock(); - return; - } - event = OPN_ACPT; - } else if (matches_local) { - switch (ftype) { - case WLAN_SP_MESH_PEERING_OPEN: - if (!mesh_plink_free_count(sdata) || - (sta->plid && sta->plid != plid)) - event = OPN_IGNR; - else - event = OPN_ACPT; - break; - case WLAN_SP_MESH_PEERING_CONFIRM: - if (!mesh_plink_free_count(sdata) || - (sta->llid != llid || sta->plid != plid)) - event = CNF_IGNR; - else - event = CNF_ACPT; - break; - case WLAN_SP_MESH_PEERING_CLOSE: - if (sta->plink_state == NL80211_PLINK_ESTAB) - /* Do not check for llid or plid. This does not - * follow the standard but since multiple plinks - * per sta are not supported, it is necessary in - * order to avoid a livelock when MP A sees an - * establish peer link to MP B but MP B does not - * see it. This can be caused by a timeout in - * B's peer link establishment or B beign - * restarted. - */ - event = CLS_ACPT; - else if (sta->plid != plid) - event = CLS_IGNR; - else if (ie_len == 7 && sta->llid != llid) - event = CLS_IGNR; - else - event = CLS_ACPT; - break; - default: - mpl_dbg(sdata, "Mesh plink: unknown frame subtype\n"); - rcu_read_unlock(); - return; - } - } +/** + * mesh_plink_fsm - step @sta MPM based on @event + * + * @sdata: interface + * @sta: mesh neighbor + * @event: peering event + * + * Return: changed MBSS flags + */ +static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, enum plink_event event) +{ + struct mesh_config *mshcfg = &sdata->u.mesh.mshcfg; + enum ieee80211_self_protected_actioncode action = 0; + u32 changed = 0; - if (event == OPN_ACPT) { - rcu_read_unlock(); - /* allocate sta entry if necessary and update info */ - sta = mesh_sta_info_get(sdata, mgmt->sa, &elems); - if (!sta) { - mpl_dbg(sdata, "Mesh plink: failed to init peer!\n"); - rcu_read_unlock(); - return; - } - } + mpl_dbg(sdata, "peer %pM in state %s got event %s\n", sta->sta.addr, + mplstates[sta->plink_state], mplevents[event]); - mpl_dbg(sdata, "peer %pM in state %s got event %s\n", mgmt->sa, - mplstates[sta->plink_state], mplevents[event]); - reason = 0; spin_lock_bh(&sta->lock); switch (sta->plink_state) { - /* spin_unlock as soon as state is updated at each case */ case NL80211_PLINK_LISTEN: switch (event) { case CLS_ACPT: mesh_plink_fsm_restart(sta); - spin_unlock_bh(&sta->lock); break; case OPN_ACPT: sta->plink_state = NL80211_PLINK_OPN_RCVD; - sta->plid = plid; - get_random_bytes(&llid, 2); - sta->llid = llid; + sta->llid = mesh_get_new_llid(sdata); mesh_plink_timer_set(sta, mshcfg->dot11MeshRetryTimeout); /* set the non-peer mode to active during peering */ changed |= ieee80211_mps_local_status_update(sdata); - - spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, - WLAN_SP_MESH_PEERING_OPEN, - sta->sta.addr, llid, 0, 0); - mesh_plink_frame_tx(sdata, - WLAN_SP_MESH_PEERING_CONFIRM, - sta->sta.addr, llid, plid, 0); + action = WLAN_SP_MESH_PEERING_OPEN; break; default: - spin_unlock_bh(&sta->lock); break; } break; - case NL80211_PLINK_OPN_SNT: switch (event) { case OPN_RJCT: case CNF_RJCT: - reason = cpu_to_le16(WLAN_REASON_MESH_CONFIG); case CLS_ACPT: - if (!reason) - reason = cpu_to_le16(WLAN_REASON_MESH_CLOSE); - sta->reason = reason; - sta->plink_state = NL80211_PLINK_HOLDING; - if (!mod_plink_timer(sta, - mshcfg->dot11MeshHoldingTimeout)) - sta->ignore_plink_timer = true; - - llid = sta->llid; - spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, - WLAN_SP_MESH_PEERING_CLOSE, - sta->sta.addr, llid, plid, reason); + mesh_plink_close(sdata, sta, event); + action = WLAN_SP_MESH_PEERING_CLOSE; break; case OPN_ACPT: /* retry timer is left untouched */ sta->plink_state = NL80211_PLINK_OPN_RCVD; - sta->plid = plid; - llid = sta->llid; - spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, - WLAN_SP_MESH_PEERING_CONFIRM, - sta->sta.addr, llid, plid, 0); + action = WLAN_SP_MESH_PEERING_CONFIRM; break; case CNF_ACPT: sta->plink_state = NL80211_PLINK_CNF_RCVD; if (!mod_plink_timer(sta, mshcfg->dot11MeshConfirmTimeout)) sta->ignore_plink_timer = true; - - spin_unlock_bh(&sta->lock); break; default: - spin_unlock_bh(&sta->lock); break; } break; - case NL80211_PLINK_OPN_RCVD: switch (event) { case OPN_RJCT: case CNF_RJCT: - reason = cpu_to_le16(WLAN_REASON_MESH_CONFIG); case CLS_ACPT: - if (!reason) - reason = cpu_to_le16(WLAN_REASON_MESH_CLOSE); - sta->reason = reason; - sta->plink_state = NL80211_PLINK_HOLDING; - if (!mod_plink_timer(sta, - mshcfg->dot11MeshHoldingTimeout)) - sta->ignore_plink_timer = true; - - llid = sta->llid; - spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, - sta->sta.addr, llid, plid, reason); + mesh_plink_close(sdata, sta, event); + action = WLAN_SP_MESH_PEERING_CLOSE; break; case OPN_ACPT: - llid = sta->llid; - spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, - WLAN_SP_MESH_PEERING_CONFIRM, - sta->sta.addr, llid, plid, 0); + action = WLAN_SP_MESH_PEERING_CONFIRM; break; case CNF_ACPT: - del_timer(&sta->plink_timer); - sta->plink_state = NL80211_PLINK_ESTAB; - spin_unlock_bh(&sta->lock); - changed |= mesh_plink_inc_estab_count(sdata); - changed |= mesh_set_ht_prot_mode(sdata); - changed |= mesh_set_short_slot_time(sdata); - mpl_dbg(sdata, "Mesh plink with %pM ESTABLISHED\n", - sta->sta.addr); - ieee80211_mps_sta_status_update(sta); - changed |= ieee80211_mps_set_sta_local_pm(sta, - mshcfg->power_mode); + changed |= mesh_plink_establish(sdata, sta); break; default: - spin_unlock_bh(&sta->lock); break; } break; - case NL80211_PLINK_CNF_RCVD: switch (event) { case OPN_RJCT: case CNF_RJCT: - reason = cpu_to_le16(WLAN_REASON_MESH_CONFIG); case CLS_ACPT: - if (!reason) - reason = cpu_to_le16(WLAN_REASON_MESH_CLOSE); - sta->reason = reason; - sta->plink_state = NL80211_PLINK_HOLDING; - if (!mod_plink_timer(sta, - mshcfg->dot11MeshHoldingTimeout)) - sta->ignore_plink_timer = true; - - llid = sta->llid; - spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, - WLAN_SP_MESH_PEERING_CLOSE, - sta->sta.addr, llid, plid, reason); + mesh_plink_close(sdata, sta, event); + action = WLAN_SP_MESH_PEERING_CLOSE; break; case OPN_ACPT: - del_timer(&sta->plink_timer); - sta->plink_state = NL80211_PLINK_ESTAB; - spin_unlock_bh(&sta->lock); - changed |= mesh_plink_inc_estab_count(sdata); - changed |= mesh_set_ht_prot_mode(sdata); - changed |= mesh_set_short_slot_time(sdata); - mpl_dbg(sdata, "Mesh plink with %pM ESTABLISHED\n", - sta->sta.addr); - mesh_plink_frame_tx(sdata, - WLAN_SP_MESH_PEERING_CONFIRM, - sta->sta.addr, llid, plid, 0); - ieee80211_mps_sta_status_update(sta); - changed |= ieee80211_mps_set_sta_local_pm(sta, - mshcfg->power_mode); + changed |= mesh_plink_establish(sdata, sta); + action = WLAN_SP_MESH_PEERING_CONFIRM; break; default: - spin_unlock_bh(&sta->lock); break; } break; - case NL80211_PLINK_ESTAB: switch (event) { case CLS_ACPT: - reason = cpu_to_le16(WLAN_REASON_MESH_CLOSE); - sta->reason = reason; changed |= __mesh_plink_deactivate(sta); - sta->plink_state = NL80211_PLINK_HOLDING; - llid = sta->llid; - mod_plink_timer(sta, mshcfg->dot11MeshHoldingTimeout); - spin_unlock_bh(&sta->lock); changed |= mesh_set_ht_prot_mode(sdata); changed |= mesh_set_short_slot_time(sdata); - mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, - sta->sta.addr, llid, plid, reason); + mesh_plink_close(sdata, sta, event); + action = WLAN_SP_MESH_PEERING_CLOSE; break; case OPN_ACPT: - llid = sta->llid; - spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, - WLAN_SP_MESH_PEERING_CONFIRM, - sta->sta.addr, llid, plid, 0); + action = WLAN_SP_MESH_PEERING_CONFIRM; break; default: - spin_unlock_bh(&sta->lock); break; } break; @@ -1049,32 +837,271 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, if (del_timer(&sta->plink_timer)) sta->ignore_plink_timer = 1; mesh_plink_fsm_restart(sta); - spin_unlock_bh(&sta->lock); break; case OPN_ACPT: case CNF_ACPT: case OPN_RJCT: case CNF_RJCT: - llid = sta->llid; - reason = sta->reason; - spin_unlock_bh(&sta->lock); - mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, - sta->sta.addr, llid, plid, reason); + action = WLAN_SP_MESH_PEERING_CLOSE; break; default: - spin_unlock_bh(&sta->lock); + break; } break; default: /* should not get here, PLINK_BLOCKED is dealt with at the * beginning of the function */ - spin_unlock_bh(&sta->lock); break; } + spin_unlock_bh(&sta->lock); + if (action) { + mesh_plink_frame_tx(sdata, action, sta->sta.addr, + sta->llid, sta->plid, sta->reason); + + /* also send confirm in open case */ + if (action == WLAN_SP_MESH_PEERING_OPEN) { + mesh_plink_frame_tx(sdata, + WLAN_SP_MESH_PEERING_CONFIRM, + sta->sta.addr, sta->llid, + sta->plid, 0); + } + } + + return changed; +} + +/* + * mesh_plink_get_event - get correct MPM event + * + * @sdata: interface + * @sta: peer, leave NULL if processing a frame from a new suitable peer + * @elems: peering management IEs + * @ftype: frame type + * @llid: peer's peer link ID + * @plid: peer's local link ID + * + * Return: new peering event for @sta, but PLINK_UNDEFINED should be treated as + * an error. + */ +static enum plink_event +mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct ieee802_11_elems *elems, + enum ieee80211_self_protected_actioncode ftype, + u16 llid, u16 plid) +{ + enum plink_event event = PLINK_UNDEFINED; + u8 ie_len = elems->peering_len; + bool matches_local; + + matches_local = (ftype == WLAN_SP_MESH_PEERING_CLOSE || + mesh_matches_local(sdata, elems)); + + /* deny open request from non-matching peer */ + if (!matches_local && !sta) { + event = OPN_RJCT; + goto out; + } + + if (!sta) { + if (ftype != WLAN_SP_MESH_PEERING_OPEN) { + mpl_dbg(sdata, "Mesh plink: cls or cnf from unknown peer\n"); + goto out; + } + /* ftype == WLAN_SP_MESH_PEERING_OPEN */ + if (!mesh_plink_free_count(sdata)) { + mpl_dbg(sdata, "Mesh plink error: no more free plinks\n"); + goto out; + } + } else { + if (!test_sta_flag(sta, WLAN_STA_AUTH)) { + mpl_dbg(sdata, "Mesh plink: Action frame from non-authed peer\n"); + goto out; + } + if (sta->plink_state == NL80211_PLINK_BLOCKED) + goto out; + } + + /* new matching peer */ + if (!sta) { + event = OPN_ACPT; + goto out; + } + + switch (ftype) { + case WLAN_SP_MESH_PEERING_OPEN: + if (!matches_local) + event = OPN_RJCT; + if (!mesh_plink_free_count(sdata) || + (sta->plid && sta->plid != plid)) + event = OPN_IGNR; + else + event = OPN_ACPT; + break; + case WLAN_SP_MESH_PEERING_CONFIRM: + if (!matches_local) + event = CNF_RJCT; + if (!mesh_plink_free_count(sdata) || + (sta->llid != llid || sta->plid != plid)) + event = CNF_IGNR; + else + event = CNF_ACPT; + break; + case WLAN_SP_MESH_PEERING_CLOSE: + if (sta->plink_state == NL80211_PLINK_ESTAB) + /* Do not check for llid or plid. This does not + * follow the standard but since multiple plinks + * per sta are not supported, it is necessary in + * order to avoid a livelock when MP A sees an + * establish peer link to MP B but MP B does not + * see it. This can be caused by a timeout in + * B's peer link establishment or B beign + * restarted. + */ + event = CLS_ACPT; + else if (sta->plid != plid) + event = CLS_IGNR; + else if (ie_len == 8 && sta->llid != llid) + event = CLS_IGNR; + else + event = CLS_ACPT; + break; + default: + mpl_dbg(sdata, "Mesh plink: unknown frame subtype\n"); + break; + } + +out: + return event; +} +static void +mesh_process_plink_frame(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, + struct ieee802_11_elems *elems) +{ + + struct sta_info *sta; + enum plink_event event; + enum ieee80211_self_protected_actioncode ftype; + u32 changed = 0; + u8 ie_len = elems->peering_len; + __le16 _plid, _llid; + u16 plid, llid = 0; + + if (!elems->peering) { + mpl_dbg(sdata, + "Mesh plink: missing necessary peer link ie\n"); + return; + } + + if (elems->rsn_len && + sdata->u.mesh.security == IEEE80211_MESH_SEC_NONE) { + mpl_dbg(sdata, + "Mesh plink: can't establish link with secure peer\n"); + return; + } + + ftype = mgmt->u.action.u.self_prot.action_code; + if ((ftype == WLAN_SP_MESH_PEERING_OPEN && ie_len != 4) || + (ftype == WLAN_SP_MESH_PEERING_CONFIRM && ie_len != 6) || + (ftype == WLAN_SP_MESH_PEERING_CLOSE && ie_len != 6 + && ie_len != 8)) { + mpl_dbg(sdata, + "Mesh plink: incorrect plink ie length %d %d\n", + ftype, ie_len); + return; + } + + if (ftype != WLAN_SP_MESH_PEERING_CLOSE && + (!elems->mesh_id || !elems->mesh_config)) { + mpl_dbg(sdata, "Mesh plink: missing necessary ie\n"); + return; + } + /* Note the lines below are correct, the llid in the frame is the plid + * from the point of view of this host. + */ + memcpy(&_plid, PLINK_GET_LLID(elems->peering), sizeof(__le16)); + plid = le16_to_cpu(_plid); + if (ftype == WLAN_SP_MESH_PEERING_CONFIRM || + (ftype == WLAN_SP_MESH_PEERING_CLOSE && ie_len == 8)) { + memcpy(&_llid, PLINK_GET_PLID(elems->peering), sizeof(__le16)); + llid = le16_to_cpu(_llid); + } + + /* WARNING: Only for sta pointer, is dropped & re-acquired */ + rcu_read_lock(); + + sta = sta_info_get(sdata, mgmt->sa); + + if (ftype == WLAN_SP_MESH_PEERING_OPEN && + !rssi_threshold_check(sdata, sta)) { + mpl_dbg(sdata, "Mesh plink: %pM does not meet rssi threshold\n", + mgmt->sa); + goto unlock_rcu; + } + + /* Now we will figure out the appropriate event... */ + event = mesh_plink_get_event(sdata, sta, elems, ftype, llid, plid); + + if (event == OPN_ACPT) { + rcu_read_unlock(); + /* allocate sta entry if necessary and update info */ + sta = mesh_sta_info_get(sdata, mgmt->sa, elems); + if (!sta) { + mpl_dbg(sdata, "Mesh plink: failed to init peer!\n"); + goto unlock_rcu; + } + sta->plid = plid; + } else if (!sta && event == OPN_RJCT) { + mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, + mgmt->sa, 0, plid, + WLAN_REASON_MESH_CONFIG); + goto unlock_rcu; + } else if (!sta || event == PLINK_UNDEFINED) { + /* something went wrong */ + goto unlock_rcu; + } + + changed |= mesh_plink_fsm(sdata, sta, event); + +unlock_rcu: rcu_read_unlock(); if (changed) ieee80211_mbss_info_change_notify(sdata, changed); } + +void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len, + struct ieee80211_rx_status *rx_status) +{ + struct ieee802_11_elems elems; + size_t baselen; + u8 *baseaddr; + + /* need action_code, aux */ + if (len < IEEE80211_MIN_ACTION_SIZE + 3) + return; + + if (sdata->u.mesh.user_mpm) + /* userspace must register for these */ + return; + + if (is_multicast_ether_addr(mgmt->da)) { + mpl_dbg(sdata, + "Mesh plink: ignore frame from multicast address\n"); + return; + } + + baseaddr = mgmt->u.action.u.self_prot.variable; + baselen = (u8 *) mgmt->u.action.u.self_prot.variable - (u8 *) mgmt; + if (mgmt->u.action.u.self_prot.action_code == + WLAN_SP_MESH_PEERING_CONFIRM) { + baseaddr += 4; + baselen += 4; + } + ieee802_11_parse_elems(baseaddr, len - baselen, true, &elems); + mesh_process_plink_frame(sdata, mgmt, &elems); +} diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c index 0f79b78b5e86..2802f9d9279d 100644 --- a/net/mac80211/mesh_ps.c +++ b/net/mac80211/mesh_ps.c @@ -576,10 +576,9 @@ void ieee80211_mps_frame_release(struct sta_info *sta, int ac, buffer_local = 0; bool has_buffered = false; - /* TIM map only for LLID <= IEEE80211_MAX_AID */ if (sta->plink_state == NL80211_PLINK_ESTAB) has_buffered = ieee80211_check_tim(elems->tim, elems->tim_len, - le16_to_cpu(sta->llid) % IEEE80211_MAX_AID); + sta->llid); if (has_buffered) mps_dbg(sta->sdata, "%pM indicates buffered frames\n", diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c index 05a256b38e24..2bc5dc25d5ad 100644 --- a/net/mac80211/mesh_sync.c +++ b/net/mac80211/mesh_sync.c @@ -92,12 +92,20 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, if (stype != IEEE80211_STYPE_BEACON) return; - /* The current tsf is a first approximation for the timestamp - * for the received beacon. Further down we try to get a - * better value from the rx_status->mactime field if - * available. Also we have to call drv_get_tsf() before - * entering the rcu-read section.*/ - t_r = drv_get_tsf(local, sdata); + /* + * Get time when timestamp field was received. If we don't + * have rx timestamps, then use current tsf as an approximation. + * drv_get_tsf() must be called before entering the rcu-read + * section. + */ + if (ieee80211_have_rx_timestamp(rx_status)) + t_r = ieee80211_calculate_rx_timestamp(local, rx_status, + 24 + 12 + + elems->total_len + + FCS_LEN, + 24); + else + t_r = drv_get_tsf(local, sdata); rcu_read_lock(); sta = sta_info_get(sdata, mgmt->sa); @@ -117,14 +125,6 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, goto no_sync; } - if (ieee80211_have_rx_timestamp(rx_status)) - /* time when timestamp field was received */ - t_r = ieee80211_calculate_rx_timestamp(local, rx_status, - 24 + 12 + - elems->total_len + - FCS_LEN, - 24); - /* Timing offset calculation (see 13.13.2.2.2) */ t_t = le64_to_cpu(mgmt->u.beacon.timestamp); sta->t_offset = t_t - t_r; @@ -164,12 +164,15 @@ no_sync: rcu_read_unlock(); } -static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata) +static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata, + struct beacon_data *beacon) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + u8 cap; WARN_ON(ifmsh->mesh_sp_id != IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET); BUG_ON(!rcu_read_lock_held()); + cap = beacon->meshconf->meshconf_cap; spin_lock_bh(&ifmsh->sync_offset_lock); @@ -194,6 +197,10 @@ static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata) ifmsh->adjusting_tbtt = false; } spin_unlock_bh(&ifmsh->sync_offset_lock); + + beacon->meshconf->meshconf_cap = ifmsh->adjusting_tbtt ? + IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING | cap : + ~IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING & cap; } static const struct sync_method sync_methods[] = { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index b3a3ce316656..fc1d82465b3c 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -330,6 +330,16 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, if (WARN_ON_ONCE(!sta)) return -EINVAL; + /* + * if bss configuration changed store the new one - + * this may be applicable even if channel is identical + */ + ht_opmode = le16_to_cpu(ht_oper->operation_mode); + if (sdata->vif.bss_conf.ht_operation_mode != ht_opmode) { + *changed |= BSS_CHANGED_HT; + sdata->vif.bss_conf.ht_operation_mode = ht_opmode; + } + chan = sdata->vif.bss_conf.chandef.chan; sband = local->hw.wiphy->bands[chan->band]; @@ -416,14 +426,6 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, IEEE80211_RC_BW_CHANGED); } - ht_opmode = le16_to_cpu(ht_oper->operation_mode); - - /* if bss configuration changed store the new one */ - if (sdata->vif.bss_conf.ht_operation_mode != ht_opmode) { - *changed |= BSS_CHANGED_HT; - sdata->vif.bss_conf.ht_operation_mode = ht_opmode; - } - return 0; } @@ -714,7 +716,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) } /* if present, add any custom IEs that go before HT */ - if (assoc_data->ie_len && assoc_data->ie) { + if (assoc_data->ie_len) { static const u8 before_ht[] = { WLAN_EID_SSID, WLAN_EID_SUPP_RATES, @@ -748,7 +750,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) &assoc_data->ap_vht_cap); /* if present, add any custom non-vendor IEs that go after HT */ - if (assoc_data->ie_len && assoc_data->ie) { + if (assoc_data->ie_len) { noffset = ieee80211_ie_split_vendor(assoc_data->ie, assoc_data->ie_len, offset); @@ -779,7 +781,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) } /* add any remaining custom (i.e. vendor specific here) IEs */ - if (assoc_data->ie_len && assoc_data->ie) { + if (assoc_data->ie_len) { noffset = assoc_data->ie_len; pos = skb_put(skb, noffset - offset); memcpy(pos, assoc_data->ie + offset, noffset - offset); @@ -886,8 +888,9 @@ static void ieee80211_chswitch_work(struct work_struct *work) if (!ifmgd->associated) goto out; - ret = ieee80211_vif_change_channel(sdata, &local->csa_chandef, - &changed); + mutex_lock(&local->mtx); + ret = ieee80211_vif_change_channel(sdata, &changed); + mutex_unlock(&local->mtx); if (ret) { sdata_info(sdata, "vif channel switch failed, disconnecting\n"); @@ -897,7 +900,7 @@ static void ieee80211_chswitch_work(struct work_struct *work) } if (!local->use_chanctx) { - local->_oper_chandef = local->csa_chandef; + local->_oper_chandef = sdata->csa_chandef; /* Call "hw_config" only if doing sw channel switch. * Otherwise update the channel directly */ @@ -908,7 +911,7 @@ static void ieee80211_chswitch_work(struct work_struct *work) } /* XXX: shouldn't really modify cfg80211-owned data! */ - ifmgd->associated->channel = local->csa_chandef.chan; + ifmgd->associated->channel = sdata->csa_chandef.chan; /* XXX: wait for a beacon first? */ ieee80211_wake_queues_by_reason(&local->hw, @@ -1035,7 +1038,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, } mutex_unlock(&local->chanctx_mtx); - local->csa_chandef = csa_ie.chandef; + sdata->csa_chandef = csa_ie.chandef; if (csa_ie.mode) ieee80211_stop_queues_by_reason(&local->hw, @@ -1398,10 +1401,16 @@ void ieee80211_dfs_cac_timer_work(struct work_struct *work) struct ieee80211_sub_if_data *sdata = container_of(delayed_work, struct ieee80211_sub_if_data, dfs_cac_timer_work); + struct cfg80211_chan_def chandef = sdata->vif.bss_conf.chandef; - ieee80211_vif_release_channel(sdata); - - cfg80211_cac_event(sdata->dev, NL80211_RADAR_CAC_FINISHED, GFP_KERNEL); + mutex_lock(&sdata->local->mtx); + if (sdata->wdev.cac_started) { + ieee80211_vif_release_channel(sdata); + cfg80211_cac_event(sdata->dev, &chandef, + NL80211_RADAR_CAC_FINISHED, + GFP_KERNEL); + } + mutex_unlock(&sdata->local->mtx); } /* MLME */ @@ -1695,7 +1704,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, memset(ifmgd->bssid, 0, ETH_ALEN); /* remove AP and TDLS peers */ - sta_info_flush_defer(sdata); + sta_info_flush(sdata); /* finally reset all BSS / config parameters */ changed |= ieee80211_reset_erp_info(sdata); @@ -1744,7 +1753,11 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ifmgd->have_beacon = false; ifmgd->flags = 0; + mutex_lock(&local->mtx); ieee80211_vif_release_channel(sdata); + mutex_unlock(&local->mtx); + + sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; } void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, @@ -2065,7 +2078,9 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata, memset(sdata->u.mgd.bssid, 0, ETH_ALEN); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID); sdata->u.mgd.flags = 0; + mutex_lock(&sdata->local->mtx); ieee80211_vif_release_channel(sdata); + mutex_unlock(&sdata->local->mtx); } cfg80211_put_bss(sdata->local->hw.wiphy, auth_data->bss); @@ -2314,7 +2329,9 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata, memset(sdata->u.mgd.bssid, 0, ETH_ALEN); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID); sdata->u.mgd.flags = 0; + mutex_lock(&sdata->local->mtx); ieee80211_vif_release_channel(sdata); + mutex_unlock(&sdata->local->mtx); } kfree(assoc_data); @@ -3665,6 +3682,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, /* will change later if needed */ sdata->smps_mode = IEEE80211_SMPS_OFF; + mutex_lock(&local->mtx); /* * If this fails (possibly due to channel context sharing * on incompatible channels, e.g. 80+80 and 160 sharing the @@ -3676,13 +3694,15 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, /* don't downgrade for 5 and 10 MHz channels, though. */ if (chandef.width == NL80211_CHAN_WIDTH_5 || chandef.width == NL80211_CHAN_WIDTH_10) - return ret; + goto out; while (ret && chandef.width != NL80211_CHAN_WIDTH_20_NOHT) { ifmgd->flags |= ieee80211_chandef_downgrade(&chandef); ret = ieee80211_vif_use_channel(sdata, &chandef, IEEE80211_CHANCTX_SHARED); } + out: + mutex_unlock(&local->mtx); return ret; } @@ -4191,6 +4211,8 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, sdata->control_port_protocol = req->crypto.control_port_ethertype; sdata->control_port_no_encrypt = req->crypto.control_port_no_encrypt; + sdata->encrypt_headroom = ieee80211_cs_headroom(local, &req->crypto, + sdata->vif.type); /* kick off associate process */ diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 340126204343..af64fb8e8add 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -37,9 +37,8 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_SUSPEND); - /* flush out all packets and station cleanup call_rcu()s */ + /* flush out all packets */ synchronize_net(); - rcu_barrier(); ieee80211_flush_queues(local, NULL); diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 505bc0dea074..b95e16c07081 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -54,6 +54,8 @@ static inline void rate_control_rate_init(struct sta_info *sta) struct ieee80211_supported_band *sband; struct ieee80211_chanctx_conf *chanctx_conf; + ieee80211_sta_set_rx_nss(sta); + if (!ref) return; @@ -67,8 +69,6 @@ static inline void rate_control_rate_init(struct sta_info *sta) sband = local->hw.wiphy->bands[chanctx_conf->def.chan->band]; - ieee80211_sta_set_rx_nss(sta); - ref->ops->rate_init(ref->priv, sband, &chanctx_conf->def, ista, priv_sta); rcu_read_unlock(); diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 7fa1b36e6202..f3d88b0c054c 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -135,7 +135,7 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi) u32 usecs; int i; - for (i=0; i < MAX_THR_RATES; i++) + for (i = 0; i < MAX_THR_RATES; i++) tmp_tp_rate[i] = 0; for (i = 0; i < mi->n_rates; i++) { @@ -190,7 +190,7 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi) * choose the maximum throughput rate as max_prob_rate * (2) if all success probabilities < 95%, the rate with * highest success probability is choosen as max_prob_rate */ - if (mr->probability >= MINSTREL_FRAC(95,100)) { + if (mr->probability >= MINSTREL_FRAC(95, 100)) { if (mr->cur_tp >= mi->r[tmp_prob_rate].cur_tp) tmp_prob_rate = i; } else { @@ -220,7 +220,7 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi) static void minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, - struct ieee80211_sta *sta, void *priv_sta, + struct ieee80211_sta *sta, void *priv_sta, struct sk_buff *skb) { struct minstrel_priv *mp = priv; @@ -260,7 +260,7 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, static inline unsigned int minstrel_get_retry_count(struct minstrel_rate *mr, - struct ieee80211_tx_info *info) + struct ieee80211_tx_info *info) { unsigned int retry = mr->adjusted_retry_count; @@ -422,10 +422,9 @@ init_sample_table(struct minstrel_sta_info *mi) memset(mi->sample_table, 0xff, SAMPLE_COLUMNS * mi->n_rates); for (col = 0; col < SAMPLE_COLUMNS; col++) { + prandom_bytes(rnd, sizeof(rnd)); for (i = 0; i < mi->n_rates; i++) { - get_random_bytes(rnd, sizeof(rnd)); new_idx = (i + rnd[i & 7]) % mi->n_rates; - while (SAMPLE_TBL(mi, new_idx, col) != 0xff) new_idx = (new_idx + 1) % mi->n_rates; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 4096ff6cc24f..c1b5b73c5b91 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -63,7 +63,7 @@ #define CCK_DURATION(_bitrate, _short, _len) \ (1000 * (10 /* SIFS */ + \ - (_short ? 72 + 24 : 144 + 48 ) + \ + (_short ? 72 + 24 : 144 + 48) + \ (8 * (_len + 4) * 10) / (_bitrate))) #define CCK_ACK_DURATION(_bitrate, _short) \ @@ -135,7 +135,7 @@ minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi); static int minstrel_ht_get_group_idx(struct ieee80211_tx_rate *rate) { - return GROUP_IDX((rate->idx / MCS_GROUP_RATES) + 1, + return GROUP_IDX((rate->idx / 8) + 1, !!(rate->flags & IEEE80211_TX_RC_SHORT_GI), !!(rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)); } @@ -148,7 +148,7 @@ minstrel_ht_get_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, if (rate->flags & IEEE80211_TX_RC_MCS) { group = minstrel_ht_get_group_idx(rate); - idx = rate->idx % MCS_GROUP_RATES; + idx = rate->idx % 8; } else { group = MINSTREL_CCK_GROUP; @@ -637,8 +637,7 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, idx = mp->cck_rates[index % ARRAY_SIZE(mp->cck_rates)]; flags = 0; } else { - idx = index % MCS_GROUP_RATES + - (group->streams - 1) * MCS_GROUP_RATES; + idx = index % MCS_GROUP_RATES + (group->streams - 1) * 8; flags = IEEE80211_TX_RC_MCS | group->flags; } @@ -702,12 +701,16 @@ minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) if (!mi->sample_tries) return -1; - mg = &mi->groups[mi->sample_group]; + sample_group = mi->sample_group; + mg = &mi->groups[sample_group]; sample_idx = sample_table[mg->column][mg->index]; + minstrel_next_sample_idx(mi); + + if (!(mg->supported & BIT(sample_idx))) + return -1; + mr = &mg->rates[sample_idx]; - sample_group = mi->sample_group; sample_idx += sample_group * MCS_GROUP_RATES; - minstrel_next_sample_idx(mi); /* * Sampling might add some overhead (RTS, no aggregation) @@ -818,7 +821,7 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, } rate->idx = sample_idx % MCS_GROUP_RATES + - (sample_group->streams - 1) * MCS_GROUP_RATES; + (sample_group->streams - 1) * 8; rate->flags = IEEE80211_TX_RC_MCS | sample_group->flags; } @@ -1053,10 +1056,9 @@ init_sample_table(void) memset(sample_table, 0xff, sizeof(sample_table)); for (col = 0; col < SAMPLE_COLUMNS; col++) { + prandom_bytes(rnd, sizeof(rnd)); for (i = 0; i < MCS_GROUP_RATES; i++) { - get_random_bytes(rnd, sizeof(rnd)); new_idx = (i + rnd[i]) % MCS_GROUP_RATES; - while (sample_table[col][new_idx] != 0xff) new_idx = (new_idx + 1) % MCS_GROUP_RATES; diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c index df44a5ad8270..3e7d793de0c3 100644 --- a/net/mac80211/rc80211_minstrel_ht_debugfs.c +++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c @@ -54,8 +54,7 @@ minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p) int r = bitrates[j % 4]; p += sprintf(p, " %2u.%1uM", r / 10, r % 10); } else { - p += sprintf(p, " MCS%-2u", (mg->streams - 1) * - MCS_GROUP_RATES + j); + p += sprintf(p, " MCS%-2u", (mg->streams - 1) * 8 + j); } tp = mr->cur_tp / 10; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 2b0debb0422b..c24ca0d0f469 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -638,6 +638,27 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb) return le16_to_cpu(mmie->key_id); } +static int iwl80211_get_cs_keyid(const struct ieee80211_cipher_scheme *cs, + struct sk_buff *skb) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + __le16 fc; + int hdrlen; + u8 keyid; + + fc = hdr->frame_control; + hdrlen = ieee80211_hdrlen(fc); + + if (skb->len < hdrlen + cs->hdr_len) + return -EINVAL; + + skb_copy_bits(skb, hdrlen + cs->key_idx_off, &keyid, 1); + keyid &= cs->key_idx_mask; + keyid >>= cs->key_idx_shift; + + return keyid; +} + static ieee80211_rx_result ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; @@ -729,9 +750,7 @@ static void ieee80211_release_reorder_frames(struct ieee80211_sub_if_data *sdata lockdep_assert_held(&tid_agg_rx->reorder_lock); while (ieee80211_sn_less(tid_agg_rx->head_seq_num, head_seq_num)) { - index = ieee80211_sn_sub(tid_agg_rx->head_seq_num, - tid_agg_rx->ssn) % - tid_agg_rx->buf_size; + index = tid_agg_rx->head_seq_num % tid_agg_rx->buf_size; ieee80211_release_reorder_frame(sdata, tid_agg_rx, index, frames); } @@ -757,8 +776,7 @@ static void ieee80211_sta_reorder_release(struct ieee80211_sub_if_data *sdata, lockdep_assert_held(&tid_agg_rx->reorder_lock); /* release the buffer until next missing frame */ - index = ieee80211_sn_sub(tid_agg_rx->head_seq_num, - tid_agg_rx->ssn) % tid_agg_rx->buf_size; + index = tid_agg_rx->head_seq_num % tid_agg_rx->buf_size; if (!tid_agg_rx->reorder_buf[index] && tid_agg_rx->stored_mpdu_num) { /* @@ -793,15 +811,11 @@ static void ieee80211_sta_reorder_release(struct ieee80211_sub_if_data *sdata, } else while (tid_agg_rx->reorder_buf[index]) { ieee80211_release_reorder_frame(sdata, tid_agg_rx, index, frames); - index = ieee80211_sn_sub(tid_agg_rx->head_seq_num, - tid_agg_rx->ssn) % - tid_agg_rx->buf_size; + index = tid_agg_rx->head_seq_num % tid_agg_rx->buf_size; } if (tid_agg_rx->stored_mpdu_num) { - j = index = ieee80211_sn_sub(tid_agg_rx->head_seq_num, - tid_agg_rx->ssn) % - tid_agg_rx->buf_size; + j = index = tid_agg_rx->head_seq_num % tid_agg_rx->buf_size; for (; j != (index - 1) % tid_agg_rx->buf_size; j = (j + 1) % tid_agg_rx->buf_size) { @@ -861,8 +875,7 @@ static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_sub_if_data *sdata /* Now the new frame is always in the range of the reordering buffer */ - index = ieee80211_sn_sub(mpdu_seq_num, - tid_agg_rx->ssn) % tid_agg_rx->buf_size; + index = mpdu_seq_num % tid_agg_rx->buf_size; /* check if we already stored this frame */ if (tid_agg_rx->reorder_buf[index]) { @@ -1369,6 +1382,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) struct ieee80211_key *sta_ptk = NULL; int mmie_keyidx = -1; __le16 fc; + const struct ieee80211_cipher_scheme *cs = NULL; /* * Key selection 101 @@ -1406,11 +1420,19 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) /* start without a key */ rx->key = NULL; + fc = hdr->frame_control; - if (rx->sta) - sta_ptk = rcu_dereference(rx->sta->ptk); + if (rx->sta) { + int keyid = rx->sta->ptk_idx; - fc = hdr->frame_control; + if (ieee80211_has_protected(fc) && rx->sta->cipher_scheme) { + cs = rx->sta->cipher_scheme; + keyid = iwl80211_get_cs_keyid(cs, rx->skb); + if (unlikely(keyid < 0)) + return RX_DROP_UNUSABLE; + } + sta_ptk = rcu_dereference(rx->sta->ptk[keyid]); + } if (!ieee80211_has_protected(fc)) mmie_keyidx = ieee80211_get_mmie_keyidx(rx->skb); @@ -1472,6 +1494,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) return RX_CONTINUE; } else { u8 keyid; + /* * The device doesn't give us the IV so we won't be * able to look up the key. That's ok though, we @@ -1487,15 +1510,21 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) hdrlen = ieee80211_hdrlen(fc); - if (rx->skb->len < 8 + hdrlen) - return RX_DROP_UNUSABLE; /* TODO: count this? */ + if (cs) { + keyidx = iwl80211_get_cs_keyid(cs, rx->skb); - /* - * no need to call ieee80211_wep_get_keyidx, - * it verifies a bunch of things we've done already - */ - skb_copy_bits(rx->skb, hdrlen + 3, &keyid, 1); - keyidx = keyid >> 6; + if (unlikely(keyidx < 0)) + return RX_DROP_UNUSABLE; + } else { + if (rx->skb->len < 8 + hdrlen) + return RX_DROP_UNUSABLE; /* TODO: count this? */ + /* + * no need to call ieee80211_wep_get_keyidx, + * it verifies a bunch of things we've done already + */ + skb_copy_bits(rx->skb, hdrlen + 3, &keyid, 1); + keyidx = keyid >> 6; + } /* check per-station GTK first, if multicast packet */ if (is_multicast_ether_addr(hdr->addr1) && rx->sta) @@ -1543,11 +1572,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) result = ieee80211_crypto_aes_cmac_decrypt(rx); break; default: - /* - * We can reach here only with HW-only algorithms - * but why didn't it decrypt the frame?! - */ - return RX_DROP_UNUSABLE; + result = ieee80211_crypto_hw_decrypt(rx); } /* the hdr variable is invalid after the decrypt handlers */ @@ -1938,20 +1963,17 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) } } - if (skb) { - int align __maybe_unused; - #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - /* - * 'align' will only take the values 0 or 2 here - * since all frames are required to be aligned - * to 2-byte boundaries when being passed to - * mac80211; the code here works just as well if - * that isn't true, but mac80211 assumes it can - * access fields as 2-byte aligned (e.g. for - * compare_ether_addr) + if (skb) { + /* 'align' will only take the values 0 or 2 here since all + * frames are required to be aligned to 2-byte boundaries + * when being passed to mac80211; the code here works just + * as well if that isn't true, but mac80211 assumes it can + * access fields as 2-byte aligned (e.g. for ether_addr_equal) */ - align = ((unsigned long)(skb->data + sizeof(struct ethhdr))) & 3; + int align; + + align = (unsigned long)(skb->data + sizeof(struct ethhdr)) & 3; if (align) { if (WARN_ON(skb_headroom(skb) < 3)) { dev_kfree_skb(skb); @@ -1964,14 +1986,14 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) skb_set_tail_pointer(skb, len); } } + } #endif - if (skb) { - /* deliver to local stack */ - skb->protocol = eth_type_trans(skb, dev); - memset(skb->cb, 0, sizeof(skb->cb)); - netif_receive_skb(skb); - } + if (skb) { + /* deliver to local stack */ + skb->protocol = eth_type_trans(skb, dev); + memset(skb->cb, 0, sizeof(skb->cb)); + netif_receive_skb(skb); } if (xmit_skb) { @@ -2057,7 +2079,6 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - __le16 reason = cpu_to_le16(WLAN_REASON_MESH_PATH_NOFORWARD); u16 q, hdrlen; hdr = (struct ieee80211_hdr *) skb->data; @@ -2165,7 +2186,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) } else { /* unable to resolve next hop */ mesh_path_error_tx(sdata, ifmsh->mshcfg.element_ttl, - fwd_hdr->addr3, 0, reason, fwd_hdr->addr2); + fwd_hdr->addr3, 0, + WLAN_REASON_MESH_PATH_NOFORWARD, + fwd_hdr->addr2); IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_no_route); kfree_skb(fwd_skb); return RX_DROP_MONITOR; @@ -3053,8 +3076,8 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) /* main receive path */ -static int prepare_for_handlers(struct ieee80211_rx_data *rx, - struct ieee80211_hdr *hdr) +static bool prepare_for_handlers(struct ieee80211_rx_data *rx, + struct ieee80211_hdr *hdr) { struct ieee80211_sub_if_data *sdata = rx->sdata; struct sk_buff *skb = rx->skb; @@ -3065,29 +3088,29 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: if (!bssid && !sdata->u.mgd.use_4addr) - return 0; + return false; if (!multicast && !ether_addr_equal(sdata->vif.addr, hdr->addr1)) { if (!(sdata->dev->flags & IFF_PROMISC) || sdata->u.mgd.use_4addr) - return 0; + return false; status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } break; case NL80211_IFTYPE_ADHOC: if (!bssid) - return 0; + return false; if (ether_addr_equal(sdata->vif.addr, hdr->addr2) || ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2)) - return 0; + return false; if (ieee80211_is_beacon(hdr->frame_control)) { - return 1; + return true; } else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) { - return 0; + return false; } else if (!multicast && !ether_addr_equal(sdata->vif.addr, hdr->addr1)) { if (!(sdata->dev->flags & IFF_PROMISC)) - return 0; + return false; status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } else if (!rx->sta) { int rate_idx; @@ -3103,7 +3126,7 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, if (!multicast && !ether_addr_equal(sdata->vif.addr, hdr->addr1)) { if (!(sdata->dev->flags & IFF_PROMISC)) - return 0; + return false; status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } @@ -3112,7 +3135,7 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, case NL80211_IFTYPE_AP: if (!bssid) { if (!ether_addr_equal(sdata->vif.addr, hdr->addr1)) - return 0; + return false; } else if (!ieee80211_bssid_match(bssid, sdata->vif.addr)) { /* * Accept public action frames even when the @@ -3122,26 +3145,26 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, */ if (!multicast && !ether_addr_equal(sdata->vif.addr, hdr->addr1)) - return 0; + return false; if (ieee80211_is_public_action(hdr, skb->len)) - return 1; + return true; if (!ieee80211_is_beacon(hdr->frame_control)) - return 0; + return false; status->rx_flags &= ~IEEE80211_RX_RA_MATCH; } break; case NL80211_IFTYPE_WDS: if (bssid || !ieee80211_is_data(hdr->frame_control)) - return 0; + return false; if (!ether_addr_equal(sdata->u.wds.remote_addr, hdr->addr2)) - return 0; + return false; break; case NL80211_IFTYPE_P2P_DEVICE: if (!ieee80211_is_public_action(hdr, skb->len) && !ieee80211_is_probe_req(hdr->frame_control) && !ieee80211_is_probe_resp(hdr->frame_control) && !ieee80211_is_beacon(hdr->frame_control)) - return 0; + return false; if (!ether_addr_equal(sdata->vif.addr, hdr->addr1) && !multicast) status->rx_flags &= ~IEEE80211_RX_RA_MATCH; @@ -3152,7 +3175,7 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, break; } - return 1; + return true; } /* @@ -3168,13 +3191,11 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_hdr *hdr = (void *)skb->data; - int prepares; rx->skb = skb; status->rx_flags |= IEEE80211_RX_RA_MATCH; - prepares = prepare_for_handlers(rx, hdr); - if (!prepares) + if (!prepare_for_handlers(rx, hdr)) return false; if (!consume) { diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index bcc4833d7542..88c81616f8f7 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -271,10 +271,11 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) return true; } -static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted, - bool was_hw_scan) +static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) { struct ieee80211_local *local = hw_to_local(hw); + bool hw_scan = local->ops->hw_scan; + bool was_scanning = local->scanning; lockdep_assert_held(&local->mtx); @@ -290,7 +291,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted, if (WARN_ON(!local->scan_req)) return; - if (was_hw_scan && !aborted && ieee80211_prep_hw_scan(local)) { + if (hw_scan && !aborted && ieee80211_prep_hw_scan(local)) { int rc; rc = drv_hw_scan(local, @@ -316,7 +317,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted, /* Set power back to normal operating levels. */ ieee80211_hw_config(local, 0); - if (!was_hw_scan) { + if (!hw_scan) { ieee80211_configure_filter(local); drv_sw_scan_complete(local); ieee80211_offchannel_return(local); @@ -327,7 +328,8 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted, ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); ieee80211_mesh_notify_scan_completed(local); - ieee80211_start_next_roc(local); + if (was_scanning) + ieee80211_start_next_roc(local); } void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) @@ -526,7 +528,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, ieee80211_hw_config(local, 0); if ((req->channels[0]->flags & - IEEE80211_CHAN_PASSIVE_SCAN) || + IEEE80211_CHAN_NO_IR) || !local->scan_req->n_ssids) { next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; } else { @@ -572,7 +574,7 @@ ieee80211_scan_get_channel_time(struct ieee80211_channel *chan) * TODO: channel switching also consumes quite some time, * add that delay as well to get a better estimation */ - if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) + if (chan->flags & IEEE80211_CHAN_NO_IR) return IEEE80211_PASSIVE_CHANNEL_TIME; return IEEE80211_PROBE_DELAY + IEEE80211_CHANNEL_TIME; } @@ -696,7 +698,7 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, * * In any case, it is not necessary for a passive scan. */ - if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN || + if (chan->flags & IEEE80211_CHAN_NO_IR || !local->scan_req->n_ssids) { *next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; local->next_scan_state = SCAN_DECISION; @@ -747,7 +749,7 @@ void ieee80211_scan_work(struct work_struct *work) container_of(work, struct ieee80211_local, scan_work.work); struct ieee80211_sub_if_data *sdata; unsigned long next_delay = 0; - bool aborted, hw_scan; + bool aborted; mutex_lock(&local->mtx); @@ -786,14 +788,6 @@ void ieee80211_scan_work(struct work_struct *work) } /* - * Avoid re-scheduling when the sdata is going away. - */ - if (!ieee80211_sdata_running(sdata)) { - aborted = true; - goto out_complete; - } - - /* * as long as no delay is required advance immediately * without scheduling a new work */ @@ -834,8 +828,7 @@ void ieee80211_scan_work(struct work_struct *work) goto out; out_complete: - hw_scan = test_bit(SCAN_HW_SCANNING, &local->scanning); - __ieee80211_scan_completed(&local->hw, aborted, hw_scan); + __ieee80211_scan_completed(&local->hw, aborted); out: mutex_unlock(&local->mtx); } @@ -881,7 +874,7 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *tmp_ch = &local->hw.wiphy->bands[band]->channels[i]; - if (tmp_ch->flags & (IEEE80211_CHAN_NO_IBSS | + if (tmp_ch->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_DISABLED)) continue; @@ -895,7 +888,7 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, local->int_scan_req->n_channels = n_ch; } else { - if (WARN_ON_ONCE(chan->flags & (IEEE80211_CHAN_NO_IBSS | + if (WARN_ON_ONCE(chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_DISABLED))) goto unlock; @@ -973,13 +966,13 @@ void ieee80211_scan_cancel(struct ieee80211_local *local) */ cancel_delayed_work(&local->scan_work); /* and clean up */ - __ieee80211_scan_completed(&local->hw, true, false); + __ieee80211_scan_completed(&local->hw, true); out: mutex_unlock(&local->mtx); } -int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, - struct cfg80211_sched_scan_request *req) +int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, + struct cfg80211_sched_scan_request *req) { struct ieee80211_local *local = sdata->local; struct ieee80211_sched_scan_ies sched_scan_ies = {}; @@ -989,17 +982,10 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, iebufsz = 2 + IEEE80211_MAX_SSID_LEN + local->scan_ies_len + req->ie_len; - mutex_lock(&local->mtx); - - if (rcu_access_pointer(local->sched_scan_sdata)) { - ret = -EBUSY; - goto out; - } + lockdep_assert_held(&local->mtx); - if (!local->ops->sched_scan_start) { - ret = -ENOTSUPP; - goto out; - } + if (!local->ops->sched_scan_start) + return -ENOTSUPP; for (i = 0; i < IEEE80211_NUM_BANDS; i++) { if (!local->hw.wiphy->bands[i]) @@ -1020,13 +1006,39 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, } ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies); - if (ret == 0) + if (ret == 0) { rcu_assign_pointer(local->sched_scan_sdata, sdata); + local->sched_scan_req = req; + } out_free: while (i > 0) kfree(sched_scan_ies.ie[--i]); -out: + + if (ret) { + /* Clean in case of failure after HW restart or upon resume. */ + rcu_assign_pointer(local->sched_scan_sdata, NULL); + local->sched_scan_req = NULL; + } + + return ret; +} + +int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, + struct cfg80211_sched_scan_request *req) +{ + struct ieee80211_local *local = sdata->local; + int ret; + + mutex_lock(&local->mtx); + + if (rcu_access_pointer(local->sched_scan_sdata)) { + mutex_unlock(&local->mtx); + return -EBUSY; + } + + ret = __ieee80211_request_sched_scan_start(sdata, req); + mutex_unlock(&local->mtx); return ret; } @@ -1043,6 +1055,9 @@ int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata) goto out; } + /* We don't want to restart sched scan anymore. */ + local->sched_scan_req = NULL; + if (rcu_access_pointer(local->sched_scan_sdata)) drv_sched_scan_stop(local, sdata); @@ -1077,6 +1092,9 @@ void ieee80211_sched_scan_stopped_work(struct work_struct *work) rcu_assign_pointer(local->sched_scan_sdata, NULL); + /* If sched scan was aborted by the driver. */ + local->sched_scan_req = NULL; + mutex_unlock(&local->mtx); cfg80211_sched_scan_stopped(local->hw.wiphy); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 1eb66e26e49d..decd30c1e290 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -99,23 +99,6 @@ static void cleanup_single_sta(struct sta_info *sta) struct ieee80211_local *local = sdata->local; struct ps_data *ps; - /* - * At this point, when being called as call_rcu callback, - * neither mac80211 nor the driver can reference this - * sta struct any more except by still existing timers - * associated with this station that we clean up below. - * - * Note though that this still uses the sdata and even - * calls the driver in AP and mesh mode, so interfaces - * of those types mush use call sta_info_flush_cleanup() - * (typically via sta_info_flush()) before deconfiguring - * the driver. - * - * In station mode, nothing happens here so it doesn't - * have to (and doesn't) do that, this is intentional to - * speed up roaming. - */ - if (test_sta_flag(sta, WLAN_STA_PS_STA)) { if (sta->sdata->vif.type == NL80211_IFTYPE_AP || sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) @@ -160,37 +143,6 @@ static void cleanup_single_sta(struct sta_info *sta) sta_info_free(local, sta); } -void ieee80211_cleanup_sdata_stas(struct ieee80211_sub_if_data *sdata) -{ - struct sta_info *sta; - - spin_lock_bh(&sdata->cleanup_stations_lock); - while (!list_empty(&sdata->cleanup_stations)) { - sta = list_first_entry(&sdata->cleanup_stations, - struct sta_info, list); - list_del(&sta->list); - spin_unlock_bh(&sdata->cleanup_stations_lock); - - cleanup_single_sta(sta); - - spin_lock_bh(&sdata->cleanup_stations_lock); - } - - spin_unlock_bh(&sdata->cleanup_stations_lock); -} - -static void free_sta_rcu(struct rcu_head *h) -{ - struct sta_info *sta = container_of(h, struct sta_info, rcu_head); - struct ieee80211_sub_if_data *sdata = sta->sdata; - - spin_lock(&sdata->cleanup_stations_lock); - list_add_tail(&sta->list, &sdata->cleanup_stations); - spin_unlock(&sdata->cleanup_stations_lock); - - ieee80211_queue_work(&sdata->local->hw, &sdata->cleanup_stations_wk); -} - /* protected by RCU */ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, const u8 *addr) @@ -266,9 +218,17 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata, */ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) { + int i; + if (sta->rate_ctrl) rate_control_free_sta(sta); + if (sta->tx_lat) { + for (i = 0; i < IEEE80211_NUM_TIDS; i++) + kfree(sta->tx_lat[i].bins); + kfree(sta->tx_lat); + } + sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr); kfree(sta); @@ -333,12 +293,42 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct sta_info *sta; struct timespec uptime; + struct ieee80211_tx_latency_bin_ranges *tx_latency; int i; sta = kzalloc(sizeof(*sta) + local->hw.sta_data_size, gfp); if (!sta) return NULL; + rcu_read_lock(); + tx_latency = rcu_dereference(local->tx_latency); + /* init stations Tx latency statistics && TID bins */ + if (tx_latency) { + sta->tx_lat = kzalloc(IEEE80211_NUM_TIDS * + sizeof(struct ieee80211_tx_latency_stat), + GFP_ATOMIC); + if (!sta->tx_lat) { + rcu_read_unlock(); + goto free; + } + + if (tx_latency->n_ranges) { + for (i = 0; i < IEEE80211_NUM_TIDS; i++) { + /* size of bins is size of the ranges +1 */ + sta->tx_lat[i].bin_count = + tx_latency->n_ranges + 1; + sta->tx_lat[i].bins = + kcalloc(sta->tx_lat[i].bin_count, + sizeof(u32), GFP_ATOMIC); + if (!sta->tx_lat[i].bins) { + rcu_read_unlock(); + goto free; + } + } + } + } + rcu_read_unlock(); + spin_lock_init(&sta->lock); INIT_WORK(&sta->drv_unblock_wk, sta_unblock); INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work); @@ -363,10 +353,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, for (i = 0; i < ARRAY_SIZE(sta->chain_signal_avg); i++) ewma_init(&sta->chain_signal_avg[i], 1024, 8); - if (sta_prepare_rate_control(local, sta, gfp)) { - kfree(sta); - return NULL; - } + if (sta_prepare_rate_control(local, sta, gfp)) + goto free; for (i = 0; i < IEEE80211_NUM_TIDS; i++) { /* @@ -411,8 +399,16 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, } sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); - return sta; + +free: + if (sta->tx_lat) { + for (i = 0; i < IEEE80211_NUM_TIDS; i++) + kfree(sta->tx_lat[i].bins); + kfree(sta->tx_lat); + } + kfree(sta); + return NULL; } static int sta_info_insert_check(struct sta_info *sta) @@ -507,6 +503,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) set_sta_flag(sta, WLAN_STA_INSERTED); + ieee80211_recalc_min_chandef(sdata); ieee80211_sta_debugfs_add(sta); rate_control_add_sta_debugfs(sta); @@ -630,8 +627,8 @@ void sta_info_recalc_tim(struct sta_info *sta) #ifdef CONFIG_MAC80211_MESH } else if (ieee80211_vif_is_mesh(&sta->sdata->vif)) { ps = &sta->sdata->u.mesh.ps; - /* TIM map only for PLID <= IEEE80211_MAX_AID */ - id = le16_to_cpu(sta->plid) % IEEE80211_MAX_AID; + /* TIM map only for 1 <= PLID <= IEEE80211_MAX_AID */ + id = sta->plid % (IEEE80211_MAX_AID + 1); #endif } else { return; @@ -807,7 +804,7 @@ static bool sta_info_cleanup_expire_buffered(struct ieee80211_local *local, return have_buffered; } -int __must_check __sta_info_destroy(struct sta_info *sta) +static int __must_check __sta_info_destroy_part1(struct sta_info *sta) { struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; @@ -833,12 +830,35 @@ int __must_check __sta_info_destroy(struct sta_info *sta) ieee80211_sta_tear_down_BA_sessions(sta, AGG_STOP_DESTROY_STA); ret = sta_info_hash_del(local, sta); - if (ret) + if (WARN_ON(ret)) return ret; list_del_rcu(&sta->list); - /* this always calls synchronize_net() */ + drv_sta_pre_rcu_remove(local, sta->sdata, sta); + + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN && + rcu_access_pointer(sdata->u.vlan.sta) == sta) + RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); + + return 0; +} + +static void __sta_info_destroy_part2(struct sta_info *sta) +{ + struct ieee80211_local *local = sta->local; + struct ieee80211_sub_if_data *sdata = sta->sdata; + int ret; + + /* + * NOTE: This assumes at least synchronize_net() was done + * after _part1 and before _part2! + */ + + might_sleep(); + lockdep_assert_held(&local->sta_mtx); + + /* now keys can no longer be reached */ ieee80211_free_sta_keys(local, sta); sta->dead = true; @@ -846,9 +866,6 @@ int __must_check __sta_info_destroy(struct sta_info *sta) local->num_sta--; local->sta_generation++; - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) - RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); - while (sta->sta_state > IEEE80211_STA_NONE) { ret = sta_info_move_state(sta, sta->sta_state - 1); if (ret) { @@ -869,8 +886,21 @@ int __must_check __sta_info_destroy(struct sta_info *sta) rate_control_remove_sta_debugfs(sta); ieee80211_sta_debugfs_remove(sta); + ieee80211_recalc_min_chandef(sdata); + + cleanup_single_sta(sta); +} - call_rcu(&sta->rcu_head, free_sta_rcu); +int __must_check __sta_info_destroy(struct sta_info *sta) +{ + int err = __sta_info_destroy_part1(sta); + + if (err) + return err; + + synchronize_net(); + + __sta_info_destroy_part2(sta); return 0; } @@ -940,32 +970,38 @@ void sta_info_stop(struct ieee80211_local *local) } -int sta_info_flush_defer(struct ieee80211_sub_if_data *sdata) +int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans) { struct ieee80211_local *local = sdata->local; struct sta_info *sta, *tmp; + LIST_HEAD(free_list); int ret = 0; might_sleep(); + WARN_ON(vlans && sdata->vif.type != NL80211_IFTYPE_AP); + WARN_ON(vlans && !sdata->bss); + mutex_lock(&local->sta_mtx); list_for_each_entry_safe(sta, tmp, &local->sta_list, list) { - if (sdata == sta->sdata) { - WARN_ON(__sta_info_destroy(sta)); + if (sdata == sta->sdata || + (vlans && sdata->bss == sta->sdata->bss)) { + if (!WARN_ON(__sta_info_destroy_part1(sta))) + list_add(&sta->free_list, &free_list); ret++; } } + + if (!list_empty(&free_list)) { + synchronize_net(); + list_for_each_entry_safe(sta, tmp, &free_list, free_list) + __sta_info_destroy_part2(sta); + } mutex_unlock(&local->sta_mtx); return ret; } -void sta_info_flush_cleanup(struct ieee80211_sub_if_data *sdata) -{ - ieee80211_cleanup_sdata_stas(sdata); - cancel_work_sync(&sdata->cleanup_stations_wk); -} - void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, unsigned long exp_time) { @@ -1117,7 +1153,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, int tid, - enum ieee80211_frame_release_type reason) + enum ieee80211_frame_release_type reason, + bool call_driver) { struct ieee80211_local *local = sdata->local; struct ieee80211_qos_hdr *nullfunc; @@ -1175,7 +1212,9 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, IEEE80211_TX_STATUS_EOSP | IEEE80211_TX_CTL_REQ_TX_STATUS; - drv_allow_buffered_frames(local, sta, BIT(tid), 1, reason, false); + if (call_driver) + drv_allow_buffered_frames(local, sta, BIT(tid), 1, + reason, false); skb->dev = sdata->dev; @@ -1191,6 +1230,17 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); } +static int find_highest_prio_tid(unsigned long tids) +{ + /* lower 3 TIDs aren't ordered perfectly */ + if (tids & 0xF8) + return fls(tids) - 1; + /* TID 0 is BE just like TID 3 */ + if (tids & BIT(0)) + return 0; + return fls(tids) - 1; +} + static void ieee80211_sta_ps_deliver_response(struct sta_info *sta, int n_frames, u8 ignored_acs, @@ -1198,7 +1248,6 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; - bool found = false; bool more_data = false; int ac; unsigned long driver_release_tids = 0; @@ -1209,9 +1258,7 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, __skb_queue_head_init(&frames); - /* - * Get response frame(s) and more data bit for it. - */ + /* Get response frame(s) and more data bit for the last one. */ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { unsigned long tids; @@ -1220,43 +1267,48 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, tids = ieee80211_tids_for_ac(ac); - if (!found) { - driver_release_tids = sta->driver_buffered_tids & tids; - if (driver_release_tids) { - found = true; - } else { - struct sk_buff *skb; - - while (n_frames > 0) { - skb = skb_dequeue(&sta->tx_filtered[ac]); - if (!skb) { - skb = skb_dequeue( - &sta->ps_tx_buf[ac]); - if (skb) - local->total_ps_buffered--; - } - if (!skb) - break; - n_frames--; - found = true; - __skb_queue_tail(&frames, skb); - } - } + /* if we already have frames from software, then we can't also + * release from hardware queues + */ + if (skb_queue_empty(&frames)) + driver_release_tids |= sta->driver_buffered_tids & tids; - /* - * If the driver has data on more than one TID then + if (driver_release_tids) { + /* If the driver has data on more than one TID then * certainly there's more data if we release just a - * single frame now (from a single TID). + * single frame now (from a single TID). This will + * only happen for PS-Poll. */ if (reason == IEEE80211_FRAME_RELEASE_PSPOLL && hweight16(driver_release_tids) > 1) { more_data = true; driver_release_tids = - BIT(ffs(driver_release_tids) - 1); + BIT(find_highest_prio_tid( + driver_release_tids)); break; } + } else { + struct sk_buff *skb; + + while (n_frames > 0) { + skb = skb_dequeue(&sta->tx_filtered[ac]); + if (!skb) { + skb = skb_dequeue( + &sta->ps_tx_buf[ac]); + if (skb) + local->total_ps_buffered--; + } + if (!skb) + break; + n_frames--; + __skb_queue_tail(&frames, skb); + } } + /* If we have more frames buffered on this AC, then set the + * more-data bit and abort the loop since we can't send more + * data from other ACs before the buffered frames from this. + */ if (!skb_queue_empty(&sta->tx_filtered[ac]) || !skb_queue_empty(&sta->ps_tx_buf[ac])) { more_data = true; @@ -1264,7 +1316,7 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, } } - if (!found) { + if (skb_queue_empty(&frames) && !driver_release_tids) { int tid; /* @@ -1285,15 +1337,13 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, /* This will evaluate to 1, 3, 5 or 7. */ tid = 7 - ((ffs(~ignored_acs) - 1) << 1); - ieee80211_send_null_response(sdata, sta, tid, reason); - return; - } - - if (!driver_release_tids) { + ieee80211_send_null_response(sdata, sta, tid, reason, true); + } else if (!driver_release_tids) { struct sk_buff_head pending; struct sk_buff *skb; int num = 0; u16 tids = 0; + bool need_null = false; skb_queue_head_init(&pending); @@ -1327,22 +1377,57 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, ieee80211_is_qos_nullfunc(hdr->frame_control)) qoshdr = ieee80211_get_qos_ctl(hdr); - /* end service period after last frame */ - if (skb_queue_empty(&frames)) { - if (reason == IEEE80211_FRAME_RELEASE_UAPSD && - qoshdr) - *qoshdr |= IEEE80211_QOS_CTL_EOSP; + tids |= BIT(skb->priority); + + __skb_queue_tail(&pending, skb); + + /* end service period after last frame or add one */ + if (!skb_queue_empty(&frames)) + continue; + if (reason != IEEE80211_FRAME_RELEASE_UAPSD) { + /* for PS-Poll, there's only one frame */ info->flags |= IEEE80211_TX_STATUS_EOSP | IEEE80211_TX_CTL_REQ_TX_STATUS; + break; } - if (qoshdr) - tids |= BIT(*qoshdr & IEEE80211_QOS_CTL_TID_MASK); - else - tids |= BIT(0); + /* For uAPSD, things are a bit more complicated. If the + * last frame has a QoS header (i.e. is a QoS-data or + * QoS-nulldata frame) then just set the EOSP bit there + * and be done. + * If the frame doesn't have a QoS header (which means + * it should be a bufferable MMPDU) then we can't set + * the EOSP bit in the QoS header; add a QoS-nulldata + * frame to the list to send it after the MMPDU. + * + * Note that this code is only in the mac80211-release + * code path, we assume that the driver will not buffer + * anything but QoS-data frames, or if it does, will + * create the QoS-nulldata frame by itself if needed. + * + * Cf. 802.11-2012 10.2.1.10 (c). + */ + if (qoshdr) { + *qoshdr |= IEEE80211_QOS_CTL_EOSP; - __skb_queue_tail(&pending, skb); + info->flags |= IEEE80211_TX_STATUS_EOSP | + IEEE80211_TX_CTL_REQ_TX_STATUS; + } else { + /* The standard isn't completely clear on this + * as it says the more-data bit should be set + * if there are more BUs. The QoS-Null frame + * we're about to send isn't buffered yet, we + * only create it below, but let's pretend it + * was buffered just in case some clients only + * expect more-data=0 when eosp=1. + */ + hdr->frame_control |= + cpu_to_le16(IEEE80211_FCTL_MOREDATA); + need_null = true; + num++; + } + break; } drv_allow_buffered_frames(local, sta, tids, num, @@ -1350,17 +1435,22 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, ieee80211_add_pending_skbs(local, &pending); + if (need_null) + ieee80211_send_null_response( + sdata, sta, find_highest_prio_tid(tids), + reason, false); + sta_info_recalc_tim(sta); } else { /* * We need to release a frame that is buffered somewhere in the * driver ... it'll have to handle that. - * Note that, as per the comment above, it'll also have to see - * if there is more than just one frame on the specific TID that - * we're releasing from, and it needs to set the more-data bit - * accordingly if we tell it that there's no more data. If we do - * tell it there's more data, then of course the more-data bit - * needs to be set anyway. + * Note that the driver also has to check the number of frames + * on the TIDs we're releasing from - if there are more than + * n_frames it has to set the more-data bit (if we didn't ask + * it to set it anyway due to other buffered frames); if there + * are fewer than n_frames it has to make sure to adjust that + * to allow the service period to end properly. */ drv_release_buffered_frames(local, sta, driver_release_tids, n_frames, reason, more_data); @@ -1368,9 +1458,9 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, /* * Note that we don't recalculate the TIM bit here as it would * most likely have no effect at all unless the driver told us - * that the TID became empty before returning here from the + * that the TID(s) became empty before returning here from the * release function. - * Either way, however, when the driver tells us that the TID + * Either way, however, when the driver tells us that the TID(s) * became empty we'll do the TIM recalculation. */ } @@ -1459,6 +1549,8 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, if (WARN_ON(tid >= IEEE80211_NUM_TIDS)) return; + trace_api_sta_set_buffered(sta->local, pubsta, tid, buffered); + if (buffered) set_bit(tid, &sta->driver_buffered_tids); else diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 3ef06a26b9cb..d77ff7090630 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -220,6 +220,25 @@ struct sta_ampdu_mlme { u8 dialog_token_allocator; }; +/* + * struct ieee80211_tx_latency_stat - Tx latency statistics + * + * Measures TX latency and jitter for a station per TID. + * + * @max: worst case latency + * @sum: sum of all latencies + * @counter: amount of Tx frames sent from interface + * @bins: each bin counts how many frames transmitted within a certain + * latency range. when disabled it is NULL. + * @bin_count: amount of bins. + */ +struct ieee80211_tx_latency_stat { + u32 max; + u32 sum; + u32 counter; + u32 *bins; + u32 bin_count; +}; /** * struct sta_info - STA information @@ -228,11 +247,14 @@ struct sta_ampdu_mlme { * mac80211 is communicating with. * * @list: global linked list entry + * @free_list: list entry for keeping track of stations to free * @hnext: hash table linked list pointer * @local: pointer to the global information * @sdata: virtual interface this station belongs to - * @ptk: peer key negotiated with this station, if any + * @ptk: peer keys negotiated with this station, if any + * @ptk_idx: last installed peer key index * @gtk: group keys negotiated with this station, if any + * @gtk_idx: last installed group key index * @rate_ctrl: rate control algorithm reference * @rate_ctrl_priv: rate control private per-STA pointer * @last_tx_rate: rate used for last transmit, to report to userspace as @@ -274,6 +296,7 @@ struct sta_ampdu_mlme { * @tid_seq: per-TID sequence numbers for sending to this STA * @ampdu_mlme: A-MPDU state machine state * @timer_to_tid: identity mapping to ID timers + * @tx_lat: Tx latency statistics * @llid: Local link ID * @plid: Peer link ID * @reason: Cancel reason on PLINK_HOLDING state @@ -303,16 +326,19 @@ struct sta_ampdu_mlme { * @chain_signal_avg: signal average (per chain) * @known_smps_mode: the smps_mode the client thinks we are in. Relevant for * AP only. + * @cipher_scheme: optional cipher scheme for this station */ struct sta_info { /* General information, mostly static */ - struct list_head list; + struct list_head list, free_list; struct rcu_head rcu_head; struct sta_info __rcu *hnext; struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; - struct ieee80211_key __rcu *ptk; + struct ieee80211_key __rcu *ptk[NUM_DEFAULT_KEYS]; + u8 gtk_idx; + u8 ptk_idx; struct rate_control_ref *rate_ctrl; void *rate_ctrl_priv; spinlock_t lock; @@ -380,14 +406,16 @@ struct sta_info { struct sta_ampdu_mlme ampdu_mlme; u8 timer_to_tid[IEEE80211_NUM_TIDS]; + struct ieee80211_tx_latency_stat *tx_lat; + #ifdef CONFIG_MAC80211_MESH /* * Mesh peer link attributes * TODO: move to a sub-structure that is referenced with pointer? */ - __le16 llid; - __le16 plid; - __le16 reason; + u16 llid; + u16 plid; + u16 reason; u8 plink_retries; bool ignore_plink_timer; enum nl80211_plink_state plink_state; @@ -414,6 +442,7 @@ struct sta_info { unsigned int beacon_loss_count; enum ieee80211_smps_mode known_smps_mode; + const struct ieee80211_cipher_scheme *cipher_scheme; /* keep last! */ struct ieee80211_sta sta; @@ -577,21 +606,6 @@ void sta_info_recalc_tim(struct sta_info *sta); void sta_info_init(struct ieee80211_local *local); void sta_info_stop(struct ieee80211_local *local); -int sta_info_flush_defer(struct ieee80211_sub_if_data *sdata); - -/** - * sta_info_flush_cleanup - flush the sta_info cleanup queue - * @sdata: the interface - * - * Flushes the sta_info cleanup queue for a given interface; - * this is necessary before the interface is removed or, for - * AP/mesh interfaces, before it is deconfigured. - * - * Note an rcu_barrier() must precede the function, after all - * stations have been flushed/removed to ensure the call_rcu() - * calls that add stations to the cleanup queue have completed. - */ -void sta_info_flush_cleanup(struct ieee80211_sub_if_data *sdata); /** * sta_info_flush - flush matching STA entries from the STA table @@ -599,15 +613,13 @@ void sta_info_flush_cleanup(struct ieee80211_sub_if_data *sdata); * Returns the number of removed STA entries. * * @sdata: sdata to remove all stations from + * @vlans: if the given interface is an AP interface, also flush VLANs */ +int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans); + static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata) { - int ret = sta_info_flush_defer(sdata); - - rcu_barrier(); - sta_info_flush_cleanup(sdata); - - return ret; + return __sta_info_flush(sdata, false); } void sta_set_rate_info_tx(struct sta_info *sta, @@ -623,6 +635,4 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta); void ieee80211_sta_ps_deliver_poll_response(struct sta_info *sta); void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta); -void ieee80211_cleanup_sdata_stas(struct ieee80211_sub_if_data *sdata); - #endif /* STA_INFO_H */ diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 52a152b01b06..1ee85c402439 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -11,6 +11,7 @@ #include <linux/export.h> #include <linux/etherdevice.h> +#include <linux/time.h> #include <net/mac80211.h> #include <asm/unaligned.h> #include "ieee80211_i.h" @@ -463,6 +464,77 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, } /* + * Measure Tx frame completion and removal time for Tx latency statistics + * calculation. A single Tx frame latency should be measured from when it + * is entering the Kernel until we receive Tx complete confirmation indication + * and remove the skb. + */ +static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local, + struct sk_buff *skb, + struct sta_info *sta, + struct ieee80211_hdr *hdr) +{ + ktime_t skb_dprt; + struct timespec dprt_time; + u32 msrmnt; + u16 tid; + u8 *qc; + int i, bin_range_count, bin_count; + u32 *bin_ranges; + __le16 fc; + struct ieee80211_tx_latency_stat *tx_lat; + struct ieee80211_tx_latency_bin_ranges *tx_latency; + ktime_t skb_arv = skb->tstamp; + + tx_latency = rcu_dereference(local->tx_latency); + + /* assert Tx latency stats are enabled & frame arrived when enabled */ + if (!tx_latency || !ktime_to_ns(skb_arv)) + return; + + fc = hdr->frame_control; + + if (!ieee80211_is_data(fc)) /* make sure it is a data frame */ + return; + + /* get frame tid */ + if (ieee80211_is_data_qos(hdr->frame_control)) { + qc = ieee80211_get_qos_ctl(hdr); + tid = qc[0] & IEEE80211_QOS_CTL_TID_MASK; + } else { + tid = 0; + } + + tx_lat = &sta->tx_lat[tid]; + + ktime_get_ts(&dprt_time); /* time stamp completion time */ + skb_dprt = ktime_set(dprt_time.tv_sec, dprt_time.tv_nsec); + msrmnt = ktime_to_ms(ktime_sub(skb_dprt, skb_arv)); + + if (tx_lat->max < msrmnt) /* update stats */ + tx_lat->max = msrmnt; + tx_lat->counter++; + tx_lat->sum += msrmnt; + + if (!tx_lat->bins) /* bins not activated */ + return; + + /* count how many Tx frames transmitted with the appropriate latency */ + bin_range_count = tx_latency->n_ranges; + bin_ranges = tx_latency->ranges; + bin_count = tx_lat->bin_count; + + for (i = 0; i < bin_range_count; i++) { + if (msrmnt <= bin_ranges[i]) { + tx_lat->bins[i]++; + break; + } + } + if (i == bin_range_count) /* msrmnt is bigger than the biggest range */ + tx_lat->bins[i]++; +} + +/* * Use a static threshold for now, best value to be determined * by testing ... * Should it depend on: @@ -620,6 +692,12 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if (acked) sta->last_ack_signal = info->status.ack_signal; + + /* + * Measure frame removal for tx latency + * statistics calculation + */ + ieee80211_tx_latency_end_msrmnt(local, skb, sta, hdr); } rcu_read_unlock(); diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c index 124b1fdc20d0..0ae207771a58 100644 --- a/net/mac80211/tkip.c +++ b/net/mac80211/tkip.c @@ -186,7 +186,7 @@ void ieee80211_get_tkip_p1k_iv(struct ieee80211_key_conf *keyconf, EXPORT_SYMBOL(ieee80211_get_tkip_p1k_iv); void ieee80211_get_tkip_rx_p1k(struct ieee80211_key_conf *keyconf, - const u8 *ta, u32 iv32, u16 *p1k) + const u8 *ta, u32 iv32, u16 *p1k) { const u8 *tk = &keyconf->key[NL80211_TKIP_DATA_OFFSET_ENCR_KEY]; struct tkip_ctx ctx; diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index d4cee98533fd..a0b0aea76525 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -41,14 +41,31 @@ #define CHANDEF_PR_ARG __entry->control_freq, __entry->chan_width, \ __entry->center_freq1, __entry->center_freq2 +#define MIN_CHANDEF_ENTRY \ + __field(u32, min_control_freq) \ + __field(u32, min_chan_width) \ + __field(u32, min_center_freq1) \ + __field(u32, min_center_freq2) + +#define MIN_CHANDEF_ASSIGN(c) \ + __entry->min_control_freq = (c)->chan ? (c)->chan->center_freq : 0; \ + __entry->min_chan_width = (c)->width; \ + __entry->min_center_freq1 = (c)->center_freq1; \ + __entry->min_center_freq2 = (c)->center_freq2; +#define MIN_CHANDEF_PR_FMT " min_control:%d MHz min_width:%d min_center: %d/%d MHz" +#define MIN_CHANDEF_PR_ARG __entry->min_control_freq, __entry->min_chan_width, \ + __entry->min_center_freq1, __entry->min_center_freq2 + #define CHANCTX_ENTRY CHANDEF_ENTRY \ + MIN_CHANDEF_ENTRY \ __field(u8, rx_chains_static) \ __field(u8, rx_chains_dynamic) #define CHANCTX_ASSIGN CHANDEF_ASSIGN(&ctx->conf.def) \ + MIN_CHANDEF_ASSIGN(&ctx->conf.min_def) \ __entry->rx_chains_static = ctx->conf.rx_chains_static; \ __entry->rx_chains_dynamic = ctx->conf.rx_chains_dynamic -#define CHANCTX_PR_FMT CHANDEF_PR_FMT " chains:%d/%d" -#define CHANCTX_PR_ARG CHANDEF_PR_ARG, \ +#define CHANCTX_PR_FMT CHANDEF_PR_FMT MIN_CHANDEF_PR_FMT " chains:%d/%d" +#define CHANCTX_PR_ARG CHANDEF_PR_ARG, MIN_CHANDEF_PR_ARG, \ __entry->rx_chains_static, __entry->rx_chains_dynamic @@ -426,30 +443,6 @@ TRACE_EVENT(drv_prepare_multicast, ) ); -TRACE_EVENT(drv_set_multicast_list, - TP_PROTO(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, int mc_count), - - TP_ARGS(local, sdata, mc_count), - - TP_STRUCT__entry( - LOCAL_ENTRY - __field(bool, allmulti) - __field(int, mc_count) - ), - - TP_fast_assign( - LOCAL_ASSIGN; - __entry->allmulti = sdata->flags & IEEE80211_SDATA_ALLMULTI; - __entry->mc_count = mc_count; - ), - - TP_printk( - LOCAL_PR_FMT " configure mc filter, count=%d, allmulti=%d", - LOCAL_PR_ARG, __entry->mc_count, __entry->allmulti - ) -); - TRACE_EVENT(drv_configure_filter, TP_PROTO(struct ieee80211_local *local, unsigned int changed_flags, @@ -560,7 +553,7 @@ TRACE_EVENT(drv_update_tkip_key, TP_printk( LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " iv32:%#x", - LOCAL_PR_ARG,VIF_PR_ARG,STA_PR_ARG, __entry->iv32 + LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->iv32 ) ); @@ -773,7 +766,7 @@ TRACE_EVENT(drv_sta_rc_update, ) ); -TRACE_EVENT(drv_sta_add, +DECLARE_EVENT_CLASS(sta_event, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_sta *sta), @@ -798,29 +791,25 @@ TRACE_EVENT(drv_sta_add, ) ); -TRACE_EVENT(drv_sta_remove, +DEFINE_EVENT(sta_event, drv_sta_add, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_sta *sta), + TP_ARGS(local, sdata, sta) +); - TP_ARGS(local, sdata, sta), - - TP_STRUCT__entry( - LOCAL_ENTRY - VIF_ENTRY - STA_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - VIF_ASSIGN; - STA_ASSIGN; - ), +DEFINE_EVENT(sta_event, drv_sta_remove, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta), + TP_ARGS(local, sdata, sta) +); - TP_printk( - LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT, - LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG - ) +DEFINE_EVENT(sta_event, drv_sta_pre_rcu_remove, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta), + TP_ARGS(local, sdata, sta) ); TRACE_EVENT(drv_conf_tx, @@ -1846,6 +1835,33 @@ TRACE_EVENT(api_eosp, ) ); +TRACE_EVENT(api_sta_set_buffered, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sta *sta, + u8 tid, bool buffered), + + TP_ARGS(local, sta, tid, buffered), + + TP_STRUCT__entry( + LOCAL_ENTRY + STA_ENTRY + __field(u8, tid) + __field(bool, buffered) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + STA_ASSIGN; + __entry->tid = tid; + __entry->buffered = buffered; + ), + + TP_printk( + LOCAL_PR_FMT STA_PR_FMT " tid:%d buffered:%d", + LOCAL_PR_ARG, STA_PR_ARG, __entry->tid, __entry->buffered + ) +); + /* * Tracing for internal functions * (which may also be called in response to driver calls) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index ca7fa7f0613d..97a02d3f7d87 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -19,6 +19,7 @@ #include <linux/bitmap.h> #include <linux/rcupdate.h> #include <linux/export.h> +#include <linux/time.h> #include <net/net_namespace.h> #include <net/ieee80211_radiotap.h> #include <net/cfg80211.h> @@ -489,6 +490,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) info->control.jiffies = jiffies; info->control.vif = &tx->sdata->vif; info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; + info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS; skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb); if (!timer_pending(&local->sta_cleanup)) @@ -560,7 +562,8 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) if (unlikely(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)) tx->key = NULL; - else if (tx->sta && (key = rcu_dereference(tx->sta->ptk))) + else if (tx->sta && + (key = rcu_dereference(tx->sta->ptk[tx->sta->ptk_idx]))) tx->key = key; else if (ieee80211_is_mgmt(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1) && @@ -843,15 +846,16 @@ static int ieee80211_fragment(struct ieee80211_tx_data *tx, rem -= fraglen; tmp = dev_alloc_skb(local->tx_headroom + frag_threshold + - IEEE80211_ENCRYPT_HEADROOM + + tx->sdata->encrypt_headroom + IEEE80211_ENCRYPT_TAILROOM); if (!tmp) return -ENOMEM; __skb_queue_tail(&tx->skbs, tmp); - skb_reserve(tmp, local->tx_headroom + - IEEE80211_ENCRYPT_HEADROOM); + skb_reserve(tmp, + local->tx_headroom + tx->sdata->encrypt_headroom); + /* copy control information */ memcpy(tmp->cb, skb->cb, sizeof(tmp->cb)); @@ -874,7 +878,7 @@ 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; } @@ -1073,6 +1077,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, queued = true; info->control.vif = &tx->sdata->vif; info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; + info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS; __skb_queue_tail(&tid_tx->pending, skb); if (skb_queue_len(&tid_tx->pending) > STA_MAX_TX_BUFFER) purge_skb = __skb_dequeue(&tid_tx->pending); @@ -1488,7 +1493,7 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, headroom = local->tx_headroom; if (may_encrypt) - headroom += IEEE80211_ENCRYPT_HEADROOM; + headroom += sdata->encrypt_headroom; headroom -= skb_headroom(skb); headroom = max_t(int, 0, headroom); @@ -1727,8 +1732,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, * radar detection by itself. We can do that later by adding a * monitor flag interfaces used for AP support. */ - if ((chan->flags & (IEEE80211_CHAN_NO_IBSS | IEEE80211_CHAN_RADAR | - IEEE80211_CHAN_PASSIVE_SCAN))) + if ((chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR))) goto fail_rcu; ieee80211_xmit(sdata, skb, chan->band); @@ -1743,6 +1747,26 @@ fail: return NETDEV_TX_OK; /* meaning, we dealt with the skb */ } +/* + * Measure Tx frame arrival time for Tx latency statistics calculation + * A single Tx frame latency should be measured from when it is entering the + * Kernel until we receive Tx complete confirmation indication and the skb is + * freed. + */ +static void ieee80211_tx_latency_start_msrmnt(struct ieee80211_local *local, + struct sk_buff *skb) +{ + struct timespec skb_arv; + struct ieee80211_tx_latency_bin_ranges *tx_latency; + + tx_latency = rcu_dereference(local->tx_latency); + if (!tx_latency) + return; + + ktime_get_ts(&skb_arv); + skb->tstamp = ktime_set(skb_arv.tv_sec, skb_arv.tv_nsec); +} + /** * ieee80211_subif_start_xmit - netif start_xmit function for Ethernet-type * subinterfaces (wlan#, WDS, and VLAN interfaces) @@ -1793,6 +1817,9 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, rcu_read_lock(); + /* Measure frame arrival for Tx latency statistics calculation */ + ieee80211_tx_latency_start_msrmnt(local, skb); + switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: sta = rcu_dereference(sdata->u.vlan.sta); @@ -2112,7 +2139,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, */ if (head_need > 0 || skb_cloned(skb)) { - head_need += IEEE80211_ENCRYPT_HEADROOM; + head_need += sdata->encrypt_headroom; head_need += local->tx_headroom; head_need = max_t(int, 0, head_need); if (ieee80211_skb_resize(sdata, skb, head_need, true)) { @@ -2139,7 +2166,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, if (ieee80211_is_data_qos(fc)) { __le16 *qos_control; - qos_control = (__le16*) skb_push(skb, 2); + qos_control = (__le16 *) skb_push(skb, 2); memcpy(skb_push(skb, hdrlen - 2), &hdr, hdrlen - 2); /* * Maybe we could actually set some fields here, for now just @@ -2301,7 +2328,7 @@ static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, if (atomic_read(&ps->num_sta_ps) > 0) /* in the hope that this is faster than * checking byte-for-byte */ - have_bits = !bitmap_empty((unsigned long*)ps->tim, + have_bits = !bitmap_empty((unsigned long *)ps->tim, IEEE80211_MAX_AID+1); if (ps->dtim_count == 0) @@ -2527,7 +2554,8 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, */ skb = dev_alloc_skb(local->tx_headroom + beacon->head_len + - beacon->tail_len + 256); + beacon->tail_len + 256 + + local->hw.extra_beacon_tailroom); if (!skb) goto out; @@ -2559,7 +2587,8 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, ieee80211_update_csa(sdata, presp); - skb = dev_alloc_skb(local->tx_headroom + presp->head_len); + skb = dev_alloc_skb(local->tx_headroom + presp->head_len + + local->hw.extra_beacon_tailroom); if (!skb) goto out; skb_reserve(skb, local->tx_headroom); @@ -2580,13 +2609,13 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, ieee80211_update_csa(sdata, bcn); if (ifmsh->sync_ops) - ifmsh->sync_ops->adjust_tbtt( - sdata); + ifmsh->sync_ops->adjust_tbtt(sdata, bcn); skb = dev_alloc_skb(local->tx_headroom + bcn->head_len + 256 + /* TIM IE */ - bcn->tail_len); + bcn->tail_len + + local->hw.extra_beacon_tailroom); if (!skb) goto out; skb_reserve(skb, local->tx_headroom); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 9f9b9bd3fd44..676dc0967f37 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -76,7 +76,7 @@ u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, } if (ieee80211_is_ctl(fc)) { - if(ieee80211_is_pspoll(fc)) + if (ieee80211_is_pspoll(fc)) return hdr->addr1; if (ieee80211_is_back_req(fc)) { @@ -642,6 +642,17 @@ void ieee80211_iterate_active_interfaces_rtnl( } EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_rtnl); +struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); + + if (!ieee80211_sdata_running(sdata) || + !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) + return NULL; + return &sdata->vif; +} +EXPORT_SYMBOL_GPL(wdev_to_ieee80211_vif); + /* * Nothing should have been stuffed into the workqueue during * the suspend->resume cycle. If this WARN is seen then there @@ -1451,6 +1462,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) struct sta_info *sta; int res, i; bool reconfig_due_to_wowlan = false; + struct ieee80211_sub_if_data *sched_scan_sdata; + bool sched_scan_stopped = false; #ifdef CONFIG_PM if (local->suspended) @@ -1754,6 +1767,27 @@ int ieee80211_reconfig(struct ieee80211_local *local) #else WARN_ON(1); #endif + + /* + * Reconfigure sched scan if it was interrupted by FW restart or + * suspend. + */ + mutex_lock(&local->mtx); + sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata, + lockdep_is_held(&local->mtx)); + if (sched_scan_sdata && local->sched_scan_req) + /* + * Sched scan stopped, but we don't want to report it. Instead, + * we're trying to reschedule. + */ + if (__ieee80211_request_sched_scan_start(sched_scan_sdata, + local->sched_scan_req)) + sched_scan_stopped = true; + mutex_unlock(&local->mtx); + + if (sched_scan_stopped) + cfg80211_sched_scan_stopped(local->hw.wiphy); + return 0; } @@ -1804,6 +1838,26 @@ void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata) mutex_unlock(&local->chanctx_mtx); } +void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_chanctx *chanctx; + + mutex_lock(&local->chanctx_mtx); + + chanctx_conf = rcu_dereference_protected(sdata->vif.chanctx_conf, + lockdep_is_held(&local->chanctx_mtx)); + + if (WARN_ON_ONCE(!chanctx_conf)) + goto unlock; + + chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); + ieee80211_recalc_chanctx_min_def(local, chanctx); + unlock: + mutex_unlock(&local->chanctx_mtx); +} + static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id) { int i; @@ -2259,19 +2313,28 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, void ieee80211_dfs_cac_cancel(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; + struct cfg80211_chan_def chandef; + mutex_lock(&local->mtx); mutex_lock(&local->iflist_mtx); list_for_each_entry(sdata, &local->interfaces, list) { - cancel_delayed_work_sync(&sdata->dfs_cac_timer_work); + /* it might be waiting for the local->mtx, but then + * by the time it gets it, sdata->wdev.cac_started + * will no longer be true + */ + cancel_delayed_work(&sdata->dfs_cac_timer_work); if (sdata->wdev.cac_started) { + chandef = sdata->vif.bss_conf.chandef; ieee80211_vif_release_channel(sdata); cfg80211_cac_event(sdata->dev, + &chandef, NL80211_RADAR_CAC_ABORTED, GFP_KERNEL); } } mutex_unlock(&local->iflist_mtx); + mutex_unlock(&local->mtx); } void ieee80211_dfs_radar_detected_work(struct work_struct *work) @@ -2445,7 +2508,6 @@ int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, if (ieee80211_vif_is_mesh(&sdata->vif)) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - __le16 pre_value; skb_put(skb, 8); *pos++ = WLAN_EID_CHAN_SWITCH_PARAM; /* EID */ @@ -2457,11 +2519,259 @@ int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT : 0x00; put_unaligned_le16(WLAN_REASON_MESH_CHAN, pos); /* Reason Cd */ pos += 2; - pre_value = cpu_to_le16(ifmsh->pre_value); - memcpy(pos, &pre_value, 2); /* Precedence Value */ + put_unaligned_le16(ifmsh->pre_value, pos);/* Precedence Value */ pos += 2; } ieee80211_tx_skb(sdata, skb); return 0; } + +bool ieee80211_cs_valid(const struct ieee80211_cipher_scheme *cs) +{ + return !(cs == NULL || cs->cipher == 0 || + cs->hdr_len < cs->pn_len + cs->pn_off || + cs->hdr_len <= cs->key_idx_off || + cs->key_idx_shift > 7 || + cs->key_idx_mask == 0); +} + +bool ieee80211_cs_list_valid(const struct ieee80211_cipher_scheme *cs, int n) +{ + int i; + + /* Ensure we have enough iftype bitmap space for all iftype values */ + WARN_ON((NUM_NL80211_IFTYPES / 8 + 1) > sizeof(cs[0].iftype)); + + for (i = 0; i < n; i++) + if (!ieee80211_cs_valid(&cs[i])) + return false; + + return true; +} + +const struct ieee80211_cipher_scheme * +ieee80211_cs_get(struct ieee80211_local *local, u32 cipher, + enum nl80211_iftype iftype) +{ + const struct ieee80211_cipher_scheme *l = local->hw.cipher_schemes; + int n = local->hw.n_cipher_schemes; + int i; + const struct ieee80211_cipher_scheme *cs = NULL; + + for (i = 0; i < n; i++) { + if (l[i].cipher == cipher) { + cs = &l[i]; + break; + } + } + + if (!cs || !(cs->iftype & BIT(iftype))) + return NULL; + + return cs; +} + +int ieee80211_cs_headroom(struct ieee80211_local *local, + struct cfg80211_crypto_settings *crypto, + enum nl80211_iftype iftype) +{ + const struct ieee80211_cipher_scheme *cs; + int headroom = IEEE80211_ENCRYPT_HEADROOM; + int i; + + for (i = 0; i < crypto->n_ciphers_pairwise; i++) { + cs = ieee80211_cs_get(local, crypto->ciphers_pairwise[i], + iftype); + + if (cs && headroom < cs->hdr_len) + headroom = cs->hdr_len; + } + + cs = ieee80211_cs_get(local, crypto->cipher_group, iftype); + if (cs && headroom < cs->hdr_len) + headroom = cs->hdr_len; + + return headroom; +} + +static bool +ieee80211_extend_noa_desc(struct ieee80211_noa_data *data, u32 tsf, int i) +{ + s32 end = data->desc[i].start + data->desc[i].duration - (tsf + 1); + int skip; + + if (end > 0) + return false; + + /* End time is in the past, check for repetitions */ + skip = DIV_ROUND_UP(-end, data->desc[i].interval); + if (data->count[i] < 255) { + if (data->count[i] <= skip) { + data->count[i] = 0; + return false; + } + + data->count[i] -= skip; + } + + data->desc[i].start += skip * data->desc[i].interval; + + return true; +} + +static bool +ieee80211_extend_absent_time(struct ieee80211_noa_data *data, u32 tsf, + s32 *offset) +{ + bool ret = false; + int i; + + for (i = 0; i < IEEE80211_P2P_NOA_DESC_MAX; i++) { + s32 cur; + + if (!data->count[i]) + continue; + + if (ieee80211_extend_noa_desc(data, tsf + *offset, i)) + ret = true; + + cur = data->desc[i].start - tsf; + if (cur > *offset) + continue; + + cur = data->desc[i].start + data->desc[i].duration - tsf; + if (cur > *offset) + *offset = cur; + } + + return ret; +} + +static u32 +ieee80211_get_noa_absent_time(struct ieee80211_noa_data *data, u32 tsf) +{ + s32 offset = 0; + int tries = 0; + /* + * arbitrary limit, used to avoid infinite loops when combined NoA + * descriptors cover the full time period. + */ + int max_tries = 5; + + ieee80211_extend_absent_time(data, tsf, &offset); + do { + if (!ieee80211_extend_absent_time(data, tsf, &offset)) + break; + + tries++; + } while (tries < max_tries); + + return offset; +} + +void ieee80211_update_p2p_noa(struct ieee80211_noa_data *data, u32 tsf) +{ + u32 next_offset = BIT(31) - 1; + int i; + + data->absent = 0; + data->has_next_tsf = false; + for (i = 0; i < IEEE80211_P2P_NOA_DESC_MAX; i++) { + s32 start; + + if (!data->count[i]) + continue; + + ieee80211_extend_noa_desc(data, tsf, i); + start = data->desc[i].start - tsf; + if (start <= 0) + data->absent |= BIT(i); + + if (next_offset > start) + next_offset = start; + + data->has_next_tsf = true; + } + + if (data->absent) + next_offset = ieee80211_get_noa_absent_time(data, tsf); + + data->next_tsf = tsf + next_offset; +} +EXPORT_SYMBOL(ieee80211_update_p2p_noa); + +int ieee80211_parse_p2p_noa(const struct ieee80211_p2p_noa_attr *attr, + struct ieee80211_noa_data *data, u32 tsf) +{ + int ret = 0; + int i; + + memset(data, 0, sizeof(*data)); + + for (i = 0; i < IEEE80211_P2P_NOA_DESC_MAX; i++) { + const struct ieee80211_p2p_noa_desc *desc = &attr->desc[i]; + + if (!desc->count || !desc->duration) + continue; + + data->count[i] = desc->count; + data->desc[i].start = le32_to_cpu(desc->start_time); + data->desc[i].duration = le32_to_cpu(desc->duration); + data->desc[i].interval = le32_to_cpu(desc->interval); + + if (data->count[i] > 1 && + data->desc[i].interval < data->desc[i].duration) + continue; + + ieee80211_extend_noa_desc(data, tsf, i); + ret++; + } + + if (ret) + ieee80211_update_p2p_noa(data, tsf); + + return ret; +} +EXPORT_SYMBOL(ieee80211_parse_p2p_noa); + +void ieee80211_recalc_dtim(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + u64 tsf = drv_get_tsf(local, sdata); + u64 dtim_count = 0; + u16 beacon_int = sdata->vif.bss_conf.beacon_int * 1024; + u8 dtim_period = sdata->vif.bss_conf.dtim_period; + struct ps_data *ps; + u8 bcns_from_dtim; + + if (tsf == -1ULL || !beacon_int || !dtim_period) + return; + + if (sdata->vif.type == NL80211_IFTYPE_AP || + sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + if (!sdata->bss) + return; + + ps = &sdata->bss->ps; + } else if (ieee80211_vif_is_mesh(&sdata->vif)) { + ps = &sdata->u.mesh.ps; + } else { + return; + } + + /* + * actually finds last dtim_count, mac80211 will update in + * __beacon_add_tim(). + * dtim_count = dtim_period - (tsf / bcn_int) % dtim_period + */ + do_div(tsf, beacon_int); + bcns_from_dtim = do_div(tsf, dtim_period); + /* just had a DTIM */ + if (!bcns_from_dtim) + dtim_count = 0; + else + dtim_count = dtim_period - bcns_from_dtim; + + ps->dtim_count = dtim_count; +} diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index de0112785aae..d75f35c6e1a0 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -182,16 +182,15 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, IEEE80211_VHT_CAP_SHORT_GI_160); /* remaining ones */ - if (own_cap.cap & IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE) { + if (own_cap.cap & IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE) vht_cap->cap |= cap_info & (IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE | - IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MAX); - } + IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK); if (own_cap.cap & IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE) vht_cap->cap |= cap_info & (IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE | - IEEE80211_VHT_CAP_BEAMFORMEE_STS_MAX); + IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK); if (own_cap.cap & IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE) vht_cap->cap |= cap_info & diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index afba19cb6f87..21211c60ca98 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -106,6 +106,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, struct sta_info *sta = NULL; const u8 *ra = NULL; bool qos = false; + struct mac80211_qos_map *qos_map; if (local->hw.queues < IEEE80211_NUM_ACS || skb->len < 6) { skb->priority = 0; /* required for correct WPA/11i MIC */ @@ -155,7 +156,11 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, /* use the data classifier to determine what 802.1d tag the * data frame has */ - skb->priority = cfg80211_classify8021d(skb); + rcu_read_lock(); + qos_map = rcu_dereference(sdata->qos_map); + skb->priority = cfg80211_classify8021d(skb, qos_map ? + &qos_map->qos_map : NULL); + rcu_read_unlock(); return ieee80211_downgrade_queue(sdata, skb); } diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index d65728220763..21448d629b15 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -127,7 +127,7 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) * APs with pairwise keys should never receive Michael MIC * errors for non-zero keyidx because these are reserved for * group keys and only the AP is sending real multicast - * frames in the BSS. ( + * frames in the BSS. */ return RX_DROP_UNUSABLE; } @@ -545,6 +545,106 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx) return RX_CONTINUE; } +static ieee80211_tx_result +ieee80211_crypto_cs_encrypt(struct ieee80211_tx_data *tx, + struct sk_buff *skb) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + struct ieee80211_key *key = tx->key; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + const struct ieee80211_cipher_scheme *cs = key->sta->cipher_scheme; + int hdrlen; + u8 *pos; + + if (info->control.hw_key && + !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) { + /* hwaccel has no need for preallocated head room */ + return TX_CONTINUE; + } + + if (unlikely(skb_headroom(skb) < cs->hdr_len && + pskb_expand_head(skb, cs->hdr_len, 0, GFP_ATOMIC))) + return TX_DROP; + + hdrlen = ieee80211_hdrlen(hdr->frame_control); + + pos = skb_push(skb, cs->hdr_len); + memmove(pos, pos + cs->hdr_len, hdrlen); + skb_set_network_header(skb, skb_network_offset(skb) + cs->hdr_len); + + return TX_CONTINUE; +} + +static inline int ieee80211_crypto_cs_pn_compare(u8 *pn1, u8 *pn2, int len) +{ + int i; + + /* pn is little endian */ + for (i = len - 1; i >= 0; i--) { + if (pn1[i] < pn2[i]) + return -1; + else if (pn1[i] > pn2[i]) + return 1; + } + + return 0; +} + +static ieee80211_rx_result +ieee80211_crypto_cs_decrypt(struct ieee80211_rx_data *rx) +{ + struct ieee80211_key *key = rx->key; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; + const struct ieee80211_cipher_scheme *cs = NULL; + int hdrlen = ieee80211_hdrlen(hdr->frame_control); + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); + int data_len; + u8 *rx_pn; + u8 *skb_pn; + u8 qos_tid; + + if (!rx->sta || !rx->sta->cipher_scheme || + !(status->flag & RX_FLAG_DECRYPTED)) + return RX_DROP_UNUSABLE; + + if (!ieee80211_is_data(hdr->frame_control)) + return RX_CONTINUE; + + cs = rx->sta->cipher_scheme; + + data_len = rx->skb->len - hdrlen - cs->hdr_len; + + if (data_len < 0) + return RX_DROP_UNUSABLE; + + if (ieee80211_is_data_qos(hdr->frame_control)) + qos_tid = *ieee80211_get_qos_ctl(hdr) & + IEEE80211_QOS_CTL_TID_MASK; + else + qos_tid = 0; + + if (skb_linearize(rx->skb)) + return RX_DROP_UNUSABLE; + + hdr = (struct ieee80211_hdr *)rx->skb->data; + + rx_pn = key->u.gen.rx_pn[qos_tid]; + skb_pn = rx->skb->data + hdrlen + cs->pn_off; + + if (ieee80211_crypto_cs_pn_compare(skb_pn, rx_pn, cs->pn_len) <= 0) + return RX_DROP_UNUSABLE; + + memcpy(rx_pn, skb_pn, cs->pn_len); + + /* remove security header and MIC */ + if (pskb_trim(rx->skb, rx->skb->len - cs->mic_len)) + return RX_DROP_UNUSABLE; + + memmove(rx->skb->data + cs->hdr_len, rx->skb->data, hdrlen); + skb_pull(rx->skb, cs->hdr_len); + + return RX_CONTINUE; +} static void bip_aad(struct sk_buff *skb, u8 *aad) { @@ -685,6 +785,7 @@ ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx) { struct sk_buff *skb; struct ieee80211_tx_info *info = NULL; + ieee80211_tx_result res; skb_queue_walk(&tx->skbs, skb) { info = IEEE80211_SKB_CB(skb); @@ -692,9 +793,24 @@ ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx) /* handle hw-only algorithm */ if (!info->control.hw_key) return TX_DROP; + + if (tx->key->sta->cipher_scheme) { + res = ieee80211_crypto_cs_encrypt(tx, skb); + if (res != TX_CONTINUE) + return res; + } } ieee80211_tx_set_protected(tx); return TX_CONTINUE; } + +ieee80211_rx_result +ieee80211_crypto_hw_decrypt(struct ieee80211_rx_data *rx) +{ + if (rx->sta->cipher_scheme) + return ieee80211_crypto_cs_decrypt(rx); + + return RX_DROP_UNUSABLE; +} diff --git a/net/mac80211/wpa.h b/net/mac80211/wpa.h index 07e33f899c71..62e5a12dfe0a 100644 --- a/net/mac80211/wpa.h +++ b/net/mac80211/wpa.h @@ -34,5 +34,7 @@ ieee80211_rx_result ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx); ieee80211_tx_result ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx); +ieee80211_rx_result +ieee80211_crypto_hw_decrypt(struct ieee80211_rx_data *rx); #endif /* WPA_H */ diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c index e24bcf977296..372d8a222b91 100644 --- a/net/mac802154/wpan.c +++ b/net/mac802154/wpan.c @@ -444,8 +444,8 @@ mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb) case IEEE802154_FC_TYPE_DATA: return mac802154_process_data(sdata->dev, skb); default: - pr_warning("ieee802154: bad frame received (type = %d)\n", - mac_cb_type(skb)); + pr_warn("ieee802154: bad frame received (type = %d)\n", + mac_cb_type(skb)); kfree_skb(skb); return NET_RX_DROP; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index c3398cd99b94..e9410d17619d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -414,47 +414,116 @@ config NETFILTER_SYNPROXY endif # NF_CONNTRACK config NF_TABLES - depends on NETFILTER_NETLINK + select NETFILTER_NETLINK tristate "Netfilter nf_tables support" + help + nftables is the new packet classification framework that intends to + replace the existing {ip,ip6,arp,eb}_tables infrastructure. It + provides a pseudo-state machine with an extensible instruction-set + (also known as expressions) that the userspace 'nft' utility + (http://www.netfilter.org/projects/nftables) uses to build the + rule-set. It also comes with the generic set infrastructure that + allows you to construct mappings between matchings and actions + for performance lookups. + + To compile it as a module, choose M here. + +config NF_TABLES_INET + depends on NF_TABLES && IPV6 + select NF_TABLES_IPV4 + select NF_TABLES_IPV6 + tristate "Netfilter nf_tables mixed IPv4/IPv6 tables support" + help + This option enables support for a mixed IPv4/IPv6 "inet" table. config NFT_EXTHDR depends on NF_TABLES tristate "Netfilter nf_tables IPv6 exthdr module" + help + This option adds the "exthdr" expression that you can use to match + IPv6 extension headers. config NFT_META depends on NF_TABLES tristate "Netfilter nf_tables meta module" + help + This option adds the "meta" expression that you can use to match and + to set packet metainformation such as the packet mark. config NFT_CT depends on NF_TABLES depends on NF_CONNTRACK tristate "Netfilter nf_tables conntrack module" + help + This option adds the "meta" expression that you can use to match + connection tracking information such as the flow state. config NFT_RBTREE depends on NF_TABLES tristate "Netfilter nf_tables rbtree set module" + help + This option adds the "rbtree" set type (Red Black tree) that is used + to build interval-based sets. config NFT_HASH depends on NF_TABLES tristate "Netfilter nf_tables hash set module" + help + This option adds the "hash" set type that is used to build one-way + mappings between matchings and actions. config NFT_COUNTER depends on NF_TABLES tristate "Netfilter nf_tables counter module" + help + This option adds the "counter" expression that you can use to + include packet and byte counters in a rule. config NFT_LOG depends on NF_TABLES tristate "Netfilter nf_tables log module" + help + This option adds the "log" expression that you can use to log + packets matching some criteria. config NFT_LIMIT depends on NF_TABLES tristate "Netfilter nf_tables limit module" + help + This option adds the "limit" expression that you can use to + ratelimit rule matchings. config NFT_NAT depends on NF_TABLES depends on NF_CONNTRACK depends on NF_NAT tristate "Netfilter nf_tables nat module" + help + This option adds the "nat" expression that you can use to perform + typical Network Address Translation (NAT) packet transformations. + +config NFT_QUEUE + depends on NF_TABLES + depends on NETFILTER_XTABLES + depends on NETFILTER_NETLINK_QUEUE + tristate "Netfilter nf_tables queue module" + help + This is required if you intend to use the userspace queueing + infrastructure (also known as NFQUEUE) from nftables. + +config NFT_REJECT + depends on NF_TABLES + default m if NETFILTER_ADVANCED=n + tristate "Netfilter nf_tables reject support" + help + This option adds the "reject" expression that you can use to + explicitly deny and notify via TCP reset/ICMP informational errors + unallowed traffic. + +config NFT_REJECT_INET + depends on NF_TABLES_INET + default NFT_REJECT + tristate config NFT_COMPAT depends on NF_TABLES @@ -858,6 +927,16 @@ config NETFILTER_XT_MATCH_BPF To compile it as a module, choose M here. If unsure, say N. +config NETFILTER_XT_MATCH_CGROUP + tristate '"control group" match support' + depends on NETFILTER_ADVANCED + depends on CGROUPS + select CGROUP_NET_CLASSID + ---help--- + Socket/process control group matching allows you to match locally + generated packets based on which net_cls control group processes + belong to. + config NETFILTER_XT_MATCH_CLUSTER tristate '"cluster" match support' depends on NF_CONNTRACK @@ -1035,6 +1114,15 @@ config NETFILTER_XT_MATCH_HL in the IPv6 header, or the time-to-live field in the IPv4 header of the packet. +config NETFILTER_XT_MATCH_IPCOMP + tristate '"ipcomp" match support' + depends on NETFILTER_ADVANCED + help + This match extension allows you to match a range of CPIs(16 bits) + inside IPComp header of IPSec packets. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_MATCH_IPRANGE tristate '"iprange" address range match support' depends on NETFILTER_ADVANCED @@ -1055,6 +1143,16 @@ config NETFILTER_XT_MATCH_IPVS If unsure, say N. +config NETFILTER_XT_MATCH_L2TP + tristate '"l2tp" match support' + depends on NETFILTER_ADVANCED + default L2TP + ---help--- + This option adds an "L2TP" match, which allows you to match against + L2TP protocol header fields. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_MATCH_LENGTH tristate '"length" match support' depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 394483b2c193..bffdad774da7 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -70,13 +70,16 @@ nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o obj-$(CONFIG_NF_TABLES) += nf_tables.o +obj-$(CONFIG_NF_TABLES_INET) += nf_tables_inet.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o obj-$(CONFIG_NFT_META) += nft_meta.o obj-$(CONFIG_NFT_CT) += nft_ct.o obj-$(CONFIG_NFT_LIMIT) += nft_limit.o obj-$(CONFIG_NFT_NAT) += nft_nat.o -#nf_tables-objs += nft_meta_target.o +obj-$(CONFIG_NFT_QUEUE) += nft_queue.o +obj-$(CONFIG_NFT_REJECT) += nft_reject.o +obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o obj-$(CONFIG_NFT_RBTREE) += nft_rbtree.o obj-$(CONFIG_NFT_HASH) += nft_hash.o obj-$(CONFIG_NFT_COUNTER) += nft_counter.o @@ -133,8 +136,10 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o obj-$(CONFIG_NETFILTER_XT_MATCH_HL) += xt_hl.o +obj-$(CONFIG_NETFILTER_XT_MATCH_IPCOMP) += xt_ipcomp.o obj-$(CONFIG_NETFILTER_XT_MATCH_IPRANGE) += xt_iprange.o obj-$(CONFIG_NETFILTER_XT_MATCH_IPVS) += xt_ipvs.o +obj-$(CONFIG_NETFILTER_XT_MATCH_L2TP) += xt_l2tp.o obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o @@ -142,6 +147,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_MULTIPORT) += xt_multiport.o obj-$(CONFIG_NETFILTER_XT_MATCH_NFACCT) += xt_nfacct.o obj-$(CONFIG_NETFILTER_XT_MATCH_OSF) += xt_osf.o obj-$(CONFIG_NETFILTER_XT_MATCH_OWNER) += xt_owner.o +obj-$(CONFIG_NETFILTER_XT_MATCH_CGROUP) += xt_cgroup.o obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig index a2d6263b6c64..44cd4f58adf0 100644 --- a/net/netfilter/ipset/Kconfig +++ b/net/netfilter/ipset/Kconfig @@ -21,7 +21,7 @@ config IP_SET_MAX You can define here default value of the maximum number of IP sets for the kernel. - The value can be overriden by the 'max_sets' module + The value can be overridden by the 'max_sets' module parameter of the 'ip_set' module. config IP_SET_BITMAP_IP diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index bac7e01df67f..de770ec39e51 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -625,34 +625,6 @@ EXPORT_SYMBOL_GPL(ip_set_name_byindex); */ /* - * Find set by name, reference it once. The reference makes sure the - * thing pointed to, does not go away under our feet. - * - * The nfnl mutex is used in the function. - */ -ip_set_id_t -ip_set_nfnl_get(struct net *net, const char *name) -{ - ip_set_id_t i, index = IPSET_INVALID_ID; - struct ip_set *s; - struct ip_set_net *inst = ip_set_pernet(net); - - nfnl_lock(NFNL_SUBSYS_IPSET); - for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); - if (s != NULL && STREQ(s->name, name)) { - __ip_set_get(s); - index = i; - break; - } - } - nfnl_unlock(NFNL_SUBSYS_IPSET); - - return index; -} -EXPORT_SYMBOL_GPL(ip_set_nfnl_get); - -/* * Find set by index, reference it once. The reference makes sure the * thing pointed to, does not go away under our feet. * diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 3f64a66bf5d9..b827a0f1f351 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -46,31 +46,12 @@ struct iface_node { static void rbtree_destroy(struct rb_root *root) { - struct rb_node *p, *n = root->rb_node; - struct iface_node *node; - - /* Non-recursive destroy, like in ext3 */ - while (n) { - if (n->rb_left) { - n = n->rb_left; - continue; - } - if (n->rb_right) { - n = n->rb_right; - continue; - } - p = rb_parent(n); - node = rb_entry(n, struct iface_node, node); - if (!p) - *root = RB_ROOT; - else if (p->rb_left == n) - p->rb_left = NULL; - else if (p->rb_right == n) - p->rb_right = NULL; + struct iface_node *node, *next; + rbtree_postorder_for_each_entry_safe(node, next, root, node) kfree(node); - n = p; - } + + *root = RB_ROOT; } static int diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 4c8e5c0aa1ab..a8eb0a89326a 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -871,11 +871,11 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, cp->protocol = p->protocol; ip_vs_addr_set(p->af, &cp->caddr, p->caddr); cp->cport = p->cport; - ip_vs_addr_set(p->af, &cp->vaddr, p->vaddr); - cp->vport = p->vport; - /* proto should only be IPPROTO_IP if d_addr is a fwmark */ + /* proto should only be IPPROTO_IP if p->vaddr is a fwmark */ ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af, - &cp->daddr, daddr); + &cp->vaddr, p->vaddr); + cp->vport = p->vport; + ip_vs_addr_set(p->af, &cp->daddr, daddr); cp->dport = dport; cp->flags = flags; cp->fwmark = fwmark; @@ -1209,7 +1209,7 @@ void ip_vs_random_dropentry(struct net *net) * Randomly scan 1/32 of the whole table every second */ for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) { - unsigned int hash = net_random() & ip_vs_conn_tab_mask; + unsigned int hash = prandom_u32() & ip_vs_conn_tab_mask; hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 5a355a46d1dc..5882bbfd198c 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -19,8 +19,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * * * Authors: diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index f63c2388f38d..db801263ee9f 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1637,7 +1637,10 @@ static int sync_thread_master(void *data) continue; } while (ip_vs_send_sync_msg(tinfo->sock, sb->mesg) < 0) { - int ret = __wait_event_interruptible(*sk_sleep(sk), + /* (Ab)use interruptible sleep to avoid increasing + * the load avg. + */ + __wait_event_interruptible(*sk_sleep(sk), sock_writeable(sk) || kthread_should_stop()); if (unlikely(kthread_should_stop())) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 43549eb7a7be..356bef519fe5 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -60,12 +60,6 @@ int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct, const struct nlattr *attr) __read_mostly; EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook); -int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff); -EXPORT_SYMBOL_GPL(nf_nat_seq_adjust_hook); - DEFINE_SPINLOCK(nf_conntrack_lock); EXPORT_SYMBOL_GPL(nf_conntrack_lock); @@ -318,6 +312,21 @@ static void death_by_timeout(unsigned long ul_conntrack) nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0); } +static inline bool +nf_ct_key_equal(struct nf_conntrack_tuple_hash *h, + const struct nf_conntrack_tuple *tuple, + u16 zone) +{ + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + + /* A conntrack can be recreated with the equal tuple, + * so we need to check that the conntrack is confirmed + */ + return nf_ct_tuple_equal(tuple, &h->tuple) && + nf_ct_zone(ct) == zone && + nf_ct_is_confirmed(ct); +} + /* * Warning : * - Caller must take a reference on returned object @@ -339,8 +348,7 @@ ____nf_conntrack_find(struct net *net, u16 zone, local_bh_disable(); begin: hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) { - if (nf_ct_tuple_equal(tuple, &h->tuple) && - nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) { + if (nf_ct_key_equal(h, tuple, zone)) { NF_CT_STAT_INC(net, found); local_bh_enable(); return h; @@ -361,15 +369,6 @@ begin: return NULL; } -struct nf_conntrack_tuple_hash * -__nf_conntrack_find(struct net *net, u16 zone, - const struct nf_conntrack_tuple *tuple) -{ - return ____nf_conntrack_find(net, zone, tuple, - hash_conntrack_raw(tuple, zone)); -} -EXPORT_SYMBOL_GPL(__nf_conntrack_find); - /* Find a connection corresponding to a tuple. */ static struct nf_conntrack_tuple_hash * __nf_conntrack_find_get(struct net *net, u16 zone, @@ -387,8 +386,7 @@ begin: !atomic_inc_not_zero(&ct->ct_general.use))) h = NULL; else { - if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) || - nf_ct_zone(ct) != zone)) { + if (unlikely(!nf_ct_key_equal(h, tuple, zone))) { nf_ct_put(ct); goto begin; } @@ -450,7 +448,9 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) goto out; add_timer(&ct->timeout); - nf_conntrack_get(&ct->ct_general); + smp_wmb(); + /* The caller holds a reference to this object */ + atomic_set(&ct->ct_general.use, 2); __nf_conntrack_hash_insert(ct, hash, repl_hash); NF_CT_STAT_INC(net, insert); spin_unlock_bh(&nf_conntrack_lock); @@ -464,6 +464,21 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); +/* deletion from this larval template list happens via nf_ct_put() */ +void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl) +{ + __set_bit(IPS_TEMPLATE_BIT, &tmpl->status); + __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); + nf_conntrack_get(&tmpl->ct_general); + + spin_lock_bh(&nf_conntrack_lock); + /* Overload tuple linked list to put us in template list. */ + hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &net->ct.tmpl); + spin_unlock_bh(&nf_conntrack_lock); +} +EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert); + /* Confirm a connection given skb; places it in hash table */ int __nf_conntrack_confirm(struct sk_buff *skb) @@ -735,11 +750,10 @@ __nf_conntrack_alloc(struct net *net, u16 zone, nf_ct_zone->id = zone; } #endif - /* - * changes to lookup keys must be done before setting refcnt to 1 + /* Because we use RCU lookups, we set ct_general.use to zero before + * this is inserted in any list. */ - smp_wmb(); - atomic_set(&ct->ct_general.use, 1); + atomic_set(&ct->ct_general.use, 0); return ct; #ifdef CONFIG_NF_CONNTRACK_ZONES @@ -763,6 +777,11 @@ void nf_conntrack_free(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); + /* A freed object has refcnt == 0, that's + * the golden rule for SLAB_DESTROY_BY_RCU + */ + NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0); + nf_ct_ext_destroy(ct); nf_ct_ext_free(ct); kmem_cache_free(net->ct.nf_conntrack_cachep, ct); @@ -858,6 +877,9 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, NF_CT_STAT_INC(net, new); } + /* Now it is inserted into the unconfirmed list, bump refcount */ + nf_conntrack_get(&ct->ct_general); + /* Overload tuple linked list to put us in unconfirmed list. */ hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, &net->ct.unconfirmed); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 08870b859046..bb322d0beb48 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2118,8 +2118,16 @@ ctnetlink_nfqueue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) return err; } #if defined(CONFIG_NF_CONNTRACK_MARK) - if (cda[CTA_MARK]) - ct->mark = ntohl(nla_get_be32(cda[CTA_MARK])); + if (cda[CTA_MARK]) { + u32 mask = 0, mark, newmark; + if (cda[CTA_MARK_MASK]) + mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK])); + + mark = ntohl(nla_get_be32(cda[CTA_MARK])); + newmark = (ct->mark & mask) ^ mark; + if (newmark != ct->mark) + ct->mark = newmark; + } #endif return 0; } diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index ce3004156eeb..b65d5864b6d9 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -92,12 +92,6 @@ nf_ct_l3proto_find_get(u_int16_t l3proto) } EXPORT_SYMBOL_GPL(nf_ct_l3proto_find_get); -void nf_ct_l3proto_put(struct nf_conntrack_l3proto *p) -{ - module_put(p->me); -} -EXPORT_SYMBOL_GPL(nf_ct_l3proto_put); - int nf_ct_l3proto_try_module_get(unsigned short l3proto) { diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index a99b6c3427b0..cb372f96f10d 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]; @@ -457,7 +457,7 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, out_invalid: if (LOG_INVALID(net, IPPROTO_DCCP)) nf_log_packet(net, nf_ct_l3num(ct), 0, skb, NULL, NULL, - NULL, msg); + NULL, "%s", msg); return false; } @@ -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; @@ -614,7 +614,7 @@ static int dccp_error(struct net *net, struct nf_conn *tmpl, out_invalid: if (LOG_INVALID(net, IPPROTO_DCCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, msg); + nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, "%s", msg); return -NF_ACCEPT; } diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 63a815402211..d3f5cd6dd962 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -315,7 +315,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, * manips not an issue. */ if (maniptype == NF_NAT_MANIP_SRC && - !(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { + !(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) { /* try the original tuple first */ if (in_range(l3proto, l4proto, orig_tuple, range)) { if (!nf_nat_used_tuple(orig_tuple, ct)) { @@ -339,7 +339,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, */ /* Only bother mapping if it's not already in range and unique */ - if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { + if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) { if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { if (l4proto->in_range(tuple, maniptype, &range->min_proto, diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c index 9baaf734c142..83a72a235cae 100644 --- a/net/netfilter/nf_nat_proto_common.c +++ b/net/netfilter/nf_nat_proto_common.c @@ -74,22 +74,24 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, range_size = ntohs(range->max_proto.all) - min + 1; } - if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) + if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) { off = l3proto->secure_port(tuple, maniptype == NF_NAT_MANIP_SRC ? tuple->dst.u.all : tuple->src.u.all); - else + } else if (range->flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY) { + off = prandom_u32(); + } else { off = *rover; + } for (i = 0; ; ++off) { *portptr = htons(min + off % range_size); if (++i != range_size && nf_nat_used_tuple(tuple, ct)) continue; - if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) + if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) *rover = off; return; } - return; } EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 9858e3e51a3a..52e20c9a46a5 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -363,9 +363,8 @@ static int __net_init synproxy_net_init(struct net *net) goto err2; if (!nfct_synproxy_ext_add(ct)) goto err2; - __set_bit(IPS_TEMPLATE_BIT, &ct->status); - __set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_tmpl_insert(net, ct); snet->tmpl = ct; snet->stats = alloc_percpu(struct synproxy_stats); @@ -390,7 +389,7 @@ static void __net_exit synproxy_net_exit(struct net *net) { struct synproxy_net *snet = synproxy_pernet(net); - nf_conntrack_free(snet->tmpl); + nf_ct_put(snet->tmpl); synproxy_proc_exit(net); free_percpu(snet->stats); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 71a9f49a768b..adce01e8bb57 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -124,37 +124,43 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table) return ++table->hgenerator; } -static struct nf_chain_type *chain_type[AF_MAX][NFT_CHAIN_T_MAX]; +static const struct nf_chain_type *chain_type[AF_MAX][NFT_CHAIN_T_MAX]; -static int __nf_tables_chain_type_lookup(int family, const struct nlattr *nla) +static const struct nf_chain_type * +__nf_tables_chain_type_lookup(int family, const struct nlattr *nla) { int i; - for (i=0; i<NFT_CHAIN_T_MAX; i++) { + for (i = 0; i < NFT_CHAIN_T_MAX; i++) { if (chain_type[family][i] != NULL && !nla_strcmp(nla, chain_type[family][i]->name)) - return i; + return chain_type[family][i]; } - return -1; + return NULL; } -static int nf_tables_chain_type_lookup(const struct nft_af_info *afi, - const struct nlattr *nla, - bool autoload) +static const struct nf_chain_type * +nf_tables_chain_type_lookup(const struct nft_af_info *afi, + const struct nlattr *nla, + bool autoload) { - int type; + const struct nf_chain_type *type; type = __nf_tables_chain_type_lookup(afi->family, nla); + if (type != NULL) + return type; #ifdef CONFIG_MODULES - if (type < 0 && autoload) { + if (autoload) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); request_module("nft-chain-%u-%*.s", afi->family, nla_len(nla)-1, (const char *)nla_data(nla)); nfnl_lock(NFNL_SUBSYS_NFTABLES); type = __nf_tables_chain_type_lookup(afi->family, nla); + if (type != NULL) + return ERR_PTR(-EAGAIN); } #endif - return type; + return ERR_PTR(-ENOENT); } static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { @@ -180,7 +186,8 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, u32 portid, u32 seq, nfmsg->res_id = 0; if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) || - nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags))) + nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) || + nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use))) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -306,7 +313,8 @@ err: return err; } -static int nf_tables_table_enable(struct nft_table *table) +static int nf_tables_table_enable(const struct nft_af_info *afi, + struct nft_table *table) { struct nft_chain *chain; int err, i = 0; @@ -315,7 +323,7 @@ static int nf_tables_table_enable(struct nft_table *table) if (!(chain->flags & NFT_BASE_CHAIN)) continue; - err = nf_register_hook(&nft_base_chain(chain)->ops); + err = nf_register_hooks(nft_base_chain(chain)->ops, afi->nops); if (err < 0) goto err; @@ -330,18 +338,20 @@ err: if (i-- <= 0) break; - nf_unregister_hook(&nft_base_chain(chain)->ops); + nf_unregister_hooks(nft_base_chain(chain)->ops, afi->nops); } return err; } -static int nf_tables_table_disable(struct nft_table *table) +static int nf_tables_table_disable(const struct nft_af_info *afi, + struct nft_table *table) { struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) { if (chain->flags & NFT_BASE_CHAIN) - nf_unregister_hook(&nft_base_chain(chain)->ops); + nf_unregister_hooks(nft_base_chain(chain)->ops, + afi->nops); } return 0; @@ -356,7 +366,7 @@ static int nf_tables_updtable(struct sock *nlsk, struct sk_buff *skb, int family = nfmsg->nfgen_family, ret = 0; if (nla[NFTA_TABLE_FLAGS]) { - __be32 flags; + u32 flags; flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS])); if (flags & ~NFT_TABLE_F_DORMANT) @@ -364,12 +374,12 @@ static int nf_tables_updtable(struct sock *nlsk, struct sk_buff *skb, if ((flags & NFT_TABLE_F_DORMANT) && !(table->flags & NFT_TABLE_F_DORMANT)) { - ret = nf_tables_table_disable(table); + ret = nf_tables_table_disable(afi, table); if (ret >= 0) table->flags |= NFT_TABLE_F_DORMANT; } else if (!(flags & NFT_TABLE_F_DORMANT) && table->flags & NFT_TABLE_F_DORMANT) { - ret = nf_tables_table_enable(table); + ret = nf_tables_table_enable(afi, table); if (ret >= 0) table->flags &= ~NFT_TABLE_F_DORMANT; } @@ -392,6 +402,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, struct nft_table *table; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + u32 flags = 0; afi = nf_tables_afinfo_lookup(net, family, true); if (IS_ERR(afi)) @@ -413,25 +424,25 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb, return nf_tables_updtable(nlsk, skb, nlh, nla, afi, table); } + if (nla[NFTA_TABLE_FLAGS]) { + flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS])); + if (flags & ~NFT_TABLE_F_DORMANT) + return -EINVAL; + } + + if (!try_module_get(afi->owner)) + return -EAFNOSUPPORT; + table = kzalloc(sizeof(*table) + nla_len(name), GFP_KERNEL); - if (table == NULL) + if (table == NULL) { + module_put(afi->owner); return -ENOMEM; + } nla_strlcpy(table->name, name, nla_len(name)); INIT_LIST_HEAD(&table->chains); INIT_LIST_HEAD(&table->sets); - - if (nla[NFTA_TABLE_FLAGS]) { - __be32 flags; - - flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS])); - if (flags & ~NFT_TABLE_F_DORMANT) { - kfree(table); - return -EINVAL; - } - - table->flags |= flags; - } + table->flags = flags; list_add_tail(&table->list, &afi->tables); nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family); @@ -456,16 +467,17 @@ static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb, if (IS_ERR(table)) return PTR_ERR(table); - if (table->use) + if (!list_empty(&table->chains) || !list_empty(&table->sets)) return -EBUSY; list_del(&table->list); nf_tables_table_notify(skb, nlh, table, NFT_MSG_DELTABLE, family); kfree(table); + module_put(afi->owner); return 0; } -int nft_register_chain_type(struct nf_chain_type *ctype) +int nft_register_chain_type(const struct nf_chain_type *ctype) { int err = 0; @@ -474,10 +486,6 @@ int nft_register_chain_type(struct nf_chain_type *ctype) err = -EBUSY; goto out; } - - if (!try_module_get(ctype->me)) - goto out; - chain_type[ctype->family][ctype->type] = ctype; out: nfnl_unlock(NFNL_SUBSYS_NFTABLES); @@ -485,11 +493,10 @@ out: } EXPORT_SYMBOL_GPL(nft_register_chain_type); -void nft_unregister_chain_type(struct nf_chain_type *ctype) +void nft_unregister_chain_type(const struct nf_chain_type *ctype) { nfnl_lock(NFNL_SUBSYS_NFTABLES); chain_type[ctype->family][ctype->type] = NULL; - module_put(ctype->me); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_chain_type); @@ -597,7 +604,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq, if (chain->flags & NFT_BASE_CHAIN) { const struct nft_base_chain *basechain = nft_base_chain(chain); - const struct nf_hook_ops *ops = &basechain->ops; + const struct nf_hook_ops *ops = &basechain->ops[0]; struct nlattr *nest; nest = nla_nest_start(skb, NFTA_CHAIN_HOOK); @@ -613,9 +620,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq, htonl(basechain->policy))) goto nla_put_failure; - if (nla_put_string(skb, NFTA_CHAIN_TYPE, - chain_type[ops->pf][nft_base_chain(chain)->type]->name)) - goto nla_put_failure; + if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name)) + goto nla_put_failure; if (nft_dump_stats(skb, nft_base_chain(chain)->stats)) goto nla_put_failure; @@ -756,22 +762,6 @@ err: return err; } -static int -nf_tables_chain_policy(struct nft_base_chain *chain, const struct nlattr *attr) -{ - switch (ntohl(nla_get_be32(attr))) { - case NF_DROP: - chain->policy = NF_DROP; - break; - case NF_ACCEPT: - chain->policy = NF_ACCEPT; - break; - default: - return -EINVAL; - } - return 0; -} - static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = { [NFTA_COUNTER_PACKETS] = { .type = NLA_U64 }, [NFTA_COUNTER_BYTES] = { .type = NLA_U64 }, @@ -830,7 +820,9 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, struct nlattr *ha[NFTA_HOOK_MAX + 1]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + u8 policy = NF_ACCEPT; u64 handle = 0; + unsigned int i; int err; bool create; @@ -844,9 +836,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, if (IS_ERR(table)) return PTR_ERR(table); - if (table->use == UINT_MAX) - return -EOVERFLOW; - chain = NULL; name = nla[NFTA_CHAIN_NAME]; @@ -864,6 +853,22 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, } } + if (nla[NFTA_CHAIN_POLICY]) { + if ((chain != NULL && + !(chain->flags & NFT_BASE_CHAIN)) || + nla[NFTA_CHAIN_HOOK] == NULL) + return -EOPNOTSUPP; + + policy = ntohl(nla_get_be32(nla[NFTA_CHAIN_POLICY])); + switch (policy) { + case NF_DROP: + case NF_ACCEPT: + break; + default: + return -EINVAL; + } + } + if (chain != NULL) { if (nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; @@ -874,16 +879,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, !IS_ERR(nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]))) return -EEXIST; - if (nla[NFTA_CHAIN_POLICY]) { - if (!(chain->flags & NFT_BASE_CHAIN)) - return -EOPNOTSUPP; - - err = nf_tables_chain_policy(nft_base_chain(chain), - nla[NFTA_CHAIN_POLICY]); - if (err < 0) - return err; - } - if (nla[NFTA_CHAIN_COUNTERS]) { if (!(chain->flags & NFT_BASE_CHAIN)) return -EOPNOTSUPP; @@ -894,24 +889,31 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, return err; } + if (nla[NFTA_CHAIN_POLICY]) + nft_base_chain(chain)->policy = policy; + if (nla[NFTA_CHAIN_HANDLE] && name) nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN); goto notify; } + if (table->use == UINT_MAX) + return -EOVERFLOW; + if (nla[NFTA_CHAIN_HOOK]) { + const struct nf_chain_type *type; struct nf_hook_ops *ops; nf_hookfn *hookfn; - u32 hooknum; - int type = NFT_CHAIN_T_DEFAULT; + u32 hooknum, priority; + type = chain_type[family][NFT_CHAIN_T_DEFAULT]; if (nla[NFTA_CHAIN_TYPE]) { type = nf_tables_chain_type_lookup(afi, nla[NFTA_CHAIN_TYPE], create); - if (type < 0) - return -ENOENT; + if (IS_ERR(type)) + return PTR_ERR(type); } err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK], @@ -925,46 +927,23 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, hooknum = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); if (hooknum >= afi->nhooks) return -EINVAL; + priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); - hookfn = chain_type[family][type]->fn[hooknum]; - if (hookfn == NULL) + if (!(type->hook_mask & (1 << hooknum))) return -EOPNOTSUPP; + if (!try_module_get(type->owner)) + return -ENOENT; + hookfn = type->hooks[hooknum]; basechain = kzalloc(sizeof(*basechain), GFP_KERNEL); if (basechain == NULL) return -ENOMEM; - basechain->type = type; - chain = &basechain->chain; - - ops = &basechain->ops; - ops->pf = family; - ops->owner = afi->owner; - ops->hooknum = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); - ops->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); - ops->priv = chain; - ops->hook = hookfn; - if (afi->hooks[ops->hooknum]) - ops->hook = afi->hooks[ops->hooknum]; - - chain->flags |= NFT_BASE_CHAIN; - - if (nla[NFTA_CHAIN_POLICY]) { - err = nf_tables_chain_policy(basechain, - nla[NFTA_CHAIN_POLICY]); - if (err < 0) { - free_percpu(basechain->stats); - kfree(basechain); - return err; - } - } else - basechain->policy = NF_ACCEPT; - if (nla[NFTA_CHAIN_COUNTERS]) { err = nf_tables_counters(basechain, nla[NFTA_CHAIN_COUNTERS]); if (err < 0) { - free_percpu(basechain->stats); + module_put(type->owner); kfree(basechain); return err; } @@ -972,12 +951,33 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, struct nft_stats __percpu *newstats; newstats = alloc_percpu(struct nft_stats); - if (newstats == NULL) + if (newstats == NULL) { + module_put(type->owner); + kfree(basechain); return -ENOMEM; + } + rcu_assign_pointer(basechain->stats, newstats); + } + + basechain->type = type; + chain = &basechain->chain; - rcu_assign_pointer(nft_base_chain(chain)->stats, - newstats); + for (i = 0; i < afi->nops; i++) { + ops = &basechain->ops[i]; + ops->pf = family; + ops->owner = afi->owner; + ops->hooknum = hooknum; + ops->priority = priority; + ops->priv = chain; + ops->hook = afi->hooks[ops->hooknum]; + if (hookfn) + ops->hook = hookfn; + if (afi->hook_ops_init) + afi->hook_ops_init(ops, i); } + + chain->flags |= NFT_BASE_CHAIN; + basechain->policy = policy; } else { chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (chain == NULL) @@ -992,8 +992,9 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb, if (!(table->flags & NFT_TABLE_F_DORMANT) && chain->flags & NFT_BASE_CHAIN) { - err = nf_register_hook(&nft_base_chain(chain)->ops); + err = nf_register_hooks(nft_base_chain(chain)->ops, afi->nops); if (err < 0) { + module_put(basechain->type->owner); free_percpu(basechain->stats); kfree(basechain); return err; @@ -1007,13 +1008,12 @@ notify: return 0; } -static void nf_tables_rcu_chain_destroy(struct rcu_head *head) +static void nf_tables_chain_destroy(struct nft_chain *chain) { - struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head); - BUG_ON(chain->use > 0); if (chain->flags & NFT_BASE_CHAIN) { + module_put(nft_base_chain(chain)->type->owner); free_percpu(nft_base_chain(chain)->stats); kfree(nft_base_chain(chain)); } else @@ -1043,7 +1043,7 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, if (IS_ERR(chain)) return PTR_ERR(chain); - if (!list_empty(&chain->rules)) + if (!list_empty(&chain->rules) || chain->use > 0) return -EBUSY; list_del(&chain->list); @@ -1051,13 +1051,15 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, if (!(table->flags & NFT_TABLE_F_DORMANT) && chain->flags & NFT_BASE_CHAIN) - nf_unregister_hook(&nft_base_chain(chain)->ops); + nf_unregister_hooks(nft_base_chain(chain)->ops, afi->nops); nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_DELCHAIN, family); /* Make sure all rule references are gone before this is released */ - call_rcu(&chain->rcu_head, nf_tables_rcu_chain_destroy); + synchronize_rcu(); + + nf_tables_chain_destroy(chain); return 0; } @@ -1112,35 +1114,45 @@ void nft_unregister_expr(struct nft_expr_type *type) } EXPORT_SYMBOL_GPL(nft_unregister_expr); -static const struct nft_expr_type *__nft_expr_type_get(struct nlattr *nla) +static const struct nft_expr_type *__nft_expr_type_get(u8 family, + struct nlattr *nla) { const struct nft_expr_type *type; list_for_each_entry(type, &nf_tables_expressions, list) { - if (!nla_strcmp(nla, type->name)) + if (!nla_strcmp(nla, type->name) && + (!type->family || type->family == family)) return type; } return NULL; } -static const struct nft_expr_type *nft_expr_type_get(struct nlattr *nla) +static const struct nft_expr_type *nft_expr_type_get(u8 family, + struct nlattr *nla) { const struct nft_expr_type *type; if (nla == NULL) return ERR_PTR(-EINVAL); - type = __nft_expr_type_get(nla); + type = __nft_expr_type_get(family, nla); if (type != NULL && try_module_get(type->owner)) return type; #ifdef CONFIG_MODULES if (type == NULL) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); + request_module("nft-expr-%u-%.*s", family, + nla_len(nla), (char *)nla_data(nla)); + nfnl_lock(NFNL_SUBSYS_NFTABLES); + if (__nft_expr_type_get(family, nla)) + return ERR_PTR(-EAGAIN); + + nfnl_unlock(NFNL_SUBSYS_NFTABLES); request_module("nft-expr-%.*s", nla_len(nla), (char *)nla_data(nla)); nfnl_lock(NFNL_SUBSYS_NFTABLES); - if (__nft_expr_type_get(nla)) + if (__nft_expr_type_get(family, nla)) return ERR_PTR(-EAGAIN); } #endif @@ -1191,7 +1203,7 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, if (err < 0) return err; - type = nft_expr_type_get(tb[NFTA_EXPR_NAME]); + type = nft_expr_type_get(ctx->afi->family, tb[NFTA_EXPR_NAME]); if (IS_ERR(type)) return PTR_ERR(type); @@ -1519,9 +1531,8 @@ err: return err; } -static void nf_tables_rcu_rule_destroy(struct rcu_head *head) +static void nf_tables_rule_destroy(struct nft_rule *rule) { - struct nft_rule *rule = container_of(head, struct nft_rule, rcu_head); struct nft_expr *expr; /* @@ -1536,11 +1547,6 @@ static void nf_tables_rcu_rule_destroy(struct rcu_head *head) kfree(rule); } -static void nf_tables_rule_destroy(struct nft_rule *rule) -{ - call_rcu(&rule->rcu_head, nf_tables_rcu_rule_destroy); -} - #define NFT_RULE_MAXEXPRS 128 static struct nft_expr_info *info; @@ -1807,9 +1813,6 @@ static int nf_tables_commit(struct sk_buff *skb) synchronize_rcu(); list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - /* Delete this rule from the dirty list */ - list_del(&rupd->list); - /* This rule was inactive in the past and just became active. * Clear the next bit of the genmask since its meaning has * changed, now it is the future. @@ -1820,6 +1823,7 @@ static int nf_tables_commit(struct sk_buff *skb) rupd->chain, rupd->rule, NFT_MSG_NEWRULE, 0, rupd->family); + list_del(&rupd->list); kfree(rupd); continue; } @@ -1829,7 +1833,15 @@ static int nf_tables_commit(struct sk_buff *skb) nf_tables_rule_notify(skb, rupd->nlh, rupd->table, rupd->chain, rupd->rule, NFT_MSG_DELRULE, 0, rupd->family); + } + + /* Make sure we don't see any packet traversing old rules */ + synchronize_rcu(); + + /* Now we can safely release unused old rules */ + list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { nf_tables_rule_destroy(rupd->rule); + list_del(&rupd->list); kfree(rupd); } @@ -1842,20 +1854,26 @@ static int nf_tables_abort(struct sk_buff *skb) struct nft_rule_trans *rupd, *tmp; list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - /* Delete all rules from the dirty list */ - list_del(&rupd->list); - if (!nft_rule_is_active_next(net, rupd->rule)) { nft_rule_clear(net, rupd->rule); + list_del(&rupd->list); kfree(rupd); continue; } /* This rule is inactive, get rid of it */ list_del_rcu(&rupd->rule->list); + } + + /* Make sure we don't see any packet accessing aborted rules */ + synchronize_rcu(); + + list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { nf_tables_rule_destroy(rupd->rule); + list_del(&rupd->list); kfree(rupd); } + return 0; } @@ -1931,14 +1949,19 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, { struct net *net = sock_net(skb->sk); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - const struct nft_af_info *afi; + const struct nft_af_info *afi = NULL; const struct nft_table *table = NULL; - afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false); - if (IS_ERR(afi)) - return PTR_ERR(afi); + if (nfmsg->nfgen_family != NFPROTO_UNSPEC) { + afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false); + if (IS_ERR(afi)) + return PTR_ERR(afi); + } if (nla[NFTA_SET_TABLE] != NULL) { + if (afi == NULL) + return -EAFNOSUPPORT; + table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]); if (IS_ERR(table)) return PTR_ERR(table); @@ -1981,14 +2004,17 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, return -ENOMEM; list_for_each_entry(i, &ctx->table->sets, list) { - if (!sscanf(i->name, name, &n)) + int tmp; + + if (!sscanf(i->name, name, &tmp)) continue; - if (n < 0 || n > BITS_PER_LONG * PAGE_SIZE) + if (tmp < 0 || tmp >= BITS_PER_BYTE * PAGE_SIZE) continue; - set_bit(n, inuse); + + set_bit(tmp, inuse); } - n = find_first_zero_bit(inuse, BITS_PER_LONG * PAGE_SIZE); + n = find_first_zero_bit(inuse, BITS_PER_BYTE * PAGE_SIZE); free_page((unsigned long)inuse); } @@ -2102,8 +2128,8 @@ done: return skb->len; } -static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb, - struct netlink_callback *cb) +static int nf_tables_dump_sets_family(struct nft_ctx *ctx, struct sk_buff *skb, + struct netlink_callback *cb) { const struct nft_set *set; unsigned int idx, s_idx = cb->args[0]; @@ -2139,6 +2165,61 @@ done: return skb->len; } +static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb, + struct netlink_callback *cb) +{ + const struct nft_set *set; + unsigned int idx, s_idx = cb->args[0]; + const struct nft_af_info *afi; + struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2]; + struct net *net = sock_net(skb->sk); + int cur_family = cb->args[3]; + + if (cb->args[1]) + return skb->len; + + list_for_each_entry(afi, &net->nft.af_info, list) { + if (cur_family) { + if (afi->family != cur_family) + continue; + + cur_family = 0; + } + + list_for_each_entry(table, &afi->tables, list) { + if (cur_table) { + if (cur_table != table) + continue; + + cur_table = NULL; + } + + ctx->table = table; + ctx->afi = afi; + idx = 0; + list_for_each_entry(set, &ctx->table->sets, list) { + if (idx < s_idx) + goto cont; + if (nf_tables_fill_set(skb, ctx, set, + NFT_MSG_NEWSET, + NLM_F_MULTI) < 0) { + cb->args[0] = idx; + cb->args[2] = (unsigned long) table; + cb->args[3] = afi->family; + goto done; + } +cont: + idx++; + } + if (s_idx) + s_idx = 0; + } + } + cb->args[1] = 1; +done: + return skb->len; +} + static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); @@ -2155,9 +2236,12 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) if (err < 0) return err; - if (ctx.table == NULL) - ret = nf_tables_dump_sets_all(&ctx, skb, cb); - else + if (ctx.table == NULL) { + if (ctx.afi == NULL) + ret = nf_tables_dump_sets_all(&ctx, skb, cb); + else + ret = nf_tables_dump_sets_family(&ctx, skb, cb); + } else ret = nf_tables_dump_sets_table(&ctx, skb, cb); return ret; @@ -2170,6 +2254,7 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb, const struct nft_set *set; struct nft_ctx ctx; struct sk_buff *skb2; + const struct nfgenmsg *nfmsg = nlmsg_data(nlh); int err; /* Verify existance before starting dump */ @@ -2184,6 +2269,10 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb, return netlink_dump_start(nlsk, skb, nlh, &c); } + /* Only accept unspec with dump */ + if (nfmsg->nfgen_family == NFPROTO_UNSPEC) + return -EAFNOSUPPORT; + set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]); if (IS_ERR(set)) return PTR_ERR(set); @@ -2353,10 +2442,13 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[]) { + const struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nft_set *set; struct nft_ctx ctx; int err; + if (nfmsg->nfgen_family == NFPROTO_UNSPEC) + return -EAFNOSUPPORT; if (nla[NFTA_SET_TABLE] == NULL) return -EINVAL; @@ -2535,9 +2627,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) u32 portid, seq; int event, err; - nfmsg = nlmsg_data(cb->nlh); - err = nlmsg_parse(cb->nlh, sizeof(*nfmsg), nla, NFTA_SET_ELEM_LIST_MAX, - nft_set_elem_list_policy); + err = nlmsg_parse(cb->nlh, sizeof(struct nfgenmsg), nla, + NFTA_SET_ELEM_LIST_MAX, nft_set_elem_list_policy); if (err < 0) return err; @@ -2650,6 +2741,9 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_DATA] == NULL && !(elem.flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; + if (nla[NFTA_SET_ELEM_DATA] != NULL && + elem.flags & NFT_SET_ELEM_INTERVAL_END) + return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) return -EINVAL; @@ -2904,6 +2998,9 @@ static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, const struct nft_set_elem *elem) { + if (elem->flags & NFT_SET_ELEM_INTERVAL_END) + return 0; + switch (elem->data.verdict) { case NFT_JUMP: case NFT_GOTO: diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index cb9e685caae1..90998a6ff8b9 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -103,20 +103,20 @@ static struct nf_loginfo trace_loginfo = { }, }; -static inline void nft_trace_packet(const struct nft_pktinfo *pkt, - const struct nft_chain *chain, - int rulenum, enum nft_trace type) +static void nft_trace_packet(const struct nft_pktinfo *pkt, + const struct nft_chain *chain, + int rulenum, enum nft_trace type) { struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); - nf_log_packet(net, pkt->xt.family, pkt->hooknum, pkt->skb, pkt->in, + nf_log_packet(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in, pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", chain->table->name, chain->name, comments[type], rulenum); } unsigned int -nft_do_chain_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) +nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) { const struct nft_chain *chain = ops->priv; const struct nft_rule *rule; @@ -164,7 +164,7 @@ next_rule: break; } - switch (data[NFT_REG_VERDICT].verdict) { + switch (data[NFT_REG_VERDICT].verdict & NF_VERDICT_MASK) { case NF_ACCEPT: case NF_DROP: case NF_QUEUE: @@ -172,6 +172,9 @@ next_rule: nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); return data[NFT_REG_VERDICT].verdict; + } + + switch (data[NFT_REG_VERDICT].verdict) { case NFT_JUMP: if (unlikely(pkt->skb->nf_trace)) nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE); @@ -213,7 +216,7 @@ next_rule: return nft_base_chain(chain)->policy; } -EXPORT_SYMBOL_GPL(nft_do_chain_pktinfo); +EXPORT_SYMBOL_GPL(nft_do_chain); int __init nf_tables_core_module_init(void) { diff --git a/net/netfilter/nf_tables_inet.c b/net/netfilter/nf_tables_inet.c new file mode 100644 index 000000000000..9dd2d216cfc1 --- /dev/null +++ b/net/netfilter/nf_tables_inet.c @@ -0,0 +1,104 @@ +/* + * Copyright (c) 2012-2014 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv6.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_ipv4.h> +#include <net/netfilter/nf_tables_ipv6.h> +#include <net/ip.h> + +static void nft_inet_hook_ops_init(struct nf_hook_ops *ops, unsigned int n) +{ + struct nft_af_info *afi; + + if (n == 1) + afi = &nft_af_ipv4; + else + afi = &nft_af_ipv6; + + ops->pf = afi->family; + if (afi->hooks[ops->hooknum]) + ops->hook = afi->hooks[ops->hooknum]; +} + +static struct nft_af_info nft_af_inet __read_mostly = { + .family = NFPROTO_INET, + .nhooks = NF_INET_NUMHOOKS, + .owner = THIS_MODULE, + .nops = 2, + .hook_ops_init = nft_inet_hook_ops_init, +}; + +static int __net_init nf_tables_inet_init_net(struct net *net) +{ + net->nft.inet = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL); + if (net->nft.inet == NULL) + return -ENOMEM; + memcpy(net->nft.inet, &nft_af_inet, sizeof(nft_af_inet)); + + if (nft_register_afinfo(net, net->nft.inet) < 0) + goto err; + + return 0; + +err: + kfree(net->nft.inet); + return -ENOMEM; +} + +static void __net_exit nf_tables_inet_exit_net(struct net *net) +{ + nft_unregister_afinfo(net->nft.inet); + kfree(net->nft.inet); +} + +static struct pernet_operations nf_tables_inet_net_ops = { + .init = nf_tables_inet_init_net, + .exit = nf_tables_inet_exit_net, +}; + +static const struct nf_chain_type filter_inet = { + .name = "filter", + .type = NFT_CHAIN_T_DEFAULT, + .family = NFPROTO_INET, + .owner = THIS_MODULE, + .hook_mask = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING), +}; + +static int __init nf_tables_inet_init(void) +{ + int ret; + + nft_register_chain_type(&filter_inet); + ret = register_pernet_subsys(&nf_tables_inet_net_ops); + if (ret < 0) + nft_unregister_chain_type(&filter_inet); + + return ret; +} + +static void __exit nf_tables_inet_exit(void) +{ + unregister_pernet_subsys(&nf_tables_inet_net_ops); + nft_unregister_chain_type(&filter_inet); +} + +module_init(nf_tables_inet_init); +module_exit(nf_tables_inet_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_FAMILY(1); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 21258cf70091..f072fe803510 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -29,6 +29,7 @@ #include <linux/netfilter/nfnetlink_queue.h> #include <linux/list.h> #include <net/sock.h> +#include <net/tcp_states.h> #include <net/netfilter/nf_queue.h> #include <net/netns/generic.h> #include <net/netfilter/nfnetlink_queue.h> @@ -235,51 +236,6 @@ 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) -{ - int i, j = 0; - int plen = 0; /* length of skb->head fragment */ - 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 (hlen) { - skb_copy_bits(from, 0, skb_put(to, hlen), hlen); - len -= hlen; - } else { - plen = min_t(int, skb_headlen(from), len); - if (plen) { - page = virt_to_head_page(from->head); - offset = from->data - (unsigned char *)page_address(page); - __skb_fill_page_desc(to, 0, page, offset, plen); - get_page(page); - j = 1; - len -= plen; - } - } - - to->truesize += len + plen; - to->len += len + plen; - to->data_len += len + plen; - - for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { - if (!len) - break; - skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; - skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len); - len -= skb_shinfo(to)->frags[j].size; - skb_frag_ref(to, j); - j++; - } - skb_shinfo(to)->nr_frags = j; -} - static int nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet, bool csum_verify) @@ -297,6 +253,31 @@ nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet, return flags ? nla_put_be32(nlskb, NFQA_SKB_INFO, htonl(flags)) : 0; } +static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk) +{ + const struct cred *cred; + + if (sk->sk_state == TCP_TIME_WAIT) + return 0; + + read_lock_bh(&sk->sk_callback_lock); + if (sk->sk_socket && sk->sk_socket->file) { + cred = sk->sk_socket->file->f_cred; + if (nla_put_be32(skb, NFQA_UID, + htonl(from_kuid_munged(&init_user_ns, cred->fsuid)))) + goto nla_put_failure; + if (nla_put_be32(skb, NFQA_GID, + htonl(from_kgid_munged(&init_user_ns, cred->fsgid)))) + goto nla_put_failure; + } + read_unlock_bh(&sk->sk_callback_lock); + return 0; + +nla_put_failure: + read_unlock_bh(&sk->sk_callback_lock); + return -1; +} + static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, @@ -304,7 +285,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, { size_t size; size_t data_len = 0, cap_len = 0; - int hlen = 0; + unsigned int hlen = 0; struct sk_buff *skb; struct nlattr *nla; struct nfqnl_msg_packet_hdr *pmsg; @@ -356,14 +337,8 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (data_len > entskb->len) data_len = entskb->len; - if (!entskb->head_frag || - skb_headlen(entskb) < L1_CACHE_BYTES || - skb_shinfo(entskb)->nr_frags >= MAX_SKB_FRAGS) - hlen = skb_headlen(entskb); - - if (skb_has_frag_list(entskb)) - hlen = entskb->len; - hlen = min_t(int, data_len, hlen); + hlen = skb_zerocopy_headlen(entskb); + hlen = min_t(unsigned int, hlen, data_len); size += sizeof(struct nlattr) + hlen; cap_len = entskb->len; break; @@ -372,6 +347,11 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (queue->flags & NFQA_CFG_F_CONNTRACK) ct = nfqnl_ct_get(entskb, &size, &ctinfo); + if (queue->flags & NFQA_CFG_F_UID_GID) { + size += (nla_total_size(sizeof(u_int32_t)) /* uid */ + + nla_total_size(sizeof(u_int32_t))); /* gid */ + } + skb = nfnetlink_alloc_skb(net, size, queue->peer_portid, GFP_ATOMIC); if (!skb) @@ -484,6 +464,10 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, goto nla_put_failure; } + if ((queue->flags & NFQA_CFG_F_UID_GID) && entskb->sk && + nfqnl_put_sk_uidgid(skb, entskb->sk) < 0) + goto nla_put_failure; + if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0) goto nla_put_failure; @@ -504,7 +488,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, nla->nla_type = NFQA_PAYLOAD; nla->nla_len = nla_attr_size(data_len); - nfqnl_zcopy(skb, entskb, data_len, hlen); + skb_zerocopy(skb, entskb, data_len, hlen); } nlh->nlmsg_len = skb->len; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index da0c1f4ada12..82cb8236f8a1 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -92,7 +92,7 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par, if (ctx->chain->flags & NFT_BASE_CHAIN) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); - const struct nf_hook_ops *ops = &basechain->ops; + const struct nf_hook_ops *ops = &basechain->ops[0]; par->hook_mask = 1 << ops->hooknum; } @@ -253,7 +253,7 @@ static int nft_target_validate(const struct nft_ctx *ctx, if (ctx->chain->flags & NFT_BASE_CHAIN) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); - const struct nf_hook_ops *ops = &basechain->ops; + const struct nf_hook_ops *ops = &basechain->ops[0]; hook_mask = 1 << ops->hooknum; if (hook_mask & target->hooks) @@ -323,7 +323,7 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, if (ctx->chain->flags & NFT_BASE_CHAIN) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); - const struct nf_hook_ops *ops = &basechain->ops; + const struct nf_hook_ops *ops = &basechain->ops[0]; par->hook_mask = 1 << ops->hooknum; } @@ -449,7 +449,7 @@ static int nft_match_validate(const struct nft_ctx *ctx, if (ctx->chain->flags & NFT_BASE_CHAIN) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); - const struct nf_hook_ops *ops = &basechain->ops; + const struct nf_hook_ops *ops = &basechain->ops[0]; hook_mask = 1 << ops->hooknum; if (hook_mask & match->hooks) diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 955f4e6e7089..46e275403838 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -18,17 +18,21 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_ecache.h> struct nft_ct { enum nft_ct_keys key:8; enum ip_conntrack_dir dir:8; - enum nft_registers dreg:8; + union{ + enum nft_registers dreg:8; + enum nft_registers sreg:8; + }; uint8_t family; }; -static void nft_ct_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], - const struct nft_pktinfo *pkt) +static void nft_ct_get_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) { const struct nft_ct *priv = nft_expr_priv(expr); struct nft_data *dest = &data[priv->dreg]; @@ -123,24 +127,79 @@ err: data[NFT_REG_VERDICT].verdict = NFT_BREAK; } +static void nft_ct_set_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + const struct nft_ct *priv = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; +#ifdef CONFIG_NF_CONNTRACK_MARK + u32 value = data[priv->sreg].data[0]; +#endif + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL) + return; + + switch (priv->key) { +#ifdef CONFIG_NF_CONNTRACK_MARK + case NFT_CT_MARK: + if (ct->mark != value) { + ct->mark = value; + nf_conntrack_event_cache(IPCT_MARK, ct); + } + break; +#endif + } +} + static const struct nla_policy nft_ct_policy[NFTA_CT_MAX + 1] = { [NFTA_CT_DREG] = { .type = NLA_U32 }, [NFTA_CT_KEY] = { .type = NLA_U32 }, [NFTA_CT_DIRECTION] = { .type = NLA_U8 }, + [NFTA_CT_SREG] = { .type = NLA_U32 }, }; -static int nft_ct_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_ct_l3proto_try_module_get(uint8_t family) { - struct nft_ct *priv = nft_expr_priv(expr); int err; - if (tb[NFTA_CT_DREG] == NULL || - tb[NFTA_CT_KEY] == NULL) - return -EINVAL; + if (family == NFPROTO_INET) { + err = nf_ct_l3proto_try_module_get(NFPROTO_IPV4); + if (err < 0) + goto err1; + err = nf_ct_l3proto_try_module_get(NFPROTO_IPV6); + if (err < 0) + goto err2; + } else { + err = nf_ct_l3proto_try_module_get(family); + if (err < 0) + goto err1; + } + return 0; + +err2: + nf_ct_l3proto_module_put(NFPROTO_IPV4); +err1: + return err; +} + +static void nft_ct_l3proto_module_put(uint8_t family) +{ + if (family == NFPROTO_INET) { + nf_ct_l3proto_module_put(NFPROTO_IPV4); + nf_ct_l3proto_module_put(NFPROTO_IPV6); + } else + nf_ct_l3proto_module_put(family); +} + +static int nft_ct_init_validate_get(const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_ct *priv = nft_expr_priv(expr); - priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); if (tb[NFTA_CT_DIRECTION] != NULL) { priv->dir = nla_get_u8(tb[NFTA_CT_DIRECTION]); switch (priv->dir) { @@ -167,6 +226,7 @@ static int nft_ct_init(const struct nft_ctx *ctx, if (tb[NFTA_CT_DIRECTION] != NULL) return -EINVAL; break; + case NFT_CT_L3PROTOCOL: case NFT_CT_PROTOCOL: case NFT_CT_SRC: case NFT_CT_DST: @@ -179,34 +239,72 @@ static int nft_ct_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - err = nf_ct_l3proto_try_module_get(ctx->afi->family); + return 0; +} + +static int nft_ct_init_validate_set(uint32_t key) +{ + switch (key) { + case NFT_CT_MARK: + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int nft_ct_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_ct *priv = nft_expr_priv(expr); + int err; + + priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); + + if (tb[NFTA_CT_DREG]) { + err = nft_ct_init_validate_get(expr, tb); + if (err < 0) + return err; + + priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG])); + err = nft_validate_output_register(priv->dreg); + if (err < 0) + return err; + + err = nft_validate_data_load(ctx, priv->dreg, NULL, + NFT_DATA_VALUE); + if (err < 0) + return err; + } else { + err = nft_ct_init_validate_set(priv->key); + if (err < 0) + return err; + + priv->sreg = ntohl(nla_get_be32(tb[NFTA_CT_SREG])); + err = nft_validate_input_register(priv->sreg); + if (err < 0) + return err; + } + + err = nft_ct_l3proto_try_module_get(ctx->afi->family); if (err < 0) return err; - priv->family = ctx->afi->family; - priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG])); - err = nft_validate_output_register(priv->dreg); - if (err < 0) - goto err1; + priv->family = ctx->afi->family; - err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); - if (err < 0) - goto err1; return 0; - -err1: - nf_ct_l3proto_module_put(ctx->afi->family); - return err; } static void nft_ct_destroy(const struct nft_expr *expr) { struct nft_ct *priv = nft_expr_priv(expr); - nf_ct_l3proto_module_put(priv->family); + nft_ct_l3proto_module_put(priv->family); } -static int nft_ct_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ct *priv = nft_expr_priv(expr); @@ -214,7 +312,32 @@ static int nft_ct_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key))) goto nla_put_failure; - if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir)) + + switch (priv->key) { + case NFT_CT_PROTOCOL: + case NFT_CT_SRC: + case NFT_CT_DST: + case NFT_CT_PROTO_SRC: + case NFT_CT_PROTO_DST: + if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir)) + goto nla_put_failure; + default: + break; + } + + return 0; + +nla_put_failure: + return -1; +} + +static int nft_ct_set_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_ct *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_CT_SREG, htonl(priv->sreg))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key))) goto nla_put_failure; return 0; @@ -223,18 +346,46 @@ nla_put_failure: } static struct nft_expr_type nft_ct_type; -static const struct nft_expr_ops nft_ct_ops = { +static const struct nft_expr_ops nft_ct_get_ops = { .type = &nft_ct_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), - .eval = nft_ct_eval, + .eval = nft_ct_get_eval, .init = nft_ct_init, .destroy = nft_ct_destroy, - .dump = nft_ct_dump, + .dump = nft_ct_get_dump, }; +static const struct nft_expr_ops nft_ct_set_ops = { + .type = &nft_ct_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), + .eval = nft_ct_set_eval, + .init = nft_ct_init, + .destroy = nft_ct_destroy, + .dump = nft_ct_set_dump, +}; + +static const struct nft_expr_ops * +nft_ct_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (tb[NFTA_CT_KEY] == NULL) + return ERR_PTR(-EINVAL); + + if (tb[NFTA_CT_DREG] && tb[NFTA_CT_SREG]) + return ERR_PTR(-EINVAL); + + if (tb[NFTA_CT_DREG]) + return &nft_ct_get_ops; + + if (tb[NFTA_CT_SREG]) + return &nft_ct_set_ops; + + return ERR_PTR(-EINVAL); +} + static struct nft_expr_type nft_ct_type __read_mostly = { .name = "ct", - .ops = &nft_ct_ops, + .select_ops = &nft_ct_select_ops, .policy = nft_ct_policy, .maxattr = NFTA_CT_MAX, .owner = THIS_MODULE, diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 57cad072a13e..26c5154e05f3 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -23,7 +23,6 @@ static const char *nft_log_null_prefix = ""; struct nft_log { struct nf_loginfo loginfo; char *prefix; - int family; }; static void nft_log_eval(const struct nft_expr *expr, @@ -33,7 +32,7 @@ static void nft_log_eval(const struct nft_expr *expr, const struct nft_log *priv = nft_expr_priv(expr); struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); - nf_log_packet(net, priv->family, pkt->hooknum, pkt->skb, pkt->in, + nf_log_packet(net, pkt->ops->pf, pkt->ops->hooknum, pkt->skb, pkt->in, pkt->out, &priv->loginfo, "%s", priv->prefix); } @@ -52,8 +51,6 @@ static int nft_log_init(const struct nft_ctx *ctx, struct nf_loginfo *li = &priv->loginfo; const struct nlattr *nla; - priv->family = ctx->afi->family; - nla = tb[NFTA_LOG_PREFIX]; if (nla != NULL) { priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL); diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 8a6116b75b5a..bb4ef4cccb6e 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -16,6 +16,7 @@ #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> struct nft_lookup { struct nft_set *set; diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 8c28220a90b3..e8254ad2e5a9 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -21,12 +21,15 @@ struct nft_meta { enum nft_meta_keys key:8; - enum nft_registers dreg:8; + union { + enum nft_registers dreg:8; + enum nft_registers sreg:8; + }; }; -static void nft_meta_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], - const struct nft_pktinfo *pkt) +static void nft_meta_get_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; @@ -40,6 +43,12 @@ static void nft_meta_eval(const struct nft_expr *expr, case NFT_META_PROTOCOL: *(__be16 *)dest->data = skb->protocol; break; + case NFT_META_NFPROTO: + dest->data[0] = pkt->ops->pf; + break; + case NFT_META_L4PROTO: + dest->data[0] = pkt->tprot; + break; case NFT_META_PRIORITY: dest->data[0] = skb->priority; break; @@ -132,25 +141,54 @@ err: data[NFT_REG_VERDICT].verdict = NFT_BREAK; } +static void nft_meta_set_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + const struct nft_meta *meta = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; + u32 value = data[meta->sreg].data[0]; + + switch (meta->key) { + case NFT_META_MARK: + skb->mark = value; + break; + case NFT_META_PRIORITY: + skb->priority = value; + break; + case NFT_META_NFTRACE: + skb->nf_trace = 1; + break; + default: + WARN_ON(1); + } +} + static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = { [NFTA_META_DREG] = { .type = NLA_U32 }, [NFTA_META_KEY] = { .type = NLA_U32 }, + [NFTA_META_SREG] = { .type = NLA_U32 }, }; -static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_meta_init_validate_set(uint32_t key) { - struct nft_meta *priv = nft_expr_priv(expr); - int err; - - if (tb[NFTA_META_DREG] == NULL || - tb[NFTA_META_KEY] == NULL) - return -EINVAL; + switch (key) { + case NFT_META_MARK: + case NFT_META_PRIORITY: + case NFT_META_NFTRACE: + return 0; + default: + return -EOPNOTSUPP; + } +} - priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); - switch (priv->key) { +static int nft_meta_init_validate_get(uint32_t key) +{ + switch (key) { case NFT_META_LEN: case NFT_META_PROTOCOL: + case NFT_META_NFPROTO: + case NFT_META_L4PROTO: case NFT_META_PRIORITY: case NFT_META_MARK: case NFT_META_IIF: @@ -167,26 +205,72 @@ static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr, #ifdef CONFIG_NETWORK_SECMARK case NFT_META_SECMARK: #endif - break; + return 0; default: return -EOPNOTSUPP; } - priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG])); - err = nft_validate_output_register(priv->dreg); +} + +static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_meta *priv = nft_expr_priv(expr); + int err; + + priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); + + if (tb[NFTA_META_DREG]) { + err = nft_meta_init_validate_get(priv->key); + if (err < 0) + return err; + + priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG])); + err = nft_validate_output_register(priv->dreg); + if (err < 0) + return err; + + return nft_validate_data_load(ctx, priv->dreg, NULL, + NFT_DATA_VALUE); + } + + err = nft_meta_init_validate_set(priv->key); + if (err < 0) + return err; + + priv->sreg = ntohl(nla_get_be32(tb[NFTA_META_SREG])); + err = nft_validate_input_register(priv->sreg); if (err < 0) return err; - return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE); + + return 0; } -static int nft_meta_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_meta_get_dump(struct sk_buff *skb, + const struct nft_expr *expr) { const struct nft_meta *priv = nft_expr_priv(expr); + if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key))) + goto nla_put_failure; if (nla_put_be32(skb, NFTA_META_DREG, htonl(priv->dreg))) goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static int nft_meta_set_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_meta *priv = nft_expr_priv(expr); + if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key))) goto nla_put_failure; + if (nla_put_be32(skb, NFTA_META_SREG, htonl(priv->sreg))) + goto nla_put_failure; + return 0; nla_put_failure: @@ -194,17 +278,44 @@ nla_put_failure: } static struct nft_expr_type nft_meta_type; -static const struct nft_expr_ops nft_meta_ops = { +static const struct nft_expr_ops nft_meta_get_ops = { + .type = &nft_meta_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), + .eval = nft_meta_get_eval, + .init = nft_meta_init, + .dump = nft_meta_get_dump, +}; + +static const struct nft_expr_ops nft_meta_set_ops = { .type = &nft_meta_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), - .eval = nft_meta_eval, + .eval = nft_meta_set_eval, .init = nft_meta_init, - .dump = nft_meta_dump, + .dump = nft_meta_set_dump, }; +static const struct nft_expr_ops * +nft_meta_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (tb[NFTA_META_KEY] == NULL) + return ERR_PTR(-EINVAL); + + if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) + return ERR_PTR(-EINVAL); + + if (tb[NFTA_META_DREG]) + return &nft_meta_get_ops; + + if (tb[NFTA_META_SREG]) + return &nft_meta_set_ops; + + return ERR_PTR(-EINVAL); +} + static struct nft_expr_type nft_meta_type __read_mostly = { .name = "meta", - .ops = &nft_meta_ops, + .select_ops = &nft_meta_select_ops, .policy = nft_meta_policy, .maxattr = NFTA_META_MAX, .owner = THIS_MODULE, diff --git a/net/netfilter/nft_meta_target.c b/net/netfilter/nft_meta_target.c deleted file mode 100644 index 71177df75ffb..000000000000 --- a/net/netfilter/nft_meta_target.c +++ /dev/null @@ -1,117 +0,0 @@ -/* - * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Development of this code funded by Astaro AG (http://www.astaro.com/) - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/list.h> -#include <linux/rbtree.h> -#include <linux/netlink.h> -#include <linux/netfilter.h> -#include <linux/netfilter/nf_tables.h> -#include <net/netfilter/nf_tables.h> - -struct nft_meta { - enum nft_meta_keys key; -}; - -static void nft_meta_eval(const struct nft_expr *expr, - struct nft_data *nfres, - struct nft_data *data, - const struct nft_pktinfo *pkt) -{ - const struct nft_meta *meta = nft_expr_priv(expr); - struct sk_buff *skb = pkt->skb; - u32 val = data->data[0]; - - switch (meta->key) { - case NFT_META_MARK: - skb->mark = val; - break; - case NFT_META_PRIORITY: - skb->priority = val; - break; - case NFT_META_NFTRACE: - skb->nf_trace = val; - break; -#ifdef CONFIG_NETWORK_SECMARK - case NFT_META_SECMARK: - skb->secmark = val; - break; -#endif - default: - WARN_ON(1); - } -} - -static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = { - [NFTA_META_KEY] = { .type = NLA_U32 }, -}; - -static int nft_meta_init(const struct nft_expr *expr, struct nlattr *tb[]) -{ - struct nft_meta *meta = nft_expr_priv(expr); - - if (tb[NFTA_META_KEY] == NULL) - return -EINVAL; - - meta->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); - switch (meta->key) { - case NFT_META_MARK: - case NFT_META_PRIORITY: - case NFT_META_NFTRACE: -#ifdef CONFIG_NETWORK_SECMARK - case NFT_META_SECMARK: -#endif - break; - default: - return -EINVAL; - } - - return 0; -} - -static int nft_meta_dump(struct sk_buff *skb, const struct nft_expr *expr) -{ - struct nft_meta *meta = nft_expr_priv(expr); - - NLA_PUT_BE32(skb, NFTA_META_KEY, htonl(meta->key)); - return 0; - -nla_put_failure: - return -1; -} - -static struct nft_expr_ops meta_target __read_mostly = { - .name = "meta", - .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), - .owner = THIS_MODULE, - .eval = nft_meta_eval, - .init = nft_meta_init, - .dump = nft_meta_dump, - .policy = nft_meta_policy, - .maxattr = NFTA_META_MAX, -}; - -static int __init nft_meta_target_init(void) -{ - return nft_register_expr(&meta_target); -} - -static void __exit nft_meta_target_exit(void) -{ - nft_unregister_expr(&meta_target); -} - -module_init(nft_meta_target_init); -module_exit(nft_meta_target_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_EXPR("meta"); diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c new file mode 100644 index 000000000000..e8ae2f6bf232 --- /dev/null +++ b/net/netfilter/nft_queue.c @@ -0,0 +1,132 @@ +/* + * Copyright (c) 2013 Eric Leblond <eric@regit.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of this code partly funded by OISF + * (http://www.openinfosecfoundation.org/) + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/jhash.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_queue.h> + +static u32 jhash_initval __read_mostly; + +struct nft_queue { + u16 queuenum; + u16 queues_total; + u16 flags; +}; + +static void nft_queue_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + struct nft_queue *priv = nft_expr_priv(expr); + u32 queue = priv->queuenum; + u32 ret; + + if (priv->queues_total > 1) { + if (priv->flags & NFT_QUEUE_FLAG_CPU_FANOUT) { + int cpu = smp_processor_id(); + + queue = priv->queuenum + cpu % priv->queues_total; + } else { + queue = nfqueue_hash(pkt->skb, queue, + priv->queues_total, pkt->ops->pf, + jhash_initval); + } + } + + ret = NF_QUEUE_NR(queue); + if (priv->flags & NFT_QUEUE_FLAG_BYPASS) + ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; + + data[NFT_REG_VERDICT].verdict = ret; +} + +static const struct nla_policy nft_queue_policy[NFTA_QUEUE_MAX + 1] = { + [NFTA_QUEUE_NUM] = { .type = NLA_U16 }, + [NFTA_QUEUE_TOTAL] = { .type = NLA_U16 }, + [NFTA_QUEUE_FLAGS] = { .type = NLA_U16 }, +}; + +static int nft_queue_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_queue *priv = nft_expr_priv(expr); + + if (tb[NFTA_QUEUE_NUM] == NULL) + return -EINVAL; + + init_hashrandom(&jhash_initval); + priv->queuenum = ntohs(nla_get_be16(tb[NFTA_QUEUE_NUM])); + + if (tb[NFTA_QUEUE_TOTAL] != NULL) + priv->queues_total = ntohs(nla_get_be16(tb[NFTA_QUEUE_TOTAL])); + if (tb[NFTA_QUEUE_FLAGS] != NULL) { + priv->flags = ntohs(nla_get_be16(tb[NFTA_QUEUE_FLAGS])); + if (priv->flags & ~NFT_QUEUE_FLAG_MASK) + return -EINVAL; + } + return 0; +} + +static int nft_queue_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_queue *priv = nft_expr_priv(expr); + + if (nla_put_be16(skb, NFTA_QUEUE_NUM, htons(priv->queuenum)) || + nla_put_be16(skb, NFTA_QUEUE_TOTAL, htons(priv->queues_total)) || + nla_put_be16(skb, NFTA_QUEUE_FLAGS, htons(priv->flags))) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_queue_type; +static const struct nft_expr_ops nft_queue_ops = { + .type = &nft_queue_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_queue)), + .eval = nft_queue_eval, + .init = nft_queue_init, + .dump = nft_queue_dump, +}; + +static struct nft_expr_type nft_queue_type __read_mostly = { + .name = "queue", + .ops = &nft_queue_ops, + .policy = nft_queue_policy, + .maxattr = NFTA_QUEUE_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_queue_module_init(void) +{ + return nft_register_expr(&nft_queue_type); +} + +static void __exit nft_queue_module_exit(void) +{ + nft_unregister_expr(&nft_queue_type); +} + +module_init(nft_queue_module_init); +module_exit(nft_queue_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Eric Leblond <eric@regit.org>"); +MODULE_ALIAS_NFT_EXPR("queue"); diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c index ca0c1b231bfe..e21d69d13506 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_rbtree.c @@ -69,8 +69,10 @@ static void nft_rbtree_elem_destroy(const struct nft_set *set, struct nft_rbtree_elem *rbe) { nft_data_uninit(&rbe->key, NFT_DATA_VALUE); - if (set->flags & NFT_SET_MAP) + if (set->flags & NFT_SET_MAP && + !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) nft_data_uninit(rbe->data, set->dtype); + kfree(rbe); } @@ -108,7 +110,8 @@ static int nft_rbtree_insert(const struct nft_set *set, int err; size = sizeof(*rbe); - if (set->flags & NFT_SET_MAP) + if (set->flags & NFT_SET_MAP && + !(elem->flags & NFT_SET_ELEM_INTERVAL_END)) size += sizeof(rbe->data[0]); rbe = kzalloc(size, GFP_KERNEL); @@ -117,7 +120,8 @@ static int nft_rbtree_insert(const struct nft_set *set, rbe->flags = elem->flags; nft_data_copy(&rbe->key, &elem->key); - if (set->flags & NFT_SET_MAP) + if (set->flags & NFT_SET_MAP && + !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) nft_data_copy(rbe->data, &elem->data); err = __nft_rbtree_insert(set, rbe); @@ -153,7 +157,8 @@ static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem) parent = parent->rb_right; else { elem->cookie = rbe; - if (set->flags & NFT_SET_MAP) + if (set->flags & NFT_SET_MAP && + !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) nft_data_copy(&elem->data, rbe->data); elem->flags = rbe->flags; return 0; @@ -177,7 +182,8 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, rbe = rb_entry(node, struct nft_rbtree_elem, node); nft_data_copy(&elem.key, &rbe->key); - if (set->flags & NFT_SET_MAP) + if (set->flags & NFT_SET_MAP && + !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) nft_data_copy(&elem.data, rbe->data); elem.flags = rbe->flags; diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c new file mode 100644 index 000000000000..f3448c296446 --- /dev/null +++ b/net/netfilter/nft_reject.c @@ -0,0 +1,74 @@ +/* + * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2013 Eric Leblond <eric@regit.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_reject.h> + +const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = { + [NFTA_REJECT_TYPE] = { .type = NLA_U32 }, + [NFTA_REJECT_ICMP_CODE] = { .type = NLA_U8 }, +}; +EXPORT_SYMBOL_GPL(nft_reject_policy); + +int nft_reject_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_reject *priv = nft_expr_priv(expr); + + if (tb[NFTA_REJECT_TYPE] == NULL) + return -EINVAL; + + priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE])); + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + if (tb[NFTA_REJECT_ICMP_CODE] == NULL) + return -EINVAL; + priv->icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]); + case NFT_REJECT_TCP_RST: + break; + default: + return -EINVAL; + } + + return 0; +} +EXPORT_SYMBOL_GPL(nft_reject_init); + +int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_reject *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type))) + goto nla_put_failure; + + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) + goto nla_put_failure; + break; + } + + return 0; + +nla_put_failure: + return -1; +} +EXPORT_SYMBOL_GPL(nft_reject_dump); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c new file mode 100644 index 000000000000..8a310f239c93 --- /dev/null +++ b/net/netfilter/nft_reject_inet.c @@ -0,0 +1,63 @@ +/* + * Copyright (c) 2014 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_reject.h> + +static void nft_reject_inet_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + switch (pkt->ops->pf) { + case NFPROTO_IPV4: + nft_reject_ipv4_eval(expr, data, pkt); + case NFPROTO_IPV6: + nft_reject_ipv6_eval(expr, data, pkt); + } +} + +static struct nft_expr_type nft_reject_inet_type; +static const struct nft_expr_ops nft_reject_inet_ops = { + .type = &nft_reject_inet_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), + .eval = nft_reject_inet_eval, + .init = nft_reject_init, + .dump = nft_reject_dump, +}; + +static struct nft_expr_type nft_reject_inet_type __read_mostly = { + .family = NFPROTO_INET, + .name = "reject", + .ops = &nft_reject_inet_ops, + .policy = nft_reject_policy, + .maxattr = NFTA_REJECT_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_reject_inet_module_init(void) +{ + return nft_register_expr(&nft_reject_inet_type); +} + +static void __exit nft_reject_inet_module_exit(void) +{ + nft_unregister_expr(&nft_reject_inet_type); +} + +module_init(nft_reject_inet_module_init); +module_exit(nft_reject_inet_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_AF_EXPR(1, "reject"); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index da35ac06a975..75747aecdebe 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -211,8 +211,10 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, ret = 0; if ((info->ct_events || info->exp_events) && !nf_ct_ecache_ext_add(ct, info->ct_events, info->exp_events, - GFP_KERNEL)) + GFP_KERNEL)) { + ret = -EINVAL; goto err3; + } if (info->helper[0]) { ret = xt_ct_set_helper(ct, info->helper, par); @@ -226,12 +228,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, goto err3; } - __set_bit(IPS_TEMPLATE_BIT, &ct->status); - __set_bit(IPS_CONFIRMED_BIT, &ct->status); - - /* Overload tuple linked list to put us in template list. */ - hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &par->net->ct.tmpl); + nf_conntrack_tmpl_insert(par->net, ct); out: info->ct = ct; return 0; diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index ed00fef58996..8f1779ff7e30 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -11,15 +11,13 @@ #include <linux/module.h> #include <linux/skbuff.h> -#include <linux/ip.h> -#include <linux/ipv6.h> -#include <linux/jhash.h> - #include <linux/netfilter.h> #include <linux/netfilter_arp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_NFQUEUE.h> +#include <net/netfilter/nf_queue.h> + MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: packet forwarding to netlink"); MODULE_LICENSE("GPL"); @@ -28,7 +26,6 @@ MODULE_ALIAS("ip6t_NFQUEUE"); MODULE_ALIAS("arpt_NFQUEUE"); static u32 jhash_initval __read_mostly; -static bool rnd_inited __read_mostly; static unsigned int nfqueue_tg(struct sk_buff *skb, const struct xt_action_param *par) @@ -38,69 +35,16 @@ nfqueue_tg(struct sk_buff *skb, const struct xt_action_param *par) return NF_QUEUE_NR(tinfo->queuenum); } -static u32 hash_v4(const struct sk_buff *skb) -{ - const struct iphdr *iph = ip_hdr(skb); - - /* packets in either direction go into same queue */ - if ((__force u32)iph->saddr < (__force u32)iph->daddr) - return jhash_3words((__force u32)iph->saddr, - (__force u32)iph->daddr, iph->protocol, jhash_initval); - - return jhash_3words((__force u32)iph->daddr, - (__force u32)iph->saddr, iph->protocol, jhash_initval); -} - -#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) -static u32 hash_v6(const struct sk_buff *skb) -{ - const struct ipv6hdr *ip6h = ipv6_hdr(skb); - u32 a, b, c; - - if ((__force u32)ip6h->saddr.s6_addr32[3] < - (__force u32)ip6h->daddr.s6_addr32[3]) { - a = (__force u32) ip6h->saddr.s6_addr32[3]; - b = (__force u32) ip6h->daddr.s6_addr32[3]; - } else { - b = (__force u32) ip6h->saddr.s6_addr32[3]; - a = (__force u32) ip6h->daddr.s6_addr32[3]; - } - - if ((__force u32)ip6h->saddr.s6_addr32[1] < - (__force u32)ip6h->daddr.s6_addr32[1]) - c = (__force u32) ip6h->saddr.s6_addr32[1]; - else - c = (__force u32) ip6h->daddr.s6_addr32[1]; - - return jhash_3words(a, b, c, jhash_initval); -} -#endif - -static u32 -nfqueue_hash(const struct sk_buff *skb, const struct xt_action_param *par) -{ - const struct xt_NFQ_info_v1 *info = par->targinfo; - u32 queue = info->queuenum; - - if (par->family == NFPROTO_IPV4) - queue += ((u64) hash_v4(skb) * info->queues_total) >> 32; -#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) - else if (par->family == NFPROTO_IPV6) - queue += ((u64) hash_v6(skb) * info->queues_total) >> 32; -#endif - - return queue; -} - static unsigned int nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v1 *info = par->targinfo; u32 queue = info->queuenum; - if (info->queues_total > 1) - queue = nfqueue_hash(skb, par); - + if (info->queues_total > 1) { + queue = nfqueue_hash(skb, queue, info->queues_total, + par->family, jhash_initval); + } return NF_QUEUE_NR(queue); } @@ -120,10 +64,8 @@ static int nfqueue_tg_check(const struct xt_tgchk_param *par) const struct xt_NFQ_info_v3 *info = par->targinfo; u32 maxid; - if (unlikely(!rnd_inited)) { - get_random_bytes(&jhash_initval, sizeof(jhash_initval)); - rnd_inited = true; - } + init_hashrandom(&jhash_initval); + if (info->queues_total == 0) { pr_err("NFQUEUE: number of total queues is 0\n"); return -EINVAL; @@ -154,8 +96,10 @@ nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par) int cpu = smp_processor_id(); queue = info->queuenum + cpu % info->queues_total; - } else - queue = nfqueue_hash(skb, par); + } else { + queue = nfqueue_hash(skb, queue, info->queues_total, + par->family, jhash_initval); + } } ret = NF_QUEUE_NR(queue); diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c new file mode 100644 index 000000000000..9a8e77e7f8d4 --- /dev/null +++ b/net/netfilter/xt_cgroup.c @@ -0,0 +1,71 @@ +/* + * Xtables module to match the process control group. + * + * Might be used to implement individual "per-application" firewall + * policies in contrast to global policies based on control groups. + * Matching is based upon processes tagged to net_cls' classid marker. + * + * (C) 2013 Daniel Borkmann <dborkman@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/skbuff.h> +#include <linux/module.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_cgroup.h> +#include <net/sock.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>"); +MODULE_DESCRIPTION("Xtables: process control group matching"); +MODULE_ALIAS("ipt_cgroup"); +MODULE_ALIAS("ip6t_cgroup"); + +static int cgroup_mt_check(const struct xt_mtchk_param *par) +{ + struct xt_cgroup_info *info = par->matchinfo; + + if (info->invert & ~1) + return -EINVAL; + + return info->id ? 0 : -EINVAL; +} + +static bool +cgroup_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_cgroup_info *info = par->matchinfo; + + if (skb->sk == NULL) + return false; + + return (info->id == skb->sk->sk_classid) ^ info->invert; +} + +static struct xt_match cgroup_mt_reg __read_mostly = { + .name = "cgroup", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = cgroup_mt_check, + .match = cgroup_mt, + .matchsize = sizeof(struct xt_cgroup_info), + .me = THIS_MODULE, + .hooks = (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING), +}; + +static int __init cgroup_mt_init(void) +{ + return xt_register_match(&cgroup_mt_reg); +} + +static void __exit cgroup_mt_exit(void) +{ + xt_unregister_match(&cgroup_mt_reg); +} + +module_init(cgroup_mt_init); +module_exit(cgroup_mt_exit); diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 7278145e6a68..69f78e96fdb4 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -17,8 +17,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/module.h> diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c new file mode 100644 index 000000000000..a4c7561698c5 --- /dev/null +++ b/net/netfilter/xt_ipcomp.c @@ -0,0 +1,111 @@ +/* Kernel module to match IPComp parameters for IPv4 and IPv6 + * + * Copyright (C) 2013 WindRiver + * + * Author: + * Fan Du <fan.du@windriver.com> + * + * Based on: + * net/netfilter/xt_esp.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/in.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ip.h> + +#include <linux/netfilter/xt_ipcomp.h> +#include <linux/netfilter/x_tables.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Fan Du <fan.du@windriver.com>"); +MODULE_DESCRIPTION("Xtables: IPv4/6 IPsec-IPComp SPI match"); + +/* Returns 1 if the spi is matched by the range, 0 otherwise */ +static inline bool +spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert) +{ + bool r; + pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n", + invert ? '!' : ' ', min, spi, max); + r = (spi >= min && spi <= max) ^ invert; + pr_debug(" result %s\n", r ? "PASS" : "FAILED"); + return r; +} + +static bool comp_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct ip_comp_hdr _comphdr; + const struct ip_comp_hdr *chdr; + const struct xt_ipcomp *compinfo = par->matchinfo; + + /* Must not be a fragment. */ + if (par->fragoff != 0) + return false; + + chdr = skb_header_pointer(skb, par->thoff, sizeof(_comphdr), &_comphdr); + if (chdr == NULL) { + /* We've been asked to examine this packet, and we + * can't. Hence, no choice but to drop. + */ + pr_debug("Dropping evil IPComp tinygram.\n"); + par->hotdrop = true; + return 0; + } + + return spi_match(compinfo->spis[0], compinfo->spis[1], + ntohl(chdr->cpi << 16), + !!(compinfo->invflags & XT_IPCOMP_INV_SPI)); +} + +static int comp_mt_check(const struct xt_mtchk_param *par) +{ + const struct xt_ipcomp *compinfo = par->matchinfo; + + /* Must specify no unknown invflags */ + if (compinfo->invflags & ~XT_IPCOMP_INV_MASK) { + pr_err("unknown flags %X\n", compinfo->invflags); + return -EINVAL; + } + return 0; +} + +static struct xt_match comp_mt_reg[] __read_mostly = { + { + .name = "ipcomp", + .family = NFPROTO_IPV4, + .match = comp_mt, + .matchsize = sizeof(struct xt_ipcomp), + .proto = IPPROTO_COMP, + .checkentry = comp_mt_check, + .me = THIS_MODULE, + }, + { + .name = "ipcomp", + .family = NFPROTO_IPV6, + .match = comp_mt, + .matchsize = sizeof(struct xt_ipcomp), + .proto = IPPROTO_COMP, + .checkentry = comp_mt_check, + .me = THIS_MODULE, + }, +}; + +static int __init comp_mt_init(void) +{ + return xt_register_matches(comp_mt_reg, ARRAY_SIZE(comp_mt_reg)); +} + +static void __exit comp_mt_exit(void) +{ + xt_unregister_matches(comp_mt_reg, ARRAY_SIZE(comp_mt_reg)); +} + +module_init(comp_mt_init); +module_exit(comp_mt_exit); diff --git a/net/netfilter/xt_l2tp.c b/net/netfilter/xt_l2tp.c new file mode 100644 index 000000000000..8aee572771f2 --- /dev/null +++ b/net/netfilter/xt_l2tp.c @@ -0,0 +1,354 @@ +/* Kernel module to match L2TP header parameters. */ + +/* (C) 2013 James Chapman <jchapman@katalix.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/if_ether.h> +#include <net/ip.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> +#include <net/udp.h> +#include <linux/l2tp.h> + +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_tcpudp.h> +#include <linux/netfilter/xt_l2tp.h> + +/* L2TP header masks */ +#define L2TP_HDR_T_BIT 0x8000 +#define L2TP_HDR_L_BIT 0x4000 +#define L2TP_HDR_VER 0x000f + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); +MODULE_DESCRIPTION("Xtables: L2TP header match"); +MODULE_ALIAS("ipt_l2tp"); +MODULE_ALIAS("ip6t_l2tp"); + +/* The L2TP fields that can be matched */ +struct l2tp_data { + u32 tid; + u32 sid; + u8 type; + u8 version; +}; + +union l2tp_val { + __be16 val16[2]; + __be32 val32; +}; + +static bool l2tp_match(const struct xt_l2tp_info *info, struct l2tp_data *data) +{ + if ((info->flags & XT_L2TP_TYPE) && (info->type != data->type)) + return false; + + if ((info->flags & XT_L2TP_VERSION) && (info->version != data->version)) + return false; + + /* Check tid only for L2TPv3 control or any L2TPv2 packets */ + if ((info->flags & XT_L2TP_TID) && + ((data->type == XT_L2TP_TYPE_CONTROL) || (data->version == 2)) && + (info->tid != data->tid)) + return false; + + /* Check sid only for L2TP data packets */ + if ((info->flags & XT_L2TP_SID) && (data->type == XT_L2TP_TYPE_DATA) && + (info->sid != data->sid)) + return false; + + return true; +} + +/* Parse L2TP header fields when UDP encapsulation is used. Handles + * L2TPv2 and L2TPv3. Note the L2TPv3 control and data packets have a + * different format. See + * RFC2661, Section 3.1, L2TPv2 Header Format + * RFC3931, Section 3.2.1, L2TPv3 Control Message Header + * RFC3931, Section 3.2.2, L2TPv3 Data Message Header + * RFC3931, Section 4.1.2.1, L2TPv3 Session Header over UDP + */ +static bool l2tp_udp_mt(const struct sk_buff *skb, struct xt_action_param *par, u16 thoff) +{ + const struct xt_l2tp_info *info = par->matchinfo; + int uhlen = sizeof(struct udphdr); + int offs = thoff + uhlen; + union l2tp_val *lh; + union l2tp_val lhbuf; + u16 flags; + struct l2tp_data data = { 0, }; + + if (par->fragoff != 0) + return false; + + /* Extract L2TP header fields. The flags in the first 16 bits + * tell us where the other fields are. + */ + lh = skb_header_pointer(skb, offs, 2, &lhbuf); + if (lh == NULL) + return false; + + flags = ntohs(lh->val16[0]); + if (flags & L2TP_HDR_T_BIT) + data.type = XT_L2TP_TYPE_CONTROL; + else + data.type = XT_L2TP_TYPE_DATA; + data.version = (u8) flags & L2TP_HDR_VER; + + /* Now extract the L2TP tid/sid. These are in different places + * for L2TPv2 (rfc2661) and L2TPv3 (rfc3931). For L2TPv2, we + * must also check to see if the length field is present, + * since this affects the offsets into the packet of the + * tid/sid fields. + */ + if (data.version == 3) { + lh = skb_header_pointer(skb, offs + 4, 4, &lhbuf); + if (lh == NULL) + return false; + if (data.type == XT_L2TP_TYPE_CONTROL) + data.tid = ntohl(lh->val32); + else + data.sid = ntohl(lh->val32); + } else if (data.version == 2) { + if (flags & L2TP_HDR_L_BIT) + offs += 2; + lh = skb_header_pointer(skb, offs + 2, 4, &lhbuf); + if (lh == NULL) + return false; + data.tid = (u32) ntohs(lh->val16[0]); + data.sid = (u32) ntohs(lh->val16[1]); + } else + return false; + + return l2tp_match(info, &data); +} + +/* Parse L2TP header fields for IP encapsulation (no UDP header). + * L2TPv3 data packets have a different form with IP encap. See + * RC3931, Section 4.1.1.1, L2TPv3 Session Header over IP. + * RC3931, Section 4.1.1.2, L2TPv3 Control and Data Traffic over IP. + */ +static bool l2tp_ip_mt(const struct sk_buff *skb, struct xt_action_param *par, u16 thoff) +{ + const struct xt_l2tp_info *info = par->matchinfo; + union l2tp_val *lh; + union l2tp_val lhbuf; + struct l2tp_data data = { 0, }; + + /* For IP encap, the L2TP sid is the first 32-bits. */ + lh = skb_header_pointer(skb, thoff, sizeof(lhbuf), &lhbuf); + if (lh == NULL) + return false; + if (lh->val32 == 0) { + /* Must be a control packet. The L2TP tid is further + * into the packet. + */ + data.type = XT_L2TP_TYPE_CONTROL; + lh = skb_header_pointer(skb, thoff + 8, sizeof(lhbuf), + &lhbuf); + if (lh == NULL) + return false; + data.tid = ntohl(lh->val32); + } else { + data.sid = ntohl(lh->val32); + data.type = XT_L2TP_TYPE_DATA; + } + + data.version = 3; + + return l2tp_match(info, &data); +} + +static bool l2tp_mt4(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct iphdr *iph = ip_hdr(skb); + u8 ipproto = iph->protocol; + + /* l2tp_mt_check4 already restricts the transport protocol */ + switch (ipproto) { + case IPPROTO_UDP: + return l2tp_udp_mt(skb, par, par->thoff); + case IPPROTO_L2TP: + return l2tp_ip_mt(skb, par, par->thoff); + } + + return false; +} + +#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) +static bool l2tp_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + unsigned int thoff = 0; + unsigned short fragoff = 0; + int ipproto; + + ipproto = ipv6_find_hdr(skb, &thoff, -1, &fragoff, NULL); + if (fragoff != 0) + return false; + + /* l2tp_mt_check6 already restricts the transport protocol */ + switch (ipproto) { + case IPPROTO_UDP: + return l2tp_udp_mt(skb, par, thoff); + case IPPROTO_L2TP: + return l2tp_ip_mt(skb, par, thoff); + } + + return false; +} +#endif + +static int l2tp_mt_check(const struct xt_mtchk_param *par) +{ + const struct xt_l2tp_info *info = par->matchinfo; + + /* Check for invalid flags */ + if (info->flags & ~(XT_L2TP_TID | XT_L2TP_SID | XT_L2TP_VERSION | + XT_L2TP_TYPE)) { + pr_info("unknown flags: %x\n", info->flags); + return -EINVAL; + } + + /* At least one of tid, sid or type=control must be specified */ + if ((!(info->flags & XT_L2TP_TID)) && + (!(info->flags & XT_L2TP_SID)) && + ((!(info->flags & XT_L2TP_TYPE)) || + (info->type != XT_L2TP_TYPE_CONTROL))) { + pr_info("invalid flags combination: %x\n", info->flags); + return -EINVAL; + } + + /* If version 2 is specified, check that incompatible params + * are not supplied + */ + if (info->flags & XT_L2TP_VERSION) { + if ((info->version < 2) || (info->version > 3)) { + pr_info("wrong L2TP version: %u\n", info->version); + return -EINVAL; + } + + if (info->version == 2) { + if ((info->flags & XT_L2TP_TID) && + (info->tid > 0xffff)) { + pr_info("v2 tid > 0xffff: %u\n", info->tid); + return -EINVAL; + } + if ((info->flags & XT_L2TP_SID) && + (info->sid > 0xffff)) { + pr_info("v2 sid > 0xffff: %u\n", info->sid); + return -EINVAL; + } + } + } + + return 0; +} + +static int l2tp_mt_check4(const struct xt_mtchk_param *par) +{ + const struct xt_l2tp_info *info = par->matchinfo; + const struct ipt_entry *e = par->entryinfo; + const struct ipt_ip *ip = &e->ip; + int ret; + + ret = l2tp_mt_check(par); + if (ret != 0) + return ret; + + if ((ip->proto != IPPROTO_UDP) && + (ip->proto != IPPROTO_L2TP)) { + pr_info("missing protocol rule (udp|l2tpip)\n"); + return -EINVAL; + } + + if ((ip->proto == IPPROTO_L2TP) && + (info->version == 2)) { + pr_info("v2 doesn't support IP mode\n"); + return -EINVAL; + } + + return 0; +} + +#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) +static int l2tp_mt_check6(const struct xt_mtchk_param *par) +{ + const struct xt_l2tp_info *info = par->matchinfo; + const struct ip6t_entry *e = par->entryinfo; + const struct ip6t_ip6 *ip = &e->ipv6; + int ret; + + ret = l2tp_mt_check(par); + if (ret != 0) + return ret; + + if ((ip->proto != IPPROTO_UDP) && + (ip->proto != IPPROTO_L2TP)) { + pr_info("missing protocol rule (udp|l2tpip)\n"); + return -EINVAL; + } + + if ((ip->proto == IPPROTO_L2TP) && + (info->version == 2)) { + pr_info("v2 doesn't support IP mode\n"); + return -EINVAL; + } + + return 0; +} +#endif + +static struct xt_match l2tp_mt_reg[] __read_mostly = { + { + .name = "l2tp", + .revision = 0, + .family = NFPROTO_IPV4, + .match = l2tp_mt4, + .matchsize = XT_ALIGN(sizeof(struct xt_l2tp_info)), + .checkentry = l2tp_mt_check4, + .hooks = ((1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_FORWARD)), + .me = THIS_MODULE, + }, +#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) + { + .name = "l2tp", + .revision = 0, + .family = NFPROTO_IPV6, + .match = l2tp_mt6, + .matchsize = XT_ALIGN(sizeof(struct xt_l2tp_info)), + .checkentry = l2tp_mt_check6, + .hooks = ((1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_FORWARD)), + .me = THIS_MODULE, + }, +#endif +}; + +static int __init l2tp_mt_init(void) +{ + return xt_register_matches(&l2tp_mt_reg[0], ARRAY_SIZE(l2tp_mt_reg)); +} + +static void __exit l2tp_mt_exit(void) +{ + xt_unregister_matches(&l2tp_mt_reg[0], ARRAY_SIZE(l2tp_mt_reg)); +} + +module_init(l2tp_mt_init); +module_exit(l2tp_mt_exit); diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 647d989a01e6..7174611bd672 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -13,8 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> diff --git a/net/netfilter/xt_statistic.c b/net/netfilter/xt_statistic.c index 4fe4fb4276d0..11de55e7a868 100644 --- a/net/netfilter/xt_statistic.c +++ b/net/netfilter/xt_statistic.c @@ -37,7 +37,7 @@ statistic_mt(const struct sk_buff *skb, struct xt_action_param *par) switch (info->mode) { case XT_STATISTIC_MODE_RANDOM: - if ((net_random() & 0x7FFFFFFF) < info->u.random.probability) + if ((prandom_u32() & 0x7FFFFFFF) < info->u.random.probability) ret = !ret; break; case XT_STATISTIC_MODE_NTH: diff --git a/net/netlabel/netlabel_addrlist.c b/net/netlabel/netlabel_addrlist.c index 6f1701322fb6..d0a3acfa5742 100644 --- a/net/netlabel/netlabel_addrlist.c +++ b/net/netlabel/netlabel_addrlist.c @@ -24,8 +24,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_addrlist.h b/net/netlabel/netlabel_addrlist.h index a1287ce18130..d0f38bc9af6d 100644 --- a/net/netlabel/netlabel_addrlist.h +++ b/net/netlabel/netlabel_addrlist.h @@ -24,8 +24,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 69345cebe3a3..c2f2a53a4879 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -23,8 +23,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_cipso_v4.h b/net/netlabel/netlabel_cipso_v4.h index d24d774bfd62..875826808b00 100644 --- a/net/netlabel/netlabel_cipso_v4.h +++ b/net/netlabel/netlabel_cipso_v4.h @@ -23,8 +23,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index 85d842e6e431..f0cb92f3ddaf 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -24,8 +24,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_domainhash.h b/net/netlabel/netlabel_domainhash.h index b9be0eed8980..680caf4dff56 100644 --- a/net/netlabel/netlabel_domainhash.h +++ b/net/netlabel/netlabel_domainhash.h @@ -24,8 +24,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index dce1bebf7aec..3045a964f39c 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -23,8 +23,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 8ef83ee97c6a..e66e977ef2fa 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -23,8 +23,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_mgmt.h b/net/netlabel/netlabel_mgmt.h index 5a9f31ce5799..8b6e1ab62b48 100644 --- a/net/netlabel/netlabel_mgmt.h +++ b/net/netlabel/netlabel_mgmt.h @@ -23,8 +23,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 43817d73ccf9..78a63c18779e 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -23,8 +23,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_unlabeled.h b/net/netlabel/netlabel_unlabeled.h index 700af49022a0..3a9e5dc9511b 100644 --- a/net/netlabel/netlabel_unlabeled.h +++ b/net/netlabel/netlabel_unlabeled.h @@ -23,8 +23,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_user.c b/net/netlabel/netlabel_user.c index 9650c4ad5f88..1e779bb7fa43 100644 --- a/net/netlabel/netlabel_user.c +++ b/net/netlabel/netlabel_user.c @@ -23,8 +23,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h index 81969785e279..4a397cde1a48 100644 --- a/net/netlabel/netlabel_user.h +++ b/net/netlabel/netlabel_user.h @@ -23,8 +23,7 @@ * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index bca50b95c182..fdf51353cf78 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -131,7 +131,7 @@ int netlink_add_tap(struct netlink_tap *nt) } EXPORT_SYMBOL_GPL(netlink_add_tap); -int __netlink_remove_tap(struct netlink_tap *nt) +static int __netlink_remove_tap(struct netlink_tap *nt) { bool found = false; struct netlink_tap *tmp; @@ -155,7 +155,6 @@ out: return found ? 0 : -ENODEV; } -EXPORT_SYMBOL_GPL(__netlink_remove_tap); int netlink_remove_tap(struct netlink_tap *nt) { @@ -204,6 +203,8 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, if (nskb) { nskb->dev = dev; nskb->protocol = htons((u16) sk->sk_protocol); + nskb->pkt_type = netlink_is_kernel(sk) ? + PACKET_KERNEL : PACKET_USER; ret = dev_queue_xmit(nskb); if (unlikely(ret > 0)) @@ -239,6 +240,13 @@ static void netlink_deliver_tap(struct sk_buff *skb) rcu_read_unlock(); } +static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src, + struct sk_buff *skb) +{ + if (!(netlink_is_kernel(dst) && netlink_is_kernel(src))) + netlink_deliver_tap(skb); +} + static void netlink_overrun(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); @@ -1697,14 +1705,10 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, ret = -ECONNREFUSED; if (nlk->netlink_rcv != NULL) { - /* We could do a netlink_deliver_tap(skb) here as well - * but since this is intended for the kernel only, we - * should rather let it stay under the hood. - */ - ret = skb->len; netlink_skb_set_owner_r(skb, sk); NETLINK_CB(skb).sk = ssk; + netlink_deliver_tap_kernel(sk, ssk, skb); nlk->netlink_rcv(skb); consume_skb(skb); } else { @@ -1769,6 +1773,9 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, if (ring->pg_vec == NULL) goto out_put; + if (ring->frame_size - NL_MMAP_HDRLEN < size) + goto out_put; + skb = alloc_skb_head(gfp_mask); if (skb == NULL) goto err1; @@ -1778,6 +1785,7 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, if (ring->pg_vec == NULL) goto out_free; + /* check again under lock */ maxlen = ring->frame_size - NL_MMAP_HDRLEN; if (maxlen < size) goto out_free; @@ -2214,7 +2222,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, struct sock_iocb *siocb = kiocb_to_siocb(kiocb); struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); - struct sockaddr_nl *addr = msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); u32 dst_portid; u32 dst_group; struct sk_buff *skb; @@ -2345,7 +2353,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, err = skb_copy_datagram_iovec(data_skb, 0, msg->msg_iov, copied); if (msg->msg_name) { - struct sockaddr_nl *addr = (struct sockaddr_nl *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); addr->nl_family = AF_NETLINK; addr->nl_pad = 0; addr->nl_pid = NETLINK_CB(skb).portid; @@ -2535,21 +2543,6 @@ void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) netlink_update_socket_mc(nlk_sk(sk), group, 0); } -/** - * netlink_clear_multicast_users - kick off multicast listeners - * - * This function removes all listeners from the given group. - * @ksk: The kernel netlink socket, as returned by - * netlink_kernel_create(). - * @group: The multicast group to clear. - */ -void netlink_clear_multicast_users(struct sock *ksk, unsigned int group) -{ - netlink_table_grab(); - __netlink_clear_multicast_users(ksk, group); - netlink_table_ungrab(); -} - struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags) { diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 713671ae45af..b1dcdb932a86 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -461,6 +461,26 @@ int genl_unregister_family(struct genl_family *family) EXPORT_SYMBOL(genl_unregister_family); /** + * genlmsg_new_unicast - Allocate generic netlink message for unicast + * @payload: size of the message payload + * @info: information on destination + * @flags: the type of memory to allocate + * + * Allocates a new sk_buff large enough to cover the specified payload + * plus required Netlink headers. Will check receiving socket for + * memory mapped i/o capability and use it if enabled. Will fall back + * to non-mapped skb if message size exceeds the frame size of the ring. + */ +struct sk_buff *genlmsg_new_unicast(size_t payload, struct genl_info *info, + gfp_t flags) +{ + size_t len = nlmsg_total_size(genlmsg_total_size(payload)); + + return netlink_alloc_skb(info->dst_sk, len, info->snd_portid, flags); +} +EXPORT_SYMBOL_GPL(genlmsg_new_unicast); + +/** * genlmsg_put - Add generic netlink header to netlink message * @skb: socket buffer holding the message * @portid: netlink portid the message is addressed to @@ -600,6 +620,7 @@ static int genl_family_rcv_msg(struct genl_family *family, info.genlhdr = nlmsg_data(nlh); info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN; info.attrs = attrbuf; + info.dst_sk = skb->sk; genl_info_net_set(&info, net); memset(&info.user_ptr, 0, sizeof(info.user_ptr)); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 53c19a35fc6d..b74aa0755521 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1028,7 +1028,7 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); - struct sockaddr_ax25 *usax = (struct sockaddr_ax25 *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_ax25 *, usax, msg->msg_name); int err; struct sockaddr_ax25 sax; struct sk_buff *skb; @@ -1137,7 +1137,7 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; - struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_ax25 *, sax, msg->msg_name); size_t copied; struct sk_buff *skb; int er; diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c index 9d68441e2a5a..2277276f52bc 100644 --- a/net/nfc/af_nfc.c +++ b/net/nfc/af_nfc.c @@ -16,9 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/nfc.h> diff --git a/net/nfc/core.c b/net/nfc/core.c index 83b9927e7d19..ca1e65f4b133 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -16,9 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ @@ -135,11 +133,8 @@ int nfc_dev_up(struct nfc_dev *dev) dev->dev_up = true; /* We have to enable the device before discovering SEs */ - if (dev->ops->discover_se) { - rc = dev->ops->discover_se(dev); - if (rc) - pr_warn("SE discovery failed\n"); - } + if (dev->ops->discover_se && dev->ops->discover_se(dev)) + pr_err("SE discovery failed\n"); error: device_unlock(&dev->dev); diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index 09fc95439955..c129d1571ca6 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -339,7 +339,6 @@ int digital_target_found(struct nfc_digital_dev *ddev, pr_debug("rf_tech=%d, protocol=%d\n", rf_tech, protocol); ddev->curr_rf_tech = rf_tech; - ddev->curr_protocol = protocol; if (DIGITAL_DRV_CAPS_IN_CRC(ddev)) { ddev->skb_add_crc = digital_skb_add_crc_none; @@ -541,8 +540,14 @@ static int digital_dep_link_up(struct nfc_dev *nfc_dev, __u8 comm_mode, __u8 *gb, size_t gb_len) { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); + int rc; + + rc = digital_in_send_atr_req(ddev, target, comm_mode, gb, gb_len); - return digital_in_send_atr_req(ddev, target, comm_mode, gb, gb_len); + if (!rc) + ddev->curr_protocol = NFC_PROTO_NFC_DEP; + + return rc; } static int digital_dep_link_down(struct nfc_dev *nfc_dev) @@ -557,6 +562,20 @@ static int digital_dep_link_down(struct nfc_dev *nfc_dev) static int digital_activate_target(struct nfc_dev *nfc_dev, struct nfc_target *target, __u32 protocol) { + struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); + + if (ddev->poll_tech_count) { + pr_err("Can't activate a target while polling\n"); + return -EBUSY; + } + + if (ddev->curr_protocol) { + pr_err("A target is already active\n"); + return -EBUSY; + } + + ddev->curr_protocol = protocol; + return 0; } @@ -565,6 +584,11 @@ static void digital_deactivate_target(struct nfc_dev *nfc_dev, { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); + if (!ddev->curr_protocol) { + pr_err("No active target\n"); + return; + } + ddev->curr_protocol = 0; } diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c index 07bbc24fb4c7..d4ed25ff723f 100644 --- a/net/nfc/digital_dep.c +++ b/net/nfc/digital_dep.c @@ -32,7 +32,6 @@ #define DIGITAL_ATR_REQ_MIN_SIZE 16 #define DIGITAL_ATR_REQ_MAX_SIZE 64 -#define DIGITAL_NFCID3_LEN ((u8)8) #define DIGITAL_LR_BITS_PAYLOAD_SIZE_254B 0x30 #define DIGITAL_GB_BIT 0x02 @@ -206,10 +205,9 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev, atr_req->dir = DIGITAL_NFC_DEP_FRAME_DIR_OUT; atr_req->cmd = DIGITAL_CMD_ATR_REQ; if (target->nfcid2_len) - memcpy(atr_req->nfcid3, target->nfcid2, - max(target->nfcid2_len, DIGITAL_NFCID3_LEN)); + memcpy(atr_req->nfcid3, target->nfcid2, NFC_NFCID2_MAXSIZE); else - get_random_bytes(atr_req->nfcid3, DIGITAL_NFCID3_LEN); + get_random_bytes(atr_req->nfcid3, NFC_NFCID3_MAXSIZE); atr_req->did = 0; atr_req->bs = 0; @@ -382,6 +380,33 @@ int digital_in_send_dep_req(struct nfc_digital_dev *ddev, data_exch); } +static void digital_tg_set_rf_tech(struct nfc_digital_dev *ddev, u8 rf_tech) +{ + ddev->curr_rf_tech = rf_tech; + + ddev->skb_add_crc = digital_skb_add_crc_none; + ddev->skb_check_crc = digital_skb_check_crc_none; + + if (DIGITAL_DRV_CAPS_TG_CRC(ddev)) + return; + + switch (ddev->curr_rf_tech) { + case NFC_DIGITAL_RF_TECH_106A: + ddev->skb_add_crc = digital_skb_add_crc_a; + ddev->skb_check_crc = digital_skb_check_crc_a; + break; + + case NFC_DIGITAL_RF_TECH_212F: + case NFC_DIGITAL_RF_TECH_424F: + ddev->skb_add_crc = digital_skb_add_crc_f; + ddev->skb_check_crc = digital_skb_check_crc_f; + break; + + default: + break; + } +} + static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg, struct sk_buff *resp) { @@ -472,11 +497,13 @@ int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb) static void digital_tg_send_psl_res_complete(struct nfc_digital_dev *ddev, void *arg, struct sk_buff *resp) { - u8 rf_tech = PTR_ERR(arg); + u8 rf_tech = (unsigned long)arg; if (IS_ERR(resp)) return; + digital_tg_set_rf_tech(ddev, rf_tech); + digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH, rf_tech); digital_tg_listen(ddev, 1500, digital_tg_recv_dep_req, NULL); @@ -508,7 +535,7 @@ static int digital_tg_send_psl_res(struct nfc_digital_dev *ddev, u8 did, ddev->skb_add_crc(skb); rc = digital_tg_send_cmd(ddev, skb, 0, digital_tg_send_psl_res_complete, - ERR_PTR(rf_tech)); + (void *)(unsigned long)rf_tech); if (rc) kfree_skb(skb); @@ -563,7 +590,7 @@ static void digital_tg_recv_psl_req(struct nfc_digital_dev *ddev, void *arg, rf_tech = NFC_DIGITAL_RF_TECH_424F; break; default: - pr_err("Unsuported dsi value %d\n", dsi); + pr_err("Unsupported dsi value %d\n", dsi); goto exit; } @@ -661,16 +688,10 @@ void digital_tg_recv_atr_req(struct nfc_digital_dev *ddev, void *arg, if (resp->data[0] == DIGITAL_NFC_DEP_NFCA_SOD_SB) { min_size = DIGITAL_ATR_REQ_MIN_SIZE + 2; - - ddev->curr_rf_tech = NFC_DIGITAL_RF_TECH_106A; - ddev->skb_add_crc = digital_skb_add_crc_a; - ddev->skb_check_crc = digital_skb_check_crc_a; + digital_tg_set_rf_tech(ddev, NFC_DIGITAL_RF_TECH_106A); } else { min_size = DIGITAL_ATR_REQ_MIN_SIZE + 1; - - ddev->curr_rf_tech = NFC_DIGITAL_RF_TECH_212F; - ddev->skb_add_crc = digital_skb_add_crc_f; - ddev->skb_check_crc = digital_skb_check_crc_f; + digital_tg_set_rf_tech(ddev, NFC_DIGITAL_RF_TECH_212F); } if (resp->len < min_size) { @@ -678,10 +699,7 @@ void digital_tg_recv_atr_req(struct nfc_digital_dev *ddev, void *arg, goto exit; } - if (DIGITAL_DRV_CAPS_TG_CRC(ddev)) { - ddev->skb_add_crc = digital_skb_add_crc_none; - ddev->skb_check_crc = digital_skb_check_crc_none; - } + ddev->curr_protocol = NFC_PROTO_NFC_DEP_MASK; rc = ddev->skb_check_crc(resp); if (rc) { diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c index 64f922be9281..a9f4d2e62d8d 100644 --- a/net/nfc/hci/command.c +++ b/net/nfc/hci/command.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #define pr_fmt(fmt) "hci: %s: " fmt, __func__ diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index d07ca4c5cf8c..d45b638e77c7 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #define pr_fmt(fmt) "hci: %s: " fmt, __func__ @@ -337,11 +335,8 @@ exit: kfree_skb(skb); exit_noskb: - if (r) { - /* TODO: There was an error dispatching the event, - * how to propagate up to nfc core? - */ - } + if (r) + nfc_hci_driver_failure(hdev, r); } static void nfc_hci_cmd_timeout(unsigned long data) diff --git a/net/nfc/hci/hci.h b/net/nfc/hci/hci.h index b274d12c18ac..c3d2e2c1394c 100644 --- a/net/nfc/hci/hci.h +++ b/net/nfc/hci/hci.h @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef __LOCAL_HCI_H diff --git a/net/nfc/hci/hcp.c b/net/nfc/hci/hcp.c index b6b4109f2343..e9de1514656e 100644 --- a/net/nfc/hci/hcp.c +++ b/net/nfc/hci/hcp.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #define pr_fmt(fmt) "hci: %s: " fmt, __func__ diff --git a/net/nfc/hci/llc.c b/net/nfc/hci/llc.c index fe5e966e5b88..a07d2b818487 100644 --- a/net/nfc/hci/llc.c +++ b/net/nfc/hci/llc.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <net/nfc/llc.h> diff --git a/net/nfc/hci/llc.h b/net/nfc/hci/llc.h index 7be0b7f3ceb6..5dad4c57ffb3 100644 --- a/net/nfc/hci/llc.h +++ b/net/nfc/hci/llc.h @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef __LOCAL_LLC_H_ diff --git a/net/nfc/hci/llc_nop.c b/net/nfc/hci/llc_nop.c index 87b10291b40f..d0435d5a197b 100644 --- a/net/nfc/hci/llc_nop.c +++ b/net/nfc/hci/llc_nop.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/types.h> diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index 27b313befc35..401c7e255273 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -13,9 +13,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #define pr_fmt(fmt) "shdlc: %s: " fmt, __func__ @@ -300,7 +298,7 @@ static void llc_shdlc_rcv_rej(struct llc_shdlc *shdlc, int y_nr) { struct sk_buff *skb; - pr_debug("remote asks retransmition from frame %d\n", y_nr); + pr_debug("remote asks retransmission from frame %d\n", y_nr); if (llc_shdlc_x_lteq_y_lt_z(shdlc->dnr, y_nr, shdlc->ns)) { if (shdlc->t2_active) { diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h index f4d48b57ea11..de1789e3cc82 100644 --- a/net/nfc/llcp.h +++ b/net/nfc/llcp.h @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ enum llcp_state { diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 1017894807c0..bec6ed15f503 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #define pr_fmt(fmt) "llcp: %s: " fmt, __func__ @@ -677,7 +675,7 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, do { remote_miu = sock->remote_miu > LLCP_MAX_MIU ? - local->remote_miu : sock->remote_miu; + LLCP_DEFAULT_MIU : sock->remote_miu; frag_len = min_t(size_t, remote_miu, remaining_len); @@ -686,8 +684,10 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock, pdu = llcp_allocate_pdu(sock, LLCP_PDU_I, frag_len + LLCP_SEQUENCE_SIZE); - if (pdu == NULL) + if (pdu == NULL) { + kfree(msg_data); return -ENOMEM; + } skb_put(pdu, LLCP_SEQUENCE_SIZE); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 81cd3416c7d4..6184bd1fba3a 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #define pr_fmt(fmt) "llcp: %s: " fmt, __func__ @@ -945,7 +943,6 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, new_sock->local = nfc_llcp_local_get(local); new_sock->rw = sock->rw; new_sock->miux = sock->miux; - new_sock->remote_miu = local->remote_miu; new_sock->nfc_protocol = sock->nfc_protocol; new_sock->dsap = ssap; new_sock->target_idx = local->target_idx; diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 824c6056bf82..51f077a92fa9 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -12,9 +12,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #define pr_fmt(fmt) "llcp: %s: " fmt, __func__ @@ -702,7 +700,6 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, llcp_sock->dev = dev; llcp_sock->local = nfc_llcp_local_get(local); - llcp_sock->remote_miu = llcp_sock->local->remote_miu; llcp_sock->ssap = nfc_llcp_get_local_ssap(local); if (llcp_sock->ssap == LLCP_SAP_MAX) { ret = -ENOMEM; @@ -772,8 +769,8 @@ static int llcp_sock_sendmsg(struct kiocb *iocb, struct socket *sock, lock_sock(sk); if (sk->sk_type == SOCK_DGRAM) { - struct sockaddr_nfc_llcp *addr = - (struct sockaddr_nfc_llcp *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, addr, + msg->msg_name); if (msg->msg_namelen < sizeof(*addr)) { release_sock(sk); @@ -845,8 +842,8 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (sk->sk_type == SOCK_DGRAM && msg->msg_name) { struct nfc_llcp_ui_cb *ui_cb = nfc_llcp_ui_skb_cb(skb); - struct sockaddr_nfc_llcp *sockaddr = - (struct sockaddr_nfc_llcp *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, sockaddr, + msg->msg_name); msg->msg_namelen = sizeof(struct sockaddr_nfc_llcp); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index b943d46a1644..46bda010bf11 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -20,8 +20,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ @@ -302,6 +301,9 @@ static int nci_open_device(struct nci_dev *ndev) rc = __nci_request(ndev, nci_reset_req, 0, msecs_to_jiffies(NCI_RESET_TIMEOUT)); + if (ndev->ops->setup(ndev)) + ndev->ops->setup(ndev); + if (!rc) { rc = __nci_request(ndev, nci_init_req, 0, msecs_to_jiffies(NCI_INIT_TIMEOUT)); @@ -362,6 +364,8 @@ static int nci_close_device(struct nci_dev *ndev) msecs_to_jiffies(NCI_RESET_TIMEOUT)); clear_bit(NCI_INIT, &ndev->flags); + del_timer_sync(&ndev->cmd_timer); + /* Flush cmd wq */ flush_workqueue(ndev->cmd_wq); @@ -409,12 +413,26 @@ static int nci_dev_down(struct nfc_dev *nfc_dev) return nci_close_device(ndev); } +int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val) +{ + struct nci_set_config_param param; + + if (!val || !len) + return 0; + + param.id = id; + param.len = len; + param.val = val; + + return __nci_request(ndev, nci_set_config_req, (unsigned long)¶m, + msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT)); +} +EXPORT_SYMBOL(nci_set_config); + static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); struct nci_set_config_param param; - __u8 local_gb[NFC_MAX_GT_LEN]; - int i; param.val = nfc_get_local_general_bytes(nfc_dev, ¶m.len); if ((param.val == NULL) || (param.len == 0)) @@ -423,11 +441,7 @@ static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev) if (param.len > NFC_MAX_GT_LEN) return -EINVAL; - for (i = 0; i < param.len; i++) - local_gb[param.len-1-i] = param.val[i]; - param.id = NCI_PN_ATR_REQ_GEN_BYTES; - param.val = local_gb; return nci_request(ndev, nci_set_config_req, (unsigned long)¶m, msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT)); diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index 2a9399dd6c68..6c3aef852876 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -16,8 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/nfc/nci/lib.c b/net/nfc/nci/lib.c index 6b7fd26c68d9..ed774a2e989a 100644 --- a/net/nfc/nci/lib.c +++ b/net/nfc/nci/lib.c @@ -20,8 +20,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index b2aa98ef0927..1e905097456b 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -20,8 +20,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c index dd072f38ad00..041de51ccdbe 100644 --- a/net/nfc/nci/rsp.c +++ b/net/nfc/nci/rsp.c @@ -20,8 +20,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index a9b2342d5253..ebbf6fb88b35 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -16,9 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index aaf606fc1faa..9d6e74f7e6b3 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -16,9 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef __LOCAL_NFC_H diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 66bcd2eb5773..c27a6e86cae4 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -16,9 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 65cfaa816075..2c77e7b1a913 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -165,7 +165,7 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, } csum_replace4(&nh->check, *addr, new_addr); - skb->rxhash = 0; + skb_clear_hash(skb); *addr = new_addr; } @@ -199,7 +199,7 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto, if (recalculate_csum) update_ipv6_checksum(skb, l4_proto, addr, new_addr); - skb->rxhash = 0; + skb_clear_hash(skb); memcpy(addr, new_addr, sizeof(__be32[4])); } @@ -296,7 +296,7 @@ static void set_tp_port(struct sk_buff *skb, __be16 *port, { inet_proto_csum_replace2(check, skb, *port, new_port, 0); *port = new_port; - skb->rxhash = 0; + skb_clear_hash(skb); } static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port) @@ -310,7 +310,7 @@ static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port) uh->check = CSUM_MANGLED_0; } else { *port = new_port; - skb->rxhash = 0; + skb_clear_hash(skb); } } @@ -381,7 +381,7 @@ static int set_sctp(struct sk_buff *skb, /* Carry any checksum errors through. */ sh->checksum = old_csum ^ old_correct_csum ^ new_csum; - skb->rxhash = 0; + skb_clear_hash(skb); } return 0; @@ -445,7 +445,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb, a = nla_next(a, &rem)) { switch (nla_type(a)) { case OVS_SAMPLE_ATTR_PROBABILITY: - if (net_random() >= nla_get_u32(a)) + if (prandom_u32() >= nla_get_u32(a)) return 0; break; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 6f5e1dd3be2d..e9a48baf8551 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -55,6 +55,7 @@ #include "datapath.h" #include "flow.h" +#include "flow_table.h" #include "flow_netlink.h" #include "vport-internal_dev.h" #include "vport-netdev.h" @@ -108,10 +109,9 @@ int lockdep_ovsl_is_held(void) #endif static struct vport *new_vport(const struct vport_parms *); -static int queue_gso_packets(struct net *, int dp_ifindex, struct sk_buff *, +static int queue_gso_packets(struct datapath *dp, struct sk_buff *, const struct dp_upcall_info *); -static int queue_userspace_packet(struct net *, int dp_ifindex, - struct sk_buff *, +static int queue_userspace_packet(struct datapath *dp, struct sk_buff *, const struct dp_upcall_info *); /* Must be called with rcu_read_lock or ovs_mutex. */ @@ -133,7 +133,7 @@ static struct datapath *get_dp(struct net *net, int dp_ifindex) } /* Must be called with rcu_read_lock or ovs_mutex. */ -const char *ovs_dp_name(const struct datapath *dp) +static const char *ovs_dp_name(const struct datapath *dp) { struct vport *vport = ovs_vport_ovsl_rcu(dp, OVSP_LOCAL); return vport->ops->get_name(vport); @@ -161,7 +161,6 @@ static void destroy_dp_rcu(struct rcu_head *rcu) { struct datapath *dp = container_of(rcu, struct datapath, rcu); - ovs_flow_tbl_destroy(&dp->table); free_percpu(dp->stats_percpu); release_net(ovs_dp_get_net(dp)); kfree(dp->ports); @@ -234,7 +233,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb) } /* Look up flow. */ - flow = ovs_flow_tbl_lookup(&dp->table, &key, &n_mask_hit); + flow = ovs_flow_tbl_lookup_stats(&dp->table, &key, &n_mask_hit); if (unlikely(!flow)) { struct dp_upcall_info upcall; @@ -251,9 +250,9 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb) OVS_CB(skb)->flow = flow; OVS_CB(skb)->pkt_key = &key; - stats_counter = &stats->n_hit; - ovs_flow_used(OVS_CB(skb)->flow, skb); + ovs_flow_stats_update(OVS_CB(skb)->flow, skb); ovs_execute_actions(dp, skb); + stats_counter = &stats->n_hit; out: /* Update datapath statistics. */ @@ -277,7 +276,6 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, const struct dp_upcall_info *upcall_info) { struct dp_stats_percpu *stats; - int dp_ifindex; int err; if (upcall_info->portid == 0) { @@ -285,16 +283,10 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, goto err; } - dp_ifindex = get_dpifindex(dp); - if (!dp_ifindex) { - err = -ENODEV; - goto err; - } - if (!skb_is_gso(skb)) - err = queue_userspace_packet(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info); + err = queue_userspace_packet(dp, skb, upcall_info); else - err = queue_gso_packets(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info); + err = queue_gso_packets(dp, skb, upcall_info); if (err) goto err; @@ -310,8 +302,7 @@ err: return err; } -static int queue_gso_packets(struct net *net, int dp_ifindex, - struct sk_buff *skb, +static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, const struct dp_upcall_info *upcall_info) { unsigned short gso_type = skb_shinfo(skb)->gso_type; @@ -320,14 +311,14 @@ static int queue_gso_packets(struct net *net, int dp_ifindex, struct sk_buff *segs, *nskb; int err; - segs = __skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM, false); + segs = __skb_gso_segment(skb, NETIF_F_SG, false); if (IS_ERR(segs)) return PTR_ERR(segs); /* Queue all of the segments. */ skb = segs; do { - err = queue_userspace_packet(net, dp_ifindex, skb, upcall_info); + err = queue_userspace_packet(dp, skb, upcall_info); if (err) break; @@ -380,11 +371,11 @@ static size_t key_attr_size(void) + nla_total_size(28); /* OVS_KEY_ATTR_ND */ } -static size_t upcall_msg_size(const struct sk_buff *skb, - const struct nlattr *userdata) +static size_t upcall_msg_size(const struct nlattr *userdata, + unsigned int hdrlen) { size_t size = NLMSG_ALIGN(sizeof(struct ovs_header)) - + nla_total_size(skb->len) /* OVS_PACKET_ATTR_PACKET */ + + nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */ + nla_total_size(key_attr_size()); /* OVS_PACKET_ATTR_KEY */ /* OVS_PACKET_ATTR_USERDATA */ @@ -394,15 +385,24 @@ static size_t upcall_msg_size(const struct sk_buff *skb, return size; } -static int queue_userspace_packet(struct net *net, int dp_ifindex, - struct sk_buff *skb, +static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, const struct dp_upcall_info *upcall_info) { struct ovs_header *upcall; struct sk_buff *nskb = NULL; struct sk_buff *user_skb; /* to be queued to userspace */ struct nlattr *nla; - int err; + struct genl_info info = { + .dst_sk = ovs_dp_get_net(dp)->genl_sock, + .snd_portid = upcall_info->portid, + }; + size_t len; + unsigned int hlen; + int err, dp_ifindex; + + dp_ifindex = get_dpifindex(dp); + if (!dp_ifindex) + return -ENODEV; if (vlan_tx_tag_present(skb)) { nskb = skb_clone(skb, GFP_ATOMIC); @@ -422,7 +422,22 @@ static int queue_userspace_packet(struct net *net, int dp_ifindex, goto out; } - user_skb = genlmsg_new(upcall_msg_size(skb, upcall_info->userdata), GFP_ATOMIC); + /* Complete checksum if needed */ + if (skb->ip_summed == CHECKSUM_PARTIAL && + (err = skb_checksum_help(skb))) + goto out; + + /* Older versions of OVS user space enforce alignment of the last + * Netlink attribute to NLA_ALIGNTO which would require extensive + * padding logic. Only perform zerocopy if padding is not required. + */ + if (dp->user_features & OVS_DP_F_UNALIGNED) + hlen = skb_zerocopy_headlen(skb); + else + hlen = skb->len; + + len = upcall_msg_size(upcall_info->userdata, hlen); + user_skb = genlmsg_new_unicast(len, &info, GFP_ATOMIC); if (!user_skb) { err = -ENOMEM; goto out; @@ -441,26 +456,32 @@ static int queue_userspace_packet(struct net *net, int dp_ifindex, nla_len(upcall_info->userdata), nla_data(upcall_info->userdata)); - nla = __nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, skb->len); + /* Only reserve room for attribute header, packet data is added + * in skb_zerocopy() */ + if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) { + err = -ENOBUFS; + goto out; + } + nla->nla_len = nla_attr_size(skb->len); - skb_copy_and_csum_dev(skb, nla_data(nla)); + skb_zerocopy(user_skb, skb, skb->len, hlen); + + /* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */ + if (!(dp->user_features & OVS_DP_F_UNALIGNED)) { + size_t plen = NLA_ALIGN(user_skb->len) - user_skb->len; + + if (plen > 0) + memset(skb_put(user_skb, plen), 0, plen); + } - genlmsg_end(user_skb, upcall); - err = genlmsg_unicast(net, user_skb, upcall_info->portid); + ((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len; + err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid); out: kfree_skb(nskb); return err; } -static void clear_stats(struct sw_flow *flow) -{ - flow->used = 0; - flow->tcp_flags = 0; - flow->packet_count = 0; - flow->byte_count = 0; -} - static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) { struct ovs_header *ovs_header = info->userhdr; @@ -499,7 +520,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) packet->protocol = htons(ETH_P_802_2); /* Build an sw_flow for sending this packet. */ - flow = ovs_flow_alloc(); + flow = ovs_flow_alloc(false); err = PTR_ERR(flow); if (IS_ERR(flow)) goto err_kfree_skb; @@ -635,10 +656,10 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, const int skb_orig_len = skb->len; struct nlattr *start; struct ovs_flow_stats stats; + __be16 tcp_flags; + unsigned long used; struct ovs_header *ovs_header; struct nlattr *nla; - unsigned long used; - u8 tcp_flags; int err; ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family, flags, cmd); @@ -667,24 +688,17 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, nla_nest_end(skb, nla); - spin_lock_bh(&flow->lock); - used = flow->used; - stats.n_packets = flow->packet_count; - stats.n_bytes = flow->byte_count; - tcp_flags = (u8)ntohs(flow->tcp_flags); - spin_unlock_bh(&flow->lock); - + ovs_flow_stats_get(flow, &stats, &used, &tcp_flags); if (used && nla_put_u64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used))) goto nla_put_failure; if (stats.n_packets && - nla_put(skb, OVS_FLOW_ATTR_STATS, - sizeof(struct ovs_flow_stats), &stats)) + nla_put(skb, OVS_FLOW_ATTR_STATS, sizeof(struct ovs_flow_stats), &stats)) goto nla_put_failure; - if (tcp_flags && - nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, tcp_flags)) + if ((u8)ntohs(tcp_flags) && + nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, (u8)ntohs(tcp_flags))) goto nla_put_failure; /* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if @@ -701,8 +715,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, if (start) { const struct sw_flow_actions *sf_acts; - sf_acts = rcu_dereference_check(flow->sf_acts, - lockdep_ovsl_is_held()); + sf_acts = rcu_dereference_ovsl(flow->sf_acts); err = ovs_nla_put_actions(sf_acts->actions, sf_acts->actions_len, skb); @@ -726,39 +739,34 @@ error: return err; } -static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow) +static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow, + struct genl_info *info) { - const struct sw_flow_actions *sf_acts; + size_t len; - sf_acts = ovsl_dereference(flow->sf_acts); + len = ovs_flow_cmd_msg_size(ovsl_dereference(flow->sf_acts)); - return genlmsg_new(ovs_flow_cmd_msg_size(sf_acts), GFP_KERNEL); + return genlmsg_new_unicast(len, info, GFP_KERNEL); } static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow, struct datapath *dp, - u32 portid, u32 seq, u8 cmd) + struct genl_info *info, + u8 cmd) { struct sk_buff *skb; int retval; - skb = ovs_flow_cmd_alloc_info(flow); + skb = ovs_flow_cmd_alloc_info(flow, info); if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_flow_cmd_fill_info(flow, dp, skb, portid, seq, 0, cmd); + retval = ovs_flow_cmd_fill_info(flow, dp, skb, info->snd_portid, + info->snd_seq, 0, cmd); BUG_ON(retval < 0); return skb; } -static struct sw_flow *__ovs_flow_tbl_lookup(struct flow_table *tbl, - const struct sw_flow_key *key) -{ - u32 __always_unused n_mask_hit; - - return ovs_flow_tbl_lookup(tbl, key, &n_mask_hit); -} - static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; @@ -770,6 +778,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; struct sw_flow_actions *acts = NULL; struct sw_flow_match match; + bool exact_5tuple; int error; /* Extract key. */ @@ -778,7 +787,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) goto error; ovs_match_init(&match, &key, &mask); - error = ovs_nla_get_match(&match, + error = ovs_nla_get_match(&match, &exact_5tuple, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]); if (error) goto error; @@ -809,7 +818,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) goto err_unlock_ovs; /* Check if this is a duplicate flow */ - flow = __ovs_flow_tbl_lookup(&dp->table, &key); + flow = ovs_flow_tbl_lookup(&dp->table, &key); if (!flow) { /* Bail out if we're not allowed to create a new flow. */ error = -ENOENT; @@ -817,12 +826,11 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) goto err_unlock_ovs; /* Allocate flow. */ - flow = ovs_flow_alloc(); + flow = ovs_flow_alloc(!exact_5tuple); if (IS_ERR(flow)) { error = PTR_ERR(flow); goto err_unlock_ovs; } - clear_stats(flow); flow->key = masked_key; flow->unmasked_key = key; @@ -835,8 +843,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) goto err_flow_free; } - reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid, - info->snd_seq, OVS_FLOW_CMD_NEW); + reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW); } else { /* We found a matching flow. */ struct sw_flow_actions *old_acts; @@ -853,26 +860,19 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) goto err_unlock_ovs; /* The unmasked key has to be the same for flow updates. */ - error = -EINVAL; - if (!ovs_flow_cmp_unmasked_key(flow, &match)) { - OVS_NLERR("Flow modification message rejected, unmasked key does not match.\n"); + if (!ovs_flow_cmp_unmasked_key(flow, &match)) goto err_unlock_ovs; - } /* Update actions. */ old_acts = ovsl_dereference(flow->sf_acts); rcu_assign_pointer(flow->sf_acts, acts); ovs_nla_free_flow_actions(old_acts); - reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid, - info->snd_seq, OVS_FLOW_CMD_NEW); + reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW); /* Clear stats. */ - if (a[OVS_FLOW_ATTR_CLEAR]) { - spin_lock_bh(&flow->lock); - clear_stats(flow); - spin_unlock_bh(&flow->lock); - } + if (a[OVS_FLOW_ATTR_CLEAR]) + ovs_flow_stats_clear(flow); } ovs_unlock(); @@ -910,7 +910,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) } ovs_match_init(&match, &key, NULL); - err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL); + err = ovs_nla_get_match(&match, NULL, a[OVS_FLOW_ATTR_KEY], NULL); if (err) return err; @@ -921,14 +921,13 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) goto unlock; } - flow = __ovs_flow_tbl_lookup(&dp->table, &key); + flow = ovs_flow_tbl_lookup(&dp->table, &key); if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) { err = -ENOENT; goto unlock; } - reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid, - info->snd_seq, OVS_FLOW_CMD_NEW); + reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW); if (IS_ERR(reply)) { err = PTR_ERR(reply); goto unlock; @@ -965,17 +964,17 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) } ovs_match_init(&match, &key, NULL); - err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL); + err = ovs_nla_get_match(&match, NULL, a[OVS_FLOW_ATTR_KEY], NULL); if (err) goto unlock; - flow = __ovs_flow_tbl_lookup(&dp->table, &key); + flow = ovs_flow_tbl_lookup(&dp->table, &key); if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) { err = -ENOENT; goto unlock; } - reply = ovs_flow_cmd_alloc_info(flow); + reply = ovs_flow_cmd_alloc_info(flow, info); if (!reply) { err = -ENOMEM; goto unlock; @@ -1061,6 +1060,7 @@ static const struct genl_ops dp_flow_genl_ops[] = { static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { [OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 }, + [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, }; static struct genl_family dp_datapath_genl_family = { @@ -1084,6 +1084,7 @@ static size_t ovs_dp_cmd_msg_size(void) msgsize += nla_total_size(IFNAMSIZ); msgsize += nla_total_size(sizeof(struct ovs_dp_stats)); msgsize += nla_total_size(sizeof(struct ovs_dp_megaflow_stats)); + msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */ return msgsize; } @@ -1119,6 +1120,9 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, &dp_megaflow_stats)) goto nla_put_failure; + if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features)) + goto nla_put_failure; + return genlmsg_end(skb, ovs_header); nla_put_failure: @@ -1127,17 +1131,17 @@ error: return -EMSGSIZE; } -static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 portid, - u32 seq, u8 cmd) +static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, + struct genl_info *info, u8 cmd) { struct sk_buff *skb; int retval; - skb = genlmsg_new(ovs_dp_cmd_msg_size(), GFP_KERNEL); + skb = genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_dp_cmd_fill_info(dp, skb, portid, seq, 0, cmd); + retval = ovs_dp_cmd_fill_info(dp, skb, info->snd_portid, info->snd_seq, 0, cmd); if (retval < 0) { kfree_skb(skb); return ERR_PTR(retval); @@ -1165,6 +1169,24 @@ static struct datapath *lookup_datapath(struct net *net, return dp ? dp : ERR_PTR(-ENODEV); } +static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *info) +{ + struct datapath *dp; + + dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + if (!dp) + return; + + WARN(dp->user_features, "Dropping previously announced user features\n"); + dp->user_features = 0; +} + +static void ovs_dp_change(struct datapath *dp, struct nlattr **a) +{ + if (a[OVS_DP_ATTR_USER_FEATURES]) + dp->user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]); +} + static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; @@ -1223,17 +1245,27 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.port_no = OVSP_LOCAL; parms.upcall_portid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]); + ovs_dp_change(dp, a); + vport = new_vport(&parms); if (IS_ERR(vport)) { err = PTR_ERR(vport); if (err == -EBUSY) err = -EEXIST; + if (err == -EEXIST) { + /* An outdated user space instance that does not understand + * the concept of user_features has attempted to create a new + * datapath and is likely to reuse it. Drop all user features. + */ + if (info->genlhdr->version < OVS_DP_VER_FEATURES) + ovs_dp_reset_user_features(skb, info); + } + goto err_destroy_ports_array; } - reply = ovs_dp_cmd_build_info(dp, info->snd_portid, - info->snd_seq, OVS_DP_CMD_NEW); + reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW); err = PTR_ERR(reply); if (IS_ERR(reply)) goto err_destroy_local_port; @@ -1253,7 +1285,7 @@ err_destroy_ports_array: err_destroy_percpu: free_percpu(dp->stats_percpu); err_destroy_table: - ovs_flow_tbl_destroy(&dp->table); + ovs_flow_tbl_destroy(&dp->table, false); err_free_dp: release_net(ovs_dp_get_net(dp)); kfree(dp); @@ -1280,10 +1312,13 @@ static void __dp_destroy(struct datapath *dp) list_del_rcu(&dp->list_node); /* OVSP_LOCAL is datapath internal port. We need to make sure that - * all port in datapath are destroyed first before freeing datapath. + * all ports in datapath are destroyed first before freeing datapath. */ ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL)); + /* RCU destroy the flow table */ + ovs_flow_tbl_destroy(&dp->table, true); + call_rcu(&dp->rcu, destroy_dp_rcu); } @@ -1299,8 +1334,7 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(dp)) goto unlock; - reply = ovs_dp_cmd_build_info(dp, info->snd_portid, - info->snd_seq, OVS_DP_CMD_DEL); + reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_DEL); err = PTR_ERR(reply); if (IS_ERR(reply)) goto unlock; @@ -1328,8 +1362,9 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(dp)) goto unlock; - reply = ovs_dp_cmd_build_info(dp, info->snd_portid, - info->snd_seq, OVS_DP_CMD_NEW); + ovs_dp_change(dp, info->attrs); + + reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW); if (IS_ERR(reply)) { err = PTR_ERR(reply); genl_set_err(&dp_datapath_genl_family, sock_net(skb->sk), 0, @@ -1360,8 +1395,7 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) goto unlock; } - reply = ovs_dp_cmd_build_info(dp, info->snd_portid, - info->snd_seq, OVS_DP_CMD_NEW); + reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW); if (IS_ERR(reply)) { err = PTR_ERR(reply); goto unlock; @@ -1441,7 +1475,7 @@ struct genl_family dp_vport_genl_family = { .parallel_ops = true, }; -struct genl_multicast_group ovs_dp_vport_multicast_group = { +static struct genl_multicast_group ovs_dp_vport_multicast_group = { .name = OVS_VPORT_MCGROUP }; diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 4067ea41be28..6be9fbb5e9cb 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -88,6 +88,8 @@ struct datapath { /* Network namespace ref. */ struct net *net; #endif + + u32 user_features; }; /** @@ -145,6 +147,8 @@ int lockdep_ovsl_is_held(void); #define ASSERT_OVSL() WARN_ON(unlikely(!lockdep_ovsl_is_held())) #define ovsl_dereference(p) \ rcu_dereference_protected(p, lockdep_ovsl_is_held()) +#define rcu_dereference_ovsl(p) \ + rcu_dereference_check(p, lockdep_ovsl_is_held()) static inline struct net *ovs_dp_get_net(struct datapath *dp) { @@ -178,14 +182,12 @@ static inline struct vport *ovs_vport_ovsl(const struct datapath *dp, int port_n extern struct notifier_block ovs_dp_device_notifier; extern struct genl_family dp_vport_genl_family; -extern struct genl_multicast_group ovs_dp_vport_multicast_group; void ovs_dp_process_received_packet(struct vport *, struct sk_buff *); void ovs_dp_detach_port(struct vport *); int ovs_dp_upcall(struct datapath *, struct sk_buff *, const struct dp_upcall_info *); -const char *ovs_dp_name(const struct datapath *dp); struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq, u8 cmd); diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index b409f5279601..16f4b46161d4 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -35,6 +35,7 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/sctp.h> +#include <linux/smp.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/icmp.h> @@ -60,10 +61,16 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies) #define TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF)) -void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb) +void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb) { + struct flow_stats *stats; __be16 tcp_flags = 0; + if (!flow->stats.is_percpu) + stats = flow->stats.stat; + else + stats = this_cpu_ptr(flow->stats.cpu_stats); + if ((flow->key.eth.type == htons(ETH_P_IP) || flow->key.eth.type == htons(ETH_P_IPV6)) && flow->key.ip.proto == IPPROTO_TCP && @@ -71,12 +78,87 @@ void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb) tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb)); } - spin_lock(&flow->lock); - flow->used = jiffies; - flow->packet_count++; - flow->byte_count += skb->len; - flow->tcp_flags |= tcp_flags; - spin_unlock(&flow->lock); + spin_lock(&stats->lock); + stats->used = jiffies; + stats->packet_count++; + stats->byte_count += skb->len; + stats->tcp_flags |= tcp_flags; + spin_unlock(&stats->lock); +} + +static void stats_read(struct flow_stats *stats, + struct ovs_flow_stats *ovs_stats, + unsigned long *used, __be16 *tcp_flags) +{ + spin_lock(&stats->lock); + if (time_after(stats->used, *used)) + *used = stats->used; + *tcp_flags |= stats->tcp_flags; + ovs_stats->n_packets += stats->packet_count; + ovs_stats->n_bytes += stats->byte_count; + spin_unlock(&stats->lock); +} + +void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats, + unsigned long *used, __be16 *tcp_flags) +{ + int cpu, cur_cpu; + + *used = 0; + *tcp_flags = 0; + memset(ovs_stats, 0, sizeof(*ovs_stats)); + + if (!flow->stats.is_percpu) { + stats_read(flow->stats.stat, ovs_stats, used, tcp_flags); + } else { + cur_cpu = get_cpu(); + for_each_possible_cpu(cpu) { + struct flow_stats *stats; + + if (cpu == cur_cpu) + local_bh_disable(); + + stats = per_cpu_ptr(flow->stats.cpu_stats, cpu); + stats_read(stats, ovs_stats, used, tcp_flags); + + if (cpu == cur_cpu) + local_bh_enable(); + } + put_cpu(); + } +} + +static void stats_reset(struct flow_stats *stats) +{ + spin_lock(&stats->lock); + stats->used = 0; + stats->packet_count = 0; + stats->byte_count = 0; + stats->tcp_flags = 0; + spin_unlock(&stats->lock); +} + +void ovs_flow_stats_clear(struct sw_flow *flow) +{ + int cpu, cur_cpu; + + if (!flow->stats.is_percpu) { + stats_reset(flow->stats.stat); + } else { + cur_cpu = get_cpu(); + + for_each_possible_cpu(cpu) { + + if (cpu == cur_cpu) + local_bh_disable(); + + stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu)); + + if (cpu == cur_cpu) + local_bh_enable(); + } + put_cpu(); + } } static int check_header(struct sk_buff *skb, int len) diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 1510f51dbf74..2d770e28a3a3 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -19,6 +19,7 @@ #ifndef FLOW_H #define FLOW_H 1 +#include <linux/cache.h> #include <linux/kernel.h> #include <linux/netlink.h> #include <linux/openvswitch.h> @@ -122,8 +123,8 @@ struct sw_flow_key { } __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */ struct sw_flow_key_range { - size_t start; - size_t end; + unsigned short int start; + unsigned short int end; }; struct sw_flow_mask { @@ -146,6 +147,22 @@ struct sw_flow_actions { struct nlattr actions[]; }; +struct flow_stats { + u64 packet_count; /* Number of packets matched. */ + u64 byte_count; /* Number of bytes matched. */ + unsigned long used; /* Last used time (in jiffies). */ + spinlock_t lock; /* Lock for atomic stats update. */ + __be16 tcp_flags; /* Union of seen TCP flags. */ +}; + +struct sw_flow_stats { + bool is_percpu; + union { + struct flow_stats *stat; + struct flow_stats __percpu *cpu_stats; + }; +}; + struct sw_flow { struct rcu_head rcu; struct hlist_node hash_node[2]; @@ -155,12 +172,7 @@ struct sw_flow { struct sw_flow_key unmasked_key; struct sw_flow_mask *mask; struct sw_flow_actions __rcu *sf_acts; - - spinlock_t lock; /* Lock for values below. */ - unsigned long used; /* Last used time (in jiffies). */ - u64 packet_count; /* Number of packets matched. */ - u64 byte_count; /* Number of bytes matched. */ - __be16 tcp_flags; /* Union of seen TCP flags. */ + struct sw_flow_stats stats; }; struct arp_eth_header { @@ -177,7 +189,10 @@ struct arp_eth_header { unsigned char ar_tip[4]; /* target IP address */ } __packed; -void ovs_flow_used(struct sw_flow *, struct sk_buff *); +void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb); +void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *stats, + unsigned long *used, __be16 *tcp_flags); +void ovs_flow_stats_clear(struct sw_flow *flow); u64 ovs_flow_used_time(unsigned long flow_jiffies); int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 2bc1bc1aca3b..4d000acaed0d 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -266,6 +266,20 @@ static bool is_all_zero(const u8 *fp, size_t size) return true; } +static bool is_all_set(const u8 *fp, size_t size) +{ + int i; + + if (!fp) + return false; + + for (i = 0; i < size; i++) + if (fp[i] != 0xff) + return false; + + return true; +} + static int __parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[], u64 *attrsp, bool nz) @@ -487,8 +501,9 @@ static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs, return 0; } -static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, - const struct nlattr **a, bool is_mask) +static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple, + u64 attrs, const struct nlattr **a, + bool is_mask) { int err; u64 orig_attrs = attrs; @@ -545,6 +560,11 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask); } + if (is_mask && exact_5tuple) { + if (match->mask->key.eth.type != htons(0xffff)) + *exact_5tuple = false; + } + if (attrs & (1 << OVS_KEY_ATTR_IPV4)) { const struct ovs_key_ipv4 *ipv4_key; @@ -567,6 +587,13 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, SW_FLOW_KEY_PUT(match, ipv4.addr.dst, ipv4_key->ipv4_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_IPV4); + + if (is_mask && exact_5tuple && *exact_5tuple) { + if (ipv4_key->ipv4_proto != 0xff || + ipv4_key->ipv4_src != htonl(0xffffffff) || + ipv4_key->ipv4_dst != htonl(0xffffffff)) + *exact_5tuple = false; + } } if (attrs & (1 << OVS_KEY_ATTR_IPV6)) { @@ -598,6 +625,13 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_IPV6); + + if (is_mask && exact_5tuple && *exact_5tuple) { + if (ipv6_key->ipv6_proto != 0xff || + !is_all_set((u8 *)ipv6_key->ipv6_src, sizeof(match->key->ipv6.addr.src)) || + !is_all_set((u8 *)ipv6_key->ipv6_dst, sizeof(match->key->ipv6.addr.dst))) + *exact_5tuple = false; + } } if (attrs & (1 << OVS_KEY_ATTR_ARP)) { @@ -640,6 +674,11 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, tcp_key->tcp_dst, is_mask); } attrs &= ~(1 << OVS_KEY_ATTR_TCP); + + if (is_mask && exact_5tuple && *exact_5tuple && + (tcp_key->tcp_src != htons(0xffff) || + tcp_key->tcp_dst != htons(0xffff))) + *exact_5tuple = false; } if (attrs & (1 << OVS_KEY_ATTR_TCP_FLAGS)) { @@ -671,6 +710,11 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, udp_key->udp_dst, is_mask); } attrs &= ~(1 << OVS_KEY_ATTR_UDP); + + if (is_mask && exact_5tuple && *exact_5tuple && + (udp_key->udp_src != htons(0xffff) || + udp_key->udp_dst != htons(0xffff))) + *exact_5tuple = false; } if (attrs & (1 << OVS_KEY_ATTR_SCTP)) { @@ -756,6 +800,7 @@ static void sw_flow_mask_set(struct sw_flow_mask *mask, * attribute specifies the mask field of the wildcarded flow. */ int ovs_nla_get_match(struct sw_flow_match *match, + bool *exact_5tuple, const struct nlattr *key, const struct nlattr *mask) { @@ -803,10 +848,13 @@ int ovs_nla_get_match(struct sw_flow_match *match, } } - err = ovs_key_from_nlattrs(match, key_attrs, a, false); + err = ovs_key_from_nlattrs(match, NULL, key_attrs, a, false); if (err) return err; + if (exact_5tuple) + *exact_5tuple = true; + if (mask) { err = parse_flow_mask_nlattrs(mask, a, &mask_attrs); if (err) @@ -844,7 +892,7 @@ int ovs_nla_get_match(struct sw_flow_match *match, } } - err = ovs_key_from_nlattrs(match, mask_attrs, a, true); + err = ovs_key_from_nlattrs(match, exact_5tuple, mask_attrs, a, true); if (err) return err; } else { @@ -1128,19 +1176,11 @@ struct sw_flow_actions *ovs_nla_alloc_flow_actions(int size) return sfa; } -/* RCU callback used by ovs_nla_free_flow_actions. */ -static void rcu_free_acts_callback(struct rcu_head *rcu) -{ - struct sw_flow_actions *sf_acts = container_of(rcu, - struct sw_flow_actions, rcu); - kfree(sf_acts); -} - /* Schedules 'sf_acts' to be freed after the next RCU grace period. * The caller must hold rcu_read_lock for this to be sensible. */ void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) { - call_rcu(&sf_acts->rcu, rcu_free_acts_callback); + kfree_rcu(sf_acts, rcu); } static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 440151045d39..b31fbe28bc7a 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -45,6 +45,7 @@ int ovs_nla_put_flow(const struct sw_flow_key *, int ovs_nla_get_flow_metadata(struct sw_flow *flow, const struct nlattr *attr); int ovs_nla_get_match(struct sw_flow_match *match, + bool *exact_5tuple, const struct nlattr *, const struct nlattr *); diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index e42542706087..3c268b3d71c3 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -25,7 +25,7 @@ #include <linux/if_vlan.h> #include <net/llc_pdu.h> #include <linux/kernel.h> -#include <linux/jhash.h> +#include <linux/hash.h> #include <linux/jiffies.h> #include <linux/llc.h> #include <linux/module.h> @@ -44,8 +44,6 @@ #include <net/ipv6.h> #include <net/ndisc.h> -#include "datapath.h" - #define TBL_MIN_BUCKETS 1024 #define REHASH_INTERVAL (10 * 60 * HZ) @@ -72,19 +70,42 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, *d++ = *s++ & *m++; } -struct sw_flow *ovs_flow_alloc(void) +struct sw_flow *ovs_flow_alloc(bool percpu_stats) { struct sw_flow *flow; + int cpu; flow = kmem_cache_alloc(flow_cache, GFP_KERNEL); if (!flow) return ERR_PTR(-ENOMEM); - spin_lock_init(&flow->lock); flow->sf_acts = NULL; flow->mask = NULL; + flow->stats.is_percpu = percpu_stats; + + if (!percpu_stats) { + flow->stats.stat = kzalloc(sizeof(*flow->stats.stat), GFP_KERNEL); + if (!flow->stats.stat) + goto err; + + spin_lock_init(&flow->stats.stat->lock); + } else { + flow->stats.cpu_stats = alloc_percpu(struct flow_stats); + if (!flow->stats.cpu_stats) + goto err; + + for_each_possible_cpu(cpu) { + struct flow_stats *cpu_stats; + + cpu_stats = per_cpu_ptr(flow->stats.cpu_stats, cpu); + spin_lock_init(&cpu_stats->lock); + } + } return flow; +err: + kmem_cache_free(flow_cache, flow); + return ERR_PTR(-ENOMEM); } int ovs_flow_tbl_count(struct flow_table *table) @@ -118,6 +139,10 @@ static struct flex_array *alloc_buckets(unsigned int n_buckets) static void flow_free(struct sw_flow *flow) { kfree((struct sf_flow_acts __force *)flow->sf_acts); + if (flow->stats.is_percpu) + free_percpu(flow->stats.cpu_stats); + else + kfree(flow->stats.stat); kmem_cache_free(flow_cache, flow); } @@ -128,36 +153,29 @@ static void rcu_free_flow_callback(struct rcu_head *rcu) flow_free(flow); } -static void rcu_free_sw_flow_mask_cb(struct rcu_head *rcu) -{ - struct sw_flow_mask *mask = container_of(rcu, struct sw_flow_mask, rcu); - - kfree(mask); -} - -static void flow_mask_del_ref(struct sw_flow_mask *mask, bool deferred) -{ - if (!mask) - return; - - BUG_ON(!mask->ref_count); - mask->ref_count--; - - if (!mask->ref_count) { - list_del_rcu(&mask->list); - if (deferred) - call_rcu(&mask->rcu, rcu_free_sw_flow_mask_cb); - else - kfree(mask); - } -} - void ovs_flow_free(struct sw_flow *flow, bool deferred) { if (!flow) return; - flow_mask_del_ref(flow->mask, deferred); + if (flow->mask) { + struct sw_flow_mask *mask = flow->mask; + + /* ovs-lock is required to protect mask-refcount and + * mask list. + */ + ASSERT_OVSL(); + BUG_ON(!mask->ref_count); + mask->ref_count--; + + if (!mask->ref_count) { + list_del_rcu(&mask->list); + if (deferred) + kfree_rcu(mask, rcu); + else + kfree(mask); + } + } if (deferred) call_rcu(&flow->rcu, rcu_free_flow_callback); @@ -170,26 +188,9 @@ static void free_buckets(struct flex_array *buckets) flex_array_free(buckets); } + static void __table_instance_destroy(struct table_instance *ti) { - int i; - - if (ti->keep_flows) - goto skip_flows; - - for (i = 0; i < ti->n_buckets; i++) { - struct sw_flow *flow; - struct hlist_head *head = flex_array_get(ti->buckets, i); - struct hlist_node *n; - int ver = ti->node_ver; - - hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) { - hlist_del(&flow->hash_node[ver]); - ovs_flow_free(flow, false); - } - } - -skip_flows: free_buckets(ti->buckets); kfree(ti); } @@ -240,20 +241,38 @@ static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu) static void table_instance_destroy(struct table_instance *ti, bool deferred) { + int i; + if (!ti) return; + if (ti->keep_flows) + goto skip_flows; + + for (i = 0; i < ti->n_buckets; i++) { + struct sw_flow *flow; + struct hlist_head *head = flex_array_get(ti->buckets, i); + struct hlist_node *n; + int ver = ti->node_ver; + + hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) { + hlist_del_rcu(&flow->hash_node[ver]); + ovs_flow_free(flow, deferred); + } + } + +skip_flows: if (deferred) call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb); else __table_instance_destroy(ti); } -void ovs_flow_tbl_destroy(struct flow_table *table) +void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred) { struct table_instance *ti = ovsl_dereference(table->ti); - table_instance_destroy(ti, false); + table_instance_destroy(ti, deferred); } struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti, @@ -362,7 +381,7 @@ static u32 flow_hash(const struct sw_flow_key *key, int key_start, /* Make sure number of hash bytes are multiple of u32. */ BUILD_BUG_ON(sizeof(long) % sizeof(u32)); - return jhash2(hash_key, hash_u32s, 0); + return arch_fast_hash2(hash_key, hash_u32s, 0); } static int flow_key_start(const struct sw_flow_key *key) @@ -429,11 +448,11 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, return NULL; } -struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl, +struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl, const struct sw_flow_key *key, u32 *n_mask_hit) { - struct table_instance *ti = rcu_dereference(tbl->ti); + struct table_instance *ti = rcu_dereference_ovsl(tbl->ti); struct sw_flow_mask *mask; struct sw_flow *flow; @@ -447,6 +466,14 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl, return NULL; } +struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl, + const struct sw_flow_key *key) +{ + u32 __always_unused n_mask_hit; + + return ovs_flow_tbl_lookup_stats(tbl, key, &n_mask_hit); +} + int ovs_flow_tbl_num_masks(const struct flow_table *table) { struct sw_flow_mask *mask; @@ -478,16 +505,11 @@ static struct sw_flow_mask *mask_alloc(void) mask = kmalloc(sizeof(*mask), GFP_KERNEL); if (mask) - mask->ref_count = 0; + mask->ref_count = 1; return mask; } -static void mask_add_ref(struct sw_flow_mask *mask) -{ - mask->ref_count++; -} - static bool mask_equal(const struct sw_flow_mask *a, const struct sw_flow_mask *b) { @@ -514,11 +536,7 @@ static struct sw_flow_mask *flow_mask_find(const struct flow_table *tbl, return NULL; } -/** - * add a new mask into the mask list. - * The caller needs to make sure that 'mask' is not the same - * as any masks that are already on the list. - */ +/* Add 'mask' into the mask list, if it is not already there. */ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow, struct sw_flow_mask *new) { @@ -532,9 +550,11 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow, mask->key = new->key; mask->range = new->range; list_add_rcu(&mask->list, &tbl->mask_list); + } else { + BUG_ON(!mask->ref_count); + mask->ref_count++; } - mask_add_ref(mask); flow->mask = mask; return 0; } diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index fbe45d5ad07d..baaeb101924d 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -55,12 +55,12 @@ struct flow_table { int ovs_flow_init(void); void ovs_flow_exit(void); -struct sw_flow *ovs_flow_alloc(void); +struct sw_flow *ovs_flow_alloc(bool percpu_stats); void ovs_flow_free(struct sw_flow *, bool deferred); int ovs_flow_tbl_init(struct flow_table *); int ovs_flow_tbl_count(struct flow_table *table); -void ovs_flow_tbl_destroy(struct flow_table *table); +void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred); int ovs_flow_tbl_flush(struct flow_table *flow_table); int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow, @@ -69,9 +69,11 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow); int ovs_flow_tbl_num_masks(const struct flow_table *table); struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *table, u32 *bucket, u32 *idx); -struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *, +struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *, const struct sw_flow_key *, u32 *n_mask_hit); +struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *, + const struct sw_flow_key *); bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow, struct sw_flow_match *match); diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index d830a95f03a4..208dd9a26dd1 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -33,6 +33,9 @@ #include "vport.h" #include "vport-internal_dev.h" +static void ovs_vport_record_error(struct vport *, + enum vport_err_type err_type); + /* List of statically compiled vport implementations. Don't forget to also * add yours to the list at the bottom of vport.h. */ static const struct vport_ops *vport_ops_list[] = { @@ -136,14 +139,14 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, vport->ops = ops; INIT_HLIST_NODE(&vport->dp_hash_node); - vport->percpu_stats = alloc_percpu(struct pcpu_tstats); + vport->percpu_stats = alloc_percpu(struct pcpu_sw_netstats); if (!vport->percpu_stats) { kfree(vport); return ERR_PTR(-ENOMEM); } for_each_possible_cpu(i) { - struct pcpu_tstats *vport_stats; + struct pcpu_sw_netstats *vport_stats; vport_stats = per_cpu_ptr(vport->percpu_stats, i); u64_stats_init(&vport_stats->syncp); } @@ -275,8 +278,8 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) spin_unlock_bh(&vport->stats_lock); for_each_possible_cpu(i) { - const struct pcpu_tstats *percpu_stats; - struct pcpu_tstats local_stats; + const struct pcpu_sw_netstats *percpu_stats; + struct pcpu_sw_netstats local_stats; unsigned int start; percpu_stats = per_cpu_ptr(vport->percpu_stats, i); @@ -344,7 +347,7 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb) void ovs_vport_receive(struct vport *vport, struct sk_buff *skb, struct ovs_key_ipv4_tunnel *tun_key) { - struct pcpu_tstats *stats; + struct pcpu_sw_netstats *stats; stats = this_cpu_ptr(vport->percpu_stats); u64_stats_update_begin(&stats->syncp); @@ -370,7 +373,7 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb) int sent = vport->ops->send(vport, skb); if (likely(sent > 0)) { - struct pcpu_tstats *stats; + struct pcpu_sw_netstats *stats; stats = this_cpu_ptr(vport->percpu_stats); @@ -396,7 +399,8 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb) * If using the vport generic stats layer indicate that an error of the given * type has occurred. */ -void ovs_vport_record_error(struct vport *vport, enum vport_err_type err_type) +static void ovs_vport_record_error(struct vport *vport, + enum vport_err_type err_type) { spin_lock(&vport->stats_lock); diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index 1a9fbcec6e1b..d7e50a17396c 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -87,7 +87,7 @@ struct vport { struct hlist_node dp_hash_node; const struct vport_ops *ops; - struct pcpu_tstats __percpu *percpu_stats; + struct pcpu_sw_netstats __percpu *percpu_stats; spinlock_t stats_lock; struct vport_err_stats err_stats; @@ -192,7 +192,6 @@ static inline struct vport *vport_from_priv(const void *priv) void ovs_vport_receive(struct vport *, struct sk_buff *, struct ovs_key_ipv4_tunnel *); -void ovs_vport_record_error(struct vport *, enum vport_err_type err_type); /* List of statically compiled vport implementations. Don't forget to also * add yours to the list at the top of vport.c. */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 88cfbc189558..48a6a93db296 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -88,7 +88,7 @@ #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> -#include <linux/reciprocal_div.h> +#include <linux/percpu.h> #ifdef CONFIG_INET #include <net/inet_common.h> #endif @@ -237,6 +237,48 @@ 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 int packet_direct_xmit(struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + const struct net_device_ops *ops = dev->netdev_ops; + netdev_features_t features; + struct netdev_queue *txq; + u16 queue_map; + int ret; + + if (unlikely(!netif_running(dev) || + !netif_carrier_ok(dev))) { + kfree_skb(skb); + return NET_XMIT_DROP; + } + + features = netif_skb_features(skb); + if (skb_needs_linearize(skb, features) && + __skb_linearize(skb)) { + kfree_skb(skb); + return NET_XMIT_DROP; + } + + queue_map = skb_get_queue_mapping(skb); + txq = netdev_get_tx_queue(dev, queue_map); + + __netif_tx_lock_bh(txq); + if (unlikely(netif_xmit_frozen_or_stopped(txq))) { + ret = NETDEV_TX_BUSY; + kfree_skb(skb); + goto out; + } + + ret = ops->ndo_start_xmit(skb, dev); + if (likely(dev_xmit_complete(ret))) + txq_trans_update(txq); + else + kfree_skb(skb); +out: + __netif_tx_unlock_bh(txq); + return ret; +} + static struct net_device *packet_cached_dev_get(struct packet_sock *po) { struct net_device *dev; @@ -261,6 +303,32 @@ static void packet_cached_dev_reset(struct packet_sock *po) RCU_INIT_POINTER(po->cached_dev, NULL); } +static bool packet_use_direct_xmit(const struct packet_sock *po) +{ + return po->xmit == packet_direct_xmit; +} + +static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) +{ + return (u16) raw_smp_processor_id() % dev->real_num_tx_queues; +} + +static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) +{ + const struct net_device_ops *ops = dev->netdev_ops; + u16 queue_index; + + if (ops->ndo_select_queue) { + queue_index = ops->ndo_select_queue(dev, skb, NULL, + __packet_pick_tx_queue); + queue_index = netdev_cap_txqueue(dev, queue_index); + } else { + queue_index = __packet_pick_tx_queue(dev, skb); + } + + skb_set_queue_mapping(skb, queue_index); +} + /* 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()). @@ -458,7 +526,8 @@ static void prb_shutdown_retire_blk_timer(struct packet_sock *po, { struct tpacket_kbdq_core *pkc; - pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc; + pkc = tx_ring ? GET_PBDQC_FROM_RB(&po->tx_ring) : + GET_PBDQC_FROM_RB(&po->rx_ring); spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; @@ -484,7 +553,8 @@ static void prb_setup_retire_blk_timer(struct packet_sock *po, int tx_ring) if (tx_ring) BUG(); - pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc; + pkc = tx_ring ? GET_PBDQC_FROM_RB(&po->tx_ring) : + GET_PBDQC_FROM_RB(&po->rx_ring); prb_init_blk_timer(po, pkc, prb_retire_rx_blk_timer_expired); } @@ -542,7 +612,7 @@ static void init_prb_bdqc(struct packet_sock *po, struct pgv *pg_vec, union tpacket_req_u *req_u, int tx_ring) { - struct tpacket_kbdq_core *p1 = &rb->prb_bdqc; + struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd; memset(p1, 0x0, sizeof(*p1)); @@ -606,7 +676,7 @@ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc) static void prb_retire_rx_blk_timer_expired(unsigned long data) { struct packet_sock *po = (struct packet_sock *)data; - struct tpacket_kbdq_core *pkc = &po->rx_ring.prb_bdqc; + struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring); unsigned int frozen; struct tpacket_block_desc *pbd; @@ -909,7 +979,7 @@ static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { - ppd->hv1.tp_rxhash = skb_get_rxhash(pkc->skb); + ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb); } static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, @@ -923,9 +993,11 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, { if (vlan_tx_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = vlan_tx_tag_get(pkc->skb); - ppd->tp_status = TP_STATUS_VLAN_VALID; + ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); + ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; + ppd->hv1.tp_vlan_tpid = 0; ppd->tp_status = TP_STATUS_AVAILABLE; } } @@ -933,6 +1005,7 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { + ppd->hv1.tp_padding = 0; prb_fill_vlan_info(pkc, ppd); if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH) @@ -1111,6 +1184,47 @@ static void packet_increment_head(struct packet_ring_buffer *buff) buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } +static void packet_inc_pending(struct packet_ring_buffer *rb) +{ + this_cpu_inc(*rb->pending_refcnt); +} + +static void packet_dec_pending(struct packet_ring_buffer *rb) +{ + this_cpu_dec(*rb->pending_refcnt); +} + +static unsigned int packet_read_pending(const struct packet_ring_buffer *rb) +{ + unsigned int refcnt = 0; + int cpu; + + /* We don't use pending refcount in rx_ring. */ + if (rb->pending_refcnt == NULL) + return 0; + + for_each_possible_cpu(cpu) + refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu); + + return refcnt; +} + +static int packet_alloc_pending(struct packet_sock *po) +{ + po->rx_ring.pending_refcnt = NULL; + + po->tx_ring.pending_refcnt = alloc_percpu(unsigned int); + if (unlikely(po->tx_ring.pending_refcnt == NULL)) + return -ENOBUFS; + + return 0; +} + +static void packet_free_pending(struct packet_sock *po) +{ + free_percpu(po->tx_ring.pending_refcnt); +} + static bool packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { struct sock *sk = &po->sk; @@ -1163,7 +1277,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - return reciprocal_divide(skb->rxhash, num); + return reciprocal_scale(skb->rxhash, num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, @@ -1190,7 +1304,7 @@ static unsigned int fanout_demux_rnd(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - return reciprocal_divide(prandom_u32(), num); + return prandom_u32_max(num); } static unsigned int fanout_demux_rollover(struct packet_fanout *f, @@ -1214,6 +1328,13 @@ static unsigned int fanout_demux_rollover(struct packet_fanout *f, return idx; } +static unsigned int fanout_demux_qm(struct packet_fanout *f, + struct sk_buff *skb, + unsigned int num) +{ + return skb_get_queue_mapping(skb) % num; +} + static bool fanout_has_flag(struct packet_fanout *f, u16 flag) { return f->flags & (flag >> 8); @@ -1241,7 +1362,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, if (!skb) return 0; } - skb_get_rxhash(skb); + skb_get_hash(skb); idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: @@ -1253,6 +1374,9 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, case PACKET_FANOUT_RND: idx = fanout_demux_rnd(f, skb, num); break; + case PACKET_FANOUT_QM: + idx = fanout_demux_qm(f, skb, num); + break; case PACKET_FANOUT_ROLLOVER: idx = fanout_demux_rollover(f, skb, 0, (unsigned int) -1, num); break; @@ -1299,9 +1423,9 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po) spin_unlock(&f->lock); } -static bool match_fanout_group(struct packet_type *ptype, struct sock * sk) +static bool match_fanout_group(struct packet_type *ptype, struct sock *sk) { - if (ptype->af_packet_priv == (void*)((struct packet_sock *)sk)->fanout) + if (ptype->af_packet_priv == (void *)((struct packet_sock *)sk)->fanout) return true; return false; @@ -1323,6 +1447,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) case PACKET_FANOUT_LB: case PACKET_FANOUT_CPU: case PACKET_FANOUT_RND: + case PACKET_FANOUT_QM: break; default: return -EINVAL; @@ -1485,7 +1610,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - struct sockaddr_pkt *saddr = (struct sockaddr_pkt *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name); struct sk_buff *skb = NULL; struct net_device *dev; __be16 proto = 0; @@ -1758,6 +1883,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct timespec ts; __u32 ts_status; + /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. + * We may add members to them until current aligned size without forcing + * userspace to call getsockopt(..., PACKET_HDRLEN, ...). + */ + BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32); + BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48); + if (skb->pkt_type == PACKET_LOOPBACK) goto drop; @@ -1864,11 +1996,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h2->tp_nsec = ts.tv_nsec; if (vlan_tx_tag_present(skb)) { h.h2->tp_vlan_tci = vlan_tx_tag_get(skb); - status |= TP_STATUS_VLAN_VALID; + h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); + status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; + h.h2->tp_vlan_tpid = 0; } - h.h2->tp_padding = 0; + memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding)); hdrlen = sizeof(*h.h2); break; case TPACKET_V3: @@ -1882,6 +2016,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h3->tp_net = netoff; h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; + memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding)); hdrlen = sizeof(*h.h3); break; default: @@ -1900,19 +2035,20 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, sll->sll_ifindex = dev->ifindex; smp_mb(); + #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 - { + if (po->tp_version <= TPACKET_V2) { u8 *start, *end; - if (po->tp_version <= TPACKET_V2) { - end = (u8 *)PAGE_ALIGN((unsigned long)h.raw - + macoff + snaplen); - for (start = h.raw; start < end; start += PAGE_SIZE) - flush_dcache_page(pgv_to_page(start)); - } - smp_wmb(); + end = (u8 *) PAGE_ALIGN((unsigned long) h.raw + + macoff + snaplen); + + for (start = h.raw; start < end; start += PAGE_SIZE) + flush_dcache_page(pgv_to_page(start)); } + smp_wmb(); #endif + if (po->tp_version <= TPACKET_V2) __packet_set_status(po, h.raw, status); else @@ -1941,14 +2077,13 @@ ring_is_full: static void tpacket_destruct_skb(struct sk_buff *skb) { struct packet_sock *po = pkt_sk(skb->sk); - void *ph; if (likely(po->tx_ring.pg_vec)) { + void *ph; __u32 ts; ph = skb_shinfo(skb)->destructor_arg; - BUG_ON(atomic_read(&po->tx_ring.pending) == 0); - atomic_dec(&po->tx_ring.pending); + packet_dec_pending(&po->tx_ring); ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); @@ -1992,9 +2127,10 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb_reserve(skb, hlen); skb_reset_network_header(skb); - skb_probe_transport_header(skb, 0); - if (po->tp_tx_has_off) { + if (!packet_use_direct_xmit(po)) + skb_probe_transport_header(skb, 0); + if (unlikely(po->tp_tx_has_off)) { int off_min, off_max, off; off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); off_max = po->tx_ring.frame_size - tp_len; @@ -2087,7 +2223,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) __be16 proto; int err, reserve = 0; void *ph; - struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); + bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); int tp_len, size_max; unsigned char *addr; int len_sum = 0; @@ -2130,10 +2267,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) do { ph = packet_current_frame(po, &po->tx_ring, - TP_STATUS_SEND_REQUEST); - + TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { - schedule(); + if (need_wait && need_resched()) + schedule(); continue; } @@ -2164,12 +2301,14 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } } + packet_pick_tx_queue(dev, skb); + skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); - atomic_inc(&po->tx_ring.pending); + packet_inc_pending(&po->tx_ring); status = TP_STATUS_SEND_REQUEST; - err = dev_queue_xmit(skb); + err = po->xmit(skb); if (unlikely(err > 0)) { err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == @@ -2187,9 +2326,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) packet_increment_head(&po->tx_ring); len_sum += tp_len; } while (likely((ph != NULL) || - ((!(msg->msg_flags & MSG_DONTWAIT)) && - (atomic_read(&po->tx_ring.pending)))) - ); + /* Note: packet_read_pending() might be slow if we have + * to call it as it's per_cpu variable, but in fast-path + * we already short-circuit the loop with the first + * condition, and luckily don't have to go that path + * anyway. + */ + (need_wait && packet_read_pending(&po->tx_ring)))); err = len_sum; goto out_put; @@ -2228,11 +2371,10 @@ static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, return skb; } -static int packet_snd(struct socket *sock, - struct msghdr *msg, size_t len) +static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); struct sk_buff *skb; struct net_device *dev; __be16 proto; @@ -2375,6 +2517,8 @@ static int packet_snd(struct socket *sock, skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; + packet_pick_tx_queue(dev, skb); + if (po->has_vnet_hdr) { if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { if (!skb_partial_csum_set(skb, vnet_hdr.csum_start, @@ -2394,16 +2538,12 @@ static int packet_snd(struct socket *sock, len += vnet_hdr_len; } - skb_probe_transport_header(skb, reserve); - + if (!packet_use_direct_xmit(po)) + skb_probe_transport_header(skb, reserve); if (unlikely(extra_len == 4)) skb->no_fcs = 1; - /* - * Now send it - */ - - err = dev_queue_xmit(skb); + err = po->xmit(skb); if (err > 0 && (err = net_xmit_errno(err)) != 0) goto out_unlock; @@ -2425,6 +2565,7 @@ static int packet_sendmsg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); + if (po->tx_ring.pg_vec) return tpacket_snd(po, msg); else @@ -2491,6 +2632,7 @@ static int packet_release(struct socket *sock) /* Purge queues */ skb_queue_purge(&sk->sk_receive_queue); + packet_free_pending(po); sk_refcnt_debug_release(sk); sock_put(sk); @@ -2501,9 +2643,12 @@ static int packet_release(struct socket *sock) * Attach a packet hook. */ -static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protocol) +static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto) { struct packet_sock *po = pkt_sk(sk); + const struct net_device *dev_curr; + __be16 proto_curr; + bool need_rehook; if (po->fanout) { if (dev) @@ -2513,21 +2658,29 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc } lock_sock(sk); - 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); + proto_curr = po->prot_hook.type; + dev_curr = po->prot_hook.dev; + + need_rehook = proto_curr != proto || dev_curr != dev; + + if (need_rehook) { + unregister_prot_hook(sk, true); - po->prot_hook.dev = dev; - po->ifindex = dev ? dev->ifindex : 0; + po->num = proto; + po->prot_hook.type = proto; + + if (po->prot_hook.dev) + dev_put(po->prot_hook.dev); - packet_cached_dev_assign(po, dev); + po->prot_hook.dev = dev; + + po->ifindex = dev ? dev->ifindex : 0; + packet_cached_dev_assign(po, dev); + } - if (protocol == 0) + if (proto == 0 || !need_rehook) goto out_unlock; if (!dev || (dev->flags & IFF_UP)) { @@ -2639,6 +2792,11 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, po = pkt_sk(sk); sk->sk_family = PF_PACKET; po->num = proto; + po->xmit = dev_queue_xmit; + + err = packet_alloc_pending(po); + if (err) + goto out2; packet_cached_dev_reset(po); @@ -2672,6 +2830,8 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, preempt_enable(); return 0; +out2: + sk_free(sk); out: return err; } @@ -2791,6 +2951,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, * in, we fill it in now. */ if (sock->type == SOCK_PACKET) { + __sockaddr_check_size(sizeof(struct sockaddr_pkt)); msg->msg_namelen = sizeof(struct sockaddr_pkt); } else { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; @@ -2813,11 +2974,12 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, aux.tp_net = skb_network_offset(skb); if (vlan_tx_tag_present(skb)) { aux.tp_vlan_tci = vlan_tx_tag_get(skb); - aux.tp_status |= TP_STATUS_VLAN_VALID; + aux.tp_vlan_tpid = ntohs(skb->vlan_proto); + aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { aux.tp_vlan_tci = 0; + aux.tp_vlan_tpid = 0; } - aux.tp_padding = 0; put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } @@ -3218,6 +3380,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv po->tp_tx_has_off = !!val; return 0; } + case PACKET_QDISC_BYPASS: + { + int val; + + if (optlen != sizeof(val)) + return -EINVAL; + if (copy_from_user(&val, optval, sizeof(val))) + return -EFAULT; + + po->xmit = val ? packet_direct_xmit : dev_queue_xmit; + return 0; + } default: return -ENOPROTOOPT; } @@ -3310,6 +3484,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, case PACKET_TX_HAS_OFF: val = po->tp_tx_has_off; break; + case PACKET_QDISC_BYPASS: + val = packet_use_direct_xmit(po); + break; default: return -ENOPROTOOPT; } @@ -3501,34 +3678,26 @@ static void free_pg_vec(struct pgv *pg_vec, unsigned int order, static char *alloc_one_pg_vec_page(unsigned long order) { - char *buffer = NULL; + char *buffer; gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); - if (buffer) return buffer; - /* - * __get_free_pages failed, fall back to vmalloc - */ + /* __get_free_pages failed, fall back to vmalloc */ buffer = vzalloc((1 << order) * PAGE_SIZE); - if (buffer) return buffer; - /* - * vmalloc failed, lets dig into swap here - */ + /* vmalloc failed, lets dig into swap here */ gfp_flags &= ~__GFP_NORETRY; - buffer = (char *)__get_free_pages(gfp_flags, order); + buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; - /* - * complete and utter failure - */ + /* complete and utter failure */ return NULL; } @@ -3583,7 +3752,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (!closing) { if (atomic_read(&po->mapped)) goto out; - if (atomic_read(&rb->pending)) + if (packet_read_pending(rb)) goto out; } @@ -3635,7 +3804,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, */ if (!tx_ring) init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring); - break; + break; default: break; } diff --git a/net/packet/diag.c b/net/packet/diag.c index a9584a2f6d69..533ce4ff108a 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -3,6 +3,7 @@ #include <linux/net.h> #include <linux/netdevice.h> #include <linux/packet_diag.h> +#include <linux/percpu.h> #include <net/net_namespace.h> #include <net/sock.h> diff --git a/net/packet/internal.h b/net/packet/internal.h index 1035fa2d909c..eb9580a6b25f 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -64,7 +64,7 @@ struct packet_ring_buffer { unsigned int pg_vec_pages; unsigned int pg_vec_len; - atomic_t pending; + unsigned int __percpu *pending_refcnt; struct tpacket_kbdq_core prb_bdqc; }; @@ -114,6 +114,7 @@ struct packet_sock { unsigned int tp_tx_has_off:1; unsigned int tp_tstamp; struct net_device __rcu *cached_dev; + int (*xmit)(struct sk_buff *skb); struct packet_type prot_hook ____cacheline_aligned_in_smp; }; diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 38946b26e471..290352c0e6b4 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -86,7 +86,7 @@ static int pn_init(struct sock *sk) static int pn_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { - struct sockaddr_pn *target; + DECLARE_SOCKADDR(struct sockaddr_pn *, target, msg->msg_name); struct sk_buff *skb; int err; @@ -94,13 +94,12 @@ static int pn_sendmsg(struct kiocb *iocb, struct sock *sk, MSG_CMSG_COMPAT)) return -EOPNOTSUPP; - if (msg->msg_name == NULL) + if (target == NULL) return -EDESTADDRREQ; if (msg->msg_namelen < sizeof(struct sockaddr_pn)) return -EINVAL; - target = (struct sockaddr_pn *)msg->msg_name; if (target->spn_family != AF_PHONET) return -EAFNOSUPPORT; @@ -160,6 +159,7 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk, rval = (flags & MSG_TRUNC) ? skb->len : copylen; if (msg->msg_name != NULL) { + __sockaddr_check_size(sizeof(sa)); memcpy(msg->msg_name, &sa, sizeof(sa)); *addr_len = sizeof(sa); } diff --git a/net/rds/bind.c b/net/rds/bind.c index b5ad65a0067e..a2e6562da751 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -117,7 +117,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port) rover = be16_to_cpu(*port); last = rover; } else { - rover = max_t(u16, net_random(), 2); + rover = max_t(u16, prandom_u32(), 2); last = rover - 1; } diff --git a/net/rds/recv.c b/net/rds/recv.c index de339b24ca14..bd82522534fc 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -402,7 +402,7 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, struct rds_sock *rs = rds_sk_to_rs(sk); long timeo; int ret = 0, nonblock = msg_flags & MSG_DONTWAIT; - struct sockaddr_in *sin; + DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct rds_incoming *inc = NULL; /* udp_recvmsg()->sock_recvtimeo() gets away without locking too.. */ @@ -479,7 +479,6 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, rds_stats_inc(s_recv_delivered); - sin = (struct sockaddr_in *)msg->msg_name; if (sin) { sin->sin_family = AF_INET; sin->sin_port = inc->i_hdr.h_sport; diff --git a/net/rds/send.c b/net/rds/send.c index 88eace57dd6b..a82fb660ec00 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -922,7 +922,7 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); - struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); __be32 daddr; __be16 dport; struct rds_message *rm = NULL; diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 1bacc1079942..ed7e0b4e7f90 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -14,9 +14,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the - * Free Software Foundation, Inc., - * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/kernel.h> diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 62ced6516c58..c2cca2ee6aef 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1012,7 +1012,7 @@ int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct ros make_rose->source_call = facilities.source_call; make_rose->source_ndigis = facilities.source_ndigis; for (n = 0 ; n < facilities.source_ndigis ; n++) - make_rose->source_digis[n]= facilities.source_digis[n]; + make_rose->source_digis[n] = facilities.source_digis[n]; make_rose->neighbour = neigh; make_rose->device = dev; make_rose->facilities = facilities; @@ -1051,7 +1051,7 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); - struct sockaddr_rose *usrose = (struct sockaddr_rose *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_rose *, usrose, msg->msg_name); int err; struct full_sockaddr_rose srose; struct sk_buff *skb; @@ -1253,7 +1253,8 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock, if (msg->msg_name) { struct sockaddr_rose *srose; - struct full_sockaddr_rose *full_srose = msg->msg_name; + DECLARE_SOCKADDR(struct full_sockaddr_rose *, full_srose, + msg->msg_name); memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose)); srose = msg->msg_name; diff --git a/net/rose/rose_dev.c b/net/rose/rose_dev.c index 28dbdb911b85..50005888be57 100644 --- a/net/rose/rose_dev.c +++ b/net/rose/rose_dev.c @@ -146,7 +146,7 @@ static netdev_tx_t rose_xmit(struct sk_buff *skb, struct net_device *dev) static const struct header_ops rose_header_ops = { .create = rose_header, - .rebuild= rose_rebuild_header, + .rebuild = rose_rebuild_header, }; static const struct net_device_ops rose_netdev_ops = { diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c index e4d9cbcff402..cd97a0ce48d8 100644 --- a/net/rxrpc/ar-ack.c +++ b/net/rxrpc/ar-ack.c @@ -21,10 +21,17 @@ static unsigned int rxrpc_ack_defer = 1; -static const char *const rxrpc_acks[] = { - "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", "IDL", - "-?-" -}; +static const char *rxrpc_acks(u8 reason) +{ + static const char *const str[] = { + "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", + "IDL", "-?-" + }; + + if (reason >= ARRAY_SIZE(str)) + reason = ARRAY_SIZE(str) - 1; + return str[reason]; +} static const s8 rxrpc_ack_priority[] = { [0] = 0, @@ -50,7 +57,7 @@ void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, ASSERTCMP(prior, >, 0); _enter("{%d},%s,%%%x,%u", - call->debug_id, rxrpc_acks[ack_reason], ntohl(serial), + call->debug_id, rxrpc_acks(ack_reason), ntohl(serial), immediate); if (prior < rxrpc_ack_priority[call->ackr_reason]) { @@ -637,7 +644,7 @@ process_further: hard, ntohl(ack.previousPacket), ntohl(ack.serial), - rxrpc_acks[ack.reason], + rxrpc_acks(ack.reason), ack.nAcks); rxrpc_extract_ackinfo(call, skb, latest, ack.nAcks); @@ -1180,7 +1187,7 @@ send_ACK: ntohl(ack.firstPacket), ntohl(ack.previousPacket), ntohl(ack.serial), - rxrpc_acks[ack.reason], + rxrpc_acks(ack.reason), ack.nAcks); del_timer_sync(&call->ack_timer); diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c index 4106ca95ec86..7bf5b5b9e8b9 100644 --- a/net/rxrpc/ar-connection.c +++ b/net/rxrpc/ar-connection.c @@ -381,6 +381,8 @@ static int rxrpc_connect_exclusive(struct rxrpc_sock *rx, rxrpc_assign_connection_id(conn); rx->conn = conn; + } else { + spin_lock(&trans->client_lock); } /* we've got a connection with a free channel and we can now attach the diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index e1ac183d50bb..d0e8f1c1898a 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -152,8 +152,8 @@ int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx, if (trans) { service_id = rx->service_id; if (msg->msg_name) { - struct sockaddr_rxrpc *srx = - (struct sockaddr_rxrpc *) msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx, + msg->msg_name); service_id = htons(srx->srx_service); } key = rx->key; diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 898492a8d61b..34b5490dde65 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -180,7 +180,8 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, if (copy > len - copied) copy = len - copied; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + if (skb->ip_summed == CHECKSUM_UNNECESSARY || + skb->ip_summed == CHECKSUM_PARTIAL) { ret = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copy); } else { @@ -353,6 +354,10 @@ csum_copy_error: if (continue_call) rxrpc_put_call(continue_call); rxrpc_kill_skb(skb); + if (!(flags & MSG_PEEK)) { + if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) + BUG(); + } skb_kill_datagram(&rx->sk, skb, flags); rxrpc_put_call(call); return -EAGAIN; diff --git a/net/sched/Kconfig b/net/sched/Kconfig index ad1f1d819203..a1a8e29e5fc9 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -286,6 +286,28 @@ config NET_SCH_FQ If unsure, say N. +config NET_SCH_HHF + tristate "Heavy-Hitter Filter (HHF)" + help + Say Y here if you want to use the Heavy-Hitter Filter (HHF) + packet scheduling algorithm. + + To compile this driver as a module, choose M here: the module + will be called sch_hhf. + +config NET_SCH_PIE + tristate "Proportional Integral controller Enhanced (PIE) scheduler" + help + Say Y here if you want to use the Proportional Integral controller + Enhanced scheduler packet scheduling algorithm. + For more information, please see + http://tools.ietf.org/html/draft-pan-tsvwg-pie-00 + + To compile this driver as a module, choose M here: the module + will be called sch_pie. + + If unsure, say N. + config NET_SCH_INGRESS tristate "Ingress Qdisc" depends on NET_CLS_ACT @@ -435,6 +457,7 @@ config NET_CLS_FLOW config NET_CLS_CGROUP tristate "Control Group Classifier" select NET_CLS + select CGROUP_NET_CLASSID depends on CGROUPS ---help--- Say Y here if you want to classify packets based on the control diff --git a/net/sched/Makefile b/net/sched/Makefile index 35fa47a494ab..0a869a11f3e6 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -40,6 +40,8 @@ obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o obj-$(CONFIG_NET_SCH_CODEL) += sch_codel.o obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o +obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o +obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 69cb848e8345..72bdc7166345 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -29,25 +29,16 @@ void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) { - unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask); - struct tcf_common **p1p; - - for (p1p = &hinfo->htab[h]; *p1p; p1p = &(*p1p)->tcfc_next) { - if (*p1p == p) { - write_lock_bh(hinfo->lock); - *p1p = p->tcfc_next; - write_unlock_bh(hinfo->lock); - gen_kill_estimator(&p->tcfc_bstats, - &p->tcfc_rate_est); - /* - * gen_estimator est_timer() might access p->tcfc_lock - * or bstats, wait a RCU grace period before freeing p - */ - kfree_rcu(p, tcfc_rcu); - return; - } - } - WARN_ON(1); + spin_lock_bh(&hinfo->lock); + hlist_del(&p->tcfc_head); + spin_unlock_bh(&hinfo->lock); + gen_kill_estimator(&p->tcfc_bstats, + &p->tcfc_rate_est); + /* + * gen_estimator est_timer() might access p->tcfc_lock + * or bstats, wait a RCU grace period before freeing p + */ + kfree_rcu(p, tcfc_rcu); } EXPORT_SYMBOL(tcf_hash_destroy); @@ -71,20 +62,22 @@ int tcf_hash_release(struct tcf_common *p, int bind, EXPORT_SYMBOL(tcf_hash_release); static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, - struct tc_action *a, struct tcf_hashinfo *hinfo) + struct tc_action *a) { + struct tcf_hashinfo *hinfo = a->ops->hinfo; + struct hlist_head *head; struct tcf_common *p; int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; struct nlattr *nest; - read_lock_bh(hinfo->lock); + spin_lock_bh(&hinfo->lock); s_i = cb->args[0]; for (i = 0; i < (hinfo->hmask + 1); i++) { - p = hinfo->htab[tcf_hash(i, hinfo->hmask)]; + head = &hinfo->htab[tcf_hash(i, hinfo->hmask)]; - for (; p; p = p->tcfc_next) { + hlist_for_each_entry_rcu(p, head, tcfc_head) { index++; if (index < s_i) continue; @@ -107,7 +100,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, } } done: - read_unlock_bh(hinfo->lock); + spin_unlock_bh(&hinfo->lock); if (n_i) cb->args[0] += n_i; return n_i; @@ -117,10 +110,12 @@ nla_put_failure: goto done; } -static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, - struct tcf_hashinfo *hinfo) +static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a) { - struct tcf_common *p, *s_p; + struct tcf_hashinfo *hinfo = a->ops->hinfo; + struct hlist_head *head; + struct hlist_node *n; + struct tcf_common *p; struct nlattr *nest; int i = 0, n_i = 0; @@ -130,14 +125,12 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, if (nla_put_string(skb, TCA_KIND, a->ops->kind)) goto nla_put_failure; for (i = 0; i < (hinfo->hmask + 1); i++) { - p = hinfo->htab[tcf_hash(i, hinfo->hmask)]; - - while (p != NULL) { - s_p = p->tcfc_next; - if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo)) + head = &hinfo->htab[tcf_hash(i, hinfo->hmask)]; + hlist_for_each_entry_safe(p, n, head, tcfc_head) { + if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo)) { module_put(a->ops->owner); - n_i++; - p = s_p; + n_i++; + } } } if (nla_put_u32(skb, TCA_FCNT, n_i)) @@ -150,48 +143,45 @@ nla_put_failure: return -EINVAL; } -int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, - int type, struct tc_action *a) +static int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, + int type, struct tc_action *a) { - struct tcf_hashinfo *hinfo = a->ops->hinfo; - if (type == RTM_DELACTION) { - return tcf_del_walker(skb, a, hinfo); + return tcf_del_walker(skb, a); } else if (type == RTM_GETACTION) { - return tcf_dump_walker(skb, cb, a, hinfo); + return tcf_dump_walker(skb, cb, a); } else { WARN(1, "tcf_generic_walker: unknown action %d\n", type); return -EINVAL; } } -EXPORT_SYMBOL(tcf_generic_walker); -struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo) +static struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo) { - struct tcf_common *p; + struct tcf_common *p = NULL; + struct hlist_head *head; - read_lock_bh(hinfo->lock); - for (p = hinfo->htab[tcf_hash(index, hinfo->hmask)]; p; - p = p->tcfc_next) { + spin_lock_bh(&hinfo->lock); + head = &hinfo->htab[tcf_hash(index, hinfo->hmask)]; + hlist_for_each_entry_rcu(p, head, tcfc_head) if (p->tcfc_index == index) break; - } - read_unlock_bh(hinfo->lock); + spin_unlock_bh(&hinfo->lock); return p; } -EXPORT_SYMBOL(tcf_hash_lookup); -u32 tcf_hash_new_index(u32 *idx_gen, struct tcf_hashinfo *hinfo) +u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo) { - u32 val = *idx_gen; + u32 val = hinfo->index; do { if (++val == 0) val = 1; } while (tcf_hash_lookup(val, hinfo)); - return (*idx_gen = val); + hinfo->index = val; + return val; } EXPORT_SYMBOL(tcf_hash_new_index); @@ -208,9 +198,9 @@ int tcf_hash_search(struct tc_action *a, u32 index) } EXPORT_SYMBOL(tcf_hash_search); -struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind, - struct tcf_hashinfo *hinfo) +struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind) { + struct tcf_hashinfo *hinfo = a->ops->hinfo; struct tcf_common *p = NULL; if (index && (p = tcf_hash_lookup(index, hinfo)) != NULL) { if (bind) @@ -223,9 +213,9 @@ struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind, EXPORT_SYMBOL(tcf_hash_check); struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, - struct tc_action *a, int size, int bind, - u32 *idx_gen, struct tcf_hashinfo *hinfo) + struct tc_action *a, int size, int bind) { + struct tcf_hashinfo *hinfo = a->ops->hinfo; struct tcf_common *p = kzalloc(size, GFP_KERNEL); if (unlikely(!p)) @@ -235,7 +225,8 @@ struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, p->tcfc_bindcnt = 1; spin_lock_init(&p->tcfc_lock); - p->tcfc_index = index ? index : tcf_hash_new_index(idx_gen, hinfo); + INIT_HLIST_NODE(&p->tcfc_head); + p->tcfc_index = index ? index : tcf_hash_new_index(hinfo); p->tcfc_tm.install = jiffies; p->tcfc_tm.lastuse = jiffies; if (est) { @@ -256,19 +247,18 @@ void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo) { unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask); - write_lock_bh(hinfo->lock); - p->tcfc_next = hinfo->htab[h]; - hinfo->htab[h] = p; - write_unlock_bh(hinfo->lock); + spin_lock_bh(&hinfo->lock); + hlist_add_head(&p->tcfc_head, &hinfo->htab[h]); + spin_unlock_bh(&hinfo->lock); } EXPORT_SYMBOL(tcf_hash_insert); -static struct tc_action_ops *act_base = NULL; +static LIST_HEAD(act_base); static DEFINE_RWLOCK(act_mod_lock); int tcf_register_action(struct tc_action_ops *act) { - struct tc_action_ops *a, **ap; + struct tc_action_ops *a; /* Must supply act, dump, cleanup and init */ if (!act->act || !act->dump || !act->cleanup || !act->init) @@ -281,14 +271,13 @@ int tcf_register_action(struct tc_action_ops *act) act->walk = tcf_generic_walker; write_lock(&act_mod_lock); - for (ap = &act_base; (a = *ap) != NULL; ap = &a->next) { + list_for_each_entry(a, &act_base, head) { if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) { write_unlock(&act_mod_lock); return -EEXIST; } } - act->next = NULL; - *ap = act; + list_add_tail(&act->head, &act_base); write_unlock(&act_mod_lock); return 0; } @@ -296,17 +285,16 @@ EXPORT_SYMBOL(tcf_register_action); int tcf_unregister_action(struct tc_action_ops *act) { - struct tc_action_ops *a, **ap; + struct tc_action_ops *a; int err = -ENOENT; write_lock(&act_mod_lock); - for (ap = &act_base; (a = *ap) != NULL; ap = &a->next) - if (a == act) + list_for_each_entry(a, &act_base, head) { + if (a == act) { + list_del(&act->head); + err = 0; break; - if (a) { - *ap = a->next; - a->next = NULL; - err = 0; + } } write_unlock(&act_mod_lock); return err; @@ -316,69 +304,42 @@ EXPORT_SYMBOL(tcf_unregister_action); /* lookup by name */ static struct tc_action_ops *tc_lookup_action_n(char *kind) { - struct tc_action_ops *a = NULL; + struct tc_action_ops *a, *res = NULL; if (kind) { read_lock(&act_mod_lock); - for (a = act_base; a; a = a->next) { + list_for_each_entry(a, &act_base, head) { if (strcmp(kind, a->kind) == 0) { - if (!try_module_get(a->owner)) { - read_unlock(&act_mod_lock); - return NULL; - } + if (try_module_get(a->owner)) + res = a; break; } } read_unlock(&act_mod_lock); } - return a; + return res; } /* lookup by nlattr */ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind) { - struct tc_action_ops *a = NULL; + struct tc_action_ops *a, *res = NULL; if (kind) { read_lock(&act_mod_lock); - for (a = act_base; a; a = a->next) { + list_for_each_entry(a, &act_base, head) { if (nla_strcmp(kind, a->kind) == 0) { - if (!try_module_get(a->owner)) { - read_unlock(&act_mod_lock); - return NULL; - } + if (try_module_get(a->owner)) + res = a; break; } } read_unlock(&act_mod_lock); } - return a; + return res; } -#if 0 -/* lookup by id */ -static struct tc_action_ops *tc_lookup_action_id(u32 type) -{ - struct tc_action_ops *a = NULL; - - if (type) { - read_lock(&act_mod_lock); - for (a = act_base; a; a = a->next) { - if (a->type == type) { - if (!try_module_get(a->owner)) { - read_unlock(&act_mod_lock); - return NULL; - } - break; - } - } - read_unlock(&act_mod_lock); - } - return a; -} -#endif - -int tcf_action_exec(struct sk_buff *skb, const struct tc_action *act, +int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, struct tcf_result *res) { const struct tc_action *a; @@ -389,53 +350,39 @@ int tcf_action_exec(struct sk_buff *skb, const struct tc_action *act, ret = TC_ACT_OK; goto exec_done; } - while ((a = act) != NULL) { + list_for_each_entry(a, actions, list) { repeat: - if (a->ops) { - ret = a->ops->act(skb, a, res); - if (TC_MUNGED & skb->tc_verd) { - /* copied already, allow trampling */ - skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd); - skb->tc_verd = CLR_TC_MUNGED(skb->tc_verd); - } - if (ret == TC_ACT_REPEAT) - goto repeat; /* we need a ttl - JHS */ - if (ret != TC_ACT_PIPE) - goto exec_done; + ret = a->ops->act(skb, a, res); + if (TC_MUNGED & skb->tc_verd) { + /* copied already, allow trampling */ + skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd); + skb->tc_verd = CLR_TC_MUNGED(skb->tc_verd); } - act = a->next; + if (ret == TC_ACT_REPEAT) + goto repeat; /* we need a ttl - JHS */ + if (ret != TC_ACT_PIPE) + goto exec_done; } exec_done: return ret; } EXPORT_SYMBOL(tcf_action_exec); -void tcf_action_destroy(struct tc_action *act, int bind) +void tcf_action_destroy(struct list_head *actions, int bind) { - struct tc_action *a; + struct tc_action *a, *tmp; - for (a = act; a; a = act) { - if (a->ops) { - if (a->ops->cleanup(a, bind) == ACT_P_DELETED) - module_put(a->ops->owner); - act = act->next; - kfree(a); - } else { - /*FIXME: Remove later - catch insertion bugs*/ - WARN(1, "tcf_action_destroy: BUG? destroying NULL ops\n"); - act = act->next; - kfree(a); - } + list_for_each_entry_safe(a, tmp, actions, list) { + if (a->ops->cleanup(a, bind) == ACT_P_DELETED) + module_put(a->ops->owner); + list_del(&a->list); + kfree(a); } } int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { - int err = -EINVAL; - - if (a->ops == NULL) - return err; return a->ops->dump(skb, a, bind, ref); } @@ -446,9 +393,6 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - if (a->ops == NULL) - return err; - if (nla_put_string(skb, TCA_KIND, a->ops->kind)) goto nla_put_failure; if (tcf_action_copy_stats(skb, a, 0)) @@ -469,14 +413,13 @@ nla_put_failure: EXPORT_SYMBOL(tcf_action_dump_1); int -tcf_action_dump(struct sk_buff *skb, struct tc_action *act, int bind, int ref) +tcf_action_dump(struct sk_buff *skb, struct list_head *actions, int bind, int ref) { struct tc_action *a; int err = -EINVAL; struct nlattr *nest; - while ((a = act) != NULL) { - act = a->next; + list_for_each_entry(a, actions, list) { nest = nla_nest_start(skb, a->order); if (nest == NULL) goto nla_put_failure; @@ -551,6 +494,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, if (a == NULL) goto err_mod; + a->ops = a_o; + INIT_LIST_HEAD(&a->list); /* backward compatibility for policer */ if (name == NULL) err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, a, ovr, bind); @@ -565,7 +510,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, */ if (err != ACT_P_CREATED) module_put(a_o->owner); - a->ops = a_o; return a; @@ -577,37 +521,33 @@ err_out: return ERR_PTR(err); } -struct tc_action *tcf_action_init(struct net *net, struct nlattr *nla, +int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est, char *name, int ovr, - int bind) + int bind, struct list_head *actions) { struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; - struct tc_action *head = NULL, *act, *act_prev = NULL; + struct tc_action *act; int err; int i; err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL); if (err < 0) - return ERR_PTR(err); + return err; for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { act = tcf_action_init_1(net, tb[i], est, name, ovr, bind); - if (IS_ERR(act)) + if (IS_ERR(act)) { + err = PTR_ERR(act); goto err; + } act->order = i; - - if (head == NULL) - head = act; - else - act_prev->next = act; - act_prev = act; + list_add_tail(&act->list, actions); } - return head; + return 0; err: - if (head != NULL) - tcf_action_destroy(head, bind); - return act; + tcf_action_destroy(actions, bind); + return err; } int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, @@ -615,9 +555,9 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, { int err = 0; struct gnet_dump d; - struct tcf_act_hdr *h = a->priv; + struct tcf_common *p = a->priv; - if (h == NULL) + if (p == NULL) goto errout; /* compat_mode being true specifies a call that is supposed @@ -626,24 +566,20 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, if (compat_mode) { if (a->type == TCA_OLD_COMPAT) err = gnet_stats_start_copy_compat(skb, 0, - TCA_STATS, TCA_XSTATS, &h->tcf_lock, &d); + TCA_STATS, TCA_XSTATS, &p->tcfc_lock, &d); else return 0; } else err = gnet_stats_start_copy(skb, TCA_ACT_STATS, - &h->tcf_lock, &d); + &p->tcfc_lock, &d); if (err < 0) goto errout; - if (a->ops != NULL && a->ops->get_stats != NULL) - if (a->ops->get_stats(skb, a) < 0) - goto errout; - - if (gnet_stats_copy_basic(&d, &h->tcf_bstats) < 0 || - gnet_stats_copy_rate_est(&d, &h->tcf_bstats, - &h->tcf_rate_est) < 0 || - gnet_stats_copy_queue(&d, &h->tcf_qstats) < 0) + if (gnet_stats_copy_basic(&d, &p->tcfc_bstats) < 0 || + gnet_stats_copy_rate_est(&d, &p->tcfc_bstats, + &p->tcfc_rate_est) < 0 || + gnet_stats_copy_queue(&d, &p->tcfc_qstats) < 0) goto errout; if (gnet_stats_finish_copy(&d) < 0) @@ -656,7 +592,7 @@ errout: } static int -tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 portid, u32 seq, +tca_get_fill(struct sk_buff *skb, struct list_head *actions, u32 portid, u32 seq, u16 flags, int event, int bind, int ref) { struct tcamsg *t; @@ -676,7 +612,7 @@ tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 portid, u32 seq, if (nest == NULL) goto out_nlmsg_trim; - if (tcf_action_dump(skb, a, bind, ref) < 0) + if (tcf_action_dump(skb, actions, bind, ref) < 0) goto out_nlmsg_trim; nla_nest_end(skb, nest); @@ -691,14 +627,14 @@ out_nlmsg_trim: static int act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, - struct tc_action *a, int event) + struct list_head *actions, int event) { struct sk_buff *skb; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; - if (tca_get_fill(skb, a, portid, n->nlmsg_seq, 0, event, 0, 0) <= 0) { + if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, 0, 0) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -729,9 +665,10 @@ tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid) if (a == NULL) goto err_out; + INIT_LIST_HEAD(&a->list); err = -EINVAL; a->ops = tc_lookup_action(tb[TCA_ACT_KIND]); - if (a->ops == NULL) + if (a->ops == NULL) /* could happen in batch of actions */ goto err_free; err = -ENOENT; if (a->ops->lookup(a, index) == 0) @@ -748,12 +685,12 @@ err_out: return ERR_PTR(err); } -static void cleanup_a(struct tc_action *act) +static void cleanup_a(struct list_head *actions) { - struct tc_action *a; + struct tc_action *a, *tmp; - for (a = act; a; a = act) { - act = a->next; + list_for_each_entry_safe(a, tmp, actions, list) { + list_del(&a->list); kfree(a); } } @@ -768,6 +705,7 @@ static struct tc_action *create_a(int i) return NULL; } act->order = i; + INIT_LIST_HEAD(&act->list); return act; } @@ -806,7 +744,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, err = -EINVAL; kind = tb[TCA_ACT_KIND]; a->ops = tc_lookup_action(kind); - if (a->ops == NULL) + if (a->ops == NULL) /*some idjot trying to flush unknown action */ goto err_out; nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0); @@ -850,12 +788,40 @@ noflush_out: } static int +tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, + u32 portid) +{ + int ret; + struct sk_buff *skb; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION, + 0, 1) <= 0) { + kfree_skb(skb); + return -EINVAL; + } + + /* now do the delete */ + tcf_action_destroy(actions, 0); + + ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + if (ret > 0) + return 0; + return ret; +} + +static int tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid, int event) { int i, ret; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; - struct tc_action *head = NULL, *act, *act_prev = NULL; + struct tc_action *act; + LIST_HEAD(actions); ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL); if (ret < 0) @@ -875,117 +841,62 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, goto err; } act->order = i; - - if (head == NULL) - head = act; - else - act_prev->next = act; - act_prev = act; + list_add_tail(&act->list, &actions); } if (event == RTM_GETACTION) - ret = act_get_notify(net, portid, n, head, event); + ret = act_get_notify(net, portid, n, &actions, event); else { /* delete */ - struct sk_buff *skb; - - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) { - ret = -ENOBUFS; - goto err; - } - - if (tca_get_fill(skb, head, portid, n->nlmsg_seq, 0, event, - 0, 1) <= 0) { - kfree_skb(skb); - ret = -EINVAL; + ret = tcf_del_notify(net, n, &actions, portid); + if (ret) goto err; - } - - /* now do the delete */ - tcf_action_destroy(head, 0); - ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); - if (ret > 0) - return 0; return ret; } err: - cleanup_a(head); + cleanup_a(&actions); return ret; } -static int tcf_add_notify(struct net *net, struct tc_action *a, - u32 portid, u32 seq, int event, u16 flags) +static int +tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, + u32 portid) { - struct tcamsg *t; - struct nlmsghdr *nlh; struct sk_buff *skb; - struct nlattr *nest; - unsigned char *b; int err = 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; - b = skb_tail_pointer(skb); - - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*t), flags); - if (!nlh) - goto out_kfree_skb; - t = nlmsg_data(nlh); - t->tca_family = AF_UNSPEC; - t->tca__pad1 = 0; - t->tca__pad2 = 0; - - nest = nla_nest_start(skb, TCA_ACT_TAB); - if (nest == NULL) - goto out_kfree_skb; - - if (tcf_action_dump(skb, a, 0, 0) < 0) - goto out_kfree_skb; - - nla_nest_end(skb, nest); - - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - NETLINK_CB(skb).dst_group = RTNLGRP_TC; + if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags, + RTM_NEWACTION, 0, 0) <= 0) { + kfree_skb(skb); + return -EINVAL; + } - err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); if (err > 0) err = 0; return err; - -out_kfree_skb: - kfree_skb(skb); - return -1; } - static int tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid, int ovr) { int ret = 0; - struct tc_action *act; - struct tc_action *a; - u32 seq = n->nlmsg_seq; + LIST_HEAD(actions); - act = tcf_action_init(net, nla, NULL, NULL, ovr, 0); - if (act == NULL) - goto done; - if (IS_ERR(act)) { - ret = PTR_ERR(act); + ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions); + if (ret) goto done; - } /* dump then free all the actions after update; inserted policy * stays intact */ - ret = tcf_add_notify(net, act, portid, seq, RTM_NEWACTION, n->nlmsg_flags); - for (a = act; a; a = act) { - act = a->next; - kfree(a); - } + ret = tcf_add_notify(net, n, &actions, portid); + cleanup_a(&actions); done: return ret; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 11fe1a416433..2210187c45c2 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -37,15 +37,7 @@ #include <net/tc_act/tc_csum.h> #define CSUM_TAB_MASK 15 -static struct tcf_common *tcf_csum_ht[CSUM_TAB_MASK + 1]; -static u32 csum_idx_gen; -static DEFINE_RWLOCK(csum_lock); - -static struct tcf_hashinfo csum_hash_info = { - .htab = tcf_csum_ht, - .hmask = CSUM_TAB_MASK, - .lock = &csum_lock, -}; +static struct tcf_hashinfo csum_hash_info; static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { [TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), }, @@ -71,17 +63,16 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); - pc = tcf_hash_check(parm->index, a, bind, &csum_hash_info); + pc = tcf_hash_check(parm->index, a, bind); if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, - &csum_idx_gen, &csum_hash_info); + pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; } else { if (bind)/* dont override defaults */ return 0; - tcf_hash_release(pc, bind, &csum_hash_info); + tcf_hash_release(pc, bind, a->ops->hinfo); if (!ovr) return -EEXIST; } @@ -93,7 +84,7 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, &csum_hash_info); + tcf_hash_insert(pc, a->ops->hinfo); return ret; } @@ -580,7 +571,6 @@ static struct tc_action_ops act_csum_ops = { .kind = "csum", .hinfo = &csum_hash_info, .type = TCA_ACT_CSUM, - .capab = TCA_CAP_NONE, .owner = THIS_MODULE, .act = tcf_csum, .dump = tcf_csum_dump, @@ -593,6 +583,10 @@ MODULE_LICENSE("GPL"); static int __init csum_init_module(void) { + int err = tcf_hashinfo_init(&csum_hash_info, CSUM_TAB_MASK); + if (err) + return err; + return tcf_register_action(&act_csum_ops); } diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index eb9ba60ebab4..a0eed30d5811 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -24,20 +24,12 @@ #include <net/tc_act/tc_gact.h> #define GACT_TAB_MASK 15 -static struct tcf_common *tcf_gact_ht[GACT_TAB_MASK + 1]; -static u32 gact_idx_gen; -static DEFINE_RWLOCK(gact_lock); - -static struct tcf_hashinfo gact_hash_info = { - .htab = tcf_gact_ht, - .hmask = GACT_TAB_MASK, - .lock = &gact_lock, -}; +static struct tcf_hashinfo gact_hash_info; #ifdef CONFIG_GACT_PROB static int gact_net_rand(struct tcf_gact *gact) { - if (!gact->tcfg_pval || net_random() % gact->tcfg_pval) + if (!gact->tcfg_pval || prandom_u32() % gact->tcfg_pval) return gact->tcf_action; return gact->tcfg_paction; } @@ -94,17 +86,16 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, } #endif - pc = tcf_hash_check(parm->index, a, bind, &gact_hash_info); + pc = tcf_hash_check(parm->index, a, bind); if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*gact), - bind, &gact_idx_gen, &gact_hash_info); + pc = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; } else { if (bind)/* dont override defaults */ return 0; - tcf_hash_release(pc, bind, &gact_hash_info); + tcf_hash_release(pc, bind, a->ops->hinfo); if (!ovr) return -EEXIST; } @@ -122,7 +113,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, #endif spin_unlock_bh(&gact->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, &gact_hash_info); + tcf_hash_insert(pc, a->ops->hinfo); return ret; } @@ -131,7 +122,7 @@ static int tcf_gact_cleanup(struct tc_action *a, int bind) struct tcf_gact *gact = a->priv; if (gact) - return tcf_hash_release(&gact->common, bind, &gact_hash_info); + return tcf_hash_release(&gact->common, bind, a->ops->hinfo); return 0; } @@ -202,7 +193,6 @@ static struct tc_action_ops act_gact_ops = { .kind = "gact", .hinfo = &gact_hash_info, .type = TCA_ACT_GACT, - .capab = TCA_CAP_NONE, .owner = THIS_MODULE, .act = tcf_gact, .dump = tcf_gact_dump, @@ -216,6 +206,9 @@ MODULE_LICENSE("GPL"); static int __init gact_init_module(void) { + int err = tcf_hashinfo_init(&gact_hash_info, GACT_TAB_MASK); + if (err) + return err; #ifdef CONFIG_GACT_PROB pr_info("GACT probability on\n"); #else @@ -227,6 +220,7 @@ static int __init gact_init_module(void) static void __exit gact_cleanup_module(void) { tcf_unregister_action(&act_gact_ops); + tcf_hashinfo_destroy(&gact_hash_info); } module_init(gact_init_module); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index dcbfe8ce04a6..0a6d62174027 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -29,15 +29,7 @@ #define IPT_TAB_MASK 15 -static struct tcf_common *tcf_ipt_ht[IPT_TAB_MASK + 1]; -static u32 ipt_idx_gen; -static DEFINE_RWLOCK(ipt_lock); - -static struct tcf_hashinfo ipt_hash_info = { - .htab = tcf_ipt_ht, - .hmask = IPT_TAB_MASK, - .lock = &ipt_lock, -}; +static struct tcf_hashinfo ipt_hash_info; static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook) { @@ -133,10 +125,9 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, if (tb[TCA_IPT_INDEX] != NULL) index = nla_get_u32(tb[TCA_IPT_INDEX]); - pc = tcf_hash_check(index, a, bind, &ipt_hash_info); + pc = tcf_hash_check(index, a, bind); if (!pc) { - pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind, - &ipt_idx_gen, &ipt_hash_info); + pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; @@ -179,7 +170,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, ipt->tcfi_hook = hook; spin_unlock_bh(&ipt->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, &ipt_hash_info); + tcf_hash_insert(pc, a->ops->hinfo); return ret; err3: @@ -295,7 +286,6 @@ static struct tc_action_ops act_ipt_ops = { .kind = "ipt", .hinfo = &ipt_hash_info, .type = TCA_ACT_IPT, - .capab = TCA_CAP_NONE, .owner = THIS_MODULE, .act = tcf_ipt, .dump = tcf_ipt_dump, @@ -306,8 +296,7 @@ static struct tc_action_ops act_ipt_ops = { static struct tc_action_ops act_xt_ops = { .kind = "xt", .hinfo = &ipt_hash_info, - .type = TCA_ACT_IPT, - .capab = TCA_CAP_NONE, + .type = TCA_ACT_XT, .owner = THIS_MODULE, .act = tcf_ipt, .dump = tcf_ipt_dump, @@ -322,7 +311,11 @@ MODULE_ALIAS("act_xt"); static int __init ipt_init_module(void) { - int ret1, ret2; + int ret1, ret2, err; + err = tcf_hashinfo_init(&ipt_hash_info, IPT_TAB_MASK); + if (err) + return err; + ret1 = tcf_register_action(&act_xt_ops); if (ret1 < 0) printk("Failed to load xt action\n"); @@ -330,9 +323,10 @@ static int __init ipt_init_module(void) if (ret2 < 0) printk("Failed to load ipt action\n"); - if (ret1 < 0 && ret2 < 0) + if (ret1 < 0 && ret2 < 0) { + tcf_hashinfo_destroy(&ipt_hash_info); return ret1; - else + } else return 0; } @@ -340,6 +334,7 @@ static void __exit ipt_cleanup_module(void) { tcf_unregister_action(&act_xt_ops); tcf_unregister_action(&act_ipt_ops); + tcf_hashinfo_destroy(&ipt_hash_info); } module_init(ipt_init_module); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 252378121ce7..0b2c6d39d396 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -30,16 +30,8 @@ #include <linux/if_arp.h> #define MIRRED_TAB_MASK 7 -static struct tcf_common *tcf_mirred_ht[MIRRED_TAB_MASK + 1]; -static u32 mirred_idx_gen; -static DEFINE_RWLOCK(mirred_lock); static LIST_HEAD(mirred_list); - -static struct tcf_hashinfo mirred_hash_info = { - .htab = tcf_mirred_ht, - .hmask = MIRRED_TAB_MASK, - .lock = &mirred_lock, -}; +static struct tcf_hashinfo mirred_hash_info; static int tcf_mirred_release(struct tcf_mirred *m, int bind) { @@ -109,12 +101,11 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, dev = NULL; } - pc = tcf_hash_check(parm->index, a, bind, &mirred_hash_info); + pc = tcf_hash_check(parm->index, a, bind); if (!pc) { if (dev == NULL) return -EINVAL; - pc = tcf_hash_create(parm->index, est, a, sizeof(*m), bind, - &mirred_idx_gen, &mirred_hash_info); + pc = tcf_hash_create(parm->index, est, a, sizeof(*m), bind); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; @@ -140,7 +131,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&m->tcf_lock); if (ret == ACT_P_CREATED) { list_add(&m->tcfm_list, &mirred_list); - tcf_hash_insert(pc, &mirred_hash_info); + tcf_hash_insert(pc, a->ops->hinfo); } return ret; @@ -261,12 +252,10 @@ static struct notifier_block mirred_device_notifier = { .notifier_call = mirred_device_event, }; - static struct tc_action_ops act_mirred_ops = { .kind = "mirred", .hinfo = &mirred_hash_info, .type = TCA_ACT_MIRRED, - .capab = TCA_CAP_NONE, .owner = THIS_MODULE, .act = tcf_mirred, .dump = tcf_mirred_dump, @@ -284,14 +273,20 @@ static int __init mirred_init_module(void) if (err) return err; + err = tcf_hashinfo_init(&mirred_hash_info, MIRRED_TAB_MASK); + if (err) { + unregister_netdevice_notifier(&mirred_device_notifier); + return err; + } pr_info("Mirror/redirect action on\n"); return tcf_register_action(&act_mirred_ops); } static void __exit mirred_cleanup_module(void) { - unregister_netdevice_notifier(&mirred_device_notifier); tcf_unregister_action(&act_mirred_ops); + tcf_hashinfo_destroy(&mirred_hash_info); + unregister_netdevice_notifier(&mirred_device_notifier); } module_init(mirred_init_module); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 76869538d028..81f0404bb335 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -30,15 +30,8 @@ #define NAT_TAB_MASK 15 -static struct tcf_common *tcf_nat_ht[NAT_TAB_MASK + 1]; -static u32 nat_idx_gen; -static DEFINE_RWLOCK(nat_lock); - -static struct tcf_hashinfo nat_hash_info = { - .htab = tcf_nat_ht, - .hmask = NAT_TAB_MASK, - .lock = &nat_lock, -}; + +static struct tcf_hashinfo nat_hash_info; static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { [TCA_NAT_PARMS] = { .len = sizeof(struct tc_nat) }, @@ -64,17 +57,16 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, return -EINVAL; parm = nla_data(tb[TCA_NAT_PARMS]); - pc = tcf_hash_check(parm->index, a, bind, &nat_hash_info); + pc = tcf_hash_check(parm->index, a, bind); if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, - &nat_idx_gen, &nat_hash_info); + pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); if (IS_ERR(pc)) return PTR_ERR(pc); ret = ACT_P_CREATED; } else { if (bind) return 0; - tcf_hash_release(pc, bind, &nat_hash_info); + tcf_hash_release(pc, bind, a->ops->hinfo); if (!ovr) return -EEXIST; } @@ -90,7 +82,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, &nat_hash_info); + tcf_hash_insert(pc, a->ops->hinfo); return ret; } @@ -303,7 +295,6 @@ static struct tc_action_ops act_nat_ops = { .kind = "nat", .hinfo = &nat_hash_info, .type = TCA_ACT_NAT, - .capab = TCA_CAP_NONE, .owner = THIS_MODULE, .act = tcf_nat, .dump = tcf_nat_dump, @@ -316,12 +307,16 @@ MODULE_LICENSE("GPL"); static int __init nat_init_module(void) { + int err = tcf_hashinfo_init(&nat_hash_info, NAT_TAB_MASK); + if (err) + return err; return tcf_register_action(&act_nat_ops); } static void __exit nat_cleanup_module(void) { tcf_unregister_action(&act_nat_ops); + tcf_hashinfo_destroy(&nat_hash_info); } module_init(nat_init_module); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 7aa2dcd989f8..be3f0f6875bb 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -24,15 +24,8 @@ #include <net/tc_act/tc_pedit.h> #define PEDIT_TAB_MASK 15 -static struct tcf_common *tcf_pedit_ht[PEDIT_TAB_MASK + 1]; -static u32 pedit_idx_gen; -static DEFINE_RWLOCK(pedit_lock); - -static struct tcf_hashinfo pedit_hash_info = { - .htab = tcf_pedit_ht, - .hmask = PEDIT_TAB_MASK, - .lock = &pedit_lock, -}; + +static struct tcf_hashinfo pedit_hash_info; static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, @@ -64,12 +57,11 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (nla_len(tb[TCA_PEDIT_PARMS]) < sizeof(*parm) + ksize) return -EINVAL; - pc = tcf_hash_check(parm->index, a, bind, &pedit_hash_info); + pc = tcf_hash_check(parm->index, a, bind); if (!pc) { if (!parm->nkeys) return -EINVAL; - pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, - &pedit_idx_gen, &pedit_hash_info); + pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); if (IS_ERR(pc)) return PTR_ERR(pc); p = to_pedit(pc); @@ -84,7 +76,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, ret = ACT_P_CREATED; } else { p = to_pedit(pc); - tcf_hash_release(pc, bind, &pedit_hash_info); + tcf_hash_release(pc, bind, a->ops->hinfo); if (bind) return 0; if (!ovr) @@ -108,7 +100,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, memcpy(p->tcfp_keys, parm->keys, ksize); spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, &pedit_hash_info); + tcf_hash_insert(pc, a->ops->hinfo); return ret; } @@ -240,7 +232,6 @@ static struct tc_action_ops act_pedit_ops = { .kind = "pedit", .hinfo = &pedit_hash_info, .type = TCA_ACT_PEDIT, - .capab = TCA_CAP_NONE, .owner = THIS_MODULE, .act = tcf_pedit, .dump = tcf_pedit_dump, @@ -254,11 +245,15 @@ MODULE_LICENSE("GPL"); static int __init pedit_init_module(void) { + int err = tcf_hashinfo_init(&pedit_hash_info, PEDIT_TAB_MASK); + if (err) + return err; return tcf_register_action(&act_pedit_ops); } static void __exit pedit_cleanup_module(void) { + tcf_hashinfo_destroy(&pedit_hash_info); tcf_unregister_action(&act_pedit_ops); } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index ef246d87e68b..1778209a332f 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -41,15 +41,7 @@ struct tcf_police { container_of(pc, struct tcf_police, common) #define POL_TAB_MASK 15 -static struct tcf_common *tcf_police_ht[POL_TAB_MASK + 1]; -static u32 police_idx_gen; -static DEFINE_RWLOCK(police_lock); - -static struct tcf_hashinfo police_hash_info = { - .htab = tcf_police_ht, - .hmask = POL_TAB_MASK, - .lock = &police_lock, -}; +static struct tcf_hashinfo police_hash_info; /* old policer structure from before tc actions */ struct tc_police_compat { @@ -67,18 +59,20 @@ struct tc_police_compat { static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *cb, int type, struct tc_action *a) { + struct tcf_hashinfo *hinfo = a->ops->hinfo; + struct hlist_head *head; struct tcf_common *p; int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; struct nlattr *nest; - read_lock_bh(&police_lock); + spin_lock_bh(&hinfo->lock); s_i = cb->args[0]; for (i = 0; i < (POL_TAB_MASK + 1); i++) { - p = tcf_police_ht[tcf_hash(i, POL_TAB_MASK)]; + head = &hinfo->htab[tcf_hash(i, POL_TAB_MASK)]; - for (; p; p = p->tcfc_next) { + hlist_for_each_entry_rcu(p, head, tcfc_head) { index++; if (index < s_i) continue; @@ -101,7 +95,7 @@ static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *c } } done: - read_unlock_bh(&police_lock); + spin_unlock_bh(&hinfo->lock); if (n_i) cb->args[0] += n_i; return n_i; @@ -111,29 +105,6 @@ nla_put_failure: goto done; } -static void tcf_police_destroy(struct tcf_police *p) -{ - unsigned int h = tcf_hash(p->tcf_index, POL_TAB_MASK); - struct tcf_common **p1p; - - for (p1p = &tcf_police_ht[h]; *p1p; p1p = &(*p1p)->tcfc_next) { - if (*p1p == &p->common) { - write_lock_bh(&police_lock); - *p1p = p->tcf_next; - write_unlock_bh(&police_lock); - gen_kill_estimator(&p->tcf_bstats, - &p->tcf_rate_est); - /* - * gen_estimator est_timer() might access p->tcf_lock - * or bstats, wait a RCU grace period before freeing p - */ - kfree_rcu(p, tcf_rcu); - return; - } - } - WARN_ON(1); -} - static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { [TCA_POLICE_RATE] = { .len = TC_RTAB_SIZE }, [TCA_POLICE_PEAKRATE] = { .len = TC_RTAB_SIZE }, @@ -151,6 +122,7 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla, struct tc_police *parm; struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; + struct tcf_hashinfo *hinfo = a->ops->hinfo; int size; if (nla == NULL) @@ -168,12 +140,8 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_POLICE_TBF]); if (parm->index) { - struct tcf_common *pc; - - pc = tcf_hash_lookup(parm->index, &police_hash_info); - if (pc != NULL) { - a->priv = pc; - police = to_police(pc); + if (tcf_hash_search(a, parm->index)) { + police = to_police(a->priv); if (bind) { police->tcf_bindcnt += 1; police->tcf_refcnt += 1; @@ -266,12 +234,11 @@ override: police->tcfp_t_c = ktime_to_ns(ktime_get()); police->tcf_index = parm->index ? parm->index : - tcf_hash_new_index(&police_idx_gen, &police_hash_info); + tcf_hash_new_index(a->ops->hinfo); h = tcf_hash(police->tcf_index, POL_TAB_MASK); - write_lock_bh(&police_lock); - police->tcf_next = tcf_police_ht[h]; - tcf_police_ht[h] = &police->common; - write_unlock_bh(&police_lock); + spin_lock_bh(&hinfo->lock); + hlist_add_head(&police->tcf_head, &hinfo->htab[h]); + spin_unlock_bh(&hinfo->lock); a->priv = police; return ret; @@ -279,10 +246,8 @@ override: failure_unlock: spin_unlock_bh(&police->tcf_lock); failure: - if (P_tab) - qdisc_put_rtab(P_tab); - if (R_tab) - qdisc_put_rtab(R_tab); + qdisc_put_rtab(P_tab); + qdisc_put_rtab(R_tab); if (ret == ACT_P_CREATED) kfree(police); return err; @@ -291,19 +256,9 @@ failure: static int tcf_act_police_cleanup(struct tc_action *a, int bind) { struct tcf_police *p = a->priv; - int ret = 0; - - if (p != NULL) { - if (bind) - p->tcf_bindcnt--; - - p->tcf_refcnt--; - if (p->tcf_refcnt <= 0 && !p->tcf_bindcnt) { - tcf_police_destroy(p); - ret = 1; - } - } - return ret; + if (p) + return tcf_hash_release(&p->common, bind, &police_hash_info); + return 0; } static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a, @@ -404,7 +359,6 @@ static struct tc_action_ops act_police_ops = { .kind = "police", .hinfo = &police_hash_info, .type = TCA_ID_POLICE, - .capab = TCA_CAP_NONE, .owner = THIS_MODULE, .act = tcf_act_police, .dump = tcf_act_police_dump, @@ -416,12 +370,19 @@ static struct tc_action_ops act_police_ops = { static int __init police_init_module(void) { - return tcf_register_action(&act_police_ops); + int err = tcf_hashinfo_init(&police_hash_info, POL_TAB_MASK); + if (err) + return err; + err = tcf_register_action(&act_police_ops); + if (err) + tcf_hashinfo_destroy(&police_hash_info); + return err; } static void __exit police_cleanup_module(void) { + tcf_hashinfo_destroy(&police_hash_info); tcf_unregister_action(&act_police_ops); } diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index f7b45ab85388..8ef2f1fcbfba 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -25,15 +25,7 @@ #include <net/tc_act/tc_defact.h> #define SIMP_TAB_MASK 7 -static struct tcf_common *tcf_simp_ht[SIMP_TAB_MASK + 1]; -static u32 simp_idx_gen; -static DEFINE_RWLOCK(simp_lock); - -static struct tcf_hashinfo simp_hash_info = { - .htab = tcf_simp_ht, - .hmask = SIMP_TAB_MASK, - .lock = &simp_lock, -}; +static struct tcf_hashinfo simp_hash_info; #define SIMP_MAX_DATA 32 static int tcf_simp(struct sk_buff *skb, const struct tc_action *a, @@ -122,10 +114,9 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_DEF_PARMS]); defdata = nla_data(tb[TCA_DEF_DATA]); - pc = tcf_hash_check(parm->index, a, bind, &simp_hash_info); + pc = tcf_hash_check(parm->index, a, bind); if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, - &simp_idx_gen, &simp_hash_info); + pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); if (IS_ERR(pc)) return PTR_ERR(pc); @@ -153,7 +144,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, } if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, &simp_hash_info); + tcf_hash_insert(pc, a->ops->hinfo); return ret; } @@ -198,7 +189,6 @@ static struct tc_action_ops act_simp_ops = { .kind = "simple", .hinfo = &simp_hash_info, .type = TCA_ACT_SIMP, - .capab = TCA_CAP_NONE, .owner = THIS_MODULE, .act = tcf_simp, .dump = tcf_simp_dump, @@ -212,14 +202,23 @@ MODULE_LICENSE("GPL"); static int __init simp_init_module(void) { - int ret = tcf_register_action(&act_simp_ops); + int err, ret; + err = tcf_hashinfo_init(&simp_hash_info, SIMP_TAB_MASK); + if (err) + return err; + + ret = tcf_register_action(&act_simp_ops); if (!ret) pr_info("Simple TC action Loaded\n"); + else + tcf_hashinfo_destroy(&simp_hash_info); + return ret; } static void __exit simp_cleanup_module(void) { + tcf_hashinfo_destroy(&simp_hash_info); tcf_unregister_action(&act_simp_ops); } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 8fe9d25c3008..98725080b5aa 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -11,8 +11,7 @@ * more details. * * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 Temple - * Place - Suite 330, Boston, MA 02111-1307 USA. + * this program; if not, see <http://www.gnu.org/licenses/>. * * Author: Alexander Duyck <alexander.h.duyck@intel.com> */ @@ -29,15 +28,7 @@ #include <net/tc_act/tc_skbedit.h> #define SKBEDIT_TAB_MASK 15 -static struct tcf_common *tcf_skbedit_ht[SKBEDIT_TAB_MASK + 1]; -static u32 skbedit_idx_gen; -static DEFINE_RWLOCK(skbedit_lock); - -static struct tcf_hashinfo skbedit_hash_info = { - .htab = tcf_skbedit_ht, - .hmask = SKBEDIT_TAB_MASK, - .lock = &skbedit_lock, -}; +static struct tcf_hashinfo skbedit_hash_info; static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) @@ -109,10 +100,9 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_SKBEDIT_PARMS]); - pc = tcf_hash_check(parm->index, a, bind, &skbedit_hash_info); + pc = tcf_hash_check(parm->index, a, bind); if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, - &skbedit_idx_gen, &skbedit_hash_info); + pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); if (IS_ERR(pc)) return PTR_ERR(pc); @@ -122,7 +112,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, d = to_skbedit(pc); if (bind) return 0; - tcf_hash_release(pc, bind, &skbedit_hash_info); + tcf_hash_release(pc, bind, a->ops->hinfo); if (!ovr) return -EEXIST; } @@ -142,7 +132,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&d->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, &skbedit_hash_info); + tcf_hash_insert(pc, a->ops->hinfo); return ret; } @@ -198,7 +188,6 @@ static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", .hinfo = &skbedit_hash_info, .type = TCA_ACT_SKBEDIT, - .capab = TCA_CAP_NONE, .owner = THIS_MODULE, .act = tcf_skbedit, .dump = tcf_skbedit_dump, @@ -212,11 +201,15 @@ MODULE_LICENSE("GPL"); static int __init skbedit_init_module(void) { + int err = tcf_hashinfo_init(&skbedit_hash_info, SKBEDIT_TAB_MASK); + if (err) + return err; return tcf_register_action(&act_skbedit_ops); } static void __exit skbedit_cleanup_module(void) { + tcf_hashinfo_destroy(&skbedit_hash_info); tcf_unregister_action(&act_skbedit_ops); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8e118af90973..29a30a14c315 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -31,8 +31,7 @@ #include <net/pkt_cls.h> /* The list of all installed classifier types */ - -static struct tcf_proto_ops *tcf_proto_base __read_mostly; +static LIST_HEAD(tcf_proto_base); /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(cls_mod_lock); @@ -41,36 +40,35 @@ static DEFINE_RWLOCK(cls_mod_lock); static const struct tcf_proto_ops *tcf_proto_lookup_ops(struct nlattr *kind) { - const struct tcf_proto_ops *t = NULL; + const struct tcf_proto_ops *t, *res = NULL; if (kind) { read_lock(&cls_mod_lock); - for (t = tcf_proto_base; t; t = t->next) { + list_for_each_entry(t, &tcf_proto_base, head) { if (nla_strcmp(kind, t->kind) == 0) { - if (!try_module_get(t->owner)) - t = NULL; + if (try_module_get(t->owner)) + res = t; break; } } read_unlock(&cls_mod_lock); } - return t; + return res; } /* Register(unregister) new classifier type */ int register_tcf_proto_ops(struct tcf_proto_ops *ops) { - struct tcf_proto_ops *t, **tp; + struct tcf_proto_ops *t; int rc = -EEXIST; write_lock(&cls_mod_lock); - for (tp = &tcf_proto_base; (t = *tp) != NULL; tp = &t->next) + list_for_each_entry(t, &tcf_proto_base, head) if (!strcmp(ops->kind, t->kind)) goto out; - ops->next = NULL; - *tp = ops; + list_add_tail(&ops->head, &tcf_proto_base); rc = 0; out: write_unlock(&cls_mod_lock); @@ -80,19 +78,17 @@ EXPORT_SYMBOL(register_tcf_proto_ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) { - struct tcf_proto_ops *t, **tp; + struct tcf_proto_ops *t; int rc = -ENOENT; write_lock(&cls_mod_lock); - for (tp = &tcf_proto_base; (t = *tp) != NULL; tp = &t->next) - if (t == ops) + list_for_each_entry(t, &tcf_proto_base, head) { + if (t == ops) { + list_del(&t->head); + rc = 0; break; - - if (!t) - goto out; - *tp = t->next; - rc = 0; -out: + } + } write_unlock(&cls_mod_lock); return rc; } @@ -344,7 +340,7 @@ errout: return err; } -static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, +static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp, unsigned long fh, u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; @@ -366,7 +362,7 @@ static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, tcm->tcm_handle = fh; if (RTM_DELTFILTER != event) { tcm->tcm_handle = 0; - if (tp->ops->dump && tp->ops->dump(tp, fh, skb, tcm) < 0) + if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0) goto nla_put_failure; } nlh->nlmsg_len = skb_tail_pointer(skb) - b; @@ -389,7 +385,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) { + if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -408,8 +404,9 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, struct tcf_walker *arg) { struct tcf_dump_args *a = (void *)arg; + struct net *net = sock_net(a->skb->sk); - return tcf_fill_node(a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, + return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER); } @@ -467,7 +464,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (t > s_t) memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(skb, tp, 0, NETLINK_CB(cb->skb).portid, + if (tcf_fill_node(net, skb, tp, 0, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) break; @@ -500,46 +497,41 @@ out: void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - if (exts->action) { - tcf_action_destroy(exts->action, TCA_ACT_UNBIND); - exts->action = NULL; - } + tcf_action_destroy(&exts->actions, TCA_ACT_UNBIND); + INIT_LIST_HEAD(&exts->actions); #endif } EXPORT_SYMBOL(tcf_exts_destroy); int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, - struct nlattr *rate_tlv, struct tcf_exts *exts, - const struct tcf_ext_map *map) + struct nlattr *rate_tlv, struct tcf_exts *exts) { - memset(exts, 0, sizeof(*exts)); - #ifdef CONFIG_NET_CLS_ACT { struct tc_action *act; - if (map->police && tb[map->police]) { - act = tcf_action_init_1(net, tb[map->police], rate_tlv, + INIT_LIST_HEAD(&exts->actions); + if (exts->police && tb[exts->police]) { + act = tcf_action_init_1(net, tb[exts->police], rate_tlv, "police", TCA_ACT_NOREPLACE, TCA_ACT_BIND); if (IS_ERR(act)) return PTR_ERR(act); - act->type = TCA_OLD_COMPAT; - exts->action = act; - } else if (map->action && tb[map->action]) { - act = tcf_action_init(net, tb[map->action], rate_tlv, + act->type = exts->type = TCA_OLD_COMPAT; + list_add(&act->list, &exts->actions); + } else if (exts->action && tb[exts->action]) { + int err; + err = tcf_action_init(net, tb[exts->action], rate_tlv, NULL, TCA_ACT_NOREPLACE, - TCA_ACT_BIND); - if (IS_ERR(act)) - return PTR_ERR(act); - - exts->action = act; + TCA_ACT_BIND, &exts->actions); + if (err) + return err; } } #else - if ((map->action && tb[map->action]) || - (map->police && tb[map->police])) + if ((exts->action && tb[exts->action]) || + (exts->police && tb[exts->police])) return -EOPNOTSUPP; #endif @@ -551,43 +543,44 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, struct tcf_exts *src) { #ifdef CONFIG_NET_CLS_ACT - if (src->action) { - struct tc_action *act; + if (!list_empty(&src->actions)) { + LIST_HEAD(tmp); tcf_tree_lock(tp); - act = dst->action; - dst->action = src->action; + list_splice_init(&dst->actions, &tmp); + list_splice(&src->actions, &dst->actions); tcf_tree_unlock(tp); - if (act) - tcf_action_destroy(act, TCA_ACT_UNBIND); + tcf_action_destroy(&tmp, TCA_ACT_UNBIND); } #endif } EXPORT_SYMBOL(tcf_exts_change); -int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts, - const struct tcf_ext_map *map) +#define tcf_exts_first_act(ext) \ + list_first_entry(&(exts)->actions, struct tc_action, list) + +int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - if (map->action && exts->action) { + if (exts->action && !list_empty(&exts->actions)) { /* * again for backward compatible mode - we want * to work with both old and new modes of entering * tc data even if iproute2 was newer - jhs */ struct nlattr *nest; - - if (exts->action->type != TCA_OLD_COMPAT) { - nest = nla_nest_start(skb, map->action); + if (exts->type != TCA_OLD_COMPAT) { + nest = nla_nest_start(skb, exts->action); if (nest == NULL) goto nla_put_failure; - if (tcf_action_dump(skb, exts->action, 0, 0) < 0) + if (tcf_action_dump(skb, &exts->actions, 0, 0) < 0) goto nla_put_failure; nla_nest_end(skb, nest); - } else if (map->police) { - nest = nla_nest_start(skb, map->police); - if (nest == NULL) + } else if (exts->police) { + struct tc_action *act = tcf_exts_first_act(exts); + nest = nla_nest_start(skb, exts->police); + if (nest == NULL || !act) goto nla_put_failure; - if (tcf_action_dump_old(skb, exts->action, 0, 0) < 0) + if (tcf_action_dump_old(skb, act, 0, 0) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } @@ -600,17 +593,14 @@ nla_put_failure: __attribute__ ((unused)) EXPORT_SYMBOL(tcf_exts_dump); -int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts, - const struct tcf_ext_map *map) +int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - if (exts->action) - if (tcf_action_copy_stats(skb, exts->action, 1) < 0) - goto nla_put_failure; + struct tc_action *a = tcf_exts_first_act(exts); + if (tcf_action_copy_stats(skb, a, 1) < 0) + return -1; #endif return 0; -nla_put_failure: __attribute__ ((unused)) - return -1; } EXPORT_SYMBOL(tcf_exts_dump_stats); diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 636d9131d870..e98ca99c202b 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -34,16 +34,11 @@ struct basic_filter { struct list_head link; }; -static const struct tcf_ext_map basic_ext_map = { - .action = TCA_BASIC_ACT, - .police = TCA_BASIC_POLICE -}; - static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { int r; - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *f; list_for_each_entry(f, &head->flist, link) { @@ -61,7 +56,7 @@ static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long basic_get(struct tcf_proto *tp, u32 handle) { unsigned long l = 0UL; - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *f; if (head == NULL) @@ -112,7 +107,7 @@ static void basic_destroy(struct tcf_proto *tp) static int basic_delete(struct tcf_proto *tp, unsigned long arg) { - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *t, *f = (struct basic_filter *) arg; list_for_each_entry(t, &head->flist, link) @@ -141,7 +136,8 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp, struct tcf_exts e; struct tcf_ematch_tree t; - err = tcf_exts_validate(net, tp, tb, est, &e, &basic_ext_map); + tcf_exts_init(&e, TCA_BASIC_ACT, TCA_BASIC_POLICE); + err = tcf_exts_validate(net, tp, tb, est, &e); if (err < 0) return err; @@ -168,7 +164,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, struct nlattr **tca, unsigned long *arg) { int err; - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct nlattr *tb[TCA_BASIC_MAX + 1]; struct basic_filter *f = (struct basic_filter *) *arg; @@ -191,6 +187,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (f == NULL) goto errout; + tcf_exts_init(&f->exts, TCA_BASIC_ACT, TCA_BASIC_POLICE); err = -EINVAL; if (handle) f->handle = handle; @@ -228,7 +225,7 @@ errout: static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct basic_head *head = (struct basic_head *) tp->root; + struct basic_head *head = tp->root; struct basic_filter *f; list_for_each_entry(f, &head->flist, link) { @@ -244,7 +241,7 @@ skip: } } -static int basic_dump(struct tcf_proto *tp, unsigned long fh, +static int basic_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct basic_filter *f = (struct basic_filter *) fh; @@ -263,13 +260,13 @@ static int basic_dump(struct tcf_proto *tp, unsigned long fh, nla_put_u32(skb, TCA_BASIC_CLASSID, f->res.classid)) goto nla_put_failure; - if (tcf_exts_dump(skb, &f->exts, &basic_ext_map) < 0 || + if (tcf_exts_dump(skb, &f->exts) < 0 || tcf_em_tree_dump(skb, &f->ematches, TCA_BASIC_EMATCHES) < 0) goto nla_put_failure; nla_nest_end(skb, nest); - if (tcf_exts_dump_stats(skb, &f->exts, &basic_ext_map) < 0) + if (tcf_exts_dump_stats(skb, &f->exts) < 0) goto nla_put_failure; return skb->len; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 1002a8226281..8e3cf49118e3 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -46,11 +46,6 @@ static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, }; -static const struct tcf_ext_map bpf_ext_map = { - .action = TCA_BPF_ACT, - .police = TCA_BPF_POLICE, -}; - static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { @@ -174,7 +169,8 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, if (!tb[TCA_BPF_OPS_LEN] || !tb[TCA_BPF_OPS] || !tb[TCA_BPF_CLASSID]) return -EINVAL; - ret = tcf_exts_validate(net, tp, tb, est, &exts, &bpf_ext_map); + tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE); + ret = tcf_exts_validate(net, tp, tb, est, &exts); if (ret < 0) return ret; @@ -271,6 +267,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, if (prog == NULL) return -ENOBUFS; + tcf_exts_init(&prog->exts, TCA_BPF_ACT, TCA_BPF_POLICE); if (handle == 0) prog->handle = cls_bpf_grab_new_handle(tp, head); else @@ -298,7 +295,7 @@ errout: return ret; } -static int cls_bpf_dump(struct tcf_proto *tp, unsigned long fh, +static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *tm) { struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh; @@ -323,14 +320,14 @@ static int cls_bpf_dump(struct tcf_proto *tp, unsigned long fh, if (nla == NULL) goto nla_put_failure; - memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); + memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); - if (tcf_exts_dump(skb, &prog->exts, &bpf_ext_map) < 0) + if (tcf_exts_dump(skb, &prog->exts) < 0) goto nla_put_failure; nla_nest_end(skb, nest); - if (tcf_exts_dump_stats(skb, &prog->exts, &bpf_ext_map) < 0) + if (tcf_exts_dump_stats(skb, &prog->exts) < 0) goto nla_put_failure; return skb->len; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 16006c92c3fd..8e2158ab551c 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -11,109 +11,13 @@ #include <linux/module.h> #include <linux/slab.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/errno.h> #include <linux/skbuff.h> -#include <linux/cgroup.h> #include <linux/rcupdate.h> -#include <linux/fdtable.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/sock.h> #include <net/cls_cgroup.h> -static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct cgroup_cls_state, css) : NULL; -} - -static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p) -{ - return css_cls_state(task_css(p, net_cls_subsys_id)); -} - -static struct cgroup_subsys_state * -cgrp_css_alloc(struct cgroup_subsys_state *parent_css) -{ - struct cgroup_cls_state *cs; - - cs = kzalloc(sizeof(*cs), GFP_KERNEL); - if (!cs) - return ERR_PTR(-ENOMEM); - return &cs->css; -} - -static int cgrp_css_online(struct cgroup_subsys_state *css) -{ - struct cgroup_cls_state *cs = css_cls_state(css); - struct cgroup_cls_state *parent = css_cls_state(css_parent(css)); - - if (parent) - cs->classid = parent->classid; - return 0; -} - -static void cgrp_css_free(struct cgroup_subsys_state *css) -{ - kfree(css_cls_state(css)); -} - -static int update_classid(const void *v, struct file *file, unsigned n) -{ - int err; - struct socket *sock = sock_from_file(file, &err); - if (sock) - sock->sk->sk_classid = (u32)(unsigned long)v; - return 0; -} - -static void cgrp_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) -{ - struct task_struct *p; - struct cgroup_cls_state *cs = css_cls_state(css); - void *v = (void *)(unsigned long)cs->classid; - - cgroup_taskset_for_each(p, css, tset) { - task_lock(p); - iterate_fd(p->files, 0, update_classid, v); - task_unlock(p); - } -} - -static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft) -{ - return css_cls_state(css)->classid; -} - -static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, - u64 value) -{ - css_cls_state(css)->classid = (u32) value; - return 0; -} - -static struct cftype ss_files[] = { - { - .name = "classid", - .read_u64 = read_classid, - .write_u64 = write_classid, - }, - { } /* terminate */ -}; - -struct cgroup_subsys net_cls_subsys = { - .name = "net_cls", - .css_alloc = cgrp_css_alloc, - .css_online = cgrp_css_online, - .css_free = cgrp_css_free, - .attach = cgrp_attach, - .subsys_id = net_cls_subsys_id, - .base_cftypes = ss_files, - .module = THIS_MODULE, -}; - struct cls_cgroup_head { u32 handle; struct tcf_exts exts; @@ -172,11 +76,6 @@ static int cls_cgroup_init(struct tcf_proto *tp) return 0; } -static const struct tcf_ext_map cgroup_ext_map = { - .action = TCA_CGROUP_ACT, - .police = TCA_CGROUP_POLICE, -}; - static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = { [TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED }, }; @@ -203,6 +102,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, if (head == NULL) return -ENOBUFS; + tcf_exts_init(&head->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); head->handle = handle; tcf_tree_lock(tp); @@ -218,8 +118,8 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, - &cgroup_ext_map); + tcf_exts_init(&e, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e); if (err < 0) return err; @@ -264,7 +164,7 @@ skip: arg->count++; } -static int cls_cgroup_dump(struct tcf_proto *tp, unsigned long fh, +static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct cls_cgroup_head *head = tp->root; @@ -277,13 +177,13 @@ static int cls_cgroup_dump(struct tcf_proto *tp, unsigned long fh, if (nest == NULL) goto nla_put_failure; - if (tcf_exts_dump(skb, &head->exts, &cgroup_ext_map) < 0 || + if (tcf_exts_dump(skb, &head->exts) < 0 || tcf_em_tree_dump(skb, &head->ematches, TCA_CGROUP_EMATCHES) < 0) goto nla_put_failure; nla_nest_end(skb, nest); - if (tcf_exts_dump_stats(skb, &head->exts, &cgroup_ext_map) < 0) + if (tcf_exts_dump_stats(skb, &head->exts) < 0) goto nla_put_failure; return skb->len; @@ -309,25 +209,12 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = { static int __init init_cgroup_cls(void) { - int ret; - - ret = cgroup_load_subsys(&net_cls_subsys); - if (ret) - goto out; - - ret = register_tcf_proto_ops(&cls_cgroup_ops); - if (ret) - cgroup_unload_subsys(&net_cls_subsys); - -out: - return ret; + return register_tcf_proto_ops(&cls_cgroup_ops); } static void __exit exit_cgroup_cls(void) { unregister_tcf_proto_ops(&cls_cgroup_ops); - - cgroup_unload_subsys(&net_cls_subsys); } module_init(init_cgroup_cls); diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 7881e2fccbc2..257029c54332 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -56,11 +56,6 @@ struct flow_filter { u32 hashrnd; }; -static const struct tcf_ext_map flow_ext_map = { - .action = TCA_FLOW_ACT, - .police = TCA_FLOW_POLICE, -}; - static inline u32 addr_fold(void *addr) { unsigned long a = (unsigned long)addr; @@ -220,7 +215,7 @@ static u32 flow_get_vlan_tag(const struct sk_buff *skb) static u32 flow_get_rxhash(struct sk_buff *skb) { - return skb_get_rxhash(skb); + return skb_get_hash(skb); } static u32 flow_key_get(struct sk_buff *skb, int key, struct flow_keys *flow) @@ -397,7 +392,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, return -EOPNOTSUPP; } - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &flow_ext_map); + tcf_exts_init(&e, TCA_FLOW_ACT, TCA_FLOW_POLICE); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e); if (err < 0) return err; @@ -455,6 +451,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, f->handle = handle; f->mask = ~0U; + tcf_exts_init(&f->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE); get_random_bytes(&f->hashrnd, 4); f->perturb_timer.function = flow_perturbation; @@ -566,7 +563,7 @@ static void flow_put(struct tcf_proto *tp, unsigned long f) { } -static int flow_dump(struct tcf_proto *tp, unsigned long fh, +static int flow_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct flow_filter *f = (struct flow_filter *)fh; @@ -608,7 +605,7 @@ static int flow_dump(struct tcf_proto *tp, unsigned long fh, nla_put_u32(skb, TCA_FLOW_PERTURB, f->perturb_period / HZ)) goto nla_put_failure; - if (tcf_exts_dump(skb, &f->exts, &flow_ext_map) < 0) + if (tcf_exts_dump(skb, &f->exts) < 0) goto nla_put_failure; #ifdef CONFIG_NET_EMATCH if (f->ematches.hdr.nmatches && @@ -617,7 +614,7 @@ static int flow_dump(struct tcf_proto *tp, unsigned long fh, #endif nla_nest_end(skb, nest); - if (tcf_exts_dump_stats(skb, &f->exts, &flow_ext_map) < 0) + if (tcf_exts_dump_stats(skb, &f->exts) < 0) goto nla_put_failure; return skb->len; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 9b97172db84a..a366537f82c6 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -41,16 +41,11 @@ struct fw_filter { u32 id; struct tcf_result res; #ifdef CONFIG_NET_CLS_IND - char indev[IFNAMSIZ]; + int ifindex; #endif /* CONFIG_NET_CLS_IND */ struct tcf_exts exts; }; -static const struct tcf_ext_map fw_ext_map = { - .action = TCA_FW_ACT, - .police = TCA_FW_POLICE -}; - static inline int fw_hash(u32 handle) { if (HTSIZE == 4096) @@ -80,7 +75,7 @@ static inline int fw_hash(u32 handle) static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f; int r; u32 id = skb->mark; @@ -91,7 +86,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, if (f->id == id) { *res = f->res; #ifdef CONFIG_NET_CLS_IND - if (!tcf_match_indev(skb, f->indev)) + if (!tcf_match_indev(skb, f->ifindex)) continue; #endif /* CONFIG_NET_CLS_IND */ r = tcf_exts_exec(skb, &f->exts, res); @@ -116,7 +111,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long fw_get(struct tcf_proto *tp, u32 handle) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f; if (head == NULL) @@ -165,7 +160,7 @@ static void fw_destroy(struct tcf_proto *tp) static int fw_delete(struct tcf_proto *tp, unsigned long arg) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f = (struct fw_filter *)arg; struct fw_filter **fp; @@ -195,12 +190,13 @@ static int fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, struct nlattr **tb, struct nlattr **tca, unsigned long base) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct tcf_exts e; u32 mask; int err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &fw_ext_map); + tcf_exts_init(&e, TCA_FW_ACT, TCA_FW_POLICE); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e); if (err < 0) return err; @@ -211,9 +207,13 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, #ifdef CONFIG_NET_CLS_IND if (tb[TCA_FW_INDEV]) { - err = tcf_change_indev(tp, f->indev, tb[TCA_FW_INDEV]); - if (err < 0) + int ret; + ret = tcf_change_indev(net, tb[TCA_FW_INDEV]); + if (ret < 0) { + err = ret; goto errout; + } + f->ifindex = ret; } #endif /* CONFIG_NET_CLS_IND */ @@ -239,7 +239,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, struct nlattr **tca, unsigned long *arg) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f = (struct fw_filter *) *arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FW_MAX + 1]; @@ -280,6 +280,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, if (f == NULL) return -ENOBUFS; + tcf_exts_init(&f->exts, TCA_FW_ACT, TCA_FW_POLICE); f->id = handle; err = fw_change_attrs(net, tp, f, tb, tca, base); @@ -301,7 +302,7 @@ errout: static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; int h; if (head == NULL) @@ -327,10 +328,10 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int fw_dump(struct tcf_proto *tp, unsigned long fh, +static int fw_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct fw_head *head = (struct fw_head *)tp->root; + struct fw_head *head = tp->root; struct fw_filter *f = (struct fw_filter *)fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; @@ -351,20 +352,23 @@ static int fw_dump(struct tcf_proto *tp, unsigned long fh, nla_put_u32(skb, TCA_FW_CLASSID, f->res.classid)) goto nla_put_failure; #ifdef CONFIG_NET_CLS_IND - if (strlen(f->indev) && - nla_put_string(skb, TCA_FW_INDEV, f->indev)) - goto nla_put_failure; + if (f->ifindex) { + struct net_device *dev; + dev = __dev_get_by_index(net, f->ifindex); + if (dev && nla_put_string(skb, TCA_FW_INDEV, dev->name)) + goto nla_put_failure; + } #endif /* CONFIG_NET_CLS_IND */ if (head->mask != 0xFFFFFFFF && nla_put_u32(skb, TCA_FW_MASK, head->mask)) goto nla_put_failure; - if (tcf_exts_dump(skb, &f->exts, &fw_ext_map) < 0) + if (tcf_exts_dump(skb, &f->exts) < 0) goto nla_put_failure; nla_nest_end(skb, nest); - if (tcf_exts_dump_stats(skb, &f->exts, &fw_ext_map) < 0) + if (tcf_exts_dump_stats(skb, &f->exts) < 0) goto nla_put_failure; return skb->len; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 37da567d833e..1ad3068f2ce1 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -59,11 +59,6 @@ struct route4_filter { #define ROUTE4_FAILURE ((struct route4_filter *)(-1L)) -static const struct tcf_ext_map route_ext_map = { - .police = TCA_ROUTE4_POLICE, - .action = TCA_ROUTE4_ACT -}; - static inline int route4_fastmap_hash(u32 id, int iif) { return id & 0xF; @@ -128,7 +123,7 @@ static inline int route4_hash_wild(void) static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct route4_head *head = (struct route4_head *)tp->root; + struct route4_head *head = tp->root; struct dst_entry *dst; struct route4_bucket *b; struct route4_filter *f; @@ -218,7 +213,7 @@ static inline u32 from_hash(u32 id) static unsigned long route4_get(struct tcf_proto *tp, u32 handle) { - struct route4_head *head = (struct route4_head *)tp->root; + struct route4_head *head = tp->root; struct route4_bucket *b; struct route4_filter *f; unsigned int h1, h2; @@ -289,7 +284,7 @@ static void route4_destroy(struct tcf_proto *tp) static int route4_delete(struct tcf_proto *tp, unsigned long arg) { - struct route4_head *head = (struct route4_head *)tp->root; + struct route4_head *head = tp->root; struct route4_filter **fp, *f = (struct route4_filter *)arg; unsigned int h = 0; struct route4_bucket *b; @@ -347,7 +342,8 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, struct route4_bucket *b; struct tcf_exts e; - err = tcf_exts_validate(net, tp, tb, est, &e, &route_ext_map); + tcf_exts_init(&e, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); + err = tcf_exts_validate(net, tp, tb, est, &e); if (err < 0) return err; @@ -481,6 +477,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (f == NULL) goto errout; + tcf_exts_init(&f->exts, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); err = route4_set_parms(net, tp, base, f, handle, head, tb, tca[TCA_RATE], 1); if (err < 0) @@ -554,7 +551,7 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int route4_dump(struct tcf_proto *tp, unsigned long fh, +static int route4_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct route4_filter *f = (struct route4_filter *)fh; @@ -589,12 +586,12 @@ static int route4_dump(struct tcf_proto *tp, unsigned long fh, nla_put_u32(skb, TCA_ROUTE4_CLASSID, f->res.classid)) goto nla_put_failure; - if (tcf_exts_dump(skb, &f->exts, &route_ext_map) < 0) + if (tcf_exts_dump(skb, &f->exts) < 0) goto nla_put_failure; nla_nest_end(skb, nest); - if (tcf_exts_dump_stats(skb, &f->exts, &route_ext_map) < 0) + if (tcf_exts_dump_stats(skb, &f->exts) < 0) goto nla_put_failure; return skb->len; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 252d8b05872e..19f8e5dfa8bd 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -116,11 +116,6 @@ static inline unsigned int hash_src(__be32 *src) return h & 0xF; } -static struct tcf_ext_map rsvp_ext_map = { - .police = TCA_RSVP_POLICE, - .action = TCA_RSVP_ACT -}; - #define RSVP_APPLY_RESULT() \ { \ int r = tcf_exts_exec(skb, &f->exts, res); \ @@ -440,7 +435,8 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &rsvp_ext_map); + tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e); if (err < 0) return err; @@ -471,6 +467,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, if (f == NULL) goto errout2; + tcf_exts_init(&f->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE); h2 = 16; if (tb[TCA_RSVP_SRC]) { memcpy(f->src, nla_data(tb[TCA_RSVP_SRC]), sizeof(f->src)); @@ -597,7 +594,7 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, +static int rsvp_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct rsvp_filter *f = (struct rsvp_filter *)fh; @@ -633,12 +630,12 @@ static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, nla_put(skb, TCA_RSVP_SRC, sizeof(f->src), f->src)) goto nla_put_failure; - if (tcf_exts_dump(skb, &f->exts, &rsvp_ext_map) < 0) + if (tcf_exts_dump(skb, &f->exts) < 0) goto nla_put_failure; nla_nest_end(skb, nest); - if (tcf_exts_dump_stats(skb, &f->exts, &rsvp_ext_map) < 0) + if (tcf_exts_dump_stats(skb, &f->exts) < 0) goto nla_put_failure; return skb->len; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index b86535a40169..eed8404443d8 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -24,9 +24,6 @@ #define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */ -#define PRIV(tp) ((struct tcindex_data *) (tp)->root) - - struct tcindex_filter_result { struct tcf_exts exts; struct tcf_result res; @@ -50,11 +47,6 @@ struct tcindex_data { int fall_through; /* 0: only classify if explicit match */ }; -static const struct tcf_ext_map tcindex_ext_map = { - .police = TCA_TCINDEX_POLICE, - .action = TCA_TCINDEX_ACT -}; - static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) { @@ -82,7 +74,7 @@ tcindex_lookup(struct tcindex_data *p, u16 key) static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *f; int key = (skb->tc_index & p->mask) >> p->shift; @@ -107,7 +99,7 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, static unsigned long tcindex_get(struct tcf_proto *tp, u32 handle) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r; pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle); @@ -145,7 +137,7 @@ static int tcindex_init(struct tcf_proto *tp) static int __tcindex_delete(struct tcf_proto *tp, unsigned long arg, int lock) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r = (struct tcindex_filter_result *) arg; struct tcindex_filter *f = NULL; @@ -209,17 +201,21 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct tcindex_filter *f = NULL; /* make gcc behave */ struct tcf_exts e; - err = tcf_exts_validate(net, tp, tb, est, &e, &tcindex_ext_map); + tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); + err = tcf_exts_validate(net, tp, tb, est, &e); if (err < 0) return err; memcpy(&cp, p, sizeof(cp)); memset(&new_filter_result, 0, sizeof(new_filter_result)); + tcf_exts_init(&new_filter_result.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (old_r) memcpy(&cr, r, sizeof(cr)); - else + else { memset(&cr, 0, sizeof(cr)); + tcf_exts_init(&cr.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); + } if (tb[TCA_TCINDEX_HASH]) cp.hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); @@ -339,7 +335,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, { struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_TCINDEX_MAX + 1]; - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r = (struct tcindex_filter_result *) *arg; int err; @@ -361,7 +357,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter *f, *next; int i; @@ -408,7 +404,7 @@ static int tcindex_destroy_element(struct tcf_proto *tp, static void tcindex_destroy(struct tcf_proto *tp) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcf_walker walker; pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); @@ -423,10 +419,10 @@ static void tcindex_destroy(struct tcf_proto *tp) } -static int tcindex_dump(struct tcf_proto *tp, unsigned long fh, +static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct tcindex_data *p = PRIV(tp); + struct tcindex_data *p = tp->root; struct tcindex_filter_result *r = (struct tcindex_filter_result *) fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; @@ -468,11 +464,11 @@ static int tcindex_dump(struct tcf_proto *tp, unsigned long fh, nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid)) goto nla_put_failure; - if (tcf_exts_dump(skb, &r->exts, &tcindex_ext_map) < 0) + if (tcf_exts_dump(skb, &r->exts) < 0) goto nla_put_failure; nla_nest_end(skb, nest); - if (tcf_exts_dump_stats(skb, &r->exts, &tcindex_ext_map) < 0) + if (tcf_exts_dump_stats(skb, &r->exts) < 0) goto nla_put_failure; } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index eb07a1e536e6..84c28daff848 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -48,7 +48,7 @@ struct tc_u_knode { struct tc_u_hnode *ht_up; struct tcf_exts exts; #ifdef CONFIG_NET_CLS_IND - char indev[IFNAMSIZ]; + int ifindex; #endif u8 fshift; struct tcf_result res; @@ -79,11 +79,6 @@ struct tc_u_common { u32 hgenerator; }; -static const struct tcf_ext_map u32_ext_map = { - .action = TCA_U32_ACT, - .police = TCA_U32_POLICE -}; - static inline unsigned int u32_hash_fold(__be32 key, const struct tc_u32_sel *sel, u8 fshift) @@ -100,7 +95,7 @@ static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct unsigned int off; } stack[TC_U32_MAXDEPTH]; - struct tc_u_hnode *ht = (struct tc_u_hnode *)tp->root; + struct tc_u_hnode *ht = tp->root; unsigned int off = skb_network_offset(skb); struct tc_u_knode *n; int sdepth = 0; @@ -157,7 +152,7 @@ check_terminal: *res = n->res; #ifdef CONFIG_NET_CLS_IND - if (!tcf_match_indev(skb, n->indev)) { + if (!tcf_match_indev(skb, n->ifindex)) { n = n->next; goto next_knode; } @@ -352,7 +347,7 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n) return 0; } -static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode* key) +static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) { struct tc_u_knode **kp; struct tc_u_hnode *ht = key->ht_up; @@ -496,7 +491,8 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, int err; struct tcf_exts e; - err = tcf_exts_validate(net, tp, tb, est, &e, &u32_ext_map); + tcf_exts_init(&e, TCA_U32_ACT, TCA_U32_POLICE); + err = tcf_exts_validate(net, tp, tb, est, &e); if (err < 0) return err; @@ -531,9 +527,11 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, #ifdef CONFIG_NET_CLS_IND if (tb[TCA_U32_INDEV]) { - err = tcf_change_indev(tp, n->indev, tb[TCA_U32_INDEV]); - if (err < 0) + int ret; + ret = tcf_change_indev(net, tb[TCA_U32_INDEV]); + if (ret < 0) goto errout; + n->ifindex = ret; } #endif tcf_exts_change(tp, &n->exts, &e); @@ -646,6 +644,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, n->ht_up = ht; n->handle = handle; n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; + tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE); #ifdef CONFIG_CLS_U32_MARK if (tb[TCA_U32_MARK]) { @@ -715,7 +714,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int u32_dump(struct tcf_proto *tp, unsigned long fh, +static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct tc_u_knode *n = (struct tc_u_knode *)fh; @@ -759,13 +758,16 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; #endif - if (tcf_exts_dump(skb, &n->exts, &u32_ext_map) < 0) + if (tcf_exts_dump(skb, &n->exts) < 0) goto nla_put_failure; #ifdef CONFIG_NET_CLS_IND - if (strlen(n->indev) && - nla_put_string(skb, TCA_U32_INDEV, n->indev)) - goto nla_put_failure; + if (n->ifindex) { + struct net_device *dev; + dev = __dev_get_by_index(net, n->ifindex); + if (dev && nla_put_string(skb, TCA_U32_INDEV, dev->name)) + goto nla_put_failure; + } #endif #ifdef CONFIG_CLS_U32_PERF if (nla_put(skb, TCA_U32_PCNT, @@ -778,7 +780,7 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh, nla_nest_end(skb, nest); if (TC_U32_KEY(n->handle)) - if (tcf_exts_dump_stats(skb, &n->exts, &u32_ext_map) < 0) + if (tcf_exts_dump_stats(skb, &n->exts) < 0) goto nla_put_failure; return skb->len; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index e5cef9567225..9b8c0b0e60d7 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -222,7 +222,7 @@ META_COLLECTOR(int_maclen) META_COLLECTOR(int_rxhash) { - dst->value = skb_get_rxhash(skb); + dst->value = skb_get_hash(skb); } /************************************************************************** @@ -271,40 +271,52 @@ META_COLLECTOR(int_rtiif) * Socket Attributes **************************************************************************/ -#define SKIP_NONLOCAL(skb) \ - if (unlikely(skb->sk == NULL)) { \ - *err = -1; \ - return; \ - } +#define skip_nonlocal(skb) \ + (unlikely(skb->sk == NULL)) META_COLLECTOR(int_sk_family) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_family; } META_COLLECTOR(int_sk_state) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_state; } META_COLLECTOR(int_sk_reuse) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_reuse; } META_COLLECTOR(int_sk_bound_if) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } /* No error if bound_dev_if is 0, legal userspace check */ dst->value = skb->sk->sk_bound_dev_if; } META_COLLECTOR(var_sk_bound_if) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } if (skb->sk->sk_bound_dev_if == 0) { dst->value = (unsigned long) "any"; @@ -322,151 +334,226 @@ META_COLLECTOR(var_sk_bound_if) META_COLLECTOR(int_sk_refcnt) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = atomic_read(&skb->sk->sk_refcnt); } META_COLLECTOR(int_sk_rcvbuf) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_rcvbuf; } META_COLLECTOR(int_sk_shutdown) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_shutdown; } META_COLLECTOR(int_sk_proto) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_protocol; } META_COLLECTOR(int_sk_type) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_type; } META_COLLECTOR(int_sk_rmem_alloc) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = sk_rmem_alloc_get(skb->sk); } META_COLLECTOR(int_sk_wmem_alloc) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = sk_wmem_alloc_get(skb->sk); } META_COLLECTOR(int_sk_omem_alloc) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = atomic_read(&skb->sk->sk_omem_alloc); } META_COLLECTOR(int_sk_rcv_qlen) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_receive_queue.qlen; } META_COLLECTOR(int_sk_snd_qlen) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_write_queue.qlen; } META_COLLECTOR(int_sk_wmem_queued) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_wmem_queued; } META_COLLECTOR(int_sk_fwd_alloc) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_forward_alloc; } META_COLLECTOR(int_sk_sndbuf) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_sndbuf; } META_COLLECTOR(int_sk_alloc) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = (__force int) skb->sk->sk_allocation; } META_COLLECTOR(int_sk_hash) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_hash; } META_COLLECTOR(int_sk_lingertime) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_lingertime / HZ; } META_COLLECTOR(int_sk_err_qlen) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_error_queue.qlen; } META_COLLECTOR(int_sk_ack_bl) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_ack_backlog; } META_COLLECTOR(int_sk_max_ack_bl) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_max_ack_backlog; } META_COLLECTOR(int_sk_prio) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_priority; } META_COLLECTOR(int_sk_rcvlowat) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_rcvlowat; } META_COLLECTOR(int_sk_rcvtimeo) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_rcvtimeo / HZ; } META_COLLECTOR(int_sk_sndtimeo) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_sndtimeo / HZ; } META_COLLECTOR(int_sk_sendmsg_off) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_frag.offset; } META_COLLECTOR(int_sk_write_pend) { - SKIP_NONLOCAL(skb); + if (skip_nonlocal(skb)) { + *err = -1; + return; + } dst->value = skb->sk->sk_write_pending; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index cd81505662b8..1313145e3b86 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -135,7 +135,7 @@ static DEFINE_RWLOCK(qdisc_mod_lock); static struct Qdisc_ops *qdisc_base; -/* Register/uregister queueing discipline */ +/* Register/unregister queueing discipline */ int register_qdisc(struct Qdisc_ops *qops) { @@ -271,11 +271,15 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) return NULL; } -static void qdisc_list_add(struct Qdisc *q) +void qdisc_list_add(struct Qdisc *q) { + struct Qdisc *root = qdisc_dev(q)->qdisc; + + WARN_ON_ONCE(root == &noop_qdisc); if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) - list_add_tail(&q->list, &qdisc_dev(q)->qdisc->list); + list_add_tail(&q->list, &root->list); } +EXPORT_SYMBOL(qdisc_list_add); void qdisc_list_del(struct Qdisc *q) { diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 7a42c81a19eb..2f80d01d42a6 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1058,9 +1058,10 @@ static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/ q->quanta[prio]; } - if (cl->quantum <= 0 || cl->quantum>32*qdisc_dev(cl->qdisc)->mtu) { - pr_warning("CBQ: class %08x has bad quantum==%ld, repaired.\n", - cl->common.classid, cl->quantum); + if (cl->quantum <= 0 || + cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) { + pr_warn("CBQ: class %08x has bad quantum==%ld, repaired.\n", + cl->common.classid, cl->quantum); cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1; } } @@ -1782,8 +1783,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t qdisc_root_sleeping_lock(sch), tca[TCA_RATE]); if (err) { - if (rtab) - qdisc_put_rtab(rtab); + qdisc_put_rtab(rtab); return err; } } diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index ddd73cb2d7ba..2aee02802c27 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -14,7 +14,6 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/skbuff.h> -#include <linux/reciprocal_div.h> #include <linux/vmalloc.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> @@ -77,12 +76,6 @@ struct choke_sched_data { struct sk_buff **tab; }; -/* deliver a random number between 0 and N - 1 */ -static u32 random_N(unsigned int N) -{ - return reciprocal_divide(prandom_u32(), N); -} - /* number of elements in queue including holes */ static unsigned int choke_len(const struct choke_sched_data *q) { @@ -233,7 +226,7 @@ static struct sk_buff *choke_peek_random(const struct choke_sched_data *q, int retrys = 3; do { - *pidx = (q->head + random_N(choke_len(q))) & q->tab_mask; + *pidx = (q->head + prandom_u32_max(choke_len(q))) & q->tab_mask; skb = q->tab[*pidx]; if (skb) return skb; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 3886365cc207..49d6ef338b55 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -47,7 +47,7 @@ struct dsmark_qdisc_data { static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index) { - return (index <= p->indices && index > 0); + return index <= p->indices && index > 0; } /* ------------------------- Class/flow operations ------------------------- */ @@ -57,8 +57,8 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg, { struct dsmark_qdisc_data *p = qdisc_priv(sch); - pr_debug("dsmark_graft(sch %p,[qdisc %p],new %p,old %p)\n", - sch, p, new, old); + pr_debug("%s(sch %p,[qdisc %p],new %p,old %p)\n", + __func__, sch, p, new, old); if (new == NULL) { new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, @@ -85,8 +85,8 @@ static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg) static unsigned long dsmark_get(struct Qdisc *sch, u32 classid) { - pr_debug("dsmark_get(sch %p,[qdisc %p],classid %x)\n", - sch, qdisc_priv(sch), classid); + pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", + __func__, sch, qdisc_priv(sch), classid); return TC_H_MIN(classid) + 1; } @@ -118,8 +118,8 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, int err = -EINVAL; u8 mask = 0; - pr_debug("dsmark_change(sch %p,[qdisc %p],classid %x,parent %x)," - "arg 0x%lx\n", sch, p, classid, parent, *arg); + pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n", + __func__, sch, p, classid, parent, *arg); if (!dsmark_valid_index(p, *arg)) { err = -ENOENT; @@ -166,7 +166,8 @@ static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) struct dsmark_qdisc_data *p = qdisc_priv(sch); int i; - pr_debug("dsmark_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); + pr_debug("%s(sch %p,[qdisc %p],walker %p)\n", + __func__, sch, p, walker); if (walker->stop) return; @@ -199,7 +200,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) struct dsmark_qdisc_data *p = qdisc_priv(sch); int err; - pr_debug("dsmark_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); + pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p); if (p->set_tc_index) { switch (skb->protocol) { @@ -275,7 +276,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) struct sk_buff *skb; u32 index; - pr_debug("dsmark_dequeue(sch %p,[qdisc %p])\n", sch, p); + pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); skb = p->q->ops->dequeue(p->q); if (skb == NULL) @@ -303,8 +304,8 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) * and don't need yet another qdisc as a bypass. */ if (p->mask[index] != 0xff || p->value[index]) - pr_warning("dsmark_dequeue: unsupported protocol %d\n", - ntohs(skb->protocol)); + pr_warn("%s: unsupported protocol %d\n", + __func__, ntohs(skb->protocol)); break; } @@ -315,7 +316,7 @@ static struct sk_buff *dsmark_peek(struct Qdisc *sch) { struct dsmark_qdisc_data *p = qdisc_priv(sch); - pr_debug("dsmark_peek(sch %p,[qdisc %p])\n", sch, p); + pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); return p->q->ops->peek(p->q); } @@ -325,7 +326,7 @@ static unsigned int dsmark_drop(struct Qdisc *sch) struct dsmark_qdisc_data *p = qdisc_priv(sch); unsigned int len; - pr_debug("dsmark_reset(sch %p,[qdisc %p])\n", sch, p); + pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); if (p->q->ops->drop == NULL) return 0; @@ -346,7 +347,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) u16 indices; u8 *mask; - pr_debug("dsmark_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); + pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt); if (!opt) goto errout; @@ -384,7 +385,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) if (p->q == NULL) p->q = &noop_qdisc; - pr_debug("dsmark_init: qdisc %p\n", p->q); + pr_debug("%s: qdisc %p\n", __func__, p->q); err = 0; errout: @@ -395,7 +396,7 @@ static void dsmark_reset(struct Qdisc *sch) { struct dsmark_qdisc_data *p = qdisc_priv(sch); - pr_debug("dsmark_reset(sch %p,[qdisc %p])\n", sch, p); + pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); qdisc_reset(p->q); sch->q.qlen = 0; } @@ -404,7 +405,7 @@ static void dsmark_destroy(struct Qdisc *sch) { struct dsmark_qdisc_data *p = qdisc_priv(sch); - pr_debug("dsmark_destroy(sch %p,[qdisc %p])\n", sch, p); + pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); tcf_destroy_chain(&p->filter_list); qdisc_destroy(p->q); @@ -417,7 +418,7 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, struct dsmark_qdisc_data *p = qdisc_priv(sch); struct nlattr *opts = NULL; - pr_debug("dsmark_dump_class(sch %p,[qdisc %p],class %ld\n", sch, p, cl); + pr_debug("%s(sch %p,[qdisc %p],class %ld\n", __func__, sch, p, cl); if (!dsmark_valid_index(p, cl)) return -EINVAL; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 95d843961907..08ef7a42c0e4 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -47,6 +47,7 @@ #include <linux/rbtree.h> #include <linux/hash.h> #include <linux/prefetch.h> +#include <linux/vmalloc.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/sock.h> @@ -225,7 +226,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) /* By forcing low order bit to 1, we make sure to not * collide with a local flow (socket pointers are word aligned) */ - sk = (struct sock *)(skb_get_rxhash(skb) | 1L); + sk = (struct sock *)(skb_get_hash(skb) | 1L); } root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)]; @@ -578,15 +579,36 @@ static void fq_rehash(struct fq_sched_data *q, q->stat_gc_flows += fcnt; } -static int fq_resize(struct fq_sched_data *q, u32 log) +static void *fq_alloc_node(size_t sz, int node) { + void *ptr; + + ptr = kmalloc_node(sz, GFP_KERNEL | __GFP_REPEAT | __GFP_NOWARN, node); + if (!ptr) + ptr = vmalloc_node(sz, node); + return ptr; +} + +static void fq_free(void *addr) +{ + if (addr && is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); +} + +static int fq_resize(struct Qdisc *sch, u32 log) +{ + struct fq_sched_data *q = qdisc_priv(sch); struct rb_root *array; u32 idx; if (q->fq_root && log == q->fq_trees_log) return 0; - array = kmalloc(sizeof(struct rb_root) << log, GFP_KERNEL); + /* If XPS was setup, we can allocate memory on right NUMA node */ + array = fq_alloc_node(sizeof(struct rb_root) << log, + netdev_queue_numa_node_read(sch->dev_queue)); if (!array) return -ENOMEM; @@ -595,7 +617,7 @@ static int fq_resize(struct fq_sched_data *q, u32 log) if (q->fq_root) { fq_rehash(q, q->fq_root, q->fq_trees_log, array, log); - kfree(q->fq_root); + fq_free(q->fq_root); } q->fq_root = array; q->fq_trees_log = log; @@ -676,7 +698,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) } if (!err) - err = fq_resize(q, fq_log); + err = fq_resize(sch, fq_log); while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_dequeue(sch); @@ -697,7 +719,7 @@ static void fq_destroy(struct Qdisc *sch) struct fq_sched_data *q = qdisc_priv(sch); fq_reset(sch); - kfree(q->fq_root); + fq_free(q->fq_root); qdisc_watchdog_cancel(&q->watchdog); } @@ -723,7 +745,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt) if (opt) err = fq_change(sch, opt); else - err = fq_resize(q, q->fq_trees_log); + err = fq_resize(sch, q->fq_trees_log); return err; } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 55786283a3df..ba5bc929eac7 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -390,7 +390,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) sch->limit = 10*1024; q->flows_cnt = 1024; q->quantum = psched_mtu(qdisc_dev(sch)); - q->perturbation = net_random(); + q->perturbation = prandom_u32(); INIT_LIST_HEAD(&q->new_flows); INIT_LIST_HEAD(&q->old_flows); codel_params_init(&q->cparams); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 7fc899a943a8..e82e43b69c33 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -338,13 +338,13 @@ EXPORT_SYMBOL(netif_carrier_off); cheaper. */ -static int noop_enqueue(struct sk_buff *skb, struct Qdisc * qdisc) +static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc) { kfree_skb(skb); return NET_XMIT_CN; } -static struct sk_buff *noop_dequeue(struct Qdisc * qdisc) +static struct sk_buff *noop_dequeue(struct Qdisc *qdisc) { return NULL; } @@ -718,8 +718,8 @@ static void attach_default_qdiscs(struct net_device *dev) } else { qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT); if (qdisc) { - qdisc->ops->attach(qdisc); dev->qdisc = qdisc; + qdisc->ops->attach(qdisc); } } } diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index d42234c0f13b..12cbc09157fc 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -370,8 +370,8 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) for (i = table->DPs; i < MAX_DPs; i++) { if (table->tab[i]) { - pr_warning("GRED: Warning: Destroying " - "shadowed VQ 0x%x\n", i); + pr_warn("GRED: Warning: Destroying shadowed VQ 0x%x\n", + i); gred_destroy_vq(table->tab[i]); table->tab[i] = NULL; } diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c new file mode 100644 index 000000000000..647680b1c625 --- /dev/null +++ b/net/sched/sch_hhf.c @@ -0,0 +1,745 @@ +/* net/sched/sch_hhf.c Heavy-Hitter Filter (HHF) + * + * Copyright (C) 2013 Terry Lam <vtlam@google.com> + * Copyright (C) 2013 Nandita Dukkipati <nanditad@google.com> + */ + +#include <linux/jhash.h> +#include <linux/jiffies.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/vmalloc.h> +#include <net/flow_keys.h> +#include <net/pkt_sched.h> +#include <net/sock.h> + +/* Heavy-Hitter Filter (HHF) + * + * Principles : + * Flows are classified into two buckets: non-heavy-hitter and heavy-hitter + * buckets. Initially, a new flow starts as non-heavy-hitter. Once classified + * as heavy-hitter, it is immediately switched to the heavy-hitter bucket. + * The buckets are dequeued by a Weighted Deficit Round Robin (WDRR) scheduler, + * in which the heavy-hitter bucket is served with less weight. + * In other words, non-heavy-hitters (e.g., short bursts of critical traffic) + * are isolated from heavy-hitters (e.g., persistent bulk traffic) and also have + * higher share of bandwidth. + * + * To capture heavy-hitters, we use the "multi-stage filter" algorithm in the + * following paper: + * [EV02] C. Estan and G. Varghese, "New Directions in Traffic Measurement and + * Accounting", in ACM SIGCOMM, 2002. + * + * Conceptually, a multi-stage filter comprises k independent hash functions + * and k counter arrays. Packets are indexed into k counter arrays by k hash + * functions, respectively. The counters are then increased by the packet sizes. + * Therefore, + * - For a heavy-hitter flow: *all* of its k array counters must be large. + * - For a non-heavy-hitter flow: some of its k array counters can be large + * due to hash collision with other small flows; however, with high + * probability, not *all* k counters are large. + * + * By the design of the multi-stage filter algorithm, the false negative rate + * (heavy-hitters getting away uncaptured) is zero. However, the algorithm is + * susceptible to false positives (non-heavy-hitters mistakenly classified as + * heavy-hitters). + * Therefore, we also implement the following optimizations to reduce false + * positives by avoiding unnecessary increment of the counter values: + * - Optimization O1: once a heavy-hitter is identified, its bytes are not + * accounted in the array counters. This technique is called "shielding" + * in Section 3.3.1 of [EV02]. + * - Optimization O2: conservative update of counters + * (Section 3.3.2 of [EV02]), + * New counter value = max {old counter value, + * smallest counter value + packet bytes} + * + * Finally, we refresh the counters periodically since otherwise the counter + * values will keep accumulating. + * + * Once a flow is classified as heavy-hitter, we also save its per-flow state + * in an exact-matching flow table so that its subsequent packets can be + * dispatched to the heavy-hitter bucket accordingly. + * + * + * At a high level, this qdisc works as follows: + * Given a packet p: + * - If the flow-id of p (e.g., TCP 5-tuple) is already in the exact-matching + * heavy-hitter flow table, denoted table T, then send p to the heavy-hitter + * bucket. + * - Otherwise, forward p to the multi-stage filter, denoted filter F + * + If F decides that p belongs to a non-heavy-hitter flow, then send p + * to the non-heavy-hitter bucket. + * + Otherwise, if F decides that p belongs to a new heavy-hitter flow, + * then set up a new flow entry for the flow-id of p in the table T and + * send p to the heavy-hitter bucket. + * + * In this implementation: + * - T is a fixed-size hash-table with 1024 entries. Hash collision is + * resolved by linked-list chaining. + * - F has four counter arrays, each array containing 1024 32-bit counters. + * That means 4 * 1024 * 32 bits = 16KB of memory. + * - Since each array in F contains 1024 counters, 10 bits are sufficient to + * index into each array. + * Hence, instead of having four hash functions, we chop the 32-bit + * skb-hash into three 10-bit chunks, and the remaining 10-bit chunk is + * computed as XOR sum of those three chunks. + * - We need to clear the counter arrays periodically; however, directly + * memsetting 16KB of memory can lead to cache eviction and unwanted delay. + * So by representing each counter by a valid bit, we only need to reset + * 4K of 1 bit (i.e. 512 bytes) instead of 16KB of memory. + * - The Deficit Round Robin engine is taken from fq_codel implementation + * (net/sched/sch_fq_codel.c). Note that wdrr_bucket corresponds to + * fq_codel_flow in fq_codel implementation. + * + */ + +/* Non-configurable parameters */ +#define HH_FLOWS_CNT 1024 /* number of entries in exact-matching table T */ +#define HHF_ARRAYS_CNT 4 /* number of arrays in multi-stage filter F */ +#define HHF_ARRAYS_LEN 1024 /* number of counters in each array of F */ +#define HHF_BIT_MASK_LEN 10 /* masking 10 bits */ +#define HHF_BIT_MASK 0x3FF /* bitmask of 10 bits */ + +#define WDRR_BUCKET_CNT 2 /* two buckets for Weighted DRR */ +enum wdrr_bucket_idx { + WDRR_BUCKET_FOR_HH = 0, /* bucket id for heavy-hitters */ + WDRR_BUCKET_FOR_NON_HH = 1 /* bucket id for non-heavy-hitters */ +}; + +#define hhf_time_before(a, b) \ + (typecheck(u32, a) && typecheck(u32, b) && ((s32)((a) - (b)) < 0)) + +/* Heavy-hitter per-flow state */ +struct hh_flow_state { + u32 hash_id; /* hash of flow-id (e.g. TCP 5-tuple) */ + u32 hit_timestamp; /* last time heavy-hitter was seen */ + struct list_head flowchain; /* chaining under hash collision */ +}; + +/* Weighted Deficit Round Robin (WDRR) scheduler */ +struct wdrr_bucket { + struct sk_buff *head; + struct sk_buff *tail; + struct list_head bucketchain; + int deficit; +}; + +struct hhf_sched_data { + struct wdrr_bucket buckets[WDRR_BUCKET_CNT]; + u32 perturbation; /* hash perturbation */ + u32 quantum; /* psched_mtu(qdisc_dev(sch)); */ + u32 drop_overlimit; /* number of times max qdisc packet + * limit was hit + */ + struct list_head *hh_flows; /* table T (currently active HHs) */ + u32 hh_flows_limit; /* max active HH allocs */ + u32 hh_flows_overlimit; /* num of disallowed HH allocs */ + u32 hh_flows_total_cnt; /* total admitted HHs */ + u32 hh_flows_current_cnt; /* total current HHs */ + u32 *hhf_arrays[HHF_ARRAYS_CNT]; /* HH filter F */ + u32 hhf_arrays_reset_timestamp; /* last time hhf_arrays + * was reset + */ + unsigned long *hhf_valid_bits[HHF_ARRAYS_CNT]; /* shadow valid bits + * of hhf_arrays + */ + /* Similar to the "new_flows" vs. "old_flows" concept in fq_codel DRR */ + struct list_head new_buckets; /* list of new buckets */ + struct list_head old_buckets; /* list of old buckets */ + + /* Configurable HHF parameters */ + u32 hhf_reset_timeout; /* interval to reset counter + * arrays in filter F + * (default 40ms) + */ + u32 hhf_admit_bytes; /* counter thresh to classify as + * HH (default 128KB). + * With these default values, + * 128KB / 40ms = 25 Mbps + * i.e., we expect to capture HHs + * sending > 25 Mbps. + */ + u32 hhf_evict_timeout; /* aging threshold to evict idle + * HHs out of table T. This should + * be large enough to avoid + * reordering during HH eviction. + * (default 1s) + */ + u32 hhf_non_hh_weight; /* WDRR weight for non-HHs + * (default 2, + * i.e., non-HH : HH = 2 : 1) + */ +}; + +static u32 hhf_time_stamp(void) +{ + return jiffies; +} + +static unsigned int skb_hash(const struct hhf_sched_data *q, + const struct sk_buff *skb) +{ + struct flow_keys keys; + unsigned int hash; + + if (skb->sk && skb->sk->sk_hash) + return skb->sk->sk_hash; + + skb_flow_dissect(skb, &keys); + hash = jhash_3words((__force u32)keys.dst, + (__force u32)keys.src ^ keys.ip_proto, + (__force u32)keys.ports, q->perturbation); + return hash; +} + +/* Looks up a heavy-hitter flow in a chaining list of table T. */ +static struct hh_flow_state *seek_list(const u32 hash, + struct list_head *head, + struct hhf_sched_data *q) +{ + struct hh_flow_state *flow, *next; + u32 now = hhf_time_stamp(); + + if (list_empty(head)) + return NULL; + + list_for_each_entry_safe(flow, next, head, flowchain) { + u32 prev = flow->hit_timestamp + q->hhf_evict_timeout; + + if (hhf_time_before(prev, now)) { + /* Delete expired heavy-hitters, but preserve one entry + * to avoid kzalloc() when next time this slot is hit. + */ + if (list_is_last(&flow->flowchain, head)) + return NULL; + list_del(&flow->flowchain); + kfree(flow); + q->hh_flows_current_cnt--; + } else if (flow->hash_id == hash) { + return flow; + } + } + return NULL; +} + +/* Returns a flow state entry for a new heavy-hitter. Either reuses an expired + * entry or dynamically alloc a new entry. + */ +static struct hh_flow_state *alloc_new_hh(struct list_head *head, + struct hhf_sched_data *q) +{ + struct hh_flow_state *flow; + u32 now = hhf_time_stamp(); + + if (!list_empty(head)) { + /* Find an expired heavy-hitter flow entry. */ + list_for_each_entry(flow, head, flowchain) { + u32 prev = flow->hit_timestamp + q->hhf_evict_timeout; + + if (hhf_time_before(prev, now)) + return flow; + } + } + + if (q->hh_flows_current_cnt >= q->hh_flows_limit) { + q->hh_flows_overlimit++; + return NULL; + } + /* Create new entry. */ + flow = kzalloc(sizeof(struct hh_flow_state), GFP_ATOMIC); + if (!flow) + return NULL; + + q->hh_flows_current_cnt++; + INIT_LIST_HEAD(&flow->flowchain); + list_add_tail(&flow->flowchain, head); + + return flow; +} + +/* Assigns packets to WDRR buckets. Implements a multi-stage filter to + * classify heavy-hitters. + */ +static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch) +{ + struct hhf_sched_data *q = qdisc_priv(sch); + u32 tmp_hash, hash; + u32 xorsum, filter_pos[HHF_ARRAYS_CNT], flow_pos; + struct hh_flow_state *flow; + u32 pkt_len, min_hhf_val; + int i; + u32 prev; + u32 now = hhf_time_stamp(); + + /* Reset the HHF counter arrays if this is the right time. */ + prev = q->hhf_arrays_reset_timestamp + q->hhf_reset_timeout; + if (hhf_time_before(prev, now)) { + for (i = 0; i < HHF_ARRAYS_CNT; i++) + bitmap_zero(q->hhf_valid_bits[i], HHF_ARRAYS_LEN); + q->hhf_arrays_reset_timestamp = now; + } + + /* Get hashed flow-id of the skb. */ + hash = skb_hash(q, skb); + + /* Check if this packet belongs to an already established HH flow. */ + flow_pos = hash & HHF_BIT_MASK; + flow = seek_list(hash, &q->hh_flows[flow_pos], q); + if (flow) { /* found its HH flow */ + flow->hit_timestamp = now; + return WDRR_BUCKET_FOR_HH; + } + + /* Now pass the packet through the multi-stage filter. */ + tmp_hash = hash; + xorsum = 0; + for (i = 0; i < HHF_ARRAYS_CNT - 1; i++) { + /* Split the skb_hash into three 10-bit chunks. */ + filter_pos[i] = tmp_hash & HHF_BIT_MASK; + xorsum ^= filter_pos[i]; + tmp_hash >>= HHF_BIT_MASK_LEN; + } + /* The last chunk is computed as XOR sum of other chunks. */ + filter_pos[HHF_ARRAYS_CNT - 1] = xorsum ^ tmp_hash; + + pkt_len = qdisc_pkt_len(skb); + min_hhf_val = ~0U; + for (i = 0; i < HHF_ARRAYS_CNT; i++) { + u32 val; + + if (!test_bit(filter_pos[i], q->hhf_valid_bits[i])) { + q->hhf_arrays[i][filter_pos[i]] = 0; + __set_bit(filter_pos[i], q->hhf_valid_bits[i]); + } + + val = q->hhf_arrays[i][filter_pos[i]] + pkt_len; + if (min_hhf_val > val) + min_hhf_val = val; + } + + /* Found a new HH iff all counter values > HH admit threshold. */ + if (min_hhf_val > q->hhf_admit_bytes) { + /* Just captured a new heavy-hitter. */ + flow = alloc_new_hh(&q->hh_flows[flow_pos], q); + if (!flow) /* memory alloc problem */ + return WDRR_BUCKET_FOR_NON_HH; + flow->hash_id = hash; + flow->hit_timestamp = now; + q->hh_flows_total_cnt++; + + /* By returning without updating counters in q->hhf_arrays, + * we implicitly implement "shielding" (see Optimization O1). + */ + return WDRR_BUCKET_FOR_HH; + } + + /* Conservative update of HHF arrays (see Optimization O2). */ + for (i = 0; i < HHF_ARRAYS_CNT; i++) { + if (q->hhf_arrays[i][filter_pos[i]] < min_hhf_val) + q->hhf_arrays[i][filter_pos[i]] = min_hhf_val; + } + return WDRR_BUCKET_FOR_NON_HH; +} + +/* Removes one skb from head of bucket. */ +static struct sk_buff *dequeue_head(struct wdrr_bucket *bucket) +{ + struct sk_buff *skb = bucket->head; + + bucket->head = skb->next; + skb->next = NULL; + return skb; +} + +/* Tail-adds skb to bucket. */ +static void bucket_add(struct wdrr_bucket *bucket, struct sk_buff *skb) +{ + if (bucket->head == NULL) + bucket->head = skb; + else + bucket->tail->next = skb; + bucket->tail = skb; + skb->next = NULL; +} + +static unsigned int hhf_drop(struct Qdisc *sch) +{ + struct hhf_sched_data *q = qdisc_priv(sch); + struct wdrr_bucket *bucket; + + /* Always try to drop from heavy-hitters first. */ + bucket = &q->buckets[WDRR_BUCKET_FOR_HH]; + if (!bucket->head) + bucket = &q->buckets[WDRR_BUCKET_FOR_NON_HH]; + + if (bucket->head) { + struct sk_buff *skb = dequeue_head(bucket); + + sch->q.qlen--; + sch->qstats.drops++; + sch->qstats.backlog -= qdisc_pkt_len(skb); + kfree_skb(skb); + } + + /* Return id of the bucket from which the packet was dropped. */ + return bucket - q->buckets; +} + +static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + struct hhf_sched_data *q = qdisc_priv(sch); + enum wdrr_bucket_idx idx; + struct wdrr_bucket *bucket; + + idx = hhf_classify(skb, sch); + + bucket = &q->buckets[idx]; + bucket_add(bucket, skb); + sch->qstats.backlog += qdisc_pkt_len(skb); + + if (list_empty(&bucket->bucketchain)) { + unsigned int weight; + + /* The logic of new_buckets vs. old_buckets is the same as + * new_flows vs. old_flows in the implementation of fq_codel, + * i.e., short bursts of non-HHs should have strict priority. + */ + if (idx == WDRR_BUCKET_FOR_HH) { + /* Always move heavy-hitters to old bucket. */ + weight = 1; + list_add_tail(&bucket->bucketchain, &q->old_buckets); + } else { + weight = q->hhf_non_hh_weight; + list_add_tail(&bucket->bucketchain, &q->new_buckets); + } + bucket->deficit = weight * q->quantum; + } + if (++sch->q.qlen < sch->limit) + return NET_XMIT_SUCCESS; + + q->drop_overlimit++; + /* Return Congestion Notification only if we dropped a packet from this + * bucket. + */ + if (hhf_drop(sch) == idx) + return NET_XMIT_CN; + + /* As we dropped a packet, better let upper stack know this. */ + qdisc_tree_decrease_qlen(sch, 1); + return NET_XMIT_SUCCESS; +} + +static struct sk_buff *hhf_dequeue(struct Qdisc *sch) +{ + struct hhf_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb = NULL; + struct wdrr_bucket *bucket; + struct list_head *head; + +begin: + head = &q->new_buckets; + if (list_empty(head)) { + head = &q->old_buckets; + if (list_empty(head)) + return NULL; + } + bucket = list_first_entry(head, struct wdrr_bucket, bucketchain); + + if (bucket->deficit <= 0) { + int weight = (bucket - q->buckets == WDRR_BUCKET_FOR_HH) ? + 1 : q->hhf_non_hh_weight; + + bucket->deficit += weight * q->quantum; + list_move_tail(&bucket->bucketchain, &q->old_buckets); + goto begin; + } + + if (bucket->head) { + skb = dequeue_head(bucket); + sch->q.qlen--; + sch->qstats.backlog -= qdisc_pkt_len(skb); + } + + if (!skb) { + /* Force a pass through old_buckets to prevent starvation. */ + if ((head == &q->new_buckets) && !list_empty(&q->old_buckets)) + list_move_tail(&bucket->bucketchain, &q->old_buckets); + else + list_del_init(&bucket->bucketchain); + goto begin; + } + qdisc_bstats_update(sch, skb); + bucket->deficit -= qdisc_pkt_len(skb); + + return skb; +} + +static void hhf_reset(struct Qdisc *sch) +{ + struct sk_buff *skb; + + while ((skb = hhf_dequeue(sch)) != NULL) + kfree_skb(skb); +} + +static void *hhf_zalloc(size_t sz) +{ + void *ptr = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN); + + if (!ptr) + ptr = vzalloc(sz); + + return ptr; +} + +static void hhf_free(void *addr) +{ + if (addr) { + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); + } +} + +static void hhf_destroy(struct Qdisc *sch) +{ + int i; + struct hhf_sched_data *q = qdisc_priv(sch); + + for (i = 0; i < HHF_ARRAYS_CNT; i++) { + hhf_free(q->hhf_arrays[i]); + hhf_free(q->hhf_valid_bits[i]); + } + + for (i = 0; i < HH_FLOWS_CNT; i++) { + struct hh_flow_state *flow, *next; + struct list_head *head = &q->hh_flows[i]; + + if (list_empty(head)) + continue; + list_for_each_entry_safe(flow, next, head, flowchain) { + list_del(&flow->flowchain); + kfree(flow); + } + } + hhf_free(q->hh_flows); +} + +static const struct nla_policy hhf_policy[TCA_HHF_MAX + 1] = { + [TCA_HHF_BACKLOG_LIMIT] = { .type = NLA_U32 }, + [TCA_HHF_QUANTUM] = { .type = NLA_U32 }, + [TCA_HHF_HH_FLOWS_LIMIT] = { .type = NLA_U32 }, + [TCA_HHF_RESET_TIMEOUT] = { .type = NLA_U32 }, + [TCA_HHF_ADMIT_BYTES] = { .type = NLA_U32 }, + [TCA_HHF_EVICT_TIMEOUT] = { .type = NLA_U32 }, + [TCA_HHF_NON_HH_WEIGHT] = { .type = NLA_U32 }, +}; + +static int hhf_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct hhf_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_HHF_MAX + 1]; + unsigned int qlen; + int err; + u64 non_hh_quantum; + u32 new_quantum = q->quantum; + u32 new_hhf_non_hh_weight = q->hhf_non_hh_weight; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_HHF_MAX, opt, hhf_policy); + if (err < 0) + return err; + + sch_tree_lock(sch); + + if (tb[TCA_HHF_BACKLOG_LIMIT]) + sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]); + + if (tb[TCA_HHF_QUANTUM]) + new_quantum = nla_get_u32(tb[TCA_HHF_QUANTUM]); + + if (tb[TCA_HHF_NON_HH_WEIGHT]) + new_hhf_non_hh_weight = nla_get_u32(tb[TCA_HHF_NON_HH_WEIGHT]); + + non_hh_quantum = (u64)new_quantum * new_hhf_non_hh_weight; + if (non_hh_quantum > INT_MAX) + return -EINVAL; + q->quantum = new_quantum; + q->hhf_non_hh_weight = new_hhf_non_hh_weight; + + if (tb[TCA_HHF_HH_FLOWS_LIMIT]) + q->hh_flows_limit = nla_get_u32(tb[TCA_HHF_HH_FLOWS_LIMIT]); + + if (tb[TCA_HHF_RESET_TIMEOUT]) { + u32 us = nla_get_u32(tb[TCA_HHF_RESET_TIMEOUT]); + + q->hhf_reset_timeout = usecs_to_jiffies(us); + } + + if (tb[TCA_HHF_ADMIT_BYTES]) + q->hhf_admit_bytes = nla_get_u32(tb[TCA_HHF_ADMIT_BYTES]); + + if (tb[TCA_HHF_EVICT_TIMEOUT]) { + u32 us = nla_get_u32(tb[TCA_HHF_EVICT_TIMEOUT]); + + q->hhf_evict_timeout = usecs_to_jiffies(us); + } + + qlen = sch->q.qlen; + while (sch->q.qlen > sch->limit) { + struct sk_buff *skb = hhf_dequeue(sch); + + kfree_skb(skb); + } + qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + + sch_tree_unlock(sch); + return 0; +} + +static int hhf_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct hhf_sched_data *q = qdisc_priv(sch); + int i; + + sch->limit = 1000; + q->quantum = psched_mtu(qdisc_dev(sch)); + q->perturbation = prandom_u32(); + INIT_LIST_HEAD(&q->new_buckets); + INIT_LIST_HEAD(&q->old_buckets); + + /* Configurable HHF parameters */ + q->hhf_reset_timeout = HZ / 25; /* 40 ms */ + q->hhf_admit_bytes = 131072; /* 128 KB */ + q->hhf_evict_timeout = HZ; /* 1 sec */ + q->hhf_non_hh_weight = 2; + + if (opt) { + int err = hhf_change(sch, opt); + + if (err) + return err; + } + + if (!q->hh_flows) { + /* Initialize heavy-hitter flow table. */ + q->hh_flows = hhf_zalloc(HH_FLOWS_CNT * + sizeof(struct list_head)); + if (!q->hh_flows) + return -ENOMEM; + for (i = 0; i < HH_FLOWS_CNT; i++) + INIT_LIST_HEAD(&q->hh_flows[i]); + + /* Cap max active HHs at twice len of hh_flows table. */ + q->hh_flows_limit = 2 * HH_FLOWS_CNT; + q->hh_flows_overlimit = 0; + q->hh_flows_total_cnt = 0; + q->hh_flows_current_cnt = 0; + + /* Initialize heavy-hitter filter arrays. */ + for (i = 0; i < HHF_ARRAYS_CNT; i++) { + q->hhf_arrays[i] = hhf_zalloc(HHF_ARRAYS_LEN * + sizeof(u32)); + if (!q->hhf_arrays[i]) { + hhf_destroy(sch); + return -ENOMEM; + } + } + q->hhf_arrays_reset_timestamp = hhf_time_stamp(); + + /* Initialize valid bits of heavy-hitter filter arrays. */ + for (i = 0; i < HHF_ARRAYS_CNT; i++) { + q->hhf_valid_bits[i] = hhf_zalloc(HHF_ARRAYS_LEN / + BITS_PER_BYTE); + if (!q->hhf_valid_bits[i]) { + hhf_destroy(sch); + return -ENOMEM; + } + } + + /* Initialize Weighted DRR buckets. */ + for (i = 0; i < WDRR_BUCKET_CNT; i++) { + struct wdrr_bucket *bucket = q->buckets + i; + + INIT_LIST_HEAD(&bucket->bucketchain); + } + } + + return 0; +} + +static int hhf_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct hhf_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + + opts = nla_nest_start(skb, TCA_OPTIONS); + if (opts == NULL) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_HHF_BACKLOG_LIMIT, sch->limit) || + nla_put_u32(skb, TCA_HHF_QUANTUM, q->quantum) || + nla_put_u32(skb, TCA_HHF_HH_FLOWS_LIMIT, q->hh_flows_limit) || + nla_put_u32(skb, TCA_HHF_RESET_TIMEOUT, + jiffies_to_usecs(q->hhf_reset_timeout)) || + nla_put_u32(skb, TCA_HHF_ADMIT_BYTES, q->hhf_admit_bytes) || + nla_put_u32(skb, TCA_HHF_EVICT_TIMEOUT, + jiffies_to_usecs(q->hhf_evict_timeout)) || + nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, q->hhf_non_hh_weight)) + goto nla_put_failure; + + nla_nest_end(skb, opts); + return skb->len; + +nla_put_failure: + return -1; +} + +static int hhf_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct hhf_sched_data *q = qdisc_priv(sch); + struct tc_hhf_xstats st = { + .drop_overlimit = q->drop_overlimit, + .hh_overlimit = q->hh_flows_overlimit, + .hh_tot_count = q->hh_flows_total_cnt, + .hh_cur_count = q->hh_flows_current_cnt, + }; + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static struct Qdisc_ops hhf_qdisc_ops __read_mostly = { + .id = "hhf", + .priv_size = sizeof(struct hhf_sched_data), + + .enqueue = hhf_enqueue, + .dequeue = hhf_dequeue, + .peek = qdisc_peek_dequeued, + .drop = hhf_drop, + .init = hhf_init, + .reset = hhf_reset, + .destroy = hhf_destroy, + .change = hhf_change, + .dump = hhf_dump, + .dump_stats = hhf_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init hhf_module_init(void) +{ + return register_qdisc(&hhf_qdisc_ops); +} + +static void __exit hhf_module_exit(void) +{ + unregister_qdisc(&hhf_qdisc_ops); +} + +module_init(hhf_module_init) +module_exit(hhf_module_exit) +MODULE_AUTHOR("Terry Lam"); +MODULE_AUTHOR("Nandita Dukkipati"); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 717b2108f852..722e137df244 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -219,11 +219,16 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, if (skb->priority == sch->handle) return HTB_DIRECT; /* X:0 (direct flow) selected */ cl = htb_find(skb->priority, sch); - if (cl && cl->level == 0) - return cl; + if (cl) { + if (cl->level == 0) + return cl; + /* Start with inner filter chain if a non-leaf class is selected */ + tcf = cl->filter_list; + } else { + tcf = q->filter_list; + } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - tcf = q->filter_list; while (tcf && (result = tc_classify(skb, tcf, &res)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -712,7 +717,7 @@ static s64 htb_do_events(struct htb_sched *q, const int level, /* too much load - let's continue after a break for scheduling */ if (!(q->warned & HTB_WARN_TOOMANYEVENTS)) { - pr_warning("htb: too many events!\n"); + pr_warn("htb: too many events!\n"); q->warned |= HTB_WARN_TOOMANYEVENTS; } @@ -1276,9 +1281,10 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) struct Qdisc *new_q = NULL; int last_child = 0; - // TODO: why don't allow to delete subtree ? references ? does - // tc subsys quarantee us that in htb_destroy it holds no class - // refs so that we can remove children safely there ? + /* TODO: why don't allow to delete subtree ? references ? does + * tc subsys guarantee us that in htb_destroy it holds no class + * refs so that we can remove children safely there ? + */ if (cl->children || cl->filter_cnt) return -EBUSY; @@ -1337,7 +1343,6 @@ 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; u64 rate64, ceil64; @@ -1361,16 +1366,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, 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 (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) + qdisc_put_rtab(qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB])); + + if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE) + qdisc_put_rtab(qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB])); if (!cl) { /* new class */ struct Qdisc *new_q; @@ -1494,15 +1494,13 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->quantum = min_t(u64, quantum, INT_MAX); if (!hopt->quantum && cl->quantum < 1000) { - pr_warning( - "HTB: quantum of class %X is small. Consider r2q change.\n", - cl->common.classid); + pr_warn("HTB: quantum of class %X is small. Consider r2q change.\n", + cl->common.classid); cl->quantum = 1000; } if (!hopt->quantum && cl->quantum > 200000) { - pr_warning( - "HTB: quantum of class %X is big. Consider r2q change.\n", - cl->common.classid); + pr_warn("HTB: quantum of class %X is big. Consider r2q change.\n", + cl->common.classid); cl->quantum = 200000; } if (hopt->quantum) diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 2e56185736d6..a8b2864a696b 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -78,14 +78,19 @@ static void mq_attach(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); - struct Qdisc *qdisc; + struct Qdisc *qdisc, *old; unsigned int ntx; for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { qdisc = priv->qdiscs[ntx]; - qdisc = dev_graft_qdisc(qdisc->dev_queue, qdisc); - if (qdisc) - qdisc_destroy(qdisc); + old = dev_graft_qdisc(qdisc->dev_queue, qdisc); + if (old) + qdisc_destroy(old); +#ifdef CONFIG_NET_SCHED + if (ntx < dev->real_num_tx_queues) + qdisc_list_add(qdisc); +#endif + } kfree(priv->qdiscs); priv->qdiscs = NULL; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index d44c868cb537..6749e2f540d0 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -167,15 +167,17 @@ static void mqprio_attach(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); - struct Qdisc *qdisc; + struct Qdisc *qdisc, *old; unsigned int ntx; /* Attach underlying qdisc */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { qdisc = priv->qdiscs[ntx]; - qdisc = dev_graft_qdisc(qdisc->dev_queue, qdisc); - if (qdisc) - qdisc_destroy(qdisc); + old = dev_graft_qdisc(qdisc->dev_queue, qdisc); + if (old) + qdisc_destroy(old); + if (ntx < dev->real_num_tx_queues) + qdisc_list_add(qdisc); } kfree(priv->qdiscs); priv->qdiscs = NULL; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 2a2b096d9a66..afb050a735fa 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -11,8 +11,7 @@ * more details. * * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 Temple - * Place - Suite 330, Boston, MA 02111-1307 USA. + * this program; if not, see <http://www.gnu.org/licenses/>. * * Author: Alexander Duyck <alexander.h.duyck@intel.com> */ diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index bccd52b36e97..de1059af6da1 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -88,10 +88,10 @@ struct netem_sched_data { u32 duplicate; u32 reorder; u32 corrupt; - u32 rate; + u64 rate; s32 packet_overhead; u32 cell_size; - u32 cell_size_reciprocal; + struct reciprocal_value cell_size_reciprocal; s32 cell_overhead; struct crndstate { @@ -110,6 +110,13 @@ struct netem_sched_data { CLG_GILB_ELL, } loss_model; + enum { + TX_IN_GAP_PERIOD = 1, + TX_IN_BURST_PERIOD, + LOST_IN_GAP_PERIOD, + LOST_IN_BURST_PERIOD, + } _4_state_model; + /* Correlated Loss Generation models */ struct clgstate { /* state of the Markov chain */ @@ -169,7 +176,7 @@ static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) static void init_crandom(struct crndstate *state, unsigned long rho) { state->rho = rho; - state->last = net_random(); + state->last = prandom_u32(); } /* get_crandom - correlated random number generator @@ -182,9 +189,9 @@ static u32 get_crandom(struct crndstate *state) unsigned long answer; if (state->rho == 0) /* no correlation */ - return net_random(); + return prandom_u32(); - value = net_random(); + value = prandom_u32(); rho = (u64)state->rho + 1; answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32; state->last = answer; @@ -198,50 +205,52 @@ static u32 get_crandom(struct crndstate *state) static bool loss_4state(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; - u32 rnd = net_random(); + u32 rnd = prandom_u32(); /* * Makes a comparison between rnd and the transition * probabilities outgoing from the current state, then decides the * next state and if the next packet has to be transmitted or lost. * The four states correspond to: - * 1 => successfully transmitted packets within a gap period - * 4 => isolated losses within a gap period - * 3 => lost packets within a burst period - * 2 => successfully transmitted packets within a burst period + * TX_IN_GAP_PERIOD => successfully transmitted packets within a gap period + * LOST_IN_BURST_PERIOD => isolated losses within a gap period + * LOST_IN_GAP_PERIOD => lost packets within a burst period + * TX_IN_GAP_PERIOD => successfully transmitted packets within a burst period */ switch (clg->state) { - case 1: + case TX_IN_GAP_PERIOD: if (rnd < clg->a4) { - clg->state = 4; + clg->state = LOST_IN_BURST_PERIOD; return true; } else if (clg->a4 < rnd && rnd < clg->a1 + clg->a4) { - clg->state = 3; + clg->state = LOST_IN_GAP_PERIOD; return true; - } else if (clg->a1 + clg->a4 < rnd) - clg->state = 1; + } else if (clg->a1 + clg->a4 < rnd) { + clg->state = TX_IN_GAP_PERIOD; + } break; - case 2: + case TX_IN_BURST_PERIOD: if (rnd < clg->a5) { - clg->state = 3; + clg->state = LOST_IN_GAP_PERIOD; return true; - } else - clg->state = 2; + } else { + clg->state = TX_IN_BURST_PERIOD; + } break; - case 3: + case LOST_IN_GAP_PERIOD: if (rnd < clg->a3) - clg->state = 2; + clg->state = TX_IN_BURST_PERIOD; else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) { - clg->state = 1; + clg->state = TX_IN_GAP_PERIOD; } else if (clg->a2 + clg->a3 < rnd) { - clg->state = 3; + clg->state = LOST_IN_GAP_PERIOD; return true; } break; - case 4: - clg->state = 1; + case LOST_IN_BURST_PERIOD: + clg->state = TX_IN_GAP_PERIOD; break; } @@ -264,15 +273,15 @@ static bool loss_gilb_ell(struct netem_sched_data *q) switch (clg->state) { case 1: - if (net_random() < clg->a1) + if (prandom_u32() < clg->a1) clg->state = 2; - if (net_random() < clg->a4) + if (prandom_u32() < clg->a4) return true; break; case 2: - if (net_random() < clg->a2) + if (prandom_u32() < clg->a2) clg->state = 1; - if (net_random() > clg->a3) + if (prandom_u32() > clg->a3) return true; } @@ -457,7 +466,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) skb_checksum_help(skb))) return qdisc_drop(skb, sch); - skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8); + skb->data[prandom_u32() % skb_headlen(skb)] ^= + 1<<(prandom_u32() % 8); } if (unlikely(skb_queue_len(&sch->q) >= sch->limit)) @@ -495,7 +505,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) now = netem_skb_cb(last)->time_to_send; } - delay += packet_len_2_sched_time(skb->len, q); + delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q); } cb->time_to_send = now + delay; @@ -715,9 +725,11 @@ static void get_rate(struct Qdisc *sch, const struct nlattr *attr) q->rate = r->rate; q->packet_overhead = r->packet_overhead; q->cell_size = r->cell_size; + q->cell_overhead = r->cell_overhead; if (q->cell_size) q->cell_size_reciprocal = reciprocal_value(q->cell_size); - q->cell_overhead = r->cell_overhead; + else + q->cell_size_reciprocal = (struct reciprocal_value) { 0 }; } static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr) @@ -729,7 +741,7 @@ static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr) nla_for_each_nested(la, attr, rem) { u16 type = nla_type(la); - switch(type) { + switch (type) { case NETEM_LOSS_GI: { const struct tc_netem_gimodel *gi = nla_data(la); @@ -782,6 +794,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_RATE] = { .len = sizeof(struct tc_netem_rate) }, [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, [TCA_NETEM_ECN] = { .type = NLA_U32 }, + [TCA_NETEM_RATE64] = { .type = NLA_U64 }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, @@ -852,6 +865,10 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_NETEM_RATE]) get_rate(sch, tb[TCA_NETEM_RATE]); + if (tb[TCA_NETEM_RATE64]) + q->rate = max_t(u64, q->rate, + nla_get_u64(tb[TCA_NETEM_RATE64])); + if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); @@ -974,7 +991,13 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt)) goto nla_put_failure; - rate.rate = q->rate; + if (q->rate >= (1ULL << 32)) { + if (nla_put_u64(skb, TCA_NETEM_RATE64, q->rate)) + goto nla_put_failure; + rate.rate = ~0U; + } else { + rate.rate = q->rate; + } rate.packet_overhead = q->packet_overhead; rate.cell_size = q->cell_size; rate.cell_overhead = q->cell_overhead; diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c new file mode 100644 index 000000000000..fefeeb73f15f --- /dev/null +++ b/net/sched/sch_pie.c @@ -0,0 +1,566 @@ +/* Copyright (C) 2013 Cisco Systems, Inc, 2013. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Author: Vijay Subramanian <vijaynsu@cisco.com> + * Author: Mythili Prabhu <mysuryan@cisco.com> + * + * ECN support is added by Naeem Khademi <naeemk@ifi.uio.no> + * University of Oslo, Norway. + * + * References: + * IETF draft submission: http://tools.ietf.org/html/draft-pan-aqm-pie-00 + * IEEE Conference on High Performance Switching and Routing 2013 : + * "PIE: A * Lightweight Control Scheme to Address the Bufferbloat Problem" + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <net/pkt_sched.h> +#include <net/inet_ecn.h> + +#define QUEUE_THRESHOLD 10000 +#define DQCOUNT_INVALID -1 +#define MAX_PROB 0xffffffff +#define PIE_SCALE 8 + +/* parameters used */ +struct pie_params { + psched_time_t target; /* user specified target delay in pschedtime */ + u32 tupdate; /* timer frequency (in jiffies) */ + u32 limit; /* number of packets that can be enqueued */ + u32 alpha; /* alpha and beta are between 0 and 32 */ + u32 beta; /* and are used for shift relative to 1 */ + bool ecn; /* true if ecn is enabled */ + bool bytemode; /* to scale drop early prob based on pkt size */ +}; + +/* variables used */ +struct pie_vars { + u32 prob; /* probability but scaled by u32 limit. */ + psched_time_t burst_time; + psched_time_t qdelay; + psched_time_t qdelay_old; + u64 dq_count; /* measured in bytes */ + psched_time_t dq_tstamp; /* drain rate */ + u32 avg_dq_rate; /* bytes per pschedtime tick,scaled */ + u32 qlen_old; /* in bytes */ +}; + +/* statistics gathering */ +struct pie_stats { + u32 packets_in; /* total number of packets enqueued */ + u32 dropped; /* packets dropped due to pie_action */ + u32 overlimit; /* dropped due to lack of space in queue */ + u32 maxq; /* maximum queue size */ + u32 ecn_mark; /* packets marked with ECN */ +}; + +/* private data for the Qdisc */ +struct pie_sched_data { + struct pie_params params; + struct pie_vars vars; + struct pie_stats stats; + struct timer_list adapt_timer; +}; + +static void pie_params_init(struct pie_params *params) +{ + params->alpha = 2; + params->beta = 20; + params->tupdate = usecs_to_jiffies(30 * USEC_PER_MSEC); /* 30 ms */ + params->limit = 1000; /* default of 1000 packets */ + params->target = PSCHED_NS2TICKS(20 * NSEC_PER_MSEC); /* 20 ms */ + params->ecn = false; + params->bytemode = false; +} + +static void pie_vars_init(struct pie_vars *vars) +{ + vars->dq_count = DQCOUNT_INVALID; + vars->avg_dq_rate = 0; + /* default of 100 ms in pschedtime */ + vars->burst_time = PSCHED_NS2TICKS(100 * NSEC_PER_MSEC); +} + +static bool drop_early(struct Qdisc *sch, u32 packet_size) +{ + struct pie_sched_data *q = qdisc_priv(sch); + u32 rnd; + u32 local_prob = q->vars.prob; + u32 mtu = psched_mtu(qdisc_dev(sch)); + + /* If there is still burst allowance left skip random early drop */ + if (q->vars.burst_time > 0) + return false; + + /* If current delay is less than half of target, and + * if drop prob is low already, disable early_drop + */ + if ((q->vars.qdelay < q->params.target / 2) + && (q->vars.prob < MAX_PROB / 5)) + return false; + + /* If we have fewer than 2 mtu-sized packets, disable drop_early, + * similar to min_th in RED + */ + if (sch->qstats.backlog < 2 * mtu) + return false; + + /* If bytemode is turned on, use packet size to compute new + * probablity. Smaller packets will have lower drop prob in this case + */ + if (q->params.bytemode && packet_size <= mtu) + local_prob = (local_prob / mtu) * packet_size; + else + local_prob = q->vars.prob; + + rnd = prandom_u32(); + if (rnd < local_prob) + return true; + + return false; +} + +static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + struct pie_sched_data *q = qdisc_priv(sch); + bool enqueue = false; + + if (unlikely(qdisc_qlen(sch) >= sch->limit)) { + q->stats.overlimit++; + goto out; + } + + if (!drop_early(sch, skb->len)) { + enqueue = true; + } else if (q->params.ecn && (q->vars.prob <= MAX_PROB / 10) && + INET_ECN_set_ce(skb)) { + /* If packet is ecn capable, mark it if drop probability + * is lower than 10%, else drop it. + */ + q->stats.ecn_mark++; + enqueue = true; + } + + /* we can enqueue the packet */ + if (enqueue) { + q->stats.packets_in++; + if (qdisc_qlen(sch) > q->stats.maxq) + q->stats.maxq = qdisc_qlen(sch); + + return qdisc_enqueue_tail(skb, sch); + } + +out: + q->stats.dropped++; + return qdisc_drop(skb, sch); +} + +static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { + [TCA_PIE_TARGET] = {.type = NLA_U32}, + [TCA_PIE_LIMIT] = {.type = NLA_U32}, + [TCA_PIE_TUPDATE] = {.type = NLA_U32}, + [TCA_PIE_ALPHA] = {.type = NLA_U32}, + [TCA_PIE_BETA] = {.type = NLA_U32}, + [TCA_PIE_ECN] = {.type = NLA_U32}, + [TCA_PIE_BYTEMODE] = {.type = NLA_U32}, +}; + +static int pie_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct pie_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_PIE_MAX + 1]; + unsigned int qlen; + int err; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_PIE_MAX, opt, pie_policy); + if (err < 0) + return err; + + sch_tree_lock(sch); + + /* convert from microseconds to pschedtime */ + if (tb[TCA_PIE_TARGET]) { + /* target is in us */ + u32 target = nla_get_u32(tb[TCA_PIE_TARGET]); + + /* convert to pschedtime */ + q->params.target = PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC); + } + + /* tupdate is in jiffies */ + if (tb[TCA_PIE_TUPDATE]) + q->params.tupdate = usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE])); + + if (tb[TCA_PIE_LIMIT]) { + u32 limit = nla_get_u32(tb[TCA_PIE_LIMIT]); + + q->params.limit = limit; + sch->limit = limit; + } + + if (tb[TCA_PIE_ALPHA]) + q->params.alpha = nla_get_u32(tb[TCA_PIE_ALPHA]); + + if (tb[TCA_PIE_BETA]) + q->params.beta = nla_get_u32(tb[TCA_PIE_BETA]); + + if (tb[TCA_PIE_ECN]) + q->params.ecn = nla_get_u32(tb[TCA_PIE_ECN]); + + if (tb[TCA_PIE_BYTEMODE]) + q->params.bytemode = nla_get_u32(tb[TCA_PIE_BYTEMODE]); + + /* Drop excess packets if new limit is lower */ + qlen = sch->q.qlen; + while (sch->q.qlen > sch->limit) { + struct sk_buff *skb = __skb_dequeue(&sch->q); + + sch->qstats.backlog -= qdisc_pkt_len(skb); + qdisc_drop(skb, sch); + } + qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + + sch_tree_unlock(sch); + return 0; +} + +static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) +{ + + struct pie_sched_data *q = qdisc_priv(sch); + int qlen = sch->qstats.backlog; /* current queue size in bytes */ + + /* If current queue is about 10 packets or more and dq_count is unset + * we have enough packets to calculate the drain rate. Save + * current time as dq_tstamp and start measurement cycle. + */ + if (qlen >= QUEUE_THRESHOLD && q->vars.dq_count == DQCOUNT_INVALID) { + q->vars.dq_tstamp = psched_get_time(); + q->vars.dq_count = 0; + } + + /* Calculate the average drain rate from this value. If queue length + * has receded to a small value viz., <= QUEUE_THRESHOLD bytes,reset + * the dq_count to -1 as we don't have enough packets to calculate the + * drain rate anymore The following if block is entered only when we + * have a substantial queue built up (QUEUE_THRESHOLD bytes or more) + * and we calculate the drain rate for the threshold here. dq_count is + * in bytes, time difference in psched_time, hence rate is in + * bytes/psched_time. + */ + if (q->vars.dq_count != DQCOUNT_INVALID) { + q->vars.dq_count += skb->len; + + if (q->vars.dq_count >= QUEUE_THRESHOLD) { + psched_time_t now = psched_get_time(); + u32 dtime = now - q->vars.dq_tstamp; + u32 count = q->vars.dq_count << PIE_SCALE; + + if (dtime == 0) + return; + + count = count / dtime; + + if (q->vars.avg_dq_rate == 0) + q->vars.avg_dq_rate = count; + else + q->vars.avg_dq_rate = + (q->vars.avg_dq_rate - + (q->vars.avg_dq_rate >> 3)) + (count >> 3); + + /* If the queue has receded below the threshold, we hold + * on to the last drain rate calculated, else we reset + * dq_count to 0 to re-enter the if block when the next + * packet is dequeued + */ + if (qlen < QUEUE_THRESHOLD) + q->vars.dq_count = DQCOUNT_INVALID; + else { + q->vars.dq_count = 0; + q->vars.dq_tstamp = psched_get_time(); + } + + if (q->vars.burst_time > 0) { + if (q->vars.burst_time > dtime) + q->vars.burst_time -= dtime; + else + q->vars.burst_time = 0; + } + } + } +} + +static void calculate_probability(struct Qdisc *sch) +{ + struct pie_sched_data *q = qdisc_priv(sch); + u32 qlen = sch->qstats.backlog; /* queue size in bytes */ + psched_time_t qdelay = 0; /* in pschedtime */ + psched_time_t qdelay_old = q->vars.qdelay; /* in pschedtime */ + s32 delta = 0; /* determines the change in probability */ + u32 oldprob; + u32 alpha, beta; + bool update_prob = true; + + q->vars.qdelay_old = q->vars.qdelay; + + if (q->vars.avg_dq_rate > 0) + qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate; + else + qdelay = 0; + + /* If qdelay is zero and qlen is not, it means qlen is very small, less + * than dequeue_rate, so we do not update probabilty in this round + */ + if (qdelay == 0 && qlen != 0) + update_prob = false; + + /* In the algorithm, alpha and beta are between 0 and 2 with typical + * value for alpha as 0.125. In this implementation, we use values 0-32 + * passed from user space to represent this. Also, alpha and beta have + * unit of HZ and need to be scaled before they can used to update + * probability. alpha/beta are updated locally below by 1) scaling them + * appropriately 2) scaling down by 16 to come to 0-2 range. + * Please see paper for details. + * + * We scale alpha and beta differently depending on whether we are in + * light, medium or high dropping mode. + */ + if (q->vars.prob < MAX_PROB / 100) { + alpha = + (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7; + beta = + (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7; + } else if (q->vars.prob < MAX_PROB / 10) { + alpha = + (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5; + beta = + (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5; + } else { + alpha = + (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; + beta = + (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; + } + + /* alpha and beta should be between 0 and 32, in multiples of 1/16 */ + delta += alpha * ((qdelay - q->params.target)); + delta += beta * ((qdelay - qdelay_old)); + + oldprob = q->vars.prob; + + /* to ensure we increase probability in steps of no more than 2% */ + if (delta > (s32) (MAX_PROB / (100 / 2)) && + q->vars.prob >= MAX_PROB / 10) + delta = (MAX_PROB / 100) * 2; + + /* Non-linear drop: + * Tune drop probability to increase quickly for high delays(>= 250ms) + * 250ms is derived through experiments and provides error protection + */ + + if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC))) + delta += MAX_PROB / (100 / 2); + + q->vars.prob += delta; + + if (delta > 0) { + /* prevent overflow */ + if (q->vars.prob < oldprob) { + q->vars.prob = MAX_PROB; + /* Prevent normalization error. If probability is at + * maximum value already, we normalize it here, and + * skip the check to do a non-linear drop in the next + * section. + */ + update_prob = false; + } + } else { + /* prevent underflow */ + if (q->vars.prob > oldprob) + q->vars.prob = 0; + } + + /* Non-linear drop in probability: Reduce drop probability quickly if + * delay is 0 for 2 consecutive Tupdate periods. + */ + + if ((qdelay == 0) && (qdelay_old == 0) && update_prob) + q->vars.prob = (q->vars.prob * 98) / 100; + + q->vars.qdelay = qdelay; + q->vars.qlen_old = qlen; + + /* We restart the measurement cycle if the following conditions are met + * 1. If the delay has been low for 2 consecutive Tupdate periods + * 2. Calculated drop probability is zero + * 3. We have atleast one estimate for the avg_dq_rate ie., + * is a non-zero value + */ + if ((q->vars.qdelay < q->params.target / 2) && + (q->vars.qdelay_old < q->params.target / 2) && + (q->vars.prob == 0) && + (q->vars.avg_dq_rate > 0)) + pie_vars_init(&q->vars); +} + +static void pie_timer(unsigned long arg) +{ + struct Qdisc *sch = (struct Qdisc *)arg; + struct pie_sched_data *q = qdisc_priv(sch); + spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + + spin_lock(root_lock); + calculate_probability(sch); + + /* reset the timer to fire after 'tupdate'. tupdate is in jiffies. */ + if (q->params.tupdate) + mod_timer(&q->adapt_timer, jiffies + q->params.tupdate); + spin_unlock(root_lock); + +} + +static int pie_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct pie_sched_data *q = qdisc_priv(sch); + + pie_params_init(&q->params); + pie_vars_init(&q->vars); + sch->limit = q->params.limit; + + setup_timer(&q->adapt_timer, pie_timer, (unsigned long)sch); + mod_timer(&q->adapt_timer, jiffies + HZ / 2); + + if (opt) { + int err = pie_change(sch, opt); + + if (err) + return err; + } + + return 0; +} + +static int pie_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct pie_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + + opts = nla_nest_start(skb, TCA_OPTIONS); + if (opts == NULL) + goto nla_put_failure; + + /* convert target from pschedtime to us */ + if (nla_put_u32(skb, TCA_PIE_TARGET, + ((u32) PSCHED_TICKS2NS(q->params.target)) / + NSEC_PER_USEC) || + nla_put_u32(skb, TCA_PIE_LIMIT, sch->limit) || + nla_put_u32(skb, TCA_PIE_TUPDATE, jiffies_to_usecs(q->params.tupdate)) || + nla_put_u32(skb, TCA_PIE_ALPHA, q->params.alpha) || + nla_put_u32(skb, TCA_PIE_BETA, q->params.beta) || + nla_put_u32(skb, TCA_PIE_ECN, q->params.ecn) || + nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode)) + goto nla_put_failure; + + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -1; + +} + +static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct pie_sched_data *q = qdisc_priv(sch); + struct tc_pie_xstats st = { + .prob = q->vars.prob, + .delay = ((u32) PSCHED_TICKS2NS(q->vars.qdelay)) / + NSEC_PER_USEC, + /* unscale and return dq_rate in bytes per sec */ + .avg_dq_rate = q->vars.avg_dq_rate * + (PSCHED_TICKS_PER_SEC) >> PIE_SCALE, + .packets_in = q->stats.packets_in, + .overlimit = q->stats.overlimit, + .maxq = q->stats.maxq, + .dropped = q->stats.dropped, + .ecn_mark = q->stats.ecn_mark, + }; + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch) +{ + struct sk_buff *skb; + skb = __qdisc_dequeue_head(sch, &sch->q); + + if (!skb) + return NULL; + + pie_process_dequeue(sch, skb); + return skb; +} + +static void pie_reset(struct Qdisc *sch) +{ + struct pie_sched_data *q = qdisc_priv(sch); + qdisc_reset_queue(sch); + pie_vars_init(&q->vars); +} + +static void pie_destroy(struct Qdisc *sch) +{ + struct pie_sched_data *q = qdisc_priv(sch); + q->params.tupdate = 0; + del_timer_sync(&q->adapt_timer); +} + +static struct Qdisc_ops pie_qdisc_ops __read_mostly = { + .id = "pie", + .priv_size = sizeof(struct pie_sched_data), + .enqueue = pie_qdisc_enqueue, + .dequeue = pie_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .init = pie_init, + .destroy = pie_destroy, + .reset = pie_reset, + .change = pie_change, + .dump = pie_dump, + .dump_stats = pie_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init pie_module_init(void) +{ + return register_qdisc(&pie_qdisc_ops); +} + +static void __exit pie_module_exit(void) +{ + unregister_qdisc(&pie_qdisc_ops); +} + +module_init(pie_module_init); +module_exit(pie_module_exit); + +MODULE_DESCRIPTION("Proportional Integral controller Enhanced (PIE) scheduler"); +MODULE_AUTHOR("Vijay Subramanian"); +MODULE_AUTHOR("Mythili Prabhu"); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 30ea4674cabd..9b0f7093d970 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -220,7 +220,7 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q) { - q->bins[slot].perturbation = net_random(); + q->bins[slot].perturbation = prandom_u32(); } static void sfb_swap_slot(struct sfb_sched_data *q) @@ -381,7 +381,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) goto enqueue; } - r = net_random() & SFB_MAX_PROB; + r = prandom_u32() & SFB_MAX_PROB; if (unlikely(r < p_min)) { if (unlikely(p_min > SFB_MAX_PROB / 2)) { diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index d3a1bc26dbfc..87317ff0b4ec 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -237,10 +237,12 @@ static inline void sfq_link(struct sfq_sched_data *q, sfq_index x) } #define sfq_unlink(q, x, n, p) \ - n = q->slots[x].dep.next; \ - p = q->slots[x].dep.prev; \ - sfq_dep_head(q, p)->next = n; \ - sfq_dep_head(q, n)->prev = p + do { \ + n = q->slots[x].dep.next; \ + p = q->slots[x].dep.prev; \ + sfq_dep_head(q, p)->next = n; \ + sfq_dep_head(q, n)->prev = p; \ + } while (0) static inline void sfq_dec(struct sfq_sched_data *q, sfq_index x) @@ -627,7 +629,7 @@ static void sfq_perturbation(unsigned long arg) spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); - q->perturbation = net_random(); + q->perturbation = prandom_u32(); if (!q->filter_list && q->tail) sfq_rehash(sch); spin_unlock(root_lock); @@ -696,7 +698,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) del_timer(&q->perturb_timer); if (q->perturb_period) { mod_timer(&q->perturb_timer, jiffies + q->perturb_period); - q->perturbation = net_random(); + q->perturbation = prandom_u32(); } sch_tree_unlock(sch); kfree(p); @@ -757,7 +759,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) q->quantum = psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); q->perturb_period = 0; - q->perturbation = net_random(); + q->perturbation = prandom_u32(); if (opt) { int err = sfq_change(sch, opt); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 887e672f9d7d..1cb413fead89 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -21,7 +21,6 @@ #include <net/netlink.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> -#include <net/tcp.h> /* Simple Token Bucket Filter. @@ -148,16 +147,10 @@ static u64 psched_ns_t2l(const struct psched_ratecfg *r, * Return length of individual segments of a gso packet, * including all headers (MAC, IP, TCP/UDP) */ -static unsigned int skb_gso_seglen(const struct sk_buff *skb) +static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) { unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); - const struct skb_shared_info *shinfo = skb_shinfo(skb); - - if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) - hdr_len += tcp_hdrlen(skb); - else - hdr_len += sizeof(struct udphdr); - return hdr_len + shinfo->gso_size; + return hdr_len + skb_gso_transport_seglen(skb); } /* GSO packet is too big, segment it so that tbf can transmit @@ -202,7 +195,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) int ret; if (qdisc_pkt_len(skb) > q->max_size) { - if (skb_is_gso(skb) && skb_gso_seglen(skb) <= q->max_size) + if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size) return tbf_segment(skb, sch); return qdisc_reshape_fail(skb, sch); } @@ -307,6 +300,8 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = { [TCA_TBF_PTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE }, [TCA_TBF_RATE64] = { .type = NLA_U64 }, [TCA_TBF_PRATE64] = { .type = NLA_U64 }, + [TCA_TBF_BURST] = { .type = NLA_U32 }, + [TCA_TBF_PBURST] = { .type = NLA_U32 }, }; static int tbf_change(struct Qdisc *sch, struct nlattr *opt) @@ -358,7 +353,12 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) rate64 = nla_get_u64(tb[TCA_TBF_RATE64]); psched_ratecfg_precompute(&rate, &qopt->rate, rate64); - max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U); + if (tb[TCA_TBF_BURST]) { + max_size = nla_get_u32(tb[TCA_TBF_BURST]); + buffer = psched_l2t_ns(&rate, max_size); + } else { + max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U); + } if (qopt->peakrate.rate) { if (tb[TCA_TBF_PRATE64]) @@ -366,12 +366,18 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) psched_ratecfg_precompute(&peak, &qopt->peakrate, prate64); if (peak.rate_bytes_ps <= rate.rate_bytes_ps) { pr_warn_ratelimited("sch_tbf: peakrate %llu is lower than or equals to rate %llu !\n", - peak.rate_bytes_ps, rate.rate_bytes_ps); + peak.rate_bytes_ps, rate.rate_bytes_ps); err = -EINVAL; goto done; } - max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu)); + if (tb[TCA_TBF_PBURST]) { + u32 pburst = nla_get_u32(tb[TCA_TBF_PBURST]); + max_size = min_t(u32, max_size, pburst); + mtu = psched_l2t_ns(&peak, pburst); + } else { + max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu)); + } } if (max_size < psched_mtu(qdisc_dev(sch))) @@ -391,9 +397,15 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) q->qdisc = child; } q->limit = qopt->limit; - q->mtu = PSCHED_TICKS2NS(qopt->mtu); + if (tb[TCA_TBF_PBURST]) + q->mtu = mtu; + else + q->mtu = PSCHED_TICKS2NS(qopt->mtu); q->max_size = max_size; - q->buffer = PSCHED_TICKS2NS(qopt->buffer); + if (tb[TCA_TBF_BURST]) + q->buffer = buffer; + else + q->buffer = PSCHED_TICKS2NS(qopt->buffer); q->tokens = q->buffer; q->ptokens = q->mtu; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 31ed008c8e13..f558433537b8 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -90,14 +89,12 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a /* Initialize the object handling fields. */ atomic_set(&asoc->base.refcnt, 1); - asoc->base.dead = false; /* Initialize the bind addr area. */ sctp_bind_addr_init(&asoc->base.bind_addr, ep->base.bind_addr.port); asoc->state = SCTP_STATE_CLOSED; asoc->cookie_life = ms_to_ktime(sp->assocparams.sasoc_cookie_life); - asoc->frag_point = 0; asoc->user_frag = sp->user_frag; /* Set the association max_retrans and RTO values from the @@ -110,8 +107,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max); asoc->rto_min = msecs_to_jiffies(sp->rtoinfo.srto_min); - asoc->overall_error_count = 0; - /* Initialize the association's heartbeat interval based on the * sock configured value. */ @@ -132,18 +127,15 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a */ asoc->param_flags = sp->param_flags; - /* Initialize the maximum mumber of new data packets that can be sent + /* Initialize the maximum number of new data packets that can be sent * in a burst. */ asoc->max_burst = sp->max_burst; /* initialize association timers */ - asoc->timeouts[SCTP_EVENT_TIMEOUT_NONE] = 0; asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE] = asoc->rto_initial; asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT] = asoc->rto_initial; asoc->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = asoc->rto_initial; - asoc->timeouts[SCTP_EVENT_TIMEOUT_T3_RTX] = 0; - asoc->timeouts[SCTP_EVENT_TIMEOUT_T4_RTO] = 0; /* sctpimpguide Section 2.12.2 * If the 'T5-shutdown-guard' timer is used, it SHOULD be set to the @@ -152,7 +144,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->timeouts[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD] = 5 * asoc->rto_max; - asoc->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ; @@ -172,11 +163,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->max_init_timeo = msecs_to_jiffies(sp->initmsg.sinit_max_init_timeo); - /* Allocate storage for the ssnmap after the inbound and outbound - * streams have been negotiated during Init. - */ - asoc->ssnmap = NULL; - /* Set the local window size for receive. * This is also the rcvbuf space per association. * RFC 6 - A SCTP receiver MUST be able to receive a minimum of @@ -189,25 +175,15 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->a_rwnd = asoc->rwnd; - asoc->rwnd_over = 0; - asoc->rwnd_press = 0; - /* Use my own max window until I learn something better. */ asoc->peer.rwnd = SCTP_DEFAULT_MAXWINDOW; - /* Set the sndbuf size for transmit. */ - asoc->sndbuf_used = 0; - /* Initialize the receive memory counter */ atomic_set(&asoc->rmem_alloc, 0); init_waitqueue_head(&asoc->wait); asoc->c.my_vtag = sctp_generate_tag(ep); - asoc->peer.i.init_tag = 0; /* INIT needs a vtag of 0. */ - asoc->c.peer_vtag = 0; - asoc->c.my_ttag = 0; - asoc->c.peer_ttag = 0; asoc->c.my_port = ep->base.bind_addr.port; asoc->c.initial_tsn = sctp_generate_tsn(ep); @@ -218,7 +194,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->adv_peer_ack_point = asoc->ctsn_ack_point; asoc->highest_sacked = asoc->ctsn_ack_point; asoc->last_cwr_tsn = asoc->ctsn_ack_point; - asoc->unack_data = 0; /* ADDIP Section 4.1 Asconf Chunk Procedures * @@ -237,7 +212,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a /* Make an empty list of remote transport addresses. */ INIT_LIST_HEAD(&asoc->peer.transport_addr_list); - asoc->peer.transport_count = 0; /* RFC 2960 5.1 Normal Establishment of an Association * @@ -251,20 +225,15 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a * already received one packet.] */ asoc->peer.sack_needed = 1; - asoc->peer.sack_cnt = 0; asoc->peer.sack_generation = 1; /* Assume that the peer will tell us if he recognizes ASCONF * as part of INIT exchange. - * The sctp_addip_noauth option is there for backward compatibilty + * The sctp_addip_noauth option is there for backward compatibility * and will revert old behavior. */ - asoc->peer.asconf_capable = 0; if (net->sctp.addip_noauth) asoc->peer.asconf_capable = 1; - asoc->asconf_addr_del_pending = NULL; - asoc->src_out_of_asoc_ok = 0; - asoc->new_transport = NULL; /* Create an input queue. */ sctp_inq_init(&asoc->base.inqueue); @@ -276,12 +245,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a if (!sctp_ulpq_init(&asoc->ulpq, asoc)) goto fail_init; - memset(&asoc->peer.tsn_map, 0, sizeof(struct sctp_tsnmap)); - - asoc->need_ecne = 0; - - asoc->assoc_id = 0; - /* Assume that peer would support both address types unless we are * told otherwise. */ @@ -297,9 +260,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->default_timetolive = sp->default_timetolive; asoc->default_rcv_context = sp->default_rcv_context; - /* SCTP_GET_ASSOC_STATS COUNTERS */ - memset(&asoc->stats, 0, sizeof(struct sctp_priv_assoc_stats)); - /* AUTH related initializations */ INIT_LIST_HEAD(&asoc->endpoint_shared_keys); err = sctp_auth_asoc_copy_shkeys(ep, asoc, gfp); @@ -307,9 +267,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a goto fail_init; asoc->active_key_id = ep->active_key_id; - asoc->asoc_shared_key = NULL; - asoc->default_hmac_id = 0; /* Save the hmacs and chunks list into this association */ if (ep->auth_hmacs_list) memcpy(asoc->c.auth_hmacs, ep->auth_hmacs_list, @@ -994,17 +952,13 @@ int sctp_cmp_addr_exact(const union sctp_addr *ss1, */ struct sctp_chunk *sctp_get_ecne_prepend(struct sctp_association *asoc) { - struct sctp_chunk *chunk; + if (!asoc->need_ecne) + return NULL; /* Send ECNE if needed. * Not being able to allocate a chunk here is not deadly. */ - if (asoc->need_ecne) - chunk = sctp_make_ecne(asoc, asoc->last_ecne_tsn); - else - chunk = NULL; - - return chunk; + return sctp_make_ecne(asoc, asoc->last_ecne_tsn); } /* @@ -1265,7 +1219,7 @@ void sctp_assoc_update(struct sctp_association *asoc, } } - /* SCTP-AUTH: Save the peer parameters from the new assocaitions + /* SCTP-AUTH: Save the peer parameters from the new associations * and also move the association shared keys over */ kfree(asoc->peer.peer_random); @@ -1393,7 +1347,7 @@ void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc) } /* Should we send a SACK to update our peer? */ -static inline int sctp_peer_needs_update(struct sctp_association *asoc) +static inline bool sctp_peer_needs_update(struct sctp_association *asoc) { struct net *net = sock_net(asoc->base.sk); switch (asoc->state) { @@ -1405,52 +1359,43 @@ static inline int sctp_peer_needs_update(struct sctp_association *asoc) ((asoc->rwnd - asoc->a_rwnd) >= max_t(__u32, (asoc->base.sk->sk_rcvbuf >> net->sctp.rwnd_upd_shift), asoc->pathmtu))) - return 1; + return true; break; default: break; } - return 0; + return false; } -/* Increase asoc's rwnd by len and send any window update SACK if needed. */ -void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) +/* Update asoc's rwnd for the approximated state in the buffer, + * and check whether SACK needs to be sent. + */ +void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer) { + int rx_count; struct sctp_chunk *sack; struct timer_list *timer; - if (asoc->rwnd_over) { - if (asoc->rwnd_over >= len) { - asoc->rwnd_over -= len; - } else { - asoc->rwnd += (len - asoc->rwnd_over); - asoc->rwnd_over = 0; - } - } else { - asoc->rwnd += len; - } + if (asoc->ep->rcvbuf_policy) + rx_count = atomic_read(&asoc->rmem_alloc); + else + rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - /* If we had window pressure, start recovering it - * once our rwnd had reached the accumulated pressure - * threshold. The idea is to recover slowly, but up - * to the initial advertised window. - */ - if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) { - int change = min(asoc->pathmtu, asoc->rwnd_press); - asoc->rwnd += change; - asoc->rwnd_press -= change; - } + if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0) + asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1; + else + asoc->rwnd = 0; - pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->a_rwnd); + pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n", + __func__, asoc, asoc->rwnd, rx_count, + asoc->base.sk->sk_rcvbuf); /* Send a window update SACK if the rwnd has increased by at least the * minimum of the association's PMTU and half of the receive buffer. * The algorithm used is similar to the one described in * Section 4.2.3.3 of RFC 1122. */ - if (sctp_peer_needs_update(asoc)) { + if (update_peer && sctp_peer_needs_update(asoc)) { asoc->a_rwnd = asoc->rwnd; pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u " @@ -1472,45 +1417,6 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) } } -/* Decrease asoc's rwnd by len. */ -void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) -{ - int rx_count; - int over = 0; - - if (unlikely(!asoc->rwnd || asoc->rwnd_over)) - pr_debug("%s: association:%p has asoc->rwnd:%u, " - "asoc->rwnd_over:%u!\n", __func__, asoc, - asoc->rwnd, asoc->rwnd_over); - - if (asoc->ep->rcvbuf_policy) - rx_count = atomic_read(&asoc->rmem_alloc); - else - rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - - /* If we've reached or overflowed our receive buffer, announce - * a 0 rwnd if rwnd would still be positive. Store the - * the pottential pressure overflow so that the window can be restored - * back to original value. - */ - if (rx_count >= asoc->base.sk->sk_rcvbuf) - over = 1; - - if (asoc->rwnd >= len) { - asoc->rwnd -= len; - if (over) { - asoc->rwnd_press += asoc->rwnd; - asoc->rwnd = 0; - } - } else { - asoc->rwnd_over = len - asoc->rwnd; - asoc->rwnd = 0; - } - - pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->rwnd_press); -} /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 46b5977978a1..683c7d1b1306 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -16,9 +16,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -42,7 +41,7 @@ static struct sctp_hmac sctp_hmac_list[SCTP_AUTH_NUM_HMACS] = { }, { .hmac_id = SCTP_AUTH_HMAC_ID_SHA1, - .hmac_name="hmac(sha1)", + .hmac_name = "hmac(sha1)", .hmac_len = SCTP_SHA1_SIG_SIZE, }, { @@ -52,7 +51,7 @@ static struct sctp_hmac sctp_hmac_list[SCTP_AUTH_NUM_HMACS] = { #if defined (CONFIG_CRYPTO_SHA256) || defined (CONFIG_CRYPTO_SHA256_MODULE) { .hmac_id = SCTP_AUTH_HMAC_ID_SHA256, - .hmac_name="hmac(sha256)", + .hmac_name = "hmac(sha256)", .hmac_len = SCTP_SHA256_SIG_SIZE, } #endif @@ -164,7 +163,7 @@ static int sctp_auth_compare_vectors(struct sctp_auth_bytes *vector1, * lead-zero padded. If it is not, it * is automatically larger numerically. */ - for (i = 0; i < abs(diff); i++ ) { + for (i = 0; i < abs(diff); i++) { if (longer[i] != 0) return diff; } @@ -227,9 +226,9 @@ static struct sctp_auth_bytes *sctp_auth_make_local_vector( gfp_t gfp) { return sctp_auth_make_key_vector( - (sctp_random_param_t*)asoc->c.auth_random, - (sctp_chunks_param_t*)asoc->c.auth_chunks, - (sctp_hmac_algo_param_t*)asoc->c.auth_hmacs, + (sctp_random_param_t *)asoc->c.auth_random, + (sctp_chunks_param_t *)asoc->c.auth_chunks, + (sctp_hmac_algo_param_t *)asoc->c.auth_hmacs, gfp); } @@ -500,8 +499,7 @@ void sctp_auth_destroy_hmacs(struct crypto_hash *auth_hmacs[]) if (!auth_hmacs) return; - for (i = 0; i < SCTP_AUTH_NUM_HMACS; i++) - { + for (i = 0; i < SCTP_AUTH_NUM_HMACS; i++) { if (auth_hmacs[i]) crypto_free_hash(auth_hmacs[i]); } @@ -648,15 +646,15 @@ static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param) */ for (i = 0; !found && i < len; i++) { switch (param->chunks[i]) { - case SCTP_CID_INIT: - case SCTP_CID_INIT_ACK: - case SCTP_CID_SHUTDOWN_COMPLETE: - case SCTP_CID_AUTH: + case SCTP_CID_INIT: + case SCTP_CID_INIT_ACK: + case SCTP_CID_SHUTDOWN_COMPLETE: + case SCTP_CID_AUTH: break; - default: + default: if (param->chunks[i] == chunk) - found = 1; + found = 1; break; } } diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 077bb070052b..871cdf9567e6 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -21,9 +21,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index f2044fcb9dd1..158701da2d31 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -18,9 +18,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -255,7 +254,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, SCTP_INC_STATS_USER(sock_net(asoc->base.sk), SCTP_MIB_FRAGUSRMSGS); /* Create chunks for all the full sized DATA chunks. */ - for (i=0, len=first_len; i < whole; i++) { + for (i = 0, len = first_len; i < whole; i++) { frag = SCTP_DATA_MIDDLE_FRAG; if (0 == i) @@ -318,7 +317,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, goto errout; } - err = sctp_user_addto_chunk(chunk, offset, over,msgh->msg_iov); + err = sctp_user_addto_chunk(chunk, offset, over, msgh->msg_iov); /* Put the chunk->skb back into the form expected by send. */ __skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr diff --git a/net/sctp/command.c b/net/sctp/command.c index 3d9a9ff69c03..dd7375851618 100644 --- a/net/sctp/command.c +++ b/net/sctp/command.c @@ -19,9 +19,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/debug.c b/net/sctp/debug.c index e89015d8935a..95d7b15dad21 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 09b8daac87c8..8e5fdea05216 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -23,9 +23,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -369,9 +368,9 @@ struct sctp_association *sctp_endpoint_lookup_assoc( { struct sctp_association *asoc; - sctp_local_bh_disable(); + local_bh_disable(); asoc = __sctp_endpoint_lookup_assoc(ep, paddr, transport); - sctp_local_bh_enable(); + local_bh_enable(); return asoc; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 98b69bbecdd9..f2e2cbd2d750 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -23,9 +23,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -120,7 +119,7 @@ int sctp_rcv(struct sk_buff *skb) struct sctp_af *af; struct net *net = dev_net(skb->dev); - if (skb->pkt_type!=PACKET_HOST) + if (skb->pkt_type != PACKET_HOST) goto discard_it; SCTP_INC_STATS_BH(net, SCTP_MIB_INSCTPPACKS); @@ -181,8 +180,7 @@ int sctp_rcv(struct sk_buff *skb) * If a frame arrives on an interface and the receiving socket is * bound to another interface, via SO_BINDTODEVICE, treat it as OOTB */ - if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb))) - { + if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb))) { if (asoc) { sctp_association_put(asoc); asoc = NULL; @@ -240,7 +238,7 @@ int sctp_rcv(struct sk_buff *skb) * bottom halves on this lock, but a user may be in the lock too, * so check if it is busy. */ - sctp_bh_lock_sock(sk); + bh_lock_sock(sk); if (sk != rcvr->sk) { /* Our cached sk is different from the rcvr->sk. This is @@ -250,14 +248,14 @@ int sctp_rcv(struct sk_buff *skb) * be doing something with the new socket. Switch our veiw * of the current sk. */ - sctp_bh_unlock_sock(sk); + bh_unlock_sock(sk); sk = rcvr->sk; - sctp_bh_lock_sock(sk); + bh_lock_sock(sk); } if (sock_owned_by_user(sk)) { if (sctp_add_backlog(sk, skb)) { - sctp_bh_unlock_sock(sk); + bh_unlock_sock(sk); sctp_chunk_free(chunk); skb = NULL; /* sctp_chunk_free already freed the skb */ goto discard_release; @@ -268,7 +266,7 @@ int sctp_rcv(struct sk_buff *skb) sctp_inq_push(&chunk->rcvr->inqueue, chunk); } - sctp_bh_unlock_sock(sk); + bh_unlock_sock(sk); /* Release the asoc/ep ref we took in the lookup calls. */ if (asoc) @@ -329,7 +327,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) */ sk = rcvr->sk; - sctp_bh_lock_sock(sk); + bh_lock_sock(sk); if (sock_owned_by_user(sk)) { if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) @@ -339,7 +337,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) } else sctp_inq_push(inqueue, chunk); - sctp_bh_unlock_sock(sk); + bh_unlock_sock(sk); /* If the chunk was backloged again, don't drop refs */ if (backloged) @@ -524,7 +522,7 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, goto out; } - sctp_bh_lock_sock(sk); + bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. @@ -537,17 +535,15 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, return sk; out: - if (asoc) - sctp_association_put(asoc); + sctp_association_put(asoc); return NULL; } /* Common cleanup code for icmp/icmpv6 error handler. */ void sctp_err_finish(struct sock *sk, struct sctp_association *asoc) { - sctp_bh_unlock_sock(sk); - if (asoc) - sctp_association_put(asoc); + bh_unlock_sock(sk); + sctp_association_put(asoc); } /* @@ -613,8 +609,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) if (ICMP_FRAG_NEEDED == code) { sctp_icmp_frag_needed(sk, asoc, transport, info); goto out_unlock; - } - else { + } else { if (ICMP_PROT_UNREACH == code) { sctp_icmp_proto_unreachable(sk, asoc, transport); @@ -723,17 +718,17 @@ static void __sctp_hash_endpoint(struct sctp_endpoint *ep) epb->hashent = sctp_ep_hashfn(net, epb->bind_addr.port); head = &sctp_ep_hashtable[epb->hashent]; - sctp_write_lock(&head->lock); + write_lock(&head->lock); hlist_add_head(&epb->node, &head->chain); - sctp_write_unlock(&head->lock); + write_unlock(&head->lock); } /* Add an endpoint to the hash. Local BH-safe. */ void sctp_hash_endpoint(struct sctp_endpoint *ep) { - sctp_local_bh_disable(); + local_bh_disable(); __sctp_hash_endpoint(ep); - sctp_local_bh_enable(); + local_bh_enable(); } /* Remove endpoint from the hash table. */ @@ -749,17 +744,17 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) head = &sctp_ep_hashtable[epb->hashent]; - sctp_write_lock(&head->lock); + write_lock(&head->lock); hlist_del_init(&epb->node); - sctp_write_unlock(&head->lock); + write_unlock(&head->lock); } /* Remove endpoint from the hash. Local BH-safe. */ void sctp_unhash_endpoint(struct sctp_endpoint *ep) { - sctp_local_bh_disable(); + local_bh_disable(); __sctp_unhash_endpoint(ep); - sctp_local_bh_enable(); + local_bh_enable(); } /* Look up an endpoint. */ @@ -803,9 +798,9 @@ static void __sctp_hash_established(struct sctp_association *asoc) head = &sctp_assoc_hashtable[epb->hashent]; - sctp_write_lock(&head->lock); + write_lock(&head->lock); hlist_add_head(&epb->node, &head->chain); - sctp_write_unlock(&head->lock); + write_unlock(&head->lock); } /* Add an association to the hash. Local BH-safe. */ @@ -814,9 +809,9 @@ void sctp_hash_established(struct sctp_association *asoc) if (asoc->temp) return; - sctp_local_bh_disable(); + local_bh_disable(); __sctp_hash_established(asoc); - sctp_local_bh_enable(); + local_bh_enable(); } /* Remove association from the hash table. */ @@ -833,9 +828,9 @@ static void __sctp_unhash_established(struct sctp_association *asoc) head = &sctp_assoc_hashtable[epb->hashent]; - sctp_write_lock(&head->lock); + write_lock(&head->lock); hlist_del_init(&epb->node); - sctp_write_unlock(&head->lock); + write_unlock(&head->lock); } /* Remove association from the hash table. Local BH-safe. */ @@ -844,9 +839,9 @@ void sctp_unhash_established(struct sctp_association *asoc) if (asoc->temp) return; - sctp_local_bh_disable(); + local_bh_disable(); __sctp_unhash_established(asoc); - sctp_local_bh_enable(); + local_bh_enable(); } /* Look up an association. */ @@ -896,9 +891,9 @@ struct sctp_association *sctp_lookup_association(struct net *net, { struct sctp_association *asoc; - sctp_local_bh_disable(); + local_bh_disable(); asoc = __sctp_lookup_association(net, laddr, paddr, transportp); - sctp_local_bh_enable(); + local_bh_enable(); return asoc; } @@ -1058,31 +1053,31 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, if (ch_end > skb_tail_pointer(skb)) break; - switch(ch->type) { - case SCTP_CID_AUTH: - have_auth = chunk_num; - break; - - case SCTP_CID_COOKIE_ECHO: - /* If a packet arrives containing an AUTH chunk as - * a first chunk, a COOKIE-ECHO chunk as the second - * chunk, and possibly more chunks after them, and - * the receiver does not have an STCB for that - * packet, then authentication is based on - * the contents of the COOKIE- ECHO chunk. - */ - if (have_auth == 1 && chunk_num == 2) - return NULL; - break; - - case SCTP_CID_ASCONF: - if (have_auth || net->sctp.addip_noauth) - asoc = __sctp_rcv_asconf_lookup( - net, ch, laddr, - sctp_hdr(skb)->source, - transportp); - default: - break; + switch (ch->type) { + case SCTP_CID_AUTH: + have_auth = chunk_num; + break; + + case SCTP_CID_COOKIE_ECHO: + /* If a packet arrives containing an AUTH chunk as + * a first chunk, a COOKIE-ECHO chunk as the second + * chunk, and possibly more chunks after them, and + * the receiver does not have an STCB for that + * packet, then authentication is based on + * the contents of the COOKIE- ECHO chunk. + */ + if (have_auth == 1 && chunk_num == 2) + return NULL; + break; + + case SCTP_CID_ASCONF: + if (have_auth || net->sctp.addip_noauth) + asoc = __sctp_rcv_asconf_lookup( + net, ch, laddr, + sctp_hdr(skb)->source, + transportp); + default: + break; } if (asoc) @@ -1119,19 +1114,10 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, return NULL; /* If this is INIT/INIT-ACK look inside the chunk too. */ - switch (ch->type) { - case SCTP_CID_INIT: - case SCTP_CID_INIT_ACK: + if (ch->type == SCTP_CID_INIT || ch->type == SCTP_CID_INIT_ACK) return __sctp_rcv_init_lookup(net, skb, laddr, transportp); - break; - default: - return __sctp_rcv_walk_lookup(net, skb, laddr, transportp); - break; - } - - - return NULL; + return __sctp_rcv_walk_lookup(net, skb, laddr, transportp); } /* Lookup an association for an inbound skb. */ diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 5856932fdc38..4de12afa13d4 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -24,9 +24,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 7567e6f1a920..2b1738ef9394 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -21,9 +21,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -173,7 +172,8 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, switch (type) { case ICMPV6_PKT_TOOBIG: - sctp_icmp_frag_needed(sk, asoc, transport, ntohl(info)); + if (ip6_sk_accept_pmtu(sk)) + sctp_icmp_frag_needed(sk, asoc, transport, ntohl(info)); goto out_unlock; case ICMPV6_PARAMPROB: if (ICMPV6_UNK_NEXTHDR == code) { @@ -263,7 +263,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, } final_p = fl6_update_dst(fl6, np->opt, &final); - dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); + dst = ip6_dst_lookup_flow(sk, fl6, final_p); if (!asoc || saddr) goto out; @@ -322,7 +322,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl6->saddr = baddr->v6.sin6_addr; fl6->fl6_sport = baddr->v6.sin6_port; final_p = fl6_update_dst(fl6, np->opt, &final); - dst = ip6_dst_lookup_flow(sk, fl6, final_p, false); + dst = ip6_dst_lookup_flow(sk, fl6, final_p); } out: @@ -402,7 +402,7 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, } /* Initialize a sockaddr_storage from in incoming skb. */ -static void sctp_v6_from_skb(union sctp_addr *addr,struct sk_buff *skb, +static void sctp_v6_from_skb(union sctp_addr *addr, struct sk_buff *skb, int is_saddr) { __be16 *port; @@ -662,6 +662,8 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, */ sctp_v6_to_sk_daddr(&asoc->peer.primary_addr, newsk); + newsk->sk_v6_rcv_saddr = sk->sk_v6_rcv_saddr; + sk_refcnt_debug_inc(newsk); if (newsk->sk_prot->init(newsk)) { diff --git a/net/sctp/objcnt.c b/net/sctp/objcnt.c index 647396baa56f..40e7fac96c41 100644 --- a/net/sctp/objcnt.c +++ b/net/sctp/objcnt.c @@ -20,9 +20,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -98,7 +97,7 @@ static void sctp_objcnt_seq_stop(struct seq_file *seq, void *v) { } -static void * sctp_objcnt_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void *sctp_objcnt_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return (*pos >= ARRAY_SIZE(sctp_dbg_objcnt)) ? NULL : (void *)pos; diff --git a/net/sctp/output.c b/net/sctp/output.c index 0fb140f8f088..0f4d15fc2627 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -20,9 +20,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -281,7 +280,7 @@ static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet, /* We believe that this chunk is OK to add to the packet */ switch (chunk->chunk_hdr->type) { - case SCTP_CID_DATA: + case SCTP_CID_DATA: /* Account for the data being in the packet */ sctp_packet_append_data(packet, chunk); /* Disallow SACK bundling after DATA. */ @@ -293,17 +292,17 @@ static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet, /* timestamp the chunk for rtx purposes */ chunk->sent_at = jiffies; break; - case SCTP_CID_COOKIE_ECHO: + case SCTP_CID_COOKIE_ECHO: packet->has_cookie_echo = 1; break; - case SCTP_CID_SACK: + case SCTP_CID_SACK: packet->has_sack = 1; if (chunk->asoc) chunk->asoc->stats.osacks++; break; - case SCTP_CID_AUTH: + case SCTP_CID_AUTH: packet->has_auth = 1; packet->auth = chunk; break; @@ -388,7 +387,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) int err = 0; int padding; /* How much padding do we need? */ __u8 has_data = 0; - struct dst_entry *dst = tp->dst; + struct dst_entry *dst; unsigned char *auth = NULL; /* pointer to auth in skb data */ pr_debug("%s: packet:%p\n", __func__, packet); @@ -421,9 +420,9 @@ int sctp_packet_transmit(struct sctp_packet *packet) } } dst = dst_clone(tp->dst); - skb_dst_set(nskb, dst); if (!dst) goto no_route; + skb_dst_set(nskb, dst); /* Build the SCTP header. */ sh = (struct sctphdr *)skb_push(nskb, sizeof(struct sctphdr)); @@ -541,8 +540,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) } else { /* no need to seed pseudo checksum for SCTP */ nskb->ip_summed = CHECKSUM_PARTIAL; - nskb->csum_start = (skb_transport_header(nskb) - - nskb->head); + nskb->csum_start = skb_transport_header(nskb) - nskb->head; nskb->csum_offset = offsetof(struct sctphdr, checksum); } } @@ -559,7 +557,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) * Note: The works for IPv6 layer checks this bit too later * in transmission. See IP6_ECN_flow_xmit(). */ - (*tp->af_specific->ecn_capable)(nskb->sk); + tp->af_specific->ecn_capable(nskb->sk); /* Set up the IP options. */ /* BUG: not implemented @@ -594,7 +592,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) pr_debug("***sctp_transmit_packet*** skb->len:%d\n", nskb->len); nskb->local_df = packet->ipfragok; - (*tp->af_specific->sctp_xmit)(nskb, tp); + tp->af_specific->sctp_xmit(nskb, tp); out: sctp_packet_reset(packet); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 59268f6e2c36..9c77947c0597 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -111,7 +110,7 @@ static inline int sctp_cacc_skip_3_1_d(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks) { - if (count_of_newacks >=2 && transport != primary) + if (count_of_newacks >= 2 && transport != primary) return 1; return 0; } @@ -468,7 +467,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, struct net *net = sock_net(q->asoc->base.sk); int error = 0; - switch(reason) { + switch (reason) { case SCTP_RTXR_T3_RTX: SCTP_INC_STATS(net, SCTP_MIB_T3_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_T3_RTX); @@ -1083,7 +1082,7 @@ sctp_flush_out: * * --xguo */ - while ((ltransport = sctp_list_dequeue(&transport_list)) != NULL ) { + while ((ltransport = sctp_list_dequeue(&transport_list)) != NULL) { struct sctp_transport *t = list_entry(ltransport, struct sctp_transport, send_ready); @@ -1212,7 +1211,7 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) * destinations for which cacc_saw_newack is set. */ if (transport->cacc.cacc_saw_newack) - count_of_newacks ++; + count_of_newacks++; } /* Move the Cumulative TSN Ack Point if appropriate. */ diff --git a/net/sctp/primitive.c b/net/sctp/primitive.c index ce1ffd811775..ab8d9f96a177 100644 --- a/net/sctp/primitive.c +++ b/net/sctp/primitive.c @@ -23,9 +23,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 0c0642156842..0947f1e15eb8 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -16,9 +16,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -178,7 +177,7 @@ static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_associa rcu_read_unlock(); } -static void * sctp_eps_seq_start(struct seq_file *seq, loff_t *pos) +static void *sctp_eps_seq_start(struct seq_file *seq, loff_t *pos) { if (*pos >= sctp_ep_hashsize) return NULL; @@ -197,7 +196,7 @@ static void sctp_eps_seq_stop(struct seq_file *seq, void *v) } -static void * sctp_eps_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void *sctp_eps_seq_next(struct seq_file *seq, void *v, loff_t *pos) { if (++*pos >= sctp_ep_hashsize) return NULL; @@ -219,7 +218,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) return -ENOMEM; head = &sctp_ep_hashtable[hash]; - sctp_local_bh_disable(); + local_bh_disable(); read_lock(&head->lock); sctp_for_each_hentry(epb, &head->chain) { ep = sctp_ep(epb); @@ -236,7 +235,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } read_unlock(&head->lock); - sctp_local_bh_enable(); + local_bh_enable(); return 0; } @@ -283,7 +282,7 @@ void sctp_eps_proc_exit(struct net *net) } -static void * sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) +static void *sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) { if (*pos >= sctp_assoc_hashsize) return NULL; @@ -306,7 +305,7 @@ static void sctp_assocs_seq_stop(struct seq_file *seq, void *v) } -static void * sctp_assocs_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void *sctp_assocs_seq_next(struct seq_file *seq, void *v, loff_t *pos) { if (++*pos >= sctp_assoc_hashsize) return NULL; @@ -327,7 +326,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) return -ENOMEM; head = &sctp_assoc_hashtable[hash]; - sctp_local_bh_disable(); + local_bh_disable(); read_lock(&head->lock); sctp_for_each_hentry(epb, &head->chain) { assoc = sctp_assoc(epb); @@ -363,7 +362,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } read_unlock(&head->lock); - sctp_local_bh_enable(); + local_bh_enable(); return 0; } @@ -447,7 +446,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) return -ENOMEM; head = &sctp_assoc_hashtable[hash]; - sctp_local_bh_disable(); + local_bh_disable(); read_lock(&head->lock); rcu_read_lock(); sctp_for_each_hentry(epb, &head->chain) { @@ -506,7 +505,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) rcu_read_unlock(); read_unlock(&head->lock); - sctp_local_bh_enable(); + local_bh_enable(); return 0; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 5e17092f4ada..4e1d0fcb028e 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -23,9 +23,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -635,10 +634,10 @@ static void sctp_addr_wq_timeout_handler(unsigned long arg) /* ignore bound-specific endpoints */ if (!sctp_is_ep_boundall(sk)) continue; - sctp_bh_lock_sock(sk); + bh_lock_sock(sk); if (sctp_asconf_mgmt(sp, addrw) < 0) pr_debug("%s: sctp_asconf_mgmt failed\n", __func__); - sctp_bh_unlock_sock(sk); + bh_unlock_sock(sk); } #if IS_ENABLED(CONFIG_IPV6) free_next: @@ -1031,6 +1030,7 @@ static const struct net_protocol sctp_protocol = { .err_handler = sctp_v4_err, .no_policy = 1, .netns_ok = 1, + .icmp_strict_tag_validation = 1, }; /* IPv4 address related functions. */ @@ -1066,8 +1066,8 @@ static struct sctp_af sctp_af_inet = { #endif }; -struct sctp_pf *sctp_get_pf_specific(sa_family_t family) { - +struct sctp_pf *sctp_get_pf_specific(sa_family_t family) +{ switch (family) { case PF_INET: return sctp_pf_inet_specific; @@ -1461,7 +1461,6 @@ static __init int sctp_init(void) if (status) goto err_v6_add_protocol; - status = 0; out: return status; err_v6_add_protocol: diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index fe690320b1e4..632090b961c3 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -23,9 +23,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -79,6 +78,8 @@ static int sctp_process_param(struct sctp_association *asoc, gfp_t gfp); static void *sctp_addto_param(struct sctp_chunk *chunk, int len, const void *data); +static void *sctp_addto_chunk_fixed(struct sctp_chunk *, int len, + const void *data); /* Control chunk destructor */ static void sctp_control_release_owner(struct sk_buff *skb) @@ -1476,8 +1477,8 @@ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data) /* Append bytes to the end of a chunk. Returns NULL if there isn't sufficient * space in the chunk */ -void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk, - int len, const void *data) +static void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk, + int len, const void *data) { if (skb_tailroom(chunk->skb) >= len) return sctp_addto_chunk(chunk, len, data); @@ -1968,13 +1969,13 @@ static int sctp_verify_ext_param(struct net *net, union sctp_params param) for (i = 0; i < num_ext; i++) { switch (param.ext->chunks[i]) { - case SCTP_CID_AUTH: - have_auth = 1; - break; - case SCTP_CID_ASCONF: - case SCTP_CID_ASCONF_ACK: - have_asconf = 1; - break; + case SCTP_CID_AUTH: + have_auth = 1; + break; + case SCTP_CID_ASCONF: + case SCTP_CID_ASCONF_ACK: + have_asconf = 1; + break; } } @@ -2001,25 +2002,24 @@ static void sctp_process_ext_param(struct sctp_association *asoc, for (i = 0; i < num_ext; i++) { switch (param.ext->chunks[i]) { - case SCTP_CID_FWD_TSN: - if (net->sctp.prsctp_enable && - !asoc->peer.prsctp_capable) + case SCTP_CID_FWD_TSN: + if (net->sctp.prsctp_enable && !asoc->peer.prsctp_capable) asoc->peer.prsctp_capable = 1; - break; - case SCTP_CID_AUTH: - /* if the peer reports AUTH, assume that he - * supports AUTH. - */ - if (net->sctp.auth_enable) - asoc->peer.auth_capable = 1; - break; - case SCTP_CID_ASCONF: - case SCTP_CID_ASCONF_ACK: - if (net->sctp.addip_enable) - asoc->peer.asconf_capable = 1; - break; - default: - break; + break; + case SCTP_CID_AUTH: + /* if the peer reports AUTH, assume that he + * supports AUTH. + */ + if (net->sctp.auth_enable) + asoc->peer.auth_capable = 1; + break; + case SCTP_CID_ASCONF: + case SCTP_CID_ASCONF_ACK: + if (net->sctp.addip_enable) + asoc->peer.asconf_capable = 1; + break; + default: + break; } } } @@ -2252,7 +2252,7 @@ int sctp_verify_init(struct net *net, const struct sctp_association *asoc, * VIOLATION error. We build the ERROR chunk here and let the normal * error handling code build and send the packet. */ - if (param.v != (void*)chunk->chunk_end) + if (param.v != (void *)chunk->chunk_end) return sctp_process_inv_paramlength(asoc, param.p, chunk, errp); /* The only missing mandatory param possible today is @@ -2267,14 +2267,14 @@ int sctp_verify_init(struct net *net, const struct sctp_association *asoc, result = sctp_verify_param(net, asoc, param, cid, chunk, errp); switch (result) { - case SCTP_IERROR_ABORT: - case SCTP_IERROR_NOMEM: - return 0; - case SCTP_IERROR_ERROR: - return 1; - case SCTP_IERROR_NO_ERROR: - default: - break; + case SCTP_IERROR_ABORT: + case SCTP_IERROR_NOMEM: + return 0; + case SCTP_IERROR_ERROR: + return 1; + case SCTP_IERROR_NO_ERROR: + default: + break; } } /* for (loop through all parameters) */ @@ -2309,7 +2309,7 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, * added as the primary transport. The source address seems to * be a a better choice than any of the embedded addresses. */ - if(!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE)) + if (!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE)) goto nomem; if (sctp_cmp_addr_exact(sctp_source(chunk), peer_addr)) @@ -3335,7 +3335,7 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, while (asconf_ack_len > 0) { if (asconf_ack_param->crr_id == asconf_param->crr_id) { - switch(asconf_ack_param->param_hdr.type) { + switch (asconf_ack_param->param_hdr.type) { case SCTP_PARAM_SUCCESS_REPORT: return SCTP_ERROR_NO_ERROR; case SCTP_PARAM_ERR_CAUSE: diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 1a6eef39ab2f..bd859154000e 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -249,7 +248,7 @@ void sctp_generate_t3_rtx_event(unsigned long peer) /* Check whether a task is in the sock. */ - sctp_bh_lock_sock(asoc->base.sk); + bh_lock_sock(asoc->base.sk); if (sock_owned_by_user(asoc->base.sk)) { pr_debug("%s: sock is busy\n", __func__); @@ -276,7 +275,7 @@ void sctp_generate_t3_rtx_event(unsigned long peer) asoc->base.sk->sk_err = -error; out_unlock: - sctp_bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(asoc->base.sk); sctp_transport_put(transport); } @@ -289,7 +288,7 @@ static void sctp_generate_timeout_event(struct sctp_association *asoc, struct net *net = sock_net(asoc->base.sk); int error = 0; - sctp_bh_lock_sock(asoc->base.sk); + bh_lock_sock(asoc->base.sk); if (sock_owned_by_user(asoc->base.sk)) { pr_debug("%s: sock is busy: timer %d\n", __func__, timeout_type); @@ -316,7 +315,7 @@ static void sctp_generate_timeout_event(struct sctp_association *asoc, asoc->base.sk->sk_err = -error; out_unlock: - sctp_bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(asoc->base.sk); sctp_association_put(asoc); } @@ -368,7 +367,7 @@ void sctp_generate_heartbeat_event(unsigned long data) struct sctp_association *asoc = transport->asoc; struct net *net = sock_net(asoc->base.sk); - sctp_bh_lock_sock(asoc->base.sk); + bh_lock_sock(asoc->base.sk); if (sock_owned_by_user(asoc->base.sk)) { pr_debug("%s: sock is busy\n", __func__); @@ -393,7 +392,7 @@ void sctp_generate_heartbeat_event(unsigned long data) asoc->base.sk->sk_err = -error; out_unlock: - sctp_bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(asoc->base.sk); sctp_transport_put(transport); } @@ -405,8 +404,8 @@ void sctp_generate_proto_unreach_event(unsigned long data) struct sctp_transport *transport = (struct sctp_transport *) data; struct sctp_association *asoc = transport->asoc; struct net *net = sock_net(asoc->base.sk); - - sctp_bh_lock_sock(asoc->base.sk); + + bh_lock_sock(asoc->base.sk); if (sock_owned_by_user(asoc->base.sk)) { pr_debug("%s: sock is busy\n", __func__); @@ -428,7 +427,7 @@ void sctp_generate_proto_unreach_event(unsigned long data) asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC); out_unlock: - sctp_bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(asoc->base.sk); sctp_association_put(asoc); } @@ -544,7 +543,7 @@ static void sctp_cmd_init_failed(sctp_cmd_seq_t *commands, { struct sctp_ulpevent *event; - event = sctp_ulpevent_make_assoc_change(asoc,0, SCTP_CANT_STR_ASSOC, + event = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_CANT_STR_ASSOC, (__u16)error, 0, 0, NULL, GFP_ATOMIC); @@ -1116,7 +1115,7 @@ int sctp_do_sm(struct net *net, sctp_event_t event_type, sctp_subtype_t subtype, sctp_init_cmd_seq(&commands); debug_pre_sfn(); - status = (*state_fn->fn)(net, ep, asoc, subtype, event_arg, &commands); + status = state_fn->fn(net, ep, asoc, subtype, event_arg, &commands); debug_post_sfn(); error = sctp_side_effects(event_type, subtype, state, diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index a26065be7289..591b44d3b7de 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -2946,7 +2945,7 @@ sctp_disposition_t sctp_sf_eat_data_6_2(struct net *net, return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); - error = sctp_eat_data(asoc, chunk, commands ); + error = sctp_eat_data(asoc, chunk, commands); switch (error) { case SCTP_IERROR_NO_ERROR: break; @@ -3067,7 +3066,7 @@ sctp_disposition_t sctp_sf_eat_data_fast_4_4(struct net *net, return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); - error = sctp_eat_data(asoc, chunk, commands ); + error = sctp_eat_data(asoc, chunk, commands); switch (error) { case SCTP_IERROR_NO_ERROR: case SCTP_IERROR_HIGH_TSN: @@ -3682,8 +3681,7 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net, asconf_ack->dest = chunk->source; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(asconf_ack)); if (asoc->new_transport) { - sctp_sf_heartbeat(ep, asoc, type, asoc->new_transport, - commands); + sctp_sf_heartbeat(ep, asoc, type, asoc->new_transport, commands); ((struct sctp_association *)asoc)->new_transport = NULL; } @@ -3766,7 +3764,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); - sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET,SCTP_NULL()); + sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, @@ -3800,7 +3798,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, /* We are going to ABORT, so we might as well stop * processing the rest of the chunks in the packet. */ - sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET,SCTP_NULL()); + sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, @@ -4452,7 +4450,7 @@ static sctp_disposition_t sctp_sf_violation_chunklen( void *arg, sctp_cmd_seq_t *commands) { - static const char err_str[]="The following chunk had invalid length:"; + static const char err_str[] = "The following chunk had invalid length:"; return sctp_sf_abort_violation(net, ep, asoc, arg, commands, err_str, sizeof(err_str)); @@ -4515,7 +4513,7 @@ static sctp_disposition_t sctp_sf_violation_ctsn( void *arg, sctp_cmd_seq_t *commands) { - static const char err_str[]="The cumulative tsn ack beyond the max tsn currently sent:"; + static const char err_str[] = "The cumulative tsn ack beyond the max tsn currently sent:"; return sctp_sf_abort_violation(net, ep, asoc, arg, commands, err_str, sizeof(err_str)); @@ -4535,7 +4533,7 @@ static sctp_disposition_t sctp_sf_violation_chunk( void *arg, sctp_cmd_seq_t *commands) { - static const char err_str[]="The following chunk violates protocol:"; + static const char err_str[] = "The following chunk violates protocol:"; if (!asoc) return sctp_sf_violation(net, ep, asoc, type, arg, commands); @@ -4611,7 +4609,7 @@ sctp_disposition_t sctp_sf_do_prm_asoc(struct net *net, sctp_cmd_seq_t *commands) { struct sctp_chunk *repl; - struct sctp_association* my_asoc; + struct sctp_association *my_asoc; /* The comment below says that we enter COOKIE-WAIT AFTER * sending the INIT, but that doesn't actually work in our @@ -6001,7 +5999,7 @@ static struct sctp_packet *sctp_ootb_pkt_new(struct net *net, /* Special case the INIT-ACK as there is no peer's vtag * yet. */ - switch(chunk->chunk_hdr->type) { + switch (chunk->chunk_hdr->type) { case SCTP_CID_INIT_ACK: { sctp_initack_chunk_t *initack; @@ -6018,7 +6016,7 @@ static struct sctp_packet *sctp_ootb_pkt_new(struct net *net, /* Special case the INIT and stale COOKIE_ECHO as there is no * vtag yet. */ - switch(chunk->chunk_hdr->type) { + switch (chunk->chunk_hdr->type) { case SCTP_CID_INIT: { sctp_init_chunk_t *init; @@ -6178,7 +6176,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * PMTU. In cases, such as loopback, this might be a rather * large spill over. */ - if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over || + if ((!chunk->data_accepted) && (!asoc->rwnd || (datalen > asoc->rwnd + asoc->frag_point))) { /* If this is the next TSN, consider reneging to make @@ -6208,7 +6206,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, */ if (*sk->sk_prot_creator->memory_pressure) { if (sctp_tsnmap_has_gap(map) && - (sctp_tsnmap_get_ctsn(map) + 1) == tsn) { + (sctp_tsnmap_get_ctsn(map) + 1) == tsn) { pr_debug("%s: under pressure, reneging for tsn:%u\n", __func__, tsn); deliver = SCTP_CMD_RENEGE; @@ -6232,7 +6230,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, /* We are going to ABORT, so we might as well stop * processing the rest of the chunks in the packet. */ - sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET,SCTP_NULL()); + sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL()); sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index c5999b2dde7d..a987d54b379c 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -70,7 +69,7 @@ static const sctp_sm_table_entry_t bug = { if ((event_subtype._type > (_max))) { \ pr_warn("table %p possible attack: event %d exceeds max %d\n", \ _table, event_subtype._type, _max); \ - rtn = &bug; \ + rtn = &bug; \ } else \ rtn = &_table[event_subtype._type][(int)state]; \ \ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 42b709c95cf3..981aaf8b6ace 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -28,9 +28,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -65,6 +64,7 @@ #include <linux/crypto.h> #include <linux/slab.h> #include <linux/file.h> +#include <linux/compat.h> #include <net/ip.h> #include <net/icmp.h> @@ -83,7 +83,7 @@ static int sctp_writeable(struct sock *sk); static void sctp_wfree(struct sk_buff *skb); static int sctp_wait_for_sndbuf(struct sctp_association *, long *timeo_p, size_t msg_len); -static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p); +static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p); static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p); static int sctp_wait_for_accept(struct sock *sk, long timeo); static void sctp_wait_for_close(struct sock *sk, long timeo); @@ -273,7 +273,7 @@ static int sctp_bind(struct sock *sk, struct sockaddr *addr, int addr_len) { int retval = 0; - sctp_lock_sock(sk); + lock_sock(sk); pr_debug("%s: sk:%p, addr:%p, addr_len:%d\n", __func__, sk, addr, addr_len); @@ -285,7 +285,7 @@ static int sctp_bind(struct sock *sk, struct sockaddr *addr, int addr_len) else retval = -EINVAL; - sctp_release_sock(sk); + release_sock(sk); return retval; } @@ -953,7 +953,7 @@ int sctp_asconf_mgmt(struct sctp_sock *sp, struct sctp_sockaddr_entry *addrw) * * Returns 0 if ok, <0 errno code on error. */ -static int sctp_setsockopt_bindx(struct sock* sk, +static int sctp_setsockopt_bindx(struct sock *sk, struct sockaddr __user *addrs, int addrs_size, int op) { @@ -1040,7 +1040,7 @@ out: * Common routine for handling connect() and sctp_connectx(). * Connect will come in with just a single address. */ -static int __sctp_connect(struct sock* sk, +static int __sctp_connect(struct sock *sk, struct sockaddr *kaddrs, int addrs_size, sctp_assoc_t *assoc_id) @@ -1300,7 +1300,7 @@ out_free: * * Returns >=0 if ok, <0 errno code on error. */ -static int __sctp_setsockopt_connectx(struct sock* sk, +static int __sctp_setsockopt_connectx(struct sock *sk, struct sockaddr __user *addrs, int addrs_size, sctp_assoc_t *assoc_id) @@ -1338,7 +1338,7 @@ static int __sctp_setsockopt_connectx(struct sock* sk, * This is an older interface. It's kept for backward compatibility * to the option that doesn't provide association id. */ -static int sctp_setsockopt_connectx_old(struct sock* sk, +static int sctp_setsockopt_connectx_old(struct sock *sk, struct sockaddr __user *addrs, int addrs_size) { @@ -1351,7 +1351,7 @@ static int sctp_setsockopt_connectx_old(struct sock* sk, * indication to the call. Error is always negative and association id is * always positive. */ -static int sctp_setsockopt_connectx(struct sock* sk, +static int sctp_setsockopt_connectx(struct sock *sk, struct sockaddr __user *addrs, int addrs_size) { @@ -1369,12 +1369,20 @@ 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. */ -static int sctp_getsockopt_connectx3(struct sock* sk, int len, +#ifdef CONFIG_COMPAT +struct compat_sctp_getaddrs_old { + sctp_assoc_t assoc_id; + s32 addr_num; + compat_uptr_t addrs; /* struct sockaddr * */ +}; +#endif + +static int sctp_getsockopt_connectx3(struct sock *sk, int len, char __user *optval, int __user *optlen) { @@ -1382,16 +1390,30 @@ 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; @@ -1462,7 +1484,7 @@ static void sctp_close(struct sock *sk, long timeout) pr_debug("%s: sk:%p, timeout:%ld\n", __func__, sk, timeout); - sctp_lock_sock(sk); + lock_sock(sk); sk->sk_shutdown = SHUTDOWN_MASK; sk->sk_state = SCTP_SS_CLOSING; @@ -1506,13 +1528,13 @@ static void sctp_close(struct sock *sk, long timeout) sctp_wait_for_close(sk, timeout); /* This will run the backlog queue. */ - sctp_release_sock(sk); + release_sock(sk); /* Supposedly, no process has access to the socket, but * the net layers still may. */ - sctp_local_bh_disable(); - sctp_bh_lock_sock(sk); + local_bh_disable(); + bh_lock_sock(sk); /* Hold the sock, since sk_common_release() will put sock_put() * and we have just a little more cleanup. @@ -1520,8 +1542,8 @@ static void sctp_close(struct sock *sk, long timeout) sock_hold(sk); sk_common_release(sk); - sctp_bh_unlock_sock(sk); - sctp_local_bh_enable(); + bh_unlock_sock(sk); + local_bh_enable(); sock_put(sk); @@ -1569,7 +1591,7 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, struct net *net = sock_net(sk); struct sctp_sock *sp; struct sctp_endpoint *ep; - struct sctp_association *new_asoc=NULL, *asoc=NULL; + struct sctp_association *new_asoc = NULL, *asoc = NULL; struct sctp_transport *transport, *chunk_tp; struct sctp_chunk *chunk; union sctp_addr to; @@ -1666,7 +1688,7 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, pr_debug("%s: about to look up association\n", __func__); - sctp_lock_sock(sk); + lock_sock(sk); /* If a msg_name has been specified, assume this is to be used. */ if (msg_name) { @@ -1744,7 +1766,7 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, * either the default or the user specified stream counts. */ if (sinfo) { - if (!sinit || (sinit && !sinit->sinit_num_ostreams)) { + if (!sinit || !sinit->sinit_num_ostreams) { /* Check against the defaults. */ if (sinfo->sinfo_stream >= sp->initmsg.sinit_num_ostreams) { @@ -1950,7 +1972,7 @@ out_free: sctp_association_free(asoc); } out_unlock: - sctp_release_sock(sk); + release_sock(sk); out_nounlock: return sctp_error(sk, msg_flags, err); @@ -2036,7 +2058,7 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, "addr_len:%p)\n", __func__, sk, msg, len, noblock, flags, addr_len); - sctp_lock_sock(sk); + lock_sock(sk); if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED)) { err = -ENOTCONN; @@ -2093,12 +2115,6 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, sctp_skb_pull(skb, copied); skb_queue_head(&sk->sk_receive_queue, skb); - /* When only partial message is copied to the user, increase - * rwnd by that amount. If all the data in the skb is read, - * rwnd is updated when the event is freed. - */ - if (!sctp_ulpevent_is_notification(event)) - sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) @@ -2120,7 +2136,7 @@ out_free: sctp_ulpevent_free(event); } out: - sctp_release_sock(sk); + release_sock(sk); return err; } @@ -2463,7 +2479,7 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, int hb_change, pmtud_change, sackdelay_change; if (optlen != sizeof(struct sctp_paddrparams)) - return - EINVAL; + return -EINVAL; if (copy_from_user(¶ms, optval, optlen)) return -EFAULT; @@ -2484,7 +2500,7 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ - if (!sctp_is_any(sk, ( union sctp_addr *)¶ms.spp_address)) { + if (!sctp_is_any(sk, (union sctp_addr *)¶ms.spp_address)) { trans = sctp_addr_id2transport(sk, ¶ms.spp_address, params.spp_assoc_id); if (!trans) @@ -2528,6 +2544,16 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, return 0; } +static inline __u32 sctp_spp_sackdelay_enable(__u32 param_flags) +{ + return (param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_ENABLE; +} + +static inline __u32 sctp_spp_sackdelay_disable(__u32 param_flags) +{ + return (param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_DISABLE; +} + /* * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK) * @@ -2579,8 +2605,11 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk, if (params.sack_delay == 0 && params.sack_freq == 0) return 0; } else if (optlen == sizeof(struct sctp_assoc_value)) { - pr_warn("Use of struct sctp_assoc_value in delayed_ack socket option deprecated\n"); - pr_warn("Use struct sctp_sack_info instead\n"); + pr_warn_ratelimited(DEPRECATED + "%s (pid %d) " + "Use of struct sctp_assoc_value in delayed_ack socket option.\n" + "Use struct sctp_sack_info instead\n", + current->comm, task_pid_nr(current)); if (copy_from_user(¶ms, optval, optlen)) return -EFAULT; @@ -2589,7 +2618,7 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk, else params.sack_freq = 0; } else - return - EINVAL; + return -EINVAL; /* Validate value parameter. */ if (params.sack_delay > 500) @@ -2608,37 +2637,31 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk, asoc->sackdelay = msecs_to_jiffies(params.sack_delay); asoc->param_flags = - (asoc->param_flags & ~SPP_SACKDELAY) | - SPP_SACKDELAY_ENABLE; + sctp_spp_sackdelay_enable(asoc->param_flags); } else { sp->sackdelay = params.sack_delay; sp->param_flags = - (sp->param_flags & ~SPP_SACKDELAY) | - SPP_SACKDELAY_ENABLE; + sctp_spp_sackdelay_enable(sp->param_flags); } } if (params.sack_freq == 1) { if (asoc) { asoc->param_flags = - (asoc->param_flags & ~SPP_SACKDELAY) | - SPP_SACKDELAY_DISABLE; + sctp_spp_sackdelay_disable(asoc->param_flags); } else { sp->param_flags = - (sp->param_flags & ~SPP_SACKDELAY) | - SPP_SACKDELAY_DISABLE; + sctp_spp_sackdelay_disable(sp->param_flags); } } else if (params.sack_freq > 1) { if (asoc) { asoc->sackfreq = params.sack_freq; asoc->param_flags = - (asoc->param_flags & ~SPP_SACKDELAY) | - SPP_SACKDELAY_ENABLE; + sctp_spp_sackdelay_enable(asoc->param_flags); } else { sp->sackfreq = params.sack_freq; sp->param_flags = - (sp->param_flags & ~SPP_SACKDELAY) | - SPP_SACKDELAY_ENABLE; + sctp_spp_sackdelay_enable(sp->param_flags); } } @@ -2650,18 +2673,15 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk, trans->sackdelay = msecs_to_jiffies(params.sack_delay); trans->param_flags = - (trans->param_flags & ~SPP_SACKDELAY) | - SPP_SACKDELAY_ENABLE; + sctp_spp_sackdelay_enable(trans->param_flags); } if (params.sack_freq == 1) { trans->param_flags = - (trans->param_flags & ~SPP_SACKDELAY) | - SPP_SACKDELAY_DISABLE; + sctp_spp_sackdelay_disable(trans->param_flags); } else if (params.sack_freq > 1) { trans->sackfreq = params.sack_freq; trans->param_flags = - (trans->param_flags & ~SPP_SACKDELAY) | - SPP_SACKDELAY_ENABLE; + sctp_spp_sackdelay_enable(trans->param_flags); } } } @@ -2995,8 +3015,11 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned int val; if (optlen == sizeof(int)) { - pr_warn("Use of int in maxseg socket option deprecated\n"); - pr_warn("Use struct sctp_assoc_value instead\n"); + pr_warn_ratelimited(DEPRECATED + "%s (pid %d) " + "Use of int in maxseg socket option.\n" + "Use struct sctp_assoc_value instead\n", + current->comm, task_pid_nr(current)); if (copy_from_user(&val, optval, optlen)) return -EFAULT; params.assoc_id = 0; @@ -3253,8 +3276,11 @@ static int sctp_setsockopt_maxburst(struct sock *sk, int assoc_id = 0; if (optlen == sizeof(int)) { - pr_warn("Use of int in max_burst socket option deprecated\n"); - pr_warn("Use struct sctp_assoc_value instead\n"); + pr_warn_ratelimited(DEPRECATED + "%s (pid %d) " + "Use of int in max_burst socket option deprecated.\n" + "Use struct sctp_assoc_value instead\n", + current->comm, task_pid_nr(current)); if (copy_from_user(&val, optval, optlen)) return -EFAULT; } else if (optlen == sizeof(struct sctp_assoc_value)) { @@ -3333,7 +3359,7 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk, if (optlen < sizeof(struct sctp_hmacalgo)) return -EINVAL; - hmacs= memdup_user(optval, optlen); + hmacs = memdup_user(optval, optlen); if (IS_ERR(hmacs)) return PTR_ERR(hmacs); @@ -3371,7 +3397,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk, if (optlen <= sizeof(struct sctp_authkey)) return -EINVAL; - authkey= memdup_user(optval, optlen); + authkey = memdup_user(optval, optlen); if (IS_ERR(authkey)) return PTR_ERR(authkey); @@ -3581,7 +3607,7 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, goto out_nounlock; } - sctp_lock_sock(sk); + lock_sock(sk); switch (optname) { case SCTP_SOCKOPT_BINDX_ADD: @@ -3699,7 +3725,7 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, break; } - sctp_release_sock(sk); + release_sock(sk); out_nounlock: return retval; @@ -3727,7 +3753,7 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr, int err = 0; struct sctp_af *af; - sctp_lock_sock(sk); + lock_sock(sk); pr_debug("%s: sk:%p, sockaddr:%p, addr_len:%d\n", __func__, sk, addr, addr_len); @@ -3743,7 +3769,7 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr, err = __sctp_connect(sk, addr, af->sockaddr_len, NULL); } - sctp_release_sock(sk); + release_sock(sk); return err; } @@ -3769,7 +3795,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err) long timeo; int error = 0; - sctp_lock_sock(sk); + lock_sock(sk); sp = sctp_sk(sk); ep = sp->ep; @@ -3807,7 +3833,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err) sctp_sock_migrate(sk, newsk, asoc, SCTP_SOCKET_TCP); out: - sctp_release_sock(sk); + release_sock(sk); *err = error; return newsk; } @@ -3817,7 +3843,7 @@ static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg) { int rc = -ENOTCONN; - sctp_lock_sock(sk); + lock_sock(sk); /* * SEQPACKET-style sockets in LISTENING state are valid, for @@ -3847,7 +3873,7 @@ static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg) break; } out: - sctp_release_sock(sk); + release_sock(sk); return rc; } @@ -3925,7 +3951,7 @@ static int sctp_init_sock(struct sock *sk) */ sp->hbinterval = net->sctp.hb_interval; sp->pathmaxrxt = net->sctp.max_retrans_path; - sp->pathmtu = 0; // allow default discovery + sp->pathmtu = 0; /* allow default discovery */ sp->sackdelay = net->sctp.sack_timeout; sp->sackfreq = 2; sp->param_flags = SPP_HB_ENABLE | @@ -4468,7 +4494,7 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ - if (!sctp_is_any(sk, ( union sctp_addr *)¶ms.spp_address)) { + if (!sctp_is_any(sk, (union sctp_addr *)¶ms.spp_address)) { trans = sctp_addr_id2transport(sk, ¶ms.spp_address, params.spp_assoc_id); if (!trans) { @@ -4574,12 +4600,15 @@ static int sctp_getsockopt_delayed_ack(struct sock *sk, int len, if (copy_from_user(¶ms, optval, len)) return -EFAULT; } else if (len == sizeof(struct sctp_assoc_value)) { - pr_warn("Use of struct sctp_assoc_value in delayed_ack socket option deprecated\n"); - pr_warn("Use struct sctp_sack_info instead\n"); + pr_warn_ratelimited(DEPRECATED + "%s (pid %d) " + "Use of struct sctp_assoc_value in delayed_ack socket option.\n" + "Use struct sctp_sack_info instead\n", + current->comm, task_pid_nr(current)); if (copy_from_user(¶ms, optval, len)) return -EFAULT; } else - return - EINVAL; + return -EINVAL; /* Get association, if sack_assoc_id != 0 and the socket is a one * to many style socket, and an association was not found, then @@ -4669,8 +4698,8 @@ static int sctp_getsockopt_peer_addrs(struct sock *sk, int len, if (!asoc) return -EINVAL; - to = optval + offsetof(struct sctp_getaddrs,addrs); - space_left = len - offsetof(struct sctp_getaddrs,addrs); + to = optval + offsetof(struct sctp_getaddrs, addrs); + space_left = len - offsetof(struct sctp_getaddrs, addrs); list_for_each_entry(from, &asoc->peer.transport_addr_list, transports) { @@ -4730,7 +4759,7 @@ static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, memcpy(to, &temp, addrlen); to += addrlen; - cnt ++; + cnt++; space_left -= addrlen; *bytes_copied += addrlen; } @@ -4779,8 +4808,8 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len, bp = &asoc->base.bind_addr; } - to = optval + offsetof(struct sctp_getaddrs,addrs); - space_left = len - offsetof(struct sctp_getaddrs,addrs); + to = optval + offsetof(struct sctp_getaddrs, addrs); + space_left = len - offsetof(struct sctp_getaddrs, addrs); addrs = kmalloc(space_left, GFP_KERNEL); if (!addrs) @@ -4819,7 +4848,7 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len, memcpy(buf, &temp, addrlen); buf += addrlen; bytes_copied += addrlen; - cnt ++; + cnt++; space_left -= addrlen; } @@ -5091,7 +5120,7 @@ static int sctp_getsockopt_associnfo(struct sock *sk, int len, assocparams.sasoc_cookie_life = ktime_to_ms(asoc->cookie_life); list_for_each(pos, &asoc->peer.transport_addr_list) { - cnt ++; + cnt++; } assocparams.sasoc_number_peer_destinations = cnt; @@ -5219,8 +5248,11 @@ static int sctp_getsockopt_maxseg(struct sock *sk, int len, struct sctp_association *asoc; if (len == sizeof(int)) { - pr_warn("Use of int in maxseg socket option deprecated\n"); - pr_warn("Use struct sctp_assoc_value instead\n"); + pr_warn_ratelimited(DEPRECATED + "%s (pid %d) " + "Use of int in maxseg socket option.\n" + "Use struct sctp_assoc_value instead\n", + current->comm, task_pid_nr(current)); params.assoc_id = 0; } else if (len >= sizeof(struct sctp_assoc_value)) { len = sizeof(struct sctp_assoc_value); @@ -5311,8 +5343,11 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, struct sctp_association *asoc; if (len == sizeof(int)) { - pr_warn("Use of int in max_burst socket option deprecated\n"); - pr_warn("Use struct sctp_assoc_value instead\n"); + pr_warn_ratelimited(DEPRECATED + "%s (pid %d) " + "Use of int in max_burst socket option.\n" + "Use struct sctp_assoc_value instead\n", + current->comm, task_pid_nr(current)); params.assoc_id = 0; } else if (len >= sizeof(struct sctp_assoc_value)) { len = sizeof(struct sctp_assoc_value); @@ -5444,7 +5479,8 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, return -EFAULT; num: len = sizeof(struct sctp_authchunks) + num_chunks; - if (put_user(len, optlen)) return -EFAULT; + if (put_user(len, optlen)) + return -EFAULT; if (put_user(num_chunks, &p->gauth_number_of_chunks)) return -EFAULT; return 0; @@ -5476,7 +5512,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, return -EINVAL; if (asoc) - ch = (struct sctp_chunks_param*)asoc->c.auth_chunks; + ch = (struct sctp_chunks_param *)asoc->c.auth_chunks; else ch = sctp_sk(sk)->ep->auth_chunk_list; @@ -5735,7 +5771,7 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - sctp_lock_sock(sk); + lock_sock(sk); switch (optname) { case SCTP_STATUS: @@ -5859,7 +5895,7 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, break; } - sctp_release_sock(sk); + release_sock(sk); return retval; } @@ -5899,7 +5935,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) pr_debug("%s: begins, snum:%d\n", __func__, snum); - sctp_local_bh_disable(); + local_bh_disable(); if (snum == 0) { /* Search for an available port. */ @@ -5908,7 +5944,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) inet_get_local_port_range(sock_net(sk), &low, &high); remaining = (high - low) + 1; - rover = net_random() % remaining + low; + rover = prandom_u32() % remaining + low; do { rover++; @@ -5918,14 +5954,14 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) continue; index = sctp_phashfn(sock_net(sk), rover); head = &sctp_port_hashtable[index]; - sctp_spin_lock(&head->lock); + spin_lock(&head->lock); sctp_for_each_hentry(pp, &head->chain) if ((pp->port == rover) && net_eq(sock_net(sk), pp->net)) goto next; break; next: - sctp_spin_unlock(&head->lock); + spin_unlock(&head->lock); } while (--remaining > 0); /* Exhausted local port range during search? */ @@ -5946,7 +5982,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) * port iterator, pp being NULL. */ head = &sctp_port_hashtable[sctp_phashfn(sock_net(sk), snum)]; - sctp_spin_lock(&head->lock); + spin_lock(&head->lock); sctp_for_each_hentry(pp, &head->chain) { if ((pp->port == snum) && net_eq(pp->net, sock_net(sk))) goto pp_found; @@ -6030,10 +6066,10 @@ success: ret = 0; fail_unlock: - sctp_spin_unlock(&head->lock); + spin_unlock(&head->lock); fail: - sctp_local_bh_enable(); + local_bh_enable(); return ret; } @@ -6125,7 +6161,7 @@ int sctp_inet_listen(struct socket *sock, int backlog) if (unlikely(backlog < 0)) return err; - sctp_lock_sock(sk); + lock_sock(sk); /* Peeled-off sockets are not allowed to listen(). */ if (sctp_style(sk, UDP_HIGH_BANDWIDTH)) @@ -6158,7 +6194,7 @@ int sctp_inet_listen(struct socket *sock, int backlog) err = 0; out: - sctp_release_sock(sk); + release_sock(sk); return err; } @@ -6267,20 +6303,20 @@ static inline void __sctp_put_port(struct sock *sk) inet_sk(sk)->inet_num)]; struct sctp_bind_bucket *pp; - sctp_spin_lock(&head->lock); + spin_lock(&head->lock); pp = sctp_sk(sk)->bind_hash; __sk_del_bind_node(sk); sctp_sk(sk)->bind_hash = NULL; inet_sk(sk)->inet_num = 0; sctp_bucket_destroy(pp); - sctp_spin_unlock(&head->lock); + spin_unlock(&head->lock); } void sctp_put_port(struct sock *sk) { - sctp_local_bh_disable(); + local_bh_disable(); __sctp_put_port(sk); - sctp_local_bh_enable(); + local_bh_enable(); } /* @@ -6418,7 +6454,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) * Note: This function is the same function as in core/datagram.c * with a few modifications to make lksctp work. */ -static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p) +static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p) { int error; DEFINE_WAIT(wait); @@ -6455,9 +6491,9 @@ static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p) * does not fit in the user's buffer, but this seems to be the * only way to honor MSG_DONTWAIT realistically. */ - sctp_release_sock(sk); + release_sock(sk); *timeo_p = schedule_timeout(*timeo_p); - sctp_lock_sock(sk); + lock_sock(sk); ready: finish_wait(sk_sleep(sk), &wait); @@ -6640,10 +6676,10 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, /* Let another process have a go. Since we are going * to sleep anyway. */ - sctp_release_sock(sk); + release_sock(sk); current_timeo = schedule_timeout(current_timeo); BUG_ON(sk != asoc->base.sk); - sctp_lock_sock(sk); + lock_sock(sk); *timeo_p = current_timeo; } @@ -6748,9 +6784,9 @@ static int sctp_wait_for_connect(struct sctp_association *asoc, long *timeo_p) /* Let another process have a go. Since we are going * to sleep anyway. */ - sctp_release_sock(sk); + release_sock(sk); current_timeo = schedule_timeout(current_timeo); - sctp_lock_sock(sk); + lock_sock(sk); *timeo_p = current_timeo; } @@ -6793,9 +6829,9 @@ static int sctp_wait_for_accept(struct sock *sk, long timeo) TASK_INTERRUPTIBLE); if (list_empty(&ep->asocs)) { - sctp_release_sock(sk); + release_sock(sk); timeo = schedule_timeout(timeo); - sctp_lock_sock(sk); + lock_sock(sk); } err = -EINVAL; @@ -6828,9 +6864,9 @@ static void sctp_wait_for_close(struct sock *sk, long timeout) prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (list_empty(&sctp_sk(sk)->ep->asocs)) break; - sctp_release_sock(sk); + release_sock(sk); timeout = schedule_timeout(timeout); - sctp_lock_sock(sk); + lock_sock(sk); } while (!signal_pending(current) && timeout); finish_wait(sk_sleep(sk), &wait); @@ -6931,14 +6967,14 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, /* Hook this new socket in to the bind_hash list. */ head = &sctp_port_hashtable[sctp_phashfn(sock_net(oldsk), inet_sk(oldsk)->inet_num)]; - sctp_local_bh_disable(); - sctp_spin_lock(&head->lock); + local_bh_disable(); + spin_lock(&head->lock); pp = sctp_sk(oldsk)->bind_hash; sk_add_bind_node(newsk, &pp->owner); sctp_sk(newsk)->bind_hash = pp; inet_sk(newsk)->inet_num = inet_sk(oldsk)->inet_num; - sctp_spin_unlock(&head->lock); - sctp_local_bh_enable(); + spin_unlock(&head->lock); + local_bh_enable(); /* Copy the bind_addr list from the original endpoint to the new * endpoint so that we can handle restarts properly @@ -7027,7 +7063,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, newsk->sk_shutdown |= RCV_SHUTDOWN; newsk->sk_state = SCTP_SS_ESTABLISHED; - sctp_release_sock(newsk); + release_sock(newsk); } diff --git a/net/sctp/ssnmap.c b/net/sctp/ssnmap.c index 6007124aefa0..b9c8521c1a98 100644 --- a/net/sctp/ssnmap.c +++ b/net/sctp/ssnmap.c @@ -18,9 +18,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index b0565afb61c7..35c8923b5554 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -19,9 +19,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -152,6 +151,7 @@ static struct ctl_table sctp_net_table[] = { }, { .procname = "cookie_hmac_alg", + .data = &init_net.sctp.sctp_hmac_alg, .maxlen = 8, .mode = 0644, .proc_handler = proc_sctp_do_hmac_alg, @@ -402,15 +402,18 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, int sctp_sysctl_net_register(struct net *net) { - struct ctl_table *table; - int i; + struct ctl_table *table = sctp_net_table; + + if (!net_eq(net, &init_net)) { + int i; - table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL); - if (!table) - return -ENOMEM; + table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL); + if (!table) + return -ENOMEM; - for (i = 0; table[i].data; i++) - table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; + for (i = 0; table[i].data; i++) + table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; + } net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table); return 0; @@ -425,7 +428,7 @@ void sctp_sysctl_net_unregister(struct net *net) kfree(table); } -static struct ctl_table_header * sctp_sysctl_header; +static struct ctl_table_header *sctp_sysctl_header; /* Sysctl registration. */ void sctp_sysctl_register(void) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index efc46ffed1fd..d0810dc5f079 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -24,9 +24,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c index fbda20028285..7635f9f2311d 100644 --- a/net/sctp/tsnmap.c +++ b/net/sctp/tsnmap.c @@ -21,9 +21,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 81089ed65456..8d198ae03606 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -22,9 +22,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -990,7 +989,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event, skb = sctp_event2skb(event); /* Set the owner and charge rwnd for bytes received. */ sctp_ulpevent_set_owner(event, asoc); - sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb)); + sctp_assoc_rwnd_update(asoc, false); if (!skb->data_len) return; @@ -1012,6 +1011,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) { struct sk_buff *skb, *frag; unsigned int len; + struct sctp_association *asoc; /* Current stack structures assume that the rcv buffer is * per socket. For UDP style sockets this is not true as @@ -1036,8 +1036,11 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) } done: - sctp_assoc_rwnd_increase(event->asoc, len); + asoc = event->asoc; + sctp_association_hold(asoc); sctp_ulpevent_release_owner(event); + sctp_assoc_rwnd_update(asoc, true); + sctp_association_put(asoc); } static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event) diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 1c1484ed605d..5dc94117e9d4 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -21,9 +21,8 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. * * Please send any bug reports or fixes you make to the * email address(es): @@ -44,9 +43,9 @@ #include <net/sctp/sm.h> /* Forward declarations for internal helpers. */ -static struct sctp_ulpevent * sctp_ulpq_reasm(struct sctp_ulpq *ulpq, +static struct sctp_ulpevent *sctp_ulpq_reasm(struct sctp_ulpq *ulpq, struct sctp_ulpevent *); -static struct sctp_ulpevent * sctp_ulpq_order(struct sctp_ulpq *, +static struct sctp_ulpevent *sctp_ulpq_order(struct sctp_ulpq *, struct sctp_ulpevent *); static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq); @@ -108,7 +107,7 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, event = sctp_ulpq_reasm(ulpq, event); /* Do ordering if needed. */ - if ((event) && (event->msg_flags & MSG_EOR)){ + if ((event) && (event->msg_flags & MSG_EOR)) { /* Create a temporary list to collect chunks on. */ skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); @@ -337,7 +336,8 @@ static struct sctp_ulpevent *sctp_make_reassembled_event(struct net *net, pos = f_frag->next; /* Get the last skb in the f_frag's frag_list if present. */ - for (last = list; list; last = list, list = list->next); + for (last = list; list; last = list, list = list->next) + ; /* Add the list of remaining fragments to the first fragments * frag_list. @@ -727,7 +727,7 @@ static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq) while ((event = sctp_ulpq_retrieve_reassembled(ulpq)) != NULL) { /* Do ordering if needed. */ - if ((event) && (event->msg_flags & MSG_EOR)){ + if ((event) && (event->msg_flags & MSG_EOR)) { skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); diff --git a/net/socket.c b/net/socket.c index e83c416708af..879933aaed4c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1445,48 +1445,61 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, err = fd1; goto out_release_both; } + fd2 = get_unused_fd_flags(flags); if (unlikely(fd2 < 0)) { err = fd2; - put_unused_fd(fd1); - goto out_release_both; + goto out_put_unused_1; } newfile1 = sock_alloc_file(sock1, flags, NULL); if (unlikely(IS_ERR(newfile1))) { err = PTR_ERR(newfile1); - put_unused_fd(fd1); - put_unused_fd(fd2); - goto out_release_both; + goto out_put_unused_both; } newfile2 = sock_alloc_file(sock2, flags, NULL); if (IS_ERR(newfile2)) { err = PTR_ERR(newfile2); - fput(newfile1); - put_unused_fd(fd1); - put_unused_fd(fd2); - sock_release(sock2); - goto out; + goto out_fput_1; } + err = put_user(fd1, &usockvec[0]); + if (err) + goto out_fput_both; + + err = put_user(fd2, &usockvec[1]); + if (err) + goto out_fput_both; + audit_fd_pair(fd1, fd2); + fd_install(fd1, newfile1); fd_install(fd2, newfile2); /* fd1 and fd2 may be already another descriptors. * Not kernel problem. */ - err = put_user(fd1, &usockvec[0]); - if (!err) - err = put_user(fd2, &usockvec[1]); - if (!err) - return 0; + return 0; - sys_close(fd2); - sys_close(fd1); - return err; +out_fput_both: + fput(newfile2); + fput(newfile1); + put_unused_fd(fd2); + put_unused_fd(fd1); + goto out; + +out_fput_1: + fput(newfile1); + put_unused_fd(fd2); + put_unused_fd(fd1); + sock_release(sock2); + goto out; +out_put_unused_both: + put_unused_fd(fd2); +out_put_unused_1: + put_unused_fd(fd1); out_release_both: sock_release(sock2); out_release_1: @@ -2968,11 +2981,8 @@ static int bond_ioctl(struct net *net, unsigned int cmd, struct compat_ifreq __user *ifr32) { struct ifreq kifr; - struct ifreq __user *uifr; mm_segment_t old_fs; int err; - u32 data; - void __user *datap; switch (cmd) { case SIOCBONDENSLAVE: @@ -2989,26 +2999,13 @@ static int bond_ioctl(struct net *net, unsigned int cmd, set_fs(old_fs); return err; - case SIOCBONDSLAVEINFOQUERY: - case SIOCBONDINFOQUERY: - uifr = compat_alloc_user_space(sizeof(*uifr)); - if (copy_in_user(&uifr->ifr_name, &ifr32->ifr_name, IFNAMSIZ)) - return -EFAULT; - - if (get_user(data, &ifr32->ifr_ifru.ifru_data)) - return -EFAULT; - - datap = compat_ptr(data); - if (put_user(datap, &uifr->ifr_ifru.ifru_data)) - return -EFAULT; - - return dev_ioctl(net, cmd, uifr); default: return -ENOIOCTLCMD; } } -static int siocdevprivate_ioctl(struct net *net, unsigned int cmd, +/* Handle ioctls that use ifreq::ifr_data and just need struct ifreq converted */ +static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct compat_ifreq __user *u_ifreq32) { struct ifreq __user *u_ifreq64; @@ -3019,19 +3016,16 @@ static int siocdevprivate_ioctl(struct net *net, unsigned int cmd, if (copy_from_user(&tmp_buf[0], &(u_ifreq32->ifr_ifrn.ifrn_name[0]), IFNAMSIZ)) return -EFAULT; - if (__get_user(data32, &u_ifreq32->ifr_ifru.ifru_data)) + if (get_user(data32, &u_ifreq32->ifr_ifru.ifru_data)) return -EFAULT; data64 = compat_ptr(data32); u_ifreq64 = compat_alloc_user_space(sizeof(*u_ifreq64)); - /* Don't check these user accesses, just let that get trapped - * in the ioctl handler instead. - */ if (copy_to_user(&u_ifreq64->ifr_ifrn.ifrn_name[0], &tmp_buf[0], IFNAMSIZ)) return -EFAULT; - if (__put_user(data64, &u_ifreq64->ifr_ifru.ifru_data)) + if (put_user(data64, &u_ifreq64->ifr_ifru.ifru_data)) return -EFAULT; return dev_ioctl(net, cmd, u_ifreq64); @@ -3111,27 +3105,6 @@ static int compat_sioc_ifmap(struct net *net, unsigned int cmd, return err; } -static int compat_siocshwtstamp(struct net *net, struct compat_ifreq __user *uifr32) -{ - void __user *uptr; - compat_uptr_t uptr32; - struct ifreq __user *uifr; - - uifr = compat_alloc_user_space(sizeof(*uifr)); - if (copy_in_user(uifr, uifr32, sizeof(struct compat_ifreq))) - return -EFAULT; - - if (get_user(uptr32, &uifr32->ifr_data)) - return -EFAULT; - - uptr = compat_ptr(uptr32); - - if (put_user(uptr, &uifr->ifr_data)) - return -EFAULT; - - return dev_ioctl(net, SIOCSHWTSTAMP, uifr); -} - struct rtentry32 { u32 rt_pad1; struct sockaddr rt_dst; /* target address */ @@ -3243,7 +3216,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, struct net *net = sock_net(sk); if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) - return siocdevprivate_ioctl(net, cmd, argp); + return compat_ifr_data_ioctl(net, cmd, argp); switch (cmd) { case SIOCSIFBR: @@ -3263,8 +3236,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: - case SIOCBONDSLAVEINFOQUERY: - case SIOCBONDINFOQUERY: case SIOCBONDCHANGEACTIVE: return bond_ioctl(net, cmd, argp); case SIOCADDRT: @@ -3274,8 +3245,11 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, return do_siocgstamp(net, sock, cmd, argp); case SIOCGSTAMPNS: return do_siocgstampns(net, sock, cmd, argp); + case SIOCBONDSLAVEINFOQUERY: + case SIOCBONDINFOQUERY: case SIOCSHWTSTAMP: - return compat_siocshwtstamp(net, argp); + case SIOCGHWTSTAMP: + return compat_ifr_data_ioctl(net, cmd, argp); case FIOSETOWN: case SIOCSPGRP: diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 42fdfc634e56..6c0513a7f992 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -532,14 +532,7 @@ gss_setup_upcall(struct gss_auth *gss_auth, struct rpc_cred *cred) static void warn_gssd(void) { - static unsigned long ratelimit; - unsigned long now = jiffies; - - if (time_after(now, ratelimit)) { - printk(KERN_WARNING "RPC: AUTH_GSS upcall timed out.\n" - "Please check user daemon is running.\n"); - ratelimit = now + 15*HZ; - } + dprintk("AUTH_GSS upcall failed. Please check user daemon is running.\n"); } static inline int @@ -600,7 +593,6 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred) struct rpc_pipe *pipe; struct rpc_cred *cred = &gss_cred->gc_base; struct gss_upcall_msg *gss_msg; - unsigned long timeout; DEFINE_WAIT(wait); int err; @@ -608,17 +600,16 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred) __func__, from_kuid(&init_user_ns, cred->cr_uid)); retry: err = 0; - /* Default timeout is 15s unless we know that gssd is not running */ - timeout = 15 * HZ; - if (!sn->gssd_running) - timeout = HZ >> 2; + /* if gssd is down, just skip upcalling altogether */ + if (!gssd_running(net)) { + warn_gssd(); + return -EACCES; + } gss_msg = gss_setup_upcall(gss_auth, cred); if (PTR_ERR(gss_msg) == -EAGAIN) { err = wait_event_interruptible_timeout(pipe_version_waitqueue, - sn->pipe_version >= 0, timeout); + sn->pipe_version >= 0, 15 * HZ); if (sn->pipe_version < 0) { - if (err == 0) - sn->gssd_running = 0; warn_gssd(); err = -EACCES; } diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index 76e42e6be755..24589bd2a4b6 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -59,6 +59,7 @@ #include <linux/crypto.h> #include <linux/sunrpc/gss_krb5.h> #include <linux/sunrpc/xdr.h> +#include <linux/lcm.h> #ifdef RPC_DEBUG # define RPCDBG_FACILITY RPCDBG_AUTH @@ -72,7 +73,7 @@ static void krb5_nfold(u32 inbits, const u8 *in, u32 outbits, u8 *out) { - int a, b, c, lcm; + unsigned long ulcm; int byte, i, msbit; /* the code below is more readable if I make these bytes @@ -82,17 +83,7 @@ static void krb5_nfold(u32 inbits, const u8 *in, outbits >>= 3; /* first compute lcm(n,k) */ - - a = outbits; - b = inbits; - - while (b != 0) { - c = b; - b = a%b; - a = c; - } - - lcm = outbits*inbits/a; + ulcm = lcm(inbits, outbits); /* now do the real work */ @@ -101,7 +92,7 @@ static void krb5_nfold(u32 inbits, const u8 *in, /* this will end up cycling through k lcm(k,n)/k times, which is correct */ - for (i = lcm-1; i >= 0; i--) { + for (i = ulcm-1; i >= 0; i--) { /* compute the msbit in k which gets added into this byte */ msbit = ( /* first, start with the msbit in the first, diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 458f85e9b0ba..abbb7dcd1689 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -137,7 +137,6 @@ void init_gssp_clnt(struct sunrpc_net *sn) { mutex_init(&sn->gssp_lock); sn->gssp_clnt = NULL; - init_waitqueue_head(&sn->gssp_wq); } int set_gssp_clnt(struct net *net) @@ -154,7 +153,6 @@ int set_gssp_clnt(struct net *net) sn->gssp_clnt = clnt; } mutex_unlock(&sn->gssp_lock); - wake_up(&sn->gssp_wq); return ret; } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 008cdade5aae..0f73f4507746 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1263,65 +1263,34 @@ out: return ret; } -DEFINE_SPINLOCK(use_gssp_lock); - -static bool use_gss_proxy(struct net *net) -{ - struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); - - if (sn->use_gss_proxy != -1) - return sn->use_gss_proxy; - spin_lock(&use_gssp_lock); - /* - * If you wanted gss-proxy, you should have said so before - * starting to accept requests: - */ - sn->use_gss_proxy = 0; - spin_unlock(&use_gssp_lock); - return 0; -} - -#ifdef CONFIG_PROC_FS - +/* + * Try to set the sn->use_gss_proxy variable to a new value. We only allow + * it to be changed if it's currently undefined (-1). If it's any other value + * then return -EBUSY unless the type wouldn't have changed anyway. + */ static int set_gss_proxy(struct net *net, int type) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); - int ret = 0; + int ret; WARN_ON_ONCE(type != 0 && type != 1); - spin_lock(&use_gssp_lock); - if (sn->use_gss_proxy == -1 || sn->use_gss_proxy == type) - sn->use_gss_proxy = type; - else - ret = -EBUSY; - spin_unlock(&use_gssp_lock); - wake_up(&sn->gssp_wq); - return ret; -} - -static inline bool gssp_ready(struct sunrpc_net *sn) -{ - switch (sn->use_gss_proxy) { - case -1: - return false; - case 0: - return true; - case 1: - return sn->gssp_clnt; - } - WARN_ON_ONCE(1); - return false; + ret = cmpxchg(&sn->use_gss_proxy, -1, type); + if (ret != -1 && ret != type) + return -EBUSY; + return 0; } -static int wait_for_gss_proxy(struct net *net, struct file *file) +static bool use_gss_proxy(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); - if (file->f_flags & O_NONBLOCK && !gssp_ready(sn)) - return -EAGAIN; - return wait_event_interruptible(sn->gssp_wq, gssp_ready(sn)); + /* If use_gss_proxy is still undefined, then try to disable it */ + if (sn->use_gss_proxy == -1) + set_gss_proxy(net, 0); + return sn->use_gss_proxy; } +#ifdef CONFIG_PROC_FS static ssize_t write_gssp(struct file *file, const char __user *buf, size_t count, loff_t *ppos) @@ -1342,10 +1311,10 @@ static ssize_t write_gssp(struct file *file, const char __user *buf, return res; if (i != 1) return -EINVAL; - res = set_gss_proxy(net, 1); + res = set_gssp_clnt(net); if (res) return res; - res = set_gssp_clnt(net); + res = set_gss_proxy(net, 1); if (res) return res; return count; @@ -1355,16 +1324,12 @@ static ssize_t read_gssp(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct net *net = PDE_DATA(file_inode(file)); + struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); unsigned long p = *ppos; char tbuf[10]; size_t len; - int ret; - ret = wait_for_gss_proxy(net, file); - if (ret) - return ret; - - snprintf(tbuf, sizeof(tbuf), "%d\n", use_gss_proxy(net)); + snprintf(tbuf, sizeof(tbuf), "%d\n", sn->use_gss_proxy); len = strlen(tbuf); if (p >= len) return 0; @@ -1626,8 +1591,7 @@ svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp) BUG_ON(integ_len % 4); *p++ = htonl(integ_len); *p++ = htonl(gc->gc_seq); - if (xdr_buf_subsegment(resbuf, &integ_buf, integ_offset, - integ_len)) + if (xdr_buf_subsegment(resbuf, &integ_buf, integ_offset, integ_len)) BUG(); if (resbuf->tail[0].iov_base == NULL) { if (resbuf->head[0].iov_len + RPC_MAX_AUTH_SIZE > PAGE_SIZE) @@ -1635,10 +1599,8 @@ svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp) resbuf->tail[0].iov_base = resbuf->head[0].iov_base + resbuf->head[0].iov_len; resbuf->tail[0].iov_len = 0; - resv = &resbuf->tail[0]; - } else { - resv = &resbuf->tail[0]; } + resv = &resbuf->tail[0]; mic.data = (u8 *)resv->iov_base + resv->iov_len + 4; if (gss_get_mic(gsd->rsci->mechctx, &integ_buf, &mic)) goto out_err; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index a72de074172d..ae333c1845bb 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -619,7 +619,7 @@ static void cache_limit_defers(void) /* Consider removing either the first or the last */ if (cache_defer_cnt > DFR_MAX) { - if (net_random() & 1) + if (prandom_u32() & 1) discard = list_entry(cache_defer_list.next, struct cache_deferred_req, recent); else @@ -1111,9 +1111,7 @@ void qword_addhex(char **bpp, int *lp, char *buf, int blen) *bp++ = 'x'; len -= 2; while (blen && len >= 2) { - unsigned char c = *buf++; - *bp++ = '0' + ((c&0xf0)>>4) + (c>=0xa0)*('a'-'9'-1); - *bp++ = '0' + (c&0x0f) + ((c&0x0f)>=0x0a)*('a'-'9'-1); + bp = hex_byte_pack(bp, *buf++); len -= 2; blen--; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f09b7db2c492..0edada973434 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1529,9 +1529,13 @@ 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 -EAGAIN: @@ -1729,6 +1733,7 @@ call_bind_status(struct rpc_task *task) return; case -ECONNREFUSED: /* connection problems */ case -ECONNRESET: + case -ECONNABORTED: case -ENOTCONN: case -EHOSTDOWN: case -EHOSTUNREACH: @@ -1799,7 +1804,9 @@ call_connect_status(struct rpc_task *task) return; case -ECONNREFUSED: case -ECONNRESET: + case -ECONNABORTED: case -ENETUNREACH: + case -EHOSTUNREACH: /* retry with existing socket, after a delay */ rpc_delay(task, 3*HZ); if (RPC_IS_SOFTCONN(task)) @@ -1902,6 +1909,7 @@ call_transmit_status(struct rpc_task *task) break; } case -ECONNRESET: + case -ECONNABORTED: case -ENOTCONN: case -EPIPE: rpc_task_force_reencode(task); @@ -2011,8 +2019,9 @@ call_status(struct rpc_task *task) xprt_conditional_disconnect(req->rq_xprt, req->rq_connect_cookie); break; - case -ECONNRESET: case -ECONNREFUSED: + case -ECONNRESET: + case -ECONNABORTED: rpc_force_rebind(clnt); rpc_delay(task, 3*HZ); case -EPIPE: diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h index 779742cfc1ff..df5826876535 100644 --- a/net/sunrpc/netns.h +++ b/net/sunrpc/netns.h @@ -14,6 +14,7 @@ struct sunrpc_net { struct cache_detail *rsi_cache; struct super_block *pipefs_sb; + struct rpc_pipe *gssd_dummy; struct mutex pipefs_sb_lock; struct list_head all_clients; @@ -26,14 +27,11 @@ struct sunrpc_net { unsigned int rpcb_is_af_local : 1; struct mutex gssp_lock; - wait_queue_head_t gssp_wq; struct rpc_clnt *gssp_clnt; int use_gss_proxy; int pipe_version; atomic_t pipe_users; struct proc_dir_entry *use_gssp_proc; - - unsigned int gssd_running; }; extern int sunrpc_net_id; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index bf04b30a788a..b18554898562 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -17,6 +17,7 @@ #include <linux/fsnotify.h> #include <linux/kernel.h> #include <linux/rcupdate.h> +#include <linux/utsname.h> #include <asm/ioctls.h> #include <linux/poll.h> @@ -38,7 +39,7 @@ #define NET_NAME(net) ((net == &init_net) ? " (init_net)" : "") static struct file_system_type rpc_pipe_fs_type; - +static const struct rpc_pipe_ops gssd_dummy_pipe_ops; static struct kmem_cache *rpc_inode_cachep __read_mostly; @@ -216,14 +217,11 @@ rpc_destroy_inode(struct inode *inode) static int rpc_pipe_open(struct inode *inode, struct file *filp) { - struct net *net = inode->i_sb->s_fs_info; - struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_pipe *pipe; int first_open; int res = -ENXIO; mutex_lock(&inode->i_mutex); - sn->gssd_running = 1; pipe = RPC_I(inode)->pipe; if (pipe == NULL) goto out; @@ -1159,6 +1157,7 @@ enum { RPCAUTH_nfsd4_cb, RPCAUTH_cache, RPCAUTH_nfsd, + RPCAUTH_gssd, RPCAUTH_RootEOF }; @@ -1195,6 +1194,10 @@ static const struct rpc_filelist files[] = { .name = "nfsd", .mode = S_IFDIR | S_IRUGO | S_IXUGO, }, + [RPCAUTH_gssd] = { + .name = "gssd", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, }; /* @@ -1208,13 +1211,24 @@ struct dentry *rpc_d_lookup_sb(const struct super_block *sb, } EXPORT_SYMBOL_GPL(rpc_d_lookup_sb); -void rpc_pipefs_init_net(struct net *net) +int rpc_pipefs_init_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + sn->gssd_dummy = rpc_mkpipe_data(&gssd_dummy_pipe_ops, 0); + if (IS_ERR(sn->gssd_dummy)) + return PTR_ERR(sn->gssd_dummy); + mutex_init(&sn->pipefs_sb_lock); - sn->gssd_running = 1; sn->pipe_version = -1; + return 0; +} + +void rpc_pipefs_exit_net(struct net *net) +{ + struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + + rpc_destroy_pipe_data(sn->gssd_dummy); } /* @@ -1244,11 +1258,134 @@ void rpc_put_sb_net(const struct net *net) } EXPORT_SYMBOL_GPL(rpc_put_sb_net); +static const struct rpc_filelist gssd_dummy_clnt_dir[] = { + [0] = { + .name = "clntXX", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, +}; + +static ssize_t +dummy_downcall(struct file *filp, const char __user *src, size_t len) +{ + return -EINVAL; +} + +static const struct rpc_pipe_ops gssd_dummy_pipe_ops = { + .upcall = rpc_pipe_generic_upcall, + .downcall = dummy_downcall, +}; + +/* + * Here we present a bogus "info" file to keep rpc.gssd happy. We don't expect + * that it will ever use this info to handle an upcall, but rpc.gssd expects + * that this file will be there and have a certain format. + */ +static int +rpc_show_dummy_info(struct seq_file *m, void *v) +{ + seq_printf(m, "RPC server: %s\n", utsname()->nodename); + seq_printf(m, "service: foo (1) version 0\n"); + seq_printf(m, "address: 127.0.0.1\n"); + seq_printf(m, "protocol: tcp\n"); + seq_printf(m, "port: 0\n"); + return 0; +} + +static int +rpc_dummy_info_open(struct inode *inode, struct file *file) +{ + return single_open(file, rpc_show_dummy_info, NULL); +} + +static const struct file_operations rpc_dummy_info_operations = { + .owner = THIS_MODULE, + .open = rpc_dummy_info_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct rpc_filelist gssd_dummy_info_file[] = { + [0] = { + .name = "info", + .i_fop = &rpc_dummy_info_operations, + .mode = S_IFREG | S_IRUSR, + }, +}; + +/** + * rpc_gssd_dummy_populate - create a dummy gssd pipe + * @root: root of the rpc_pipefs filesystem + * @pipe_data: pipe data created when netns is initialized + * + * Create a dummy set of directories and a pipe that gssd can hold open to + * indicate that it is up and running. + */ +static struct dentry * +rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) +{ + int ret = 0; + struct dentry *gssd_dentry; + struct dentry *clnt_dentry = NULL; + struct dentry *pipe_dentry = NULL; + struct qstr q = QSTR_INIT(files[RPCAUTH_gssd].name, + strlen(files[RPCAUTH_gssd].name)); + + /* We should never get this far if "gssd" doesn't exist */ + gssd_dentry = d_hash_and_lookup(root, &q); + if (!gssd_dentry) + return ERR_PTR(-ENOENT); + + ret = rpc_populate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1, NULL); + if (ret) { + pipe_dentry = ERR_PTR(ret); + goto out; + } + + q.name = gssd_dummy_clnt_dir[0].name; + q.len = strlen(gssd_dummy_clnt_dir[0].name); + clnt_dentry = d_hash_and_lookup(gssd_dentry, &q); + if (!clnt_dentry) { + pipe_dentry = ERR_PTR(-ENOENT); + goto out; + } + + ret = rpc_populate(clnt_dentry, gssd_dummy_info_file, 0, 1, NULL); + if (ret) { + __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); + pipe_dentry = ERR_PTR(ret); + goto out; + } + + pipe_dentry = rpc_mkpipe_dentry(clnt_dentry, "gssd", NULL, pipe_data); + if (IS_ERR(pipe_dentry)) { + __rpc_depopulate(clnt_dentry, gssd_dummy_info_file, 0, 1); + __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); + } +out: + dput(clnt_dentry); + dput(gssd_dentry); + return pipe_dentry; +} + +static void +rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry) +{ + struct dentry *clnt_dir = pipe_dentry->d_parent; + struct dentry *gssd_dir = clnt_dir->d_parent; + + __rpc_rmpipe(clnt_dir->d_inode, pipe_dentry); + __rpc_depopulate(clnt_dir, gssd_dummy_info_file, 0, 1); + __rpc_depopulate(gssd_dir, gssd_dummy_clnt_dir, 0, 1); + dput(pipe_dentry); +} + static int rpc_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; - struct dentry *root; + struct dentry *root, *gssd_dentry; struct net *net = data; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); int err; @@ -1266,6 +1403,13 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) return -ENOMEM; if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL)) return -ENOMEM; + + gssd_dentry = rpc_gssd_dummy_populate(root, sn->gssd_dummy); + if (IS_ERR(gssd_dentry)) { + __rpc_depopulate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF); + return PTR_ERR(gssd_dentry); + } + dprintk("RPC: sending pipefs MOUNT notification for net %p%s\n", net, NET_NAME(net)); mutex_lock(&sn->pipefs_sb_lock); @@ -1280,6 +1424,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) return 0; err_depopulate: + rpc_gssd_dummy_depopulate(gssd_dentry); blocking_notifier_call_chain(&rpc_pipefs_notifier_list, RPC_PIPEFS_UMOUNT, sb); @@ -1289,6 +1434,16 @@ err_depopulate: return err; } +bool +gssd_running(struct net *net) +{ + struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + struct rpc_pipe *pipe = sn->gssd_dummy; + + return pipe->nreaders || pipe->nwriters; +} +EXPORT_SYMBOL_GPL(gssd_running); + static struct dentry * rpc_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 3d6498af9adc..cd30120de9e4 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -44,12 +44,17 @@ static __net_init int sunrpc_init_net(struct net *net) if (err) goto err_unixgid; - rpc_pipefs_init_net(net); + err = rpc_pipefs_init_net(net); + if (err) + goto err_pipefs; + INIT_LIST_HEAD(&sn->all_clients); spin_lock_init(&sn->rpc_client_lock); spin_lock_init(&sn->rpcb_clnt_lock); return 0; +err_pipefs: + unix_gid_cache_destroy(net); err_unixgid: ip_map_cache_destroy(net); err_ipmap: @@ -60,6 +65,7 @@ err_proc: static __net_exit void sunrpc_exit_net(struct net *net) { + rpc_pipefs_exit_net(net); unix_gid_cache_destroy(net); ip_map_cache_destroy(net); rpc_proc_exit(net); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index e7fbe368b4a3..5de6801cd924 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -916,9 +916,6 @@ static int __svc_register(struct net *net, const char *progname, #endif } - if (error < 0) - printk(KERN_WARNING "svc: failed to register %sv%u RPC " - "service (errno %d).\n", progname, version, -error); return error; } @@ -937,6 +934,7 @@ int svc_register(const struct svc_serv *serv, struct net *net, const unsigned short port) { struct svc_program *progp; + struct svc_version *vers; unsigned int i; int error = 0; @@ -946,7 +944,8 @@ int svc_register(const struct svc_serv *serv, struct net *net, for (progp = serv->sv_program; progp; progp = progp->pg_next) { for (i = 0; i < progp->pg_nvers; i++) { - if (progp->pg_vers[i] == NULL) + vers = progp->pg_vers[i]; + if (vers == NULL) continue; dprintk("svc: svc_register(%sv%d, %s, %u, %u)%s\n", @@ -955,16 +954,26 @@ int svc_register(const struct svc_serv *serv, struct net *net, proto == IPPROTO_UDP? "udp" : "tcp", port, family, - progp->pg_vers[i]->vs_hidden? - " (but not telling portmap)" : ""); + vers->vs_hidden ? + " (but not telling portmap)" : ""); - if (progp->pg_vers[i]->vs_hidden) + if (vers->vs_hidden) continue; error = __svc_register(net, progp->pg_name, progp->pg_prog, i, family, proto, port); - if (error < 0) + + if (vers->vs_rpcb_optnl) { + error = 0; + continue; + } + + if (error < 0) { + printk(KERN_WARNING "svc: failed to register " + "%sv%u RPC service (errno %d).\n", + progp->pg_name, i, -error); break; + } } } diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 80a6640f329b..06c6ff0cb911 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -571,7 +571,7 @@ static void svc_check_conn_limits(struct svc_serv *serv) } } -int svc_alloc_arg(struct svc_rqst *rqstp) +static int svc_alloc_arg(struct svc_rqst *rqstp) { struct svc_serv *serv = rqstp->rq_server; struct xdr_buf *arg; @@ -612,7 +612,7 @@ int svc_alloc_arg(struct svc_rqst *rqstp) return 0; } -struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) +static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) { struct svc_xprt *xprt; struct svc_pool *pool = rqstp->rq_pool; @@ -691,7 +691,7 @@ struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) return xprt; } -void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt) +static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt) { spin_lock_bh(&serv->sv_lock); set_bit(XPT_TEMP, &newxpt->xpt_flags); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 04199bc8416f..7d4df99f761f 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -749,6 +749,11 @@ static void xprt_connect_status(struct rpc_task *task) } switch (task->tk_status) { + case -ECONNREFUSED: + case -ECONNRESET: + case -ECONNABORTED: + case -ENETUNREACH: + case -EHOSTUNREACH: case -EAGAIN: dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid); break; @@ -1188,7 +1193,7 @@ static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt) static inline void xprt_init_xid(struct rpc_xprt *xprt) { - xprt->xid = net_random(); + xprt->xid = prandom_u32(); } static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index dd9d295813cf..817a1e523969 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -257,6 +257,7 @@ struct sock_xprt { void (*old_data_ready)(struct sock *, int); void (*old_state_change)(struct sock *); void (*old_write_space)(struct sock *); + void (*old_error_report)(struct sock *); }; /* @@ -274,6 +275,11 @@ struct sock_xprt { */ #define TCP_RPC_REPLY (1UL << 6) +static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) +{ + return (struct rpc_xprt *) sk->sk_user_data; +} + static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt) { return (struct sockaddr *) &xprt->addr; @@ -799,6 +805,7 @@ static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk) transport->old_data_ready = sk->sk_data_ready; transport->old_state_change = sk->sk_state_change; transport->old_write_space = sk->sk_write_space; + transport->old_error_report = sk->sk_error_report; } static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk) @@ -806,6 +813,34 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s sk->sk_data_ready = transport->old_data_ready; sk->sk_state_change = transport->old_state_change; sk->sk_write_space = transport->old_write_space; + sk->sk_error_report = transport->old_error_report; +} + +/** + * xs_error_report - callback to handle TCP socket state errors + * @sk: socket + * + * Note: we don't call sock_error() since there may be a rpc_task + * using the socket, and so we don't want to clear sk->sk_err. + */ +static void xs_error_report(struct sock *sk) +{ + struct rpc_xprt *xprt; + int err; + + read_lock_bh(&sk->sk_callback_lock); + if (!(xprt = xprt_from_sock(sk))) + goto out; + + err = -sk->sk_err; + if (err == 0) + goto out; + dprintk("RPC: xs_error_report client %p, error=%d...\n", + xprt, -err); + trace_rpc_socket_error(xprt, sk->sk_socket, err); + xprt_wake_pending_tasks(xprt, err); + out: + read_unlock_bh(&sk->sk_callback_lock); } static void xs_reset_transport(struct sock_xprt *transport) @@ -885,11 +920,6 @@ static void xs_destroy(struct rpc_xprt *xprt) module_put(THIS_MODULE); } -static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) -{ - return (struct rpc_xprt *) sk->sk_user_data; -} - static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb) { struct xdr_skb_reader desc = { @@ -1674,7 +1704,7 @@ static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task) static unsigned short xs_get_random_port(void) { unsigned short range = xprt_max_resvport - xprt_min_resvport; - unsigned short rand = (unsigned short) net_random() % range; + unsigned short rand = (unsigned short) prandom_u32() % range; return rand + xprt_min_resvport; } @@ -1869,6 +1899,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, sk->sk_user_data = xprt; sk->sk_data_ready = xs_local_data_ready; sk->sk_write_space = xs_udp_write_space; + sk->sk_error_report = xs_error_report; sk->sk_allocation = GFP_ATOMIC; xprt_clear_connected(xprt); @@ -2146,6 +2177,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_data_ready = xs_tcp_data_ready; sk->sk_state_change = xs_tcp_state_change; sk->sk_write_space = xs_tcp_write_space; + sk->sk_error_report = xs_error_report; sk->sk_allocation = GFP_ATOMIC; /* socket options */ @@ -2932,10 +2964,9 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) /* * Once we've associated a backchannel xprt with a connection, - * we want to keep it around as long as long as the connection - * lasts, in case we need to start using it for a backchannel - * again; this reference won't be dropped until bc_xprt is - * destroyed. + * we want to keep it around as long as the connection lasts, + * in case we need to start using it for a backchannel again; + * this reference won't be dropped until bc_xprt is destroyed. */ xprt_get(xprt); args->bc_xprt->xpt_bc_xprt = xprt; diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 0d4402587fdf..bf860d9e75af 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -621,12 +621,6 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1, if (!p) break; /* No more bearers to try */ - if (tipc_bearer_blocked(p)) { - if (!s || tipc_bearer_blocked(s)) - continue; /* Can't use either bearer */ - b = s; - } - tipc_nmap_diff(&bcbearer->remains, &b->nodes, &bcbearer->remains_new); if (bcbearer->remains_new.count == bcbearer->remains.count) @@ -800,7 +794,7 @@ void tipc_bclink_init(void) void tipc_bclink_stop(void) { spin_lock_bh(&bc_lock); - tipc_link_stop(bcl); + tipc_link_purge_queues(bcl); spin_unlock_bh(&bc_lock); memset(bclink, 0, sizeof(*bclink)); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 3f9707a16d06..a38c89969c68 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1,8 +1,8 @@ /* * net/tipc/bearer.c: TIPC bearer code * - * Copyright (c) 1996-2006, Ericsson AB - * Copyright (c) 2004-2006, 2010-2011, Wind River Systems + * Copyright (c) 1996-2006, 2013, Ericsson AB + * Copyright (c) 2004-2006, 2010-2013, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -41,8 +41,13 @@ #define MAX_ADDR_STR 60 -static struct tipc_media *media_list[MAX_MEDIA]; -static u32 media_count; +static struct tipc_media * const media_info_array[] = { + ð_media_info, +#ifdef CONFIG_TIPC_MEDIA_IB + &ib_media_info, +#endif + NULL +}; struct tipc_bearer tipc_bearers[MAX_BEARERS]; @@ -55,11 +60,11 @@ struct tipc_media *tipc_media_find(const char *name) { u32 i; - for (i = 0; i < media_count; i++) { - if (!strcmp(media_list[i]->name, name)) - return media_list[i]; + for (i = 0; media_info_array[i] != NULL; i++) { + if (!strcmp(media_info_array[i]->name, name)) + break; } - return NULL; + return media_info_array[i]; } /** @@ -69,44 +74,11 @@ static struct tipc_media *media_find_id(u8 type) { u32 i; - for (i = 0; i < media_count; i++) { - if (media_list[i]->type_id == type) - return media_list[i]; + for (i = 0; media_info_array[i] != NULL; i++) { + if (media_info_array[i]->type_id == type) + break; } - return NULL; -} - -/** - * tipc_register_media - register a media type - * - * Bearers for this media type must be activated separately at a later stage. - */ -int tipc_register_media(struct tipc_media *m_ptr) -{ - int res = -EINVAL; - - write_lock_bh(&tipc_net_lock); - - if ((strlen(m_ptr->name) + 1) > TIPC_MAX_MEDIA_NAME) - goto exit; - if (m_ptr->priority > TIPC_MAX_LINK_PRI) - goto exit; - if ((m_ptr->tolerance < TIPC_MIN_LINK_TOL) || - (m_ptr->tolerance > TIPC_MAX_LINK_TOL)) - goto exit; - if (media_count >= MAX_MEDIA) - goto exit; - if (tipc_media_find(m_ptr->name) || media_find_id(m_ptr->type_id)) - goto exit; - - media_list[media_count] = m_ptr; - media_count++; - res = 0; -exit: - write_unlock_bh(&tipc_net_lock); - if (res) - pr_warn("Media <%s> registration error\n", m_ptr->name); - return res; + return media_info_array[i]; } /** @@ -144,13 +116,11 @@ struct sk_buff *tipc_media_get_names(void) if (!buf) return NULL; - read_lock_bh(&tipc_net_lock); - for (i = 0; i < media_count; i++) { + for (i = 0; media_info_array[i] != NULL; i++) { tipc_cfg_append_tlv(buf, TIPC_TLV_MEDIA_NAME, - media_list[i]->name, - strlen(media_list[i]->name) + 1); + media_info_array[i]->name, + strlen(media_info_array[i]->name) + 1); } - read_unlock_bh(&tipc_net_lock); return buf; } @@ -215,31 +185,12 @@ struct tipc_bearer *tipc_bearer_find(const char *name) } /** - * tipc_bearer_find_interface - locates bearer object with matching interface name - */ -struct tipc_bearer *tipc_bearer_find_interface(const char *if_name) -{ - struct tipc_bearer *b_ptr; - char *b_if_name; - u32 i; - - for (i = 0, b_ptr = tipc_bearers; i < MAX_BEARERS; i++, b_ptr++) { - if (!b_ptr->active) - continue; - b_if_name = strchr(b_ptr->name, ':') + 1; - if (!strcmp(b_if_name, if_name)) - return b_ptr; - } - return NULL; -} - -/** * tipc_bearer_get_names - record names of bearers in buffer */ struct sk_buff *tipc_bearer_get_names(void) { struct sk_buff *buf; - struct tipc_bearer *b_ptr; + struct tipc_bearer *b; int i, j; buf = tipc_cfg_reply_alloc(MAX_BEARERS * TLV_SPACE(TIPC_MAX_BEARER_NAME)); @@ -247,13 +198,13 @@ struct sk_buff *tipc_bearer_get_names(void) return NULL; read_lock_bh(&tipc_net_lock); - for (i = 0; i < media_count; i++) { + for (i = 0; media_info_array[i] != NULL; i++) { for (j = 0; j < MAX_BEARERS; j++) { - b_ptr = &tipc_bearers[j]; - if (b_ptr->active && (b_ptr->media == media_list[i])) { + b = &tipc_bearers[j]; + if (b->active && (b->media == media_info_array[i])) { tipc_cfg_append_tlv(buf, TIPC_TLV_BEARER_NAME, - b_ptr->name, - strlen(b_ptr->name) + 1); + b->name, + strlen(b->name) + 1); } } } @@ -275,31 +226,6 @@ void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest) tipc_disc_remove_dest(b_ptr->link_req); } -/* - * Interrupt enabling new requests after bearer blocking: - * See bearer_send(). - */ -void tipc_continue(struct tipc_bearer *b) -{ - spin_lock_bh(&b->lock); - b->blocked = 0; - spin_unlock_bh(&b->lock); -} - -/* - * tipc_bearer_blocked - determines if bearer is currently blocked - */ -int tipc_bearer_blocked(struct tipc_bearer *b) -{ - int res; - - spin_lock_bh(&b->lock); - res = b->blocked; - spin_unlock_bh(&b->lock); - - return res; -} - /** * tipc_enable_bearer - enable bearer with the given name */ @@ -387,6 +313,7 @@ restart: b_ptr = &tipc_bearers[bearer_id]; strcpy(b_ptr->name, name); + b_ptr->media = m_ptr; res = m_ptr->enable_media(b_ptr); if (res) { pr_warn("Bearer <%s> rejected, enable failure (%d)\n", @@ -395,7 +322,6 @@ restart: } b_ptr->identity = bearer_id; - b_ptr->media = m_ptr; b_ptr->tolerance = m_ptr->tolerance; b_ptr->window = m_ptr->window; b_ptr->net_plane = bearer_id + 'A'; @@ -420,17 +346,16 @@ exit: } /** - * tipc_block_bearer - Block the bearer, and reset all its links + * tipc_reset_bearer - Reset all links established over this bearer */ -int tipc_block_bearer(struct tipc_bearer *b_ptr) +static int tipc_reset_bearer(struct tipc_bearer *b_ptr) { struct tipc_link *l_ptr; struct tipc_link *temp_l_ptr; read_lock_bh(&tipc_net_lock); - pr_info("Blocking bearer <%s>\n", b_ptr->name); + pr_info("Resetting bearer <%s>\n", b_ptr->name); spin_lock_bh(&b_ptr->lock); - b_ptr->blocked = 1; list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { struct tipc_node *n_ptr = l_ptr->owner; @@ -456,7 +381,6 @@ static void bearer_disable(struct tipc_bearer *b_ptr) pr_info("Disabling bearer <%s>\n", b_ptr->name); spin_lock_bh(&b_ptr->lock); - b_ptr->blocked = 1; b_ptr->media->disable_media(b_ptr); list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { tipc_link_delete(l_ptr); @@ -490,6 +414,211 @@ int tipc_disable_bearer(const char *name) } +/* tipc_l2_media_addr_set - initialize Ethernet media address structure + * + * Media-dependent "value" field stores MAC address in first 6 bytes + * and zeroes out the remaining bytes. + */ +void tipc_l2_media_addr_set(const struct tipc_bearer *b, + struct tipc_media_addr *a, char *mac) +{ + int len = b->media->hwaddr_len; + + if (unlikely(sizeof(a->value) < len)) { + WARN_ONCE(1, "Media length invalid\n"); + return; + } + + memcpy(a->value, mac, len); + memset(a->value + len, 0, sizeof(a->value) - len); + a->media_id = b->media->type_id; + a->broadcast = !memcmp(mac, b->bcast_addr.value, len); +} + +int tipc_enable_l2_media(struct tipc_bearer *b) +{ + struct net_device *dev; + char *driver_name = strchr((const char *)b->name, ':') + 1; + + /* Find device with specified name */ + dev = dev_get_by_name(&init_net, driver_name); + if (!dev) + return -ENODEV; + + /* Associate TIPC bearer with Ethernet bearer */ + b->media_ptr = dev; + memset(b->bcast_addr.value, 0, sizeof(b->bcast_addr.value)); + memcpy(b->bcast_addr.value, dev->broadcast, b->media->hwaddr_len); + b->bcast_addr.media_id = b->media->type_id; + b->bcast_addr.broadcast = 1; + b->mtu = dev->mtu; + tipc_l2_media_addr_set(b, &b->addr, (char *)dev->dev_addr); + rcu_assign_pointer(dev->tipc_ptr, b); + return 0; +} + +/* tipc_disable_l2_media - detach TIPC bearer from an Ethernet interface + * + * Mark Ethernet bearer as inactive so that incoming buffers are thrown away, + * then get worker thread to complete bearer cleanup. (Can't do cleanup + * here because cleanup code needs to sleep and caller holds spinlocks.) + */ +void tipc_disable_l2_media(struct tipc_bearer *b) +{ + struct net_device *dev = (struct net_device *)b->media_ptr; + RCU_INIT_POINTER(dev->tipc_ptr, NULL); + dev_put(dev); +} + +/** + * tipc_l2_send_msg - send a TIPC packet out over an Ethernet interface + * @buf: the packet to be sent + * @b_ptr: the bearer through which the packet is to be sent + * @dest: peer destination address + */ +int tipc_l2_send_msg(struct sk_buff *buf, struct tipc_bearer *b, + struct tipc_media_addr *dest) +{ + struct sk_buff *clone; + int delta; + struct net_device *dev = (struct net_device *)b->media_ptr; + + clone = skb_clone(buf, GFP_ATOMIC); + if (!clone) + return 0; + + delta = dev->hard_header_len - skb_headroom(buf); + if ((delta > 0) && + pskb_expand_head(clone, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { + kfree_skb(clone); + return 0; + } + + skb_reset_network_header(clone); + clone->dev = dev; + clone->protocol = htons(ETH_P_TIPC); + dev_hard_header(clone, dev, ETH_P_TIPC, dest->value, + dev->dev_addr, clone->len); + dev_queue_xmit(clone); + return 0; +} + +/* tipc_bearer_send- sends buffer to destination over bearer + * + * IMPORTANT: + * The media send routine must not alter the buffer being passed in + * as it may be needed for later retransmission! + */ +void tipc_bearer_send(struct tipc_bearer *b, struct sk_buff *buf, + struct tipc_media_addr *dest) +{ + b->media->send_msg(buf, b, dest); +} + +/** + * tipc_l2_rcv_msg - handle incoming TIPC message from an interface + * @buf: the received packet + * @dev: the net device that the packet was received on + * @pt: the packet_type structure which was used to register this handler + * @orig_dev: the original receive net device in case the device is a bond + * + * Accept only packets explicitly sent to this node, or broadcast packets; + * ignores packets sent using interface multicast, and traffic sent to other + * nodes (which can happen if interface is running in promiscuous mode). + */ +static int tipc_l2_rcv_msg(struct sk_buff *buf, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct tipc_bearer *b_ptr; + + if (!net_eq(dev_net(dev), &init_net)) { + kfree_skb(buf); + return NET_RX_DROP; + } + + rcu_read_lock(); + b_ptr = rcu_dereference(dev->tipc_ptr); + if (likely(b_ptr)) { + if (likely(buf->pkt_type <= PACKET_BROADCAST)) { + buf->next = NULL; + tipc_rcv(buf, b_ptr); + rcu_read_unlock(); + return NET_RX_SUCCESS; + } + } + rcu_read_unlock(); + + kfree_skb(buf); + return NET_RX_DROP; +} + +/** + * tipc_l2_device_event - handle device events from network device + * @nb: the context of the notification + * @evt: the type of event + * @ptr: the net device that the event was on + * + * This function is called by the Ethernet driver in case of link + * change event. + */ +static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, + void *ptr) +{ + struct tipc_bearer *b_ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (!net_eq(dev_net(dev), &init_net)) + return NOTIFY_DONE; + + rcu_read_lock(); + b_ptr = rcu_dereference(dev->tipc_ptr); + if (!b_ptr) { + rcu_read_unlock(); + return NOTIFY_DONE; + } + + b_ptr->mtu = dev->mtu; + + switch (evt) { + case NETDEV_CHANGE: + if (netif_carrier_ok(dev)) + break; + case NETDEV_DOWN: + case NETDEV_CHANGEMTU: + case NETDEV_CHANGEADDR: + tipc_reset_bearer(b_ptr); + break; + case NETDEV_UNREGISTER: + case NETDEV_CHANGENAME: + tipc_disable_bearer(b_ptr->name); + break; + } + rcu_read_unlock(); + + return NOTIFY_OK; +} + +static struct packet_type tipc_packet_type __read_mostly = { + .type = __constant_htons(ETH_P_TIPC), + .func = tipc_l2_rcv_msg, +}; + +static struct notifier_block notifier = { + .notifier_call = tipc_l2_device_event, + .priority = 0, +}; + +int tipc_bearer_setup(void) +{ + dev_add_pack(&tipc_packet_type); + return register_netdevice_notifier(¬ifier); +} + +void tipc_bearer_cleanup(void) +{ + unregister_netdevice_notifier(¬ifier); + dev_remove_pack(&tipc_packet_type); +} void tipc_bearer_stop(void) { @@ -499,5 +628,4 @@ void tipc_bearer_stop(void) if (tipc_bearers[i].active) bearer_disable(&tipc_bearers[i]); } - media_count = 0; } diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index e5e04be6fffa..4f5db9ad5bf6 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -1,7 +1,7 @@ /* * net/tipc/bearer.h: Include file for TIPC bearer code * - * Copyright (c) 1996-2006, Ericsson AB + * Copyright (c) 1996-2006, 2013, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * @@ -73,18 +73,18 @@ struct tipc_media_addr { struct tipc_bearer; /** - * struct tipc_media - TIPC media information available to internal users + * struct tipc_media - Media specific info exposed to generic bearer layer * @send_msg: routine which handles buffer transmission * @enable_media: routine which enables a media * @disable_media: routine which disables a media * @addr2str: routine which converts media address to string * @addr2msg: routine which converts media address to protocol message area * @msg2addr: routine which converts media address from protocol message area - * @bcast_addr: media address used in broadcasting * @priority: default link (and bearer) priority * @tolerance: default time (in ms) before declaring link failure * @window: default window (in packets) before declaring link congestion * @type_id: TIPC media identifier + * @hwaddr_len: TIPC media address len * @name: media name */ struct tipc_media { @@ -101,18 +101,20 @@ struct tipc_media { u32 tolerance; u32 window; u32 type_id; + u32 hwaddr_len; char name[TIPC_MAX_MEDIA_NAME]; }; /** - * struct tipc_bearer - TIPC bearer structure + * struct tipc_bearer - Generic TIPC bearer structure + * @dev: ptr to associated network device * @usr_handle: pointer to additional media-specific information about bearer * @mtu: max packet size bearer can support - * @blocked: non-zero if bearer is blocked * @lock: spinlock for controlling access to bearer * @addr: media-specific address associated with bearer * @name: bearer name (format = media:interface) * @media: ptr to media structure associated with bearer + * @bcast_addr: media address used in broadcasting * @priority: default link priority for bearer * @window: default window size for bearer * @tolerance: default link tolerance for bearer @@ -128,9 +130,8 @@ struct tipc_media { * care of initializing all other fields. */ struct tipc_bearer { - void *usr_handle; /* initalized by media */ + void *media_ptr; /* initalized by media */ u32 mtu; /* initalized by media */ - int blocked; /* initalized by media */ struct tipc_media_addr addr; /* initalized by media */ char name[TIPC_MAX_BEARER_NAME]; spinlock_t lock; @@ -159,55 +160,40 @@ extern struct tipc_bearer tipc_bearers[]; /* * TIPC routines available to supported media types */ -int tipc_register_media(struct tipc_media *m_ptr); - -void tipc_recv_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr); - -int tipc_block_bearer(struct tipc_bearer *b_ptr); -void tipc_continue(struct tipc_bearer *tb_ptr); +void tipc_rcv(struct sk_buff *buf, struct tipc_bearer *tb_ptr); int tipc_enable_bearer(const char *bearer_name, u32 disc_domain, u32 priority); int tipc_disable_bearer(const char *name); /* * Routines made available to TIPC by supported media types */ -int tipc_eth_media_start(void); -void tipc_eth_media_stop(void); +extern struct tipc_media eth_media_info; #ifdef CONFIG_TIPC_MEDIA_IB -int tipc_ib_media_start(void); -void tipc_ib_media_stop(void); -#else -static inline int tipc_ib_media_start(void) { return 0; } -static inline void tipc_ib_media_stop(void) { return; } +extern struct tipc_media ib_media_info; #endif int tipc_media_set_priority(const char *name, u32 new_value); int tipc_media_set_window(const char *name, u32 new_value); void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a); struct sk_buff *tipc_media_get_names(void); +void tipc_l2_media_addr_set(const struct tipc_bearer *b, + struct tipc_media_addr *a, char *mac); +int tipc_enable_l2_media(struct tipc_bearer *b); +void tipc_disable_l2_media(struct tipc_bearer *b); +int tipc_l2_send_msg(struct sk_buff *buf, struct tipc_bearer *b, + struct tipc_media_addr *dest); struct sk_buff *tipc_bearer_get_names(void); void tipc_bearer_add_dest(struct tipc_bearer *b_ptr, u32 dest); void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest); struct tipc_bearer *tipc_bearer_find(const char *name); -struct tipc_bearer *tipc_bearer_find_interface(const char *if_name); struct tipc_media *tipc_media_find(const char *name); -int tipc_bearer_blocked(struct tipc_bearer *b_ptr); +int tipc_bearer_setup(void); +void tipc_bearer_cleanup(void); void tipc_bearer_stop(void); - -/** - * tipc_bearer_send- sends buffer to destination over bearer - * - * IMPORTANT: - * The media send routine must not alter the buffer being passed in - * as it may be needed for later retransmission! - */ -static inline void tipc_bearer_send(struct tipc_bearer *b, struct sk_buff *buf, - struct tipc_media_addr *dest) -{ - b->media->send_msg(buf, b, dest); -} +void tipc_bearer_send(struct tipc_bearer *b, struct sk_buff *buf, + struct tipc_media_addr *dest); #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/core.c b/net/tipc/core.c index c6d3f75a9e1b..f9e88d8b04ca 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -82,8 +82,7 @@ struct sk_buff *tipc_buf_acquire(u32 size) static void tipc_core_stop_net(void) { tipc_net_stop(); - tipc_eth_media_stop(); - tipc_ib_media_stop(); + tipc_bearer_cleanup(); } /** @@ -94,10 +93,7 @@ int tipc_core_start_net(unsigned long addr) int res; tipc_net_start(addr); - res = tipc_eth_media_start(); - if (res < 0) - goto err; - res = tipc_ib_media_start(); + res = tipc_bearer_setup(); if (res < 0) goto err; return res; diff --git a/net/tipc/core.h b/net/tipc/core.h index 94895d4e86ab..5569d96b4da3 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -47,7 +47,7 @@ #include <linux/mm.h> #include <linux/timer.h> #include <linux/string.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <linux/interrupt.h> #include <linux/atomic.h> #include <asm/hardirq.h> @@ -192,6 +192,7 @@ static inline void k_term_timer(struct timer_list *timer) struct tipc_skb_cb { void *handle; + bool deferred; }; #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0])) diff --git a/net/tipc/discover.c b/net/tipc/discover.c index ecc758c6eacf..412ff41b8611 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -50,6 +50,7 @@ * @dest: destination address for request messages * @domain: network domain to which links can be established * @num_nodes: number of nodes currently discovered (i.e. with an active link) + * @lock: spinlock for controlling access to requests * @buf: request message to be (repeatedly) sent * @timer: timer governing period between requests * @timer_intv: current interval between requests (in ms) @@ -59,6 +60,7 @@ struct tipc_link_req { struct tipc_media_addr dest; u32 domain; int num_nodes; + spinlock_t lock; struct sk_buff *buf; struct timer_list timer; unsigned int timer_intv; @@ -239,7 +241,7 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) /* Accept discovery message & send response, if necessary */ link_fully_up = link_working_working(link); - if ((type == DSC_REQ_MSG) && !link_fully_up && !b_ptr->blocked) { + if ((type == DSC_REQ_MSG) && !link_fully_up) { rbuf = tipc_disc_init_msg(DSC_RESP_MSG, orig, b_ptr); if (rbuf) { tipc_bearer_send(b_ptr, rbuf, &media_addr); @@ -274,7 +276,9 @@ static void disc_update(struct tipc_link_req *req) */ void tipc_disc_add_dest(struct tipc_link_req *req) { + spin_lock_bh(&req->lock); req->num_nodes++; + spin_unlock_bh(&req->lock); } /** @@ -283,18 +287,10 @@ void tipc_disc_add_dest(struct tipc_link_req *req) */ void tipc_disc_remove_dest(struct tipc_link_req *req) { + spin_lock_bh(&req->lock); req->num_nodes--; disc_update(req); -} - -/** - * disc_send_msg - send link setup request message - * @req: ptr to link request structure - */ -static void disc_send_msg(struct tipc_link_req *req) -{ - if (!req->bearer->blocked) - tipc_bearer_send(req->bearer, req->buf, &req->dest); + spin_unlock_bh(&req->lock); } /** @@ -307,7 +303,7 @@ static void disc_timeout(struct tipc_link_req *req) { int max_delay; - spin_lock_bh(&req->bearer->lock); + spin_lock_bh(&req->lock); /* Stop searching if only desired node has been found */ if (tipc_node(req->domain) && req->num_nodes) { @@ -322,7 +318,8 @@ static void disc_timeout(struct tipc_link_req *req) * hold at fast polling rate if don't have any associated nodes, * otherwise hold at slow polling rate */ - disc_send_msg(req); + tipc_bearer_send(req->bearer, req->buf, &req->dest); + req->timer_intv *= 2; if (req->num_nodes) @@ -334,7 +331,7 @@ static void disc_timeout(struct tipc_link_req *req) k_start_timer(&req->timer, req->timer_intv); exit: - spin_unlock_bh(&req->bearer->lock); + spin_unlock_bh(&req->lock); } /** @@ -365,10 +362,11 @@ int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest, req->domain = dest_domain; req->num_nodes = 0; req->timer_intv = TIPC_LINK_REQ_INIT; + spin_lock_init(&req->lock); k_init_timer(&req->timer, (Handler)disc_timeout, (unsigned long)req); k_start_timer(&req->timer, req->timer_intv); b_ptr->link_req = req; - disc_send_msg(req); + tipc_bearer_send(req->bearer, req->buf, &req->dest); return 0; } diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index f80d59f5a161..67cf3f935dba 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -1,7 +1,7 @@ /* * net/tipc/eth_media.c: Ethernet bearer support for TIPC * - * Copyright (c) 2001-2007, Ericsson AB + * Copyright (c) 2001-2007, 2013, Ericsson AB * Copyright (c) 2005-2008, 2011-2013, Wind River Systems * All rights reserved. * @@ -37,259 +37,11 @@ #include "core.h" #include "bearer.h" -#define MAX_ETH_MEDIA MAX_BEARERS - #define ETH_ADDR_OFFSET 4 /* message header offset of MAC address */ -/** - * struct eth_media - Ethernet bearer data structure - * @bearer: ptr to associated "generic" bearer structure - * @dev: ptr to associated Ethernet network device - * @tipc_packet_type: used in binding TIPC to Ethernet driver - * @setup: work item used when enabling bearer - * @cleanup: work item used when disabling bearer - */ -struct eth_media { - struct tipc_bearer *bearer; - struct net_device *dev; - struct packet_type tipc_packet_type; - struct work_struct setup; - struct work_struct cleanup; -}; - -static struct tipc_media eth_media_info; -static struct eth_media eth_media_array[MAX_ETH_MEDIA]; -static int eth_started; - -static int recv_notification(struct notifier_block *nb, unsigned long evt, - void *dv); -/* - * Network device notifier info - */ -static struct notifier_block notifier = { - .notifier_call = recv_notification, - .priority = 0 -}; - -/** - * eth_media_addr_set - initialize Ethernet media address structure - * - * Media-dependent "value" field stores MAC address in first 6 bytes - * and zeroes out the remaining bytes. - */ -static void eth_media_addr_set(const struct tipc_bearer *tb_ptr, - struct tipc_media_addr *a, char *mac) -{ - memcpy(a->value, mac, ETH_ALEN); - memset(a->value + ETH_ALEN, 0, sizeof(a->value) - ETH_ALEN); - a->media_id = TIPC_MEDIA_TYPE_ETH; - a->broadcast = !memcmp(mac, tb_ptr->bcast_addr.value, ETH_ALEN); -} - -/** - * send_msg - send a TIPC message out over an Ethernet interface - */ -static int send_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr, - struct tipc_media_addr *dest) -{ - struct sk_buff *clone; - struct net_device *dev; - int delta; - - clone = skb_clone(buf, GFP_ATOMIC); - if (!clone) - return 0; - - dev = ((struct eth_media *)(tb_ptr->usr_handle))->dev; - delta = dev->hard_header_len - skb_headroom(buf); - - if ((delta > 0) && - pskb_expand_head(clone, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { - kfree_skb(clone); - return 0; - } - - skb_reset_network_header(clone); - clone->dev = dev; - clone->protocol = htons(ETH_P_TIPC); - dev_hard_header(clone, dev, ETH_P_TIPC, dest->value, - dev->dev_addr, clone->len); - dev_queue_xmit(clone); - return 0; -} - -/** - * recv_msg - handle incoming TIPC message from an Ethernet interface - * - * Accept only packets explicitly sent to this node, or broadcast packets; - * ignores packets sent using Ethernet multicast, and traffic sent to other - * nodes (which can happen if interface is running in promiscuous mode). - */ -static int recv_msg(struct sk_buff *buf, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) -{ - struct eth_media *eb_ptr = (struct eth_media *)pt->af_packet_priv; - - if (!net_eq(dev_net(dev), &init_net)) { - kfree_skb(buf); - return NET_RX_DROP; - } - - if (likely(eb_ptr->bearer)) { - if (likely(buf->pkt_type <= PACKET_BROADCAST)) { - buf->next = NULL; - tipc_recv_msg(buf, eb_ptr->bearer); - return NET_RX_SUCCESS; - } - } - kfree_skb(buf); - return NET_RX_DROP; -} - -/** - * setup_media - setup association between Ethernet bearer and interface - */ -static void setup_media(struct work_struct *work) -{ - struct eth_media *eb_ptr = - container_of(work, struct eth_media, setup); - - dev_add_pack(&eb_ptr->tipc_packet_type); -} - -/** - * enable_media - attach TIPC bearer to an Ethernet interface - */ -static int enable_media(struct tipc_bearer *tb_ptr) -{ - struct net_device *dev; - struct eth_media *eb_ptr = ð_media_array[0]; - struct eth_media *stop = ð_media_array[MAX_ETH_MEDIA]; - char *driver_name = strchr((const char *)tb_ptr->name, ':') + 1; - int pending_dev = 0; - - /* Find unused Ethernet bearer structure */ - while (eb_ptr->dev) { - if (!eb_ptr->bearer) - pending_dev++; - if (++eb_ptr == stop) - return pending_dev ? -EAGAIN : -EDQUOT; - } - - /* Find device with specified name */ - dev = dev_get_by_name(&init_net, driver_name); - if (!dev) - return -ENODEV; - - /* Create Ethernet bearer for device */ - eb_ptr->dev = dev; - eb_ptr->tipc_packet_type.type = htons(ETH_P_TIPC); - eb_ptr->tipc_packet_type.dev = dev; - eb_ptr->tipc_packet_type.func = recv_msg; - eb_ptr->tipc_packet_type.af_packet_priv = eb_ptr; - INIT_LIST_HEAD(&(eb_ptr->tipc_packet_type.list)); - INIT_WORK(&eb_ptr->setup, setup_media); - schedule_work(&eb_ptr->setup); - - /* Associate TIPC bearer with Ethernet bearer */ - eb_ptr->bearer = tb_ptr; - tb_ptr->usr_handle = (void *)eb_ptr; - memset(tb_ptr->bcast_addr.value, 0, sizeof(tb_ptr->bcast_addr.value)); - memcpy(tb_ptr->bcast_addr.value, dev->broadcast, ETH_ALEN); - tb_ptr->bcast_addr.media_id = TIPC_MEDIA_TYPE_ETH; - tb_ptr->bcast_addr.broadcast = 1; - tb_ptr->mtu = dev->mtu; - tb_ptr->blocked = 0; - eth_media_addr_set(tb_ptr, &tb_ptr->addr, (char *)dev->dev_addr); - return 0; -} - -/** - * cleanup_media - break association between Ethernet bearer and interface - * - * This routine must be invoked from a work queue because it can sleep. - */ -static void cleanup_media(struct work_struct *work) -{ - struct eth_media *eb_ptr = - container_of(work, struct eth_media, cleanup); - - dev_remove_pack(&eb_ptr->tipc_packet_type); - dev_put(eb_ptr->dev); - eb_ptr->dev = NULL; -} - -/** - * disable_media - detach TIPC bearer from an Ethernet interface - * - * Mark Ethernet bearer as inactive so that incoming buffers are thrown away, - * then get worker thread to complete bearer cleanup. (Can't do cleanup - * here because cleanup code needs to sleep and caller holds spinlocks.) - */ -static void disable_media(struct tipc_bearer *tb_ptr) -{ - struct eth_media *eb_ptr = (struct eth_media *)tb_ptr->usr_handle; - - eb_ptr->bearer = NULL; - INIT_WORK(&eb_ptr->cleanup, cleanup_media); - schedule_work(&eb_ptr->cleanup); -} - -/** - * recv_notification - handle device updates from OS - * - * Change the state of the Ethernet bearer (if any) associated with the - * specified device. - */ -static int recv_notification(struct notifier_block *nb, unsigned long evt, - void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct eth_media *eb_ptr = ð_media_array[0]; - struct eth_media *stop = ð_media_array[MAX_ETH_MEDIA]; - - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - while ((eb_ptr->dev != dev)) { - if (++eb_ptr == stop) - return NOTIFY_DONE; /* couldn't find device */ - } - if (!eb_ptr->bearer) - return NOTIFY_DONE; /* bearer had been disabled */ - - eb_ptr->bearer->mtu = dev->mtu; - - switch (evt) { - case NETDEV_CHANGE: - if (netif_carrier_ok(dev)) - tipc_continue(eb_ptr->bearer); - else - tipc_block_bearer(eb_ptr->bearer); - break; - case NETDEV_UP: - tipc_continue(eb_ptr->bearer); - break; - case NETDEV_DOWN: - tipc_block_bearer(eb_ptr->bearer); - break; - case NETDEV_CHANGEMTU: - case NETDEV_CHANGEADDR: - tipc_block_bearer(eb_ptr->bearer); - tipc_continue(eb_ptr->bearer); - break; - case NETDEV_UNREGISTER: - case NETDEV_CHANGENAME: - tipc_disable_bearer(eb_ptr->bearer->name); - break; - } - return NOTIFY_OK; -} - -/** - * eth_addr2str - convert Ethernet address to string - */ -static int eth_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size) +/* convert Ethernet address to string */ +static int tipc_eth_addr2str(struct tipc_media_addr *a, char *str_buf, + int str_size) { if (str_size < 18) /* 18 = strlen("aa:bb:cc:dd:ee:ff\0") */ return 1; @@ -298,10 +50,8 @@ static int eth_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size) return 0; } -/** - * eth_str2addr - convert Ethernet address format to message header format - */ -static int eth_addr2msg(struct tipc_media_addr *a, char *msg_area) +/* convert Ethernet address format to message header format */ +static int tipc_eth_addr2msg(struct tipc_media_addr *a, char *msg_area) { memset(msg_area, 0, TIPC_MEDIA_ADDR_SIZE); msg_area[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_ETH; @@ -309,68 +59,30 @@ static int eth_addr2msg(struct tipc_media_addr *a, char *msg_area) return 0; } -/** - * eth_str2addr - convert message header address format to Ethernet format - */ -static int eth_msg2addr(const struct tipc_bearer *tb_ptr, - struct tipc_media_addr *a, char *msg_area) +/* convert message header address format to Ethernet format */ +static int tipc_eth_msg2addr(const struct tipc_bearer *tb_ptr, + struct tipc_media_addr *a, char *msg_area) { if (msg_area[TIPC_MEDIA_TYPE_OFFSET] != TIPC_MEDIA_TYPE_ETH) return 1; - eth_media_addr_set(tb_ptr, a, msg_area + ETH_ADDR_OFFSET); + tipc_l2_media_addr_set(tb_ptr, a, msg_area + ETH_ADDR_OFFSET); return 0; } -/* - * Ethernet media registration info - */ -static struct tipc_media eth_media_info = { - .send_msg = send_msg, - .enable_media = enable_media, - .disable_media = disable_media, - .addr2str = eth_addr2str, - .addr2msg = eth_addr2msg, - .msg2addr = eth_msg2addr, +/* Ethernet media registration info */ +struct tipc_media eth_media_info = { + .send_msg = tipc_l2_send_msg, + .enable_media = tipc_enable_l2_media, + .disable_media = tipc_disable_l2_media, + .addr2str = tipc_eth_addr2str, + .addr2msg = tipc_eth_addr2msg, + .msg2addr = tipc_eth_msg2addr, .priority = TIPC_DEF_LINK_PRI, .tolerance = TIPC_DEF_LINK_TOL, .window = TIPC_DEF_LINK_WIN, .type_id = TIPC_MEDIA_TYPE_ETH, + .hwaddr_len = ETH_ALEN, .name = "eth" }; -/** - * tipc_eth_media_start - activate Ethernet bearer support - * - * Register Ethernet media type with TIPC bearer code. Also register - * with OS for notifications about device state changes. - */ -int tipc_eth_media_start(void) -{ - int res; - - if (eth_started) - return -EINVAL; - - res = tipc_register_media(ð_media_info); - if (res) - return res; - - res = register_netdevice_notifier(¬ifier); - if (!res) - eth_started = 1; - return res; -} - -/** - * tipc_eth_media_stop - deactivate Ethernet bearer support - */ -void tipc_eth_media_stop(void) -{ - if (!eth_started) - return; - - flush_scheduled_work(); - unregister_netdevice_notifier(¬ifier); - eth_started = 0; -} diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c index c13989297464..844a77e25828 100644 --- a/net/tipc/ib_media.c +++ b/net/tipc/ib_media.c @@ -42,252 +42,9 @@ #include "core.h" #include "bearer.h" -#define MAX_IB_MEDIA MAX_BEARERS - -/** - * struct ib_media - Infiniband media data structure - * @bearer: ptr to associated "generic" bearer structure - * @dev: ptr to associated Infiniband network device - * @tipc_packet_type: used in binding TIPC to Infiniband driver - * @cleanup: work item used when disabling bearer - */ - -struct ib_media { - struct tipc_bearer *bearer; - struct net_device *dev; - struct packet_type tipc_packet_type; - struct work_struct setup; - struct work_struct cleanup; -}; - -static struct tipc_media ib_media_info; -static struct ib_media ib_media_array[MAX_IB_MEDIA]; -static int ib_started; - -/** - * ib_media_addr_set - initialize Infiniband media address structure - * - * Media-dependent "value" field stores MAC address in first 6 bytes - * and zeroes out the remaining bytes. - */ -static void ib_media_addr_set(const struct tipc_bearer *tb_ptr, - struct tipc_media_addr *a, char *mac) -{ - BUILD_BUG_ON(sizeof(a->value) < INFINIBAND_ALEN); - memcpy(a->value, mac, INFINIBAND_ALEN); - a->media_id = TIPC_MEDIA_TYPE_IB; - a->broadcast = !memcmp(mac, tb_ptr->bcast_addr.value, INFINIBAND_ALEN); -} - -/** - * send_msg - send a TIPC message out over an InfiniBand interface - */ -static int send_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr, - struct tipc_media_addr *dest) -{ - struct sk_buff *clone; - struct net_device *dev; - int delta; - - clone = skb_clone(buf, GFP_ATOMIC); - if (!clone) - return 0; - - dev = ((struct ib_media *)(tb_ptr->usr_handle))->dev; - delta = dev->hard_header_len - skb_headroom(buf); - - if ((delta > 0) && - pskb_expand_head(clone, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { - kfree_skb(clone); - return 0; - } - - skb_reset_network_header(clone); - clone->dev = dev; - clone->protocol = htons(ETH_P_TIPC); - dev_hard_header(clone, dev, ETH_P_TIPC, dest->value, - dev->dev_addr, clone->len); - dev_queue_xmit(clone); - return 0; -} - -/** - * recv_msg - handle incoming TIPC message from an InfiniBand interface - * - * Accept only packets explicitly sent to this node, or broadcast packets; - * ignores packets sent using InfiniBand multicast, and traffic sent to other - * nodes (which can happen if interface is running in promiscuous mode). - */ -static int recv_msg(struct sk_buff *buf, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) -{ - struct ib_media *ib_ptr = (struct ib_media *)pt->af_packet_priv; - - if (!net_eq(dev_net(dev), &init_net)) { - kfree_skb(buf); - return NET_RX_DROP; - } - - if (likely(ib_ptr->bearer)) { - if (likely(buf->pkt_type <= PACKET_BROADCAST)) { - buf->next = NULL; - tipc_recv_msg(buf, ib_ptr->bearer); - return NET_RX_SUCCESS; - } - } - kfree_skb(buf); - return NET_RX_DROP; -} - -/** - * setup_bearer - setup association between InfiniBand bearer and interface - */ -static void setup_media(struct work_struct *work) -{ - struct ib_media *ib_ptr = - container_of(work, struct ib_media, setup); - - dev_add_pack(&ib_ptr->tipc_packet_type); -} - -/** - * enable_media - attach TIPC bearer to an InfiniBand interface - */ -static int enable_media(struct tipc_bearer *tb_ptr) -{ - struct net_device *dev; - struct ib_media *ib_ptr = &ib_media_array[0]; - struct ib_media *stop = &ib_media_array[MAX_IB_MEDIA]; - char *driver_name = strchr((const char *)tb_ptr->name, ':') + 1; - int pending_dev = 0; - - /* Find unused InfiniBand bearer structure */ - while (ib_ptr->dev) { - if (!ib_ptr->bearer) - pending_dev++; - if (++ib_ptr == stop) - return pending_dev ? -EAGAIN : -EDQUOT; - } - - /* Find device with specified name */ - dev = dev_get_by_name(&init_net, driver_name); - if (!dev) - return -ENODEV; - - /* Create InfiniBand bearer for device */ - ib_ptr->dev = dev; - ib_ptr->tipc_packet_type.type = htons(ETH_P_TIPC); - ib_ptr->tipc_packet_type.dev = dev; - ib_ptr->tipc_packet_type.func = recv_msg; - ib_ptr->tipc_packet_type.af_packet_priv = ib_ptr; - INIT_LIST_HEAD(&(ib_ptr->tipc_packet_type.list)); - INIT_WORK(&ib_ptr->setup, setup_media); - schedule_work(&ib_ptr->setup); - - /* Associate TIPC bearer with InfiniBand bearer */ - ib_ptr->bearer = tb_ptr; - tb_ptr->usr_handle = (void *)ib_ptr; - memset(tb_ptr->bcast_addr.value, 0, sizeof(tb_ptr->bcast_addr.value)); - memcpy(tb_ptr->bcast_addr.value, dev->broadcast, INFINIBAND_ALEN); - tb_ptr->bcast_addr.media_id = TIPC_MEDIA_TYPE_IB; - tb_ptr->bcast_addr.broadcast = 1; - tb_ptr->mtu = dev->mtu; - tb_ptr->blocked = 0; - ib_media_addr_set(tb_ptr, &tb_ptr->addr, (char *)dev->dev_addr); - return 0; -} - -/** - * cleanup_bearer - break association between InfiniBand bearer and interface - * - * This routine must be invoked from a work queue because it can sleep. - */ -static void cleanup_bearer(struct work_struct *work) -{ - struct ib_media *ib_ptr = - container_of(work, struct ib_media, cleanup); - - dev_remove_pack(&ib_ptr->tipc_packet_type); - dev_put(ib_ptr->dev); - ib_ptr->dev = NULL; -} - -/** - * disable_media - detach TIPC bearer from an InfiniBand interface - * - * Mark InfiniBand bearer as inactive so that incoming buffers are thrown away, - * then get worker thread to complete bearer cleanup. (Can't do cleanup - * here because cleanup code needs to sleep and caller holds spinlocks.) - */ -static void disable_media(struct tipc_bearer *tb_ptr) -{ - struct ib_media *ib_ptr = (struct ib_media *)tb_ptr->usr_handle; - - ib_ptr->bearer = NULL; - INIT_WORK(&ib_ptr->cleanup, cleanup_bearer); - schedule_work(&ib_ptr->cleanup); -} - -/** - * recv_notification - handle device updates from OS - * - * Change the state of the InfiniBand bearer (if any) associated with the - * specified device. - */ -static int recv_notification(struct notifier_block *nb, unsigned long evt, - void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct ib_media *ib_ptr = &ib_media_array[0]; - struct ib_media *stop = &ib_media_array[MAX_IB_MEDIA]; - - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - while ((ib_ptr->dev != dev)) { - if (++ib_ptr == stop) - return NOTIFY_DONE; /* couldn't find device */ - } - if (!ib_ptr->bearer) - return NOTIFY_DONE; /* bearer had been disabled */ - - ib_ptr->bearer->mtu = dev->mtu; - - switch (evt) { - case NETDEV_CHANGE: - if (netif_carrier_ok(dev)) - tipc_continue(ib_ptr->bearer); - else - tipc_block_bearer(ib_ptr->bearer); - break; - case NETDEV_UP: - tipc_continue(ib_ptr->bearer); - break; - case NETDEV_DOWN: - tipc_block_bearer(ib_ptr->bearer); - break; - case NETDEV_CHANGEMTU: - case NETDEV_CHANGEADDR: - tipc_block_bearer(ib_ptr->bearer); - tipc_continue(ib_ptr->bearer); - break; - case NETDEV_UNREGISTER: - case NETDEV_CHANGENAME: - tipc_disable_bearer(ib_ptr->bearer->name); - break; - } - return NOTIFY_OK; -} - -static struct notifier_block notifier = { - .notifier_call = recv_notification, - .priority = 0, -}; - -/** - * ib_addr2str - convert InfiniBand address to string - */ -static int ib_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size) +/* convert InfiniBand address to string */ +static int tipc_ib_addr2str(struct tipc_media_addr *a, char *str_buf, + int str_size) { if (str_size < 60) /* 60 = 19 * strlen("xx:") + strlen("xx\0") */ return 1; @@ -297,10 +54,8 @@ static int ib_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size) return 0; } -/** - * ib_addr2msg - convert InfiniBand address format to message header format - */ -static int ib_addr2msg(struct tipc_media_addr *a, char *msg_area) +/* convert InfiniBand address format to message header format */ +static int tipc_ib_addr2msg(struct tipc_media_addr *a, char *msg_area) { memset(msg_area, 0, TIPC_MEDIA_ADDR_SIZE); msg_area[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_IB; @@ -308,65 +63,27 @@ static int ib_addr2msg(struct tipc_media_addr *a, char *msg_area) return 0; } -/** - * ib_msg2addr - convert message header address format to InfiniBand format - */ -static int ib_msg2addr(const struct tipc_bearer *tb_ptr, - struct tipc_media_addr *a, char *msg_area) +/* convert message header address format to InfiniBand format */ +static int tipc_ib_msg2addr(const struct tipc_bearer *tb_ptr, + struct tipc_media_addr *a, char *msg_area) { - ib_media_addr_set(tb_ptr, a, msg_area); + tipc_l2_media_addr_set(tb_ptr, a, msg_area); return 0; } -/* - * InfiniBand media registration info - */ -static struct tipc_media ib_media_info = { - .send_msg = send_msg, - .enable_media = enable_media, - .disable_media = disable_media, - .addr2str = ib_addr2str, - .addr2msg = ib_addr2msg, - .msg2addr = ib_msg2addr, +/* InfiniBand media registration info */ +struct tipc_media ib_media_info = { + .send_msg = tipc_l2_send_msg, + .enable_media = tipc_enable_l2_media, + .disable_media = tipc_disable_l2_media, + .addr2str = tipc_ib_addr2str, + .addr2msg = tipc_ib_addr2msg, + .msg2addr = tipc_ib_msg2addr, .priority = TIPC_DEF_LINK_PRI, .tolerance = TIPC_DEF_LINK_TOL, .window = TIPC_DEF_LINK_WIN, .type_id = TIPC_MEDIA_TYPE_IB, + .hwaddr_len = INFINIBAND_ALEN, .name = "ib" }; -/** - * tipc_ib_media_start - activate InfiniBand bearer support - * - * Register InfiniBand media type with TIPC bearer code. Also register - * with OS for notifications about device state changes. - */ -int tipc_ib_media_start(void) -{ - int res; - - if (ib_started) - return -EINVAL; - - res = tipc_register_media(&ib_media_info); - if (res) - return res; - - res = register_netdevice_notifier(¬ifier); - if (!res) - ib_started = 1; - return res; -} - -/** - * tipc_ib_media_stop - deactivate InfiniBand bearer support - */ -void tipc_ib_media_stop(void) -{ - if (!ib_started) - return; - - flush_scheduled_work(); - unregister_netdevice_notifier(¬ifier); - ib_started = 0; -} diff --git a/net/tipc/link.c b/net/tipc/link.c index 13b987745820..da6018beb6eb 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1,7 +1,7 @@ /* * net/tipc/link.c: TIPC link code * - * Copyright (c) 1996-2007, 2012, Ericsson AB + * Copyright (c) 1996-2007, 2012-2014, Ericsson AB * Copyright (c) 2004-2007, 2010-2013, Wind River Systems * All rights reserved. * @@ -78,8 +78,8 @@ static const char *link_unk_evt = "Unknown link event "; static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, struct sk_buff *buf); static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf); -static int link_recv_changeover_msg(struct tipc_link **l_ptr, - struct sk_buff **buf); +static int tipc_link_tunnel_rcv(struct tipc_link **l_ptr, + struct sk_buff **buf); static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance); static int link_send_sections_long(struct tipc_port *sender, struct iovec const *msg_sect, @@ -87,7 +87,6 @@ static int link_send_sections_long(struct tipc_port *sender, static void link_state_event(struct tipc_link *l_ptr, u32 event); static void link_reset_statistics(struct tipc_link *l_ptr); static void link_print(struct tipc_link *l_ptr, const char *str); -static void link_start(struct tipc_link *l_ptr); static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf); static void tipc_link_send_sync(struct tipc_link *l); static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf); @@ -278,9 +277,11 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, tipc_node_attach_link(n_ptr, l_ptr); - k_init_timer(&l_ptr->timer, (Handler)link_timeout, (unsigned long)l_ptr); + k_init_timer(&l_ptr->timer, (Handler)link_timeout, + (unsigned long)l_ptr); list_add_tail(&l_ptr->link_list, &b_ptr->links); - tipc_k_signal((Handler)link_start, (unsigned long)l_ptr); + + link_state_event(l_ptr, STARTING_EVT); return l_ptr; } @@ -305,19 +306,13 @@ void tipc_link_delete(struct tipc_link *l_ptr) tipc_node_lock(l_ptr->owner); tipc_link_reset(l_ptr); tipc_node_detach_link(l_ptr->owner, l_ptr); - tipc_link_stop(l_ptr); + tipc_link_purge_queues(l_ptr); list_del_init(&l_ptr->link_list); tipc_node_unlock(l_ptr->owner); k_term_timer(&l_ptr->timer); kfree(l_ptr); } -static void link_start(struct tipc_link *l_ptr) -{ - tipc_node_lock(l_ptr->owner); - link_state_event(l_ptr, STARTING_EVT); - tipc_node_unlock(l_ptr->owner); -} /** * link_schedule_port - schedule port for deferred sending @@ -386,14 +381,7 @@ exit: */ static void link_release_outqueue(struct tipc_link *l_ptr) { - struct sk_buff *buf = l_ptr->first_out; - struct sk_buff *next; - - while (buf) { - next = buf->next; - kfree_skb(buf); - buf = next; - } + kfree_skb_list(l_ptr->first_out); l_ptr->first_out = NULL; l_ptr->out_queue_size = 0; } @@ -410,37 +398,20 @@ void tipc_link_reset_fragments(struct tipc_link *l_ptr) } /** - * tipc_link_stop - purge all inbound and outbound messages associated with link + * tipc_link_purge_queues - purge all pkt queues associated with link * @l_ptr: pointer to link */ -void tipc_link_stop(struct tipc_link *l_ptr) +void tipc_link_purge_queues(struct tipc_link *l_ptr) { - struct sk_buff *buf; - struct sk_buff *next; - - buf = l_ptr->oldest_deferred_in; - while (buf) { - next = buf->next; - kfree_skb(buf); - buf = next; - } - - buf = l_ptr->first_out; - while (buf) { - next = buf->next; - kfree_skb(buf); - buf = next; - } - + kfree_skb_list(l_ptr->oldest_deferred_in); + kfree_skb_list(l_ptr->first_out); tipc_link_reset_fragments(l_ptr); - kfree_skb(l_ptr->proto_msg_queue); l_ptr->proto_msg_queue = NULL; } void tipc_link_reset(struct tipc_link *l_ptr) { - struct sk_buff *buf; u32 prev_state = l_ptr->state; u32 checkpoint = l_ptr->next_in_no; int was_active_link = tipc_link_is_active(l_ptr); @@ -461,8 +432,7 @@ void tipc_link_reset(struct tipc_link *l_ptr) tipc_node_link_down(l_ptr->owner, l_ptr); tipc_bearer_remove_dest(l_ptr->b_ptr, l_ptr->addr); - if (was_active_link && tipc_node_active_links(l_ptr->owner) && - l_ptr->owner->permit_changeover) { + if (was_active_link && tipc_node_active_links(l_ptr->owner)) { l_ptr->reset_checkpoint = checkpoint; l_ptr->exp_msg_count = START_CHANGEOVER; } @@ -471,12 +441,7 @@ void tipc_link_reset(struct tipc_link *l_ptr) link_release_outqueue(l_ptr); kfree_skb(l_ptr->proto_msg_queue); l_ptr->proto_msg_queue = NULL; - buf = l_ptr->oldest_deferred_in; - while (buf) { - struct sk_buff *next = buf->next; - kfree_skb(buf); - buf = next; - } + kfree_skb_list(l_ptr->oldest_deferred_in); if (!list_empty(&l_ptr->waiting_ports)) tipc_link_wakeup_ports(l_ptr, 1); @@ -517,10 +482,11 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) if (!l_ptr->started && (event != STARTING_EVT)) return; /* Not yet. */ - if (link_blocked(l_ptr)) { + /* Check whether changeover is going on */ + if (l_ptr->exp_msg_count) { if (event == TIMEOUT_EVT) link_set_timer(l_ptr, cont_intv); - return; /* Changeover going on */ + return; } switch (l_ptr->state) { @@ -790,8 +756,7 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) return link_send_long_buf(l_ptr, buf); /* Packet can be queued or sent. */ - if (likely(!tipc_bearer_blocked(l_ptr->b_ptr) && - !link_congested(l_ptr))) { + if (likely(!link_congested(l_ptr))) { link_add_to_outqueue(l_ptr, buf, msg); tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr); @@ -957,14 +922,13 @@ static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf, if (likely(!link_congested(l_ptr))) { if (likely(msg_size(msg) <= l_ptr->max_pkt)) { - if (likely(!tipc_bearer_blocked(l_ptr->b_ptr))) { - link_add_to_outqueue(l_ptr, buf, msg); - tipc_bearer_send(l_ptr->b_ptr, buf, - &l_ptr->media_addr); - l_ptr->unacked_window = 0; - return res; - } - } else + link_add_to_outqueue(l_ptr, buf, msg); + tipc_bearer_send(l_ptr->b_ptr, buf, + &l_ptr->media_addr); + l_ptr->unacked_window = 0; + return res; + } + else *used_max_pkt = l_ptr->max_pkt; } return tipc_link_send_buf(l_ptr, buf); /* All other cases */ @@ -1013,8 +977,7 @@ exit: } /* Exit if link (or bearer) is congested */ - if (link_congested(l_ptr) || - tipc_bearer_blocked(l_ptr->b_ptr)) { + if (link_congested(l_ptr)) { res = link_schedule_port(l_ptr, sender->ref, res); goto exit; @@ -1127,10 +1090,7 @@ again: if (copy_from_user(buf->data + fragm_crs, sect_crs, sz)) { res = -EFAULT; error: - for (; buf_chain; buf_chain = buf) { - buf = buf_chain->next; - kfree_skb(buf_chain); - } + kfree_skb_list(buf_chain); return res; } sect_crs += sz; @@ -1180,18 +1140,12 @@ error: if (l_ptr->max_pkt < max_pkt) { sender->max_pkt = l_ptr->max_pkt; tipc_node_unlock(node); - for (; buf_chain; buf_chain = buf) { - buf = buf_chain->next; - kfree_skb(buf_chain); - } + kfree_skb_list(buf_chain); goto again; } } else { reject: - for (; buf_chain; buf_chain = buf) { - buf = buf_chain->next; - kfree_skb(buf_chain); - } + kfree_skb_list(buf_chain); return tipc_port_reject_sections(sender, hdr, msg_sect, len, TIPC_ERR_NO_NODE); } @@ -1209,7 +1163,7 @@ reject: /* * tipc_link_push_packet: Push one unsent packet to the media */ -u32 tipc_link_push_packet(struct tipc_link *l_ptr) +static u32 tipc_link_push_packet(struct tipc_link *l_ptr) { struct sk_buff *buf = l_ptr->first_out; u32 r_q_size = l_ptr->retransm_queue_size; @@ -1281,9 +1235,6 @@ void tipc_link_push_queue(struct tipc_link *l_ptr) { u32 res; - if (tipc_bearer_blocked(l_ptr->b_ptr)) - return; - do { res = tipc_link_push_packet(l_ptr); } while (!res); @@ -1370,26 +1321,15 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf, msg = buf_msg(buf); - if (tipc_bearer_blocked(l_ptr->b_ptr)) { - if (l_ptr->retransm_queue_size == 0) { - l_ptr->retransm_queue_head = msg_seqno(msg); - l_ptr->retransm_queue_size = retransmits; - } else { - pr_err("Unexpected retransmit on link %s (qsize=%d)\n", - l_ptr->name, l_ptr->retransm_queue_size); + /* Detect repeated retransmit failures */ + if (l_ptr->last_retransmitted == msg_seqno(msg)) { + if (++l_ptr->stale_count > 100) { + link_retransmit_failure(l_ptr, buf); + return; } - return; } else { - /* Detect repeated retransmit failures on unblocked bearer */ - if (l_ptr->last_retransmitted == msg_seqno(msg)) { - if (++l_ptr->stale_count > 100) { - link_retransmit_failure(l_ptr, buf); - return; - } - } else { - l_ptr->last_retransmitted = msg_seqno(msg); - l_ptr->stale_count = 1; - } + l_ptr->last_retransmitted = msg_seqno(msg); + l_ptr->stale_count = 1; } while (retransmits && (buf != l_ptr->next_out) && buf) { @@ -1451,6 +1391,12 @@ static int link_recv_buf_validate(struct sk_buff *buf) u32 hdr_size; u32 min_hdr_size; + /* If this packet comes from the defer queue, the skb has already + * been validated + */ + if (unlikely(TIPC_SKB_CB(buf)->deferred)) + return 1; + if (unlikely(buf->len < MIN_H_SIZE)) return 0; @@ -1476,14 +1422,14 @@ static int link_recv_buf_validate(struct sk_buff *buf) } /** - * tipc_recv_msg - process TIPC messages arriving from off-node + * tipc_rcv - process TIPC packets/messages arriving from off-node * @head: pointer to message buffer chain * @tb_ptr: pointer to bearer message arrived on * * Invoked with no locks held. Bearer pointer must point to a valid bearer * structure (i.e. cannot be NULL), but bearer can be inactive. */ -void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) +void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) { read_lock_bh(&tipc_net_lock); while (head) { @@ -1658,7 +1604,7 @@ deliver: continue; case CHANGEOVER_PROTOCOL: type = msg_type(msg); - if (link_recv_changeover_msg(&l_ptr, &buf)) { + if (tipc_link_tunnel_rcv(&l_ptr, &buf)) { msg = buf_msg(buf); seq_no = msg_seqno(msg); if (type == ORIGINAL_MSG) @@ -1763,6 +1709,7 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, &l_ptr->newest_deferred_in, buf)) { l_ptr->deferred_inqueue_sz++; l_ptr->stats.deferred_recv++; + TIPC_SKB_CB(buf)->deferred = true; if ((l_ptr->deferred_inqueue_sz % 16) == 1) tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); } else @@ -1787,7 +1734,8 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, l_ptr->proto_msg_queue = NULL; } - if (link_blocked(l_ptr)) + /* Don't send protocol message during link changeover */ + if (l_ptr->exp_msg_count) return; /* Abort non-RESET send if communication with node is prohibited */ @@ -1862,12 +1810,6 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg)); buf->priority = TC_PRIO_CONTROL; - /* Defer message if bearer is already blocked */ - if (tipc_bearer_blocked(l_ptr->b_ptr)) { - l_ptr->proto_msg_queue = buf; - return; - } - tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr); l_ptr->unacked_window = 0; kfree_skb(buf); @@ -1886,7 +1828,8 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) u32 msg_tol; struct tipc_msg *msg = buf_msg(buf); - if (link_blocked(l_ptr)) + /* Discard protocol message during link changeover */ + if (l_ptr->exp_msg_count) goto exit; /* record unnumbered packet arrival (force mismatch on next timeout) */ @@ -1896,8 +1839,6 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) if (tipc_own_addr > msg_prevnode(msg)) l_ptr->b_ptr->net_plane = msg_net_plane(msg); - l_ptr->owner->permit_changeover = msg_redundant_link(msg); - switch (msg_type(msg)) { case RESET_MSG: @@ -2013,13 +1954,13 @@ exit: } -/* - * tipc_link_tunnel(): Send one message via a link belonging to - * another bearer. Owner node is locked. +/* tipc_link_tunnel_xmit(): Tunnel one packet via a link belonging to + * a different bearer. Owner node is locked. */ -static void tipc_link_tunnel(struct tipc_link *l_ptr, - struct tipc_msg *tunnel_hdr, struct tipc_msg *msg, - u32 selector) +static void tipc_link_tunnel_xmit(struct tipc_link *l_ptr, + struct tipc_msg *tunnel_hdr, + struct tipc_msg *msg, + u32 selector) { struct tipc_link *tunnel; struct sk_buff *buf; @@ -2042,12 +1983,13 @@ static void tipc_link_tunnel(struct tipc_link *l_ptr, } - -/* - * changeover(): Send whole message queue via the remaining link - * Owner node is locked. +/* tipc_link_failover_send_queue(): A link has gone down, but a second + * link is still active. We can do failover. Tunnel the failing link's + * whole send queue via the remaining link. This way, we don't lose + * any packets, and sequence order is preserved for subsequent traffic + * sent over the remaining link. Owner node is locked. */ -void tipc_link_changeover(struct tipc_link *l_ptr) +void tipc_link_failover_send_queue(struct tipc_link *l_ptr) { u32 msgcount = l_ptr->out_queue_size; struct sk_buff *crs = l_ptr->first_out; @@ -2058,11 +2000,6 @@ void tipc_link_changeover(struct tipc_link *l_ptr) if (!tunnel) return; - if (!l_ptr->owner->permit_changeover) { - pr_warn("%speer did not permit changeover\n", link_co_err); - return; - } - tipc_msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL, ORIGINAL_MSG, INT_H_SIZE, l_ptr->addr); msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); @@ -2096,20 +2033,30 @@ void tipc_link_changeover(struct tipc_link *l_ptr) msgcount = msg_msgcnt(msg); while (msgcount--) { msg_set_seqno(m, msg_seqno(msg)); - tipc_link_tunnel(l_ptr, &tunnel_hdr, m, - msg_link_selector(m)); + tipc_link_tunnel_xmit(l_ptr, &tunnel_hdr, m, + msg_link_selector(m)); pos += align(msg_size(m)); m = (struct tipc_msg *)pos; } } else { - tipc_link_tunnel(l_ptr, &tunnel_hdr, msg, - msg_link_selector(msg)); + tipc_link_tunnel_xmit(l_ptr, &tunnel_hdr, msg, + msg_link_selector(msg)); } crs = crs->next; } } -void tipc_link_send_duplicate(struct tipc_link *l_ptr, struct tipc_link *tunnel) +/* tipc_link_dup_send_queue(): A second link has become active. Tunnel a + * duplicate of the first link's send queue via the new link. This way, we + * are guaranteed that currently queued packets from a socket are delivered + * before future traffic from the same socket, even if this is using the + * new link. The last arriving copy of each duplicate packet is dropped at + * the receiving end by the regular protocol check, so packet cardinality + * and sequence order is preserved per sender/receiver socket pair. + * Owner node is locked. + */ +void tipc_link_dup_send_queue(struct tipc_link *l_ptr, + struct tipc_link *tunnel) { struct sk_buff *iter; struct tipc_msg tunnel_hdr; @@ -2165,12 +2112,14 @@ static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos) return eb; } -/* - * link_recv_changeover_msg(): Receive tunneled packet sent - * via other link. Node is locked. Return extracted buffer. +/* tipc_link_tunnel_rcv(): Receive a tunneled packet, sent + * via other link as result of a failover (ORIGINAL_MSG) or + * a new active link (DUPLICATE_MSG). Failover packets are + * returned to the active link for delivery upwards. + * Owner node is locked. */ -static int link_recv_changeover_msg(struct tipc_link **l_ptr, - struct sk_buff **buf) +static int tipc_link_tunnel_rcv(struct tipc_link **l_ptr, + struct sk_buff **buf) { struct sk_buff *tunnel_buf = *buf; struct tipc_link *dest_link; @@ -2307,11 +2256,7 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf) fragm = tipc_buf_acquire(fragm_sz + INT_H_SIZE); if (fragm == NULL) { kfree_skb(buf); - while (buf_chain) { - buf = buf_chain; - buf_chain = buf_chain->next; - kfree_skb(buf); - } + kfree_skb_list(buf_chain); return -ENOMEM; } msg_set_size(&fragm_hdr, fragm_sz + INT_H_SIZE); diff --git a/net/tipc/link.h b/net/tipc/link.h index 8a6c1026644d..3b6aa65b608c 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -112,7 +112,6 @@ struct tipc_stats { * @continuity_interval: link continuity testing interval [in ms] * @abort_limit: # of unacknowledged continuity probes needed to reset link * @state: current state of link FSM - * @blocked: indicates if link has been administratively blocked * @fsm_msg_cnt: # of protocol messages link FSM has sent in current state * @proto_msg: template for control messages generated by link * @pmsg: convenience pointer to "proto_msg" field @@ -162,7 +161,6 @@ struct tipc_link { u32 continuity_interval; u32 abort_limit; int state; - int blocked; u32 fsm_msg_cnt; struct { unchar hdr[INT_H_SIZE]; @@ -218,16 +216,20 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, struct tipc_bearer *b_ptr, const struct tipc_media_addr *media_addr); void tipc_link_delete(struct tipc_link *l_ptr); -void tipc_link_changeover(struct tipc_link *l_ptr); -void tipc_link_send_duplicate(struct tipc_link *l_ptr, struct tipc_link *dest); +void tipc_link_failover_send_queue(struct tipc_link *l_ptr); +void tipc_link_dup_send_queue(struct tipc_link *l_ptr, + struct tipc_link *dest); void tipc_link_reset_fragments(struct tipc_link *l_ptr); int tipc_link_is_up(struct tipc_link *l_ptr); int tipc_link_is_active(struct tipc_link *l_ptr); -u32 tipc_link_push_packet(struct tipc_link *l_ptr); -void tipc_link_stop(struct tipc_link *l_ptr); -struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space, u16 cmd); -struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_space); -struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_space); +void tipc_link_purge_queues(struct tipc_link *l_ptr); +struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, + int req_tlv_space, + u16 cmd); +struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, + int req_tlv_space); +struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, + int req_tlv_space); void tipc_link_reset(struct tipc_link *l_ptr); int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector); void tipc_link_send_names(struct list_head *message_list, u32 dest); @@ -312,11 +314,6 @@ static inline int link_reset_reset(struct tipc_link *l_ptr) return l_ptr->state == RESET_RESET; } -static inline int link_blocked(struct tipc_link *l_ptr) -{ - return l_ptr->exp_msg_count || l_ptr->blocked; -} - static inline int link_congested(struct tipc_link *l_ptr) { return l_ptr->out_queue_size >= l_ptr->queue_limit[0]; diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 09dcd54b04e1..92a1533af4e0 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -148,8 +148,7 @@ static struct publication *publ_create(u32 type, u32 lower, u32 upper, */ static struct sub_seq *tipc_subseq_alloc(u32 cnt) { - struct sub_seq *sseq = kcalloc(cnt, sizeof(struct sub_seq), GFP_ATOMIC); - return sseq; + return kcalloc(cnt, sizeof(struct sub_seq), GFP_ATOMIC); } /** diff --git a/net/tipc/node.c b/net/tipc/node.c index 25100c0a6fe8..efe4d41bf11b 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -162,7 +162,7 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) pr_info("New link <%s> becomes standby\n", l_ptr->name); return; } - tipc_link_send_duplicate(active[0], l_ptr); + tipc_link_dup_send_queue(active[0], l_ptr); if (l_ptr->priority == active[0]->priority) { active[0] = l_ptr; return; @@ -225,7 +225,7 @@ void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr) if (active[0] == l_ptr) node_select_active_links(n_ptr); if (tipc_node_is_up(n_ptr)) - tipc_link_changeover(l_ptr); + tipc_link_failover_send_queue(l_ptr); else node_lost_contact(n_ptr); } @@ -235,11 +235,6 @@ int tipc_node_active_links(struct tipc_node *n_ptr) return n_ptr->active_links[0] != NULL; } -int tipc_node_redundant_links(struct tipc_node *n_ptr) -{ - return n_ptr->working_links > 1; -} - int tipc_node_is_up(struct tipc_node *n_ptr) { return tipc_node_active_links(n_ptr); @@ -291,11 +286,7 @@ static void node_lost_contact(struct tipc_node *n_ptr) /* Flush broadcast link info associated with lost node */ if (n_ptr->bclink.recv_permitted) { - while (n_ptr->bclink.deferred_head) { - struct sk_buff *buf = n_ptr->bclink.deferred_head; - n_ptr->bclink.deferred_head = buf->next; - kfree_skb(buf); - } + kfree_skb_list(n_ptr->bclink.deferred_head); n_ptr->bclink.deferred_size = 0; if (n_ptr->bclink.reasm_head) { diff --git a/net/tipc/node.h b/net/tipc/node.h index e5e96c04e167..63e2e8ead2fe 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -64,7 +64,6 @@ * @working_links: number of working links to node (both active and standby) * @block_setup: bit mask of conditions preventing link establishment to node * @link_cnt: number of links to node - * @permit_changeover: non-zero if node has redundant links to this system * @signature: node instance identifier * @bclink: broadcast-related info * @acked: sequence # of last outbound b'cast message acknowledged by node @@ -89,7 +88,6 @@ struct tipc_node { int link_cnt; int working_links; int block_setup; - int permit_changeover; u32 signature; struct { u32 acked; @@ -115,7 +113,6 @@ void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr); void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr); int tipc_node_active_links(struct tipc_node *n_ptr); -int tipc_node_redundant_links(struct tipc_node *n_ptr); int tipc_node_is_up(struct tipc_node *n_ptr); struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space); struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space); diff --git a/net/tipc/port.c b/net/tipc/port.c index d43f3182b1d4..b742b2654525 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -817,17 +817,14 @@ exit: */ int __tipc_disconnect(struct tipc_port *tp_ptr) { - int res; - if (tp_ptr->connected) { tp_ptr->connected = 0; /* let timer expire on it's own to avoid deadlock! */ tipc_nodesub_unsubscribe(&tp_ptr->subscription); - res = 0; - } else { - res = -ENOTCONN; + return 0; } - return res; + + return -ENOTCONN; } /* diff --git a/net/tipc/server.c b/net/tipc/server.c index fd3fa57a410e..b635ca347a87 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -55,7 +55,7 @@ * @usr_data: user-specified field * @rx_action: what to do when connection socket is active * @outqueue: pointer to first outbound message in queue - * @outqueue_lock: controll access to the outqueue + * @outqueue_lock: control access to the outqueue * @outqueue: list of connection objects for its server * @swork: send work item */ diff --git a/net/tipc/socket.c b/net/tipc/socket.c index e741416d1d24..aab4948f0aff 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -55,9 +55,6 @@ struct tipc_sock { #define tipc_sk(sk) ((struct tipc_sock *)(sk)) #define tipc_sk_port(sk) (tipc_sk(sk)->p) -#define tipc_rx_ready(sock) (!skb_queue_empty(&sock->sk->sk_receive_queue) || \ - (sock->state == SS_DISCONNECTING)) - static int backlog_rcv(struct sock *sk, struct sk_buff *skb); static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf); static void wakeupdispatch(struct tipc_port *tport); @@ -239,7 +236,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, int tipc_sock_create_local(int type, struct socket **res) { int rc; - struct sock *sk; rc = sock_create_lite(AF_TIPC, type, 0, res); if (rc < 0) { @@ -248,8 +244,6 @@ int tipc_sock_create_local(int type, struct socket **res) } tipc_sk_create(&init_net, *res, 0, 1); - sk = (*res)->sk; - return 0; } @@ -570,6 +564,31 @@ static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m) return 0; } +static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) +{ + struct sock *sk = sock->sk; + struct tipc_port *tport = tipc_sk_port(sk); + DEFINE_WAIT(wait); + int done; + + do { + int err = sock_error(sk); + if (err) + return err; + if (sock->state == SS_DISCONNECTING) + return -EPIPE; + if (!*timeo_p) + return -EAGAIN; + if (signal_pending(current)) + return sock_intr_errno(*timeo_p); + + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + done = sk_wait_event(sk, timeo_p, !tport->congested); + finish_wait(sk_sleep(sk), &wait); + } while (!done); + return 0; +} + /** * send_msg - send message in connectionless manner * @iocb: if NULL, indicates that socket lock is already held @@ -589,9 +608,9 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct tipc_port *tport = tipc_sk_port(sk); - struct sockaddr_tipc *dest = (struct sockaddr_tipc *)m->msg_name; + DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); int needs_conn; - long timeout_val; + long timeo; int res = -EINVAL; if (unlikely(!dest)) @@ -628,8 +647,7 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, reject_rx_queue(sk); } - timeout_val = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); - + timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); do { if (dest->addrtype == TIPC_ADDR_NAME) { res = dest_name_check(dest, m); @@ -663,14 +681,9 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, sock->state = SS_CONNECTING; break; } - if (timeout_val <= 0L) { - res = timeout_val ? timeout_val : -EWOULDBLOCK; + res = tipc_wait_for_sndmsg(sock, &timeo); + if (res) break; - } - release_sock(sk); - timeout_val = wait_event_interruptible_timeout(*sk_sleep(sk), - !tport->congested, timeout_val); - lock_sock(sk); } while (1); exit: @@ -679,6 +692,34 @@ exit: return res; } +static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) +{ + struct sock *sk = sock->sk; + struct tipc_port *tport = tipc_sk_port(sk); + DEFINE_WAIT(wait); + int done; + + do { + int err = sock_error(sk); + if (err) + return err; + if (sock->state == SS_DISCONNECTING) + return -EPIPE; + else if (sock->state != SS_CONNECTED) + return -ENOTCONN; + if (!*timeo_p) + return -EAGAIN; + if (signal_pending(current)) + return sock_intr_errno(*timeo_p); + + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + done = sk_wait_event(sk, timeo_p, + (!tport->congested || !tport->connected)); + finish_wait(sk_sleep(sk), &wait); + } while (!done); + return 0; +} + /** * send_packet - send a connection-oriented message * @iocb: if NULL, indicates that socket lock is already held @@ -695,9 +736,9 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct tipc_port *tport = tipc_sk_port(sk); - struct sockaddr_tipc *dest = (struct sockaddr_tipc *)m->msg_name; - long timeout_val; - int res; + DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + int res = -EINVAL; + long timeo; /* Handle implied connection establishment */ if (unlikely(dest)) @@ -709,30 +750,24 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, if (iocb) lock_sock(sk); - timeout_val = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); + if (unlikely(sock->state != SS_CONNECTED)) { + if (sock->state == SS_DISCONNECTING) + res = -EPIPE; + else + res = -ENOTCONN; + goto exit; + } + timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); do { - if (unlikely(sock->state != SS_CONNECTED)) { - if (sock->state == SS_DISCONNECTING) - res = -EPIPE; - else - res = -ENOTCONN; - break; - } - res = tipc_send(tport->ref, m->msg_iov, total_len); if (likely(res != -ELINKCONG)) break; - if (timeout_val <= 0L) { - res = timeout_val ? timeout_val : -EWOULDBLOCK; + res = tipc_wait_for_sndpkt(sock, &timeo); + if (res) break; - } - release_sock(sk); - timeout_val = wait_event_interruptible_timeout(*sk_sleep(sk), - (!tport->congested || !tport->connected), timeout_val); - lock_sock(sk); } while (1); - +exit: if (iocb) release_sock(sk); return res; @@ -770,16 +805,11 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, /* Handle special cases where there is no connection */ if (unlikely(sock->state != SS_CONNECTED)) { - if (sock->state == SS_UNCONNECTED) { + if (sock->state == SS_UNCONNECTED) res = send_packet(NULL, sock, m, total_len); - goto exit; - } else if (sock->state == SS_DISCONNECTING) { - res = -EPIPE; - goto exit; - } else { - res = -ENOTCONN; - goto exit; - } + else + res = sock->state == SS_DISCONNECTING ? -EPIPE : -ENOTCONN; + goto exit; } if (unlikely(m->msg_name)) { @@ -876,7 +906,7 @@ static int auto_connect(struct socket *sock, struct tipc_msg *msg) */ static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) { - struct sockaddr_tipc *addr = (struct sockaddr_tipc *)m->msg_name; + DECLARE_SOCKADDR(struct sockaddr_tipc *, addr, m->msg_name); if (addr) { addr->family = AF_TIPC; @@ -961,6 +991,37 @@ static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg, return 0; } +static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo) +{ + struct sock *sk = sock->sk; + DEFINE_WAIT(wait); + int err; + + for (;;) { + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + if (skb_queue_empty(&sk->sk_receive_queue)) { + if (sock->state == SS_DISCONNECTING) { + err = -ENOTCONN; + break; + } + release_sock(sk); + timeo = schedule_timeout(timeo); + lock_sock(sk); + } + err = 0; + if (!skb_queue_empty(&sk->sk_receive_queue)) + break; + err = sock_intr_errno(timeo); + if (signal_pending(current)) + break; + err = -EAGAIN; + if (!timeo) + break; + } + finish_wait(sk_sleep(sk), &wait); + return err; +} + /** * recv_msg - receive packet-oriented message * @iocb: (unused) @@ -980,7 +1041,7 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock, struct tipc_port *tport = tipc_sk_port(sk); struct sk_buff *buf; struct tipc_msg *msg; - long timeout; + long timeo; unsigned int sz; u32 err; int res; @@ -996,25 +1057,13 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock, goto exit; } - timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); restart: /* Look for a message in receive queue; wait if necessary */ - while (skb_queue_empty(&sk->sk_receive_queue)) { - if (sock->state == SS_DISCONNECTING) { - res = -ENOTCONN; - goto exit; - } - if (timeout <= 0L) { - res = timeout ? timeout : -EWOULDBLOCK; - goto exit; - } - release_sock(sk); - timeout = wait_event_interruptible_timeout(*sk_sleep(sk), - tipc_rx_ready(sock), - timeout); - lock_sock(sk); - } + res = tipc_wait_for_rcvmsg(sock, timeo); + if (res) + goto exit; /* Look at first message in receive queue */ buf = skb_peek(&sk->sk_receive_queue); @@ -1086,7 +1135,7 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock, struct tipc_port *tport = tipc_sk_port(sk); struct sk_buff *buf; struct tipc_msg *msg; - long timeout; + long timeo; unsigned int sz; int sz_to_copy, target, needed; int sz_copied = 0; @@ -1099,31 +1148,19 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock, lock_sock(sk); - if (unlikely((sock->state == SS_UNCONNECTED))) { + if (unlikely(sock->state == SS_UNCONNECTED)) { res = -ENOTCONN; goto exit; } target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len); - timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); restart: /* Look for a message in receive queue; wait if necessary */ - while (skb_queue_empty(&sk->sk_receive_queue)) { - if (sock->state == SS_DISCONNECTING) { - res = -ENOTCONN; - goto exit; - } - if (timeout <= 0L) { - res = timeout ? timeout : -EWOULDBLOCK; - goto exit; - } - release_sock(sk); - timeout = wait_event_interruptible_timeout(*sk_sleep(sk), - tipc_rx_ready(sock), - timeout); - lock_sock(sk); - } + res = tipc_wait_for_rcvmsg(sock, timeo); + if (res) + goto exit; /* Look at first message in receive queue */ buf = skb_peek(&sk->sk_receive_queue); @@ -1327,14 +1364,12 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); - unsigned int limit; if (msg_connected(msg)) - limit = sysctl_tipc_rmem[2]; - else - limit = sk->sk_rcvbuf >> TIPC_CRITICAL_IMPORTANCE << - msg_importance(msg); - return limit; + return sysctl_tipc_rmem[2]; + + return sk->sk_rcvbuf >> TIPC_CRITICAL_IMPORTANCE << + msg_importance(msg); } /** @@ -1448,6 +1483,28 @@ static void wakeupdispatch(struct tipc_port *tport) sk->sk_write_space(sk); } +static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) +{ + struct sock *sk = sock->sk; + DEFINE_WAIT(wait); + int done; + + do { + int err = sock_error(sk); + if (err) + return err; + if (!*timeo_p) + return -ETIMEDOUT; + if (signal_pending(current)) + return sock_intr_errno(*timeo_p); + + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + done = sk_wait_event(sk, timeo_p, sock->state != SS_CONNECTING); + finish_wait(sk_sleep(sk), &wait); + } while (!done); + return 0; +} + /** * connect - establish a connection to another TIPC port * @sock: socket structure @@ -1463,7 +1520,8 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, struct sock *sk = sock->sk; struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest; struct msghdr m = {NULL,}; - unsigned int timeout; + long timeout = (flags & O_NONBLOCK) ? 0 : tipc_sk(sk)->conn_timeout; + socket_state previous; int res; lock_sock(sk); @@ -1485,8 +1543,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, goto exit; } - timeout = (flags & O_NONBLOCK) ? 0 : tipc_sk(sk)->conn_timeout; - + previous = sock->state; switch (sock->state) { case SS_UNCONNECTED: /* Send a 'SYN-' to destination */ @@ -1508,43 +1565,22 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, * case is EINPROGRESS, rather than EALREADY. */ res = -EINPROGRESS; - break; case SS_CONNECTING: - res = -EALREADY; + if (previous == SS_CONNECTING) + res = -EALREADY; + if (!timeout) + goto exit; + timeout = msecs_to_jiffies(timeout); + /* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */ + res = tipc_wait_for_connect(sock, &timeout); break; case SS_CONNECTED: res = -EISCONN; break; default: res = -EINVAL; - goto exit; - } - - if (sock->state == SS_CONNECTING) { - if (!timeout) - goto exit; - - /* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */ - release_sock(sk); - res = wait_event_interruptible_timeout(*sk_sleep(sk), - sock->state != SS_CONNECTING, - timeout ? (long)msecs_to_jiffies(timeout) - : MAX_SCHEDULE_TIMEOUT); - lock_sock(sk); - if (res <= 0) { - if (res == 0) - res = -ETIMEDOUT; - else - ; /* leave "res" unchanged */ - goto exit; - } + break; } - - if (unlikely(sock->state == SS_DISCONNECTING)) - res = sock_error(sk); - else - res = 0; - exit: release_sock(sk); return res; @@ -1575,6 +1611,42 @@ static int listen(struct socket *sock, int len) return res; } +static int tipc_wait_for_accept(struct socket *sock, long timeo) +{ + struct sock *sk = sock->sk; + DEFINE_WAIT(wait); + int err; + + /* True wake-one mechanism for incoming connections: only + * one process gets woken up, not the 'whole herd'. + * Since we do not 'race & poll' for established sockets + * anymore, the common case will execute the loop only once. + */ + for (;;) { + prepare_to_wait_exclusive(sk_sleep(sk), &wait, + TASK_INTERRUPTIBLE); + if (skb_queue_empty(&sk->sk_receive_queue)) { + release_sock(sk); + timeo = schedule_timeout(timeo); + lock_sock(sk); + } + err = 0; + if (!skb_queue_empty(&sk->sk_receive_queue)) + break; + err = -EINVAL; + if (sock->state != SS_LISTENING) + break; + err = sock_intr_errno(timeo); + if (signal_pending(current)) + break; + err = -EAGAIN; + if (!timeo) + break; + } + finish_wait(sk_sleep(sk), &wait); + return err; +} + /** * accept - wait for connection request * @sock: listening socket @@ -1591,7 +1663,7 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) struct tipc_port *new_tport; struct tipc_msg *msg; u32 new_ref; - + long timeo; int res; lock_sock(sk); @@ -1601,18 +1673,10 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) goto exit; } - while (skb_queue_empty(&sk->sk_receive_queue)) { - if (flags & O_NONBLOCK) { - res = -EWOULDBLOCK; - goto exit; - } - release_sock(sk); - res = wait_event_interruptible(*sk_sleep(sk), - (!skb_queue_empty(&sk->sk_receive_queue))); - lock_sock(sk); - if (res) - goto exit; - } + timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + res = tipc_wait_for_accept(sock, timeo); + if (res) + goto exit; buf = skb_peek(&sk->sk_receive_queue); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index d38bb45d82e9..7cb0bd5b1176 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -42,7 +42,7 @@ /** * struct tipc_subscriber - TIPC network topology subscriber * @conid: connection identifier to server connecting to subscriber - * @lock: controll access to subscriber + * @lock: control access to subscriber * @subscription_list: list of subscription objects for this subscriber */ struct tipc_subscriber { diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index a427623ee574..29fc8bee9702 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -80,6 +80,8 @@ * with BSD names. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/kernel.h> #include <linux/signal.h> @@ -366,7 +368,7 @@ static void unix_sock_destructor(struct sock *sk) WARN_ON(!sk_unhashed(sk)); WARN_ON(sk->sk_socket); if (!sock_flag(sk, SOCK_DEAD)) { - printk(KERN_INFO "Attempt to release alive unix socket: %p\n", sk); + pr_info("Attempt to release alive unix socket: %p\n", sk); return; } @@ -378,7 +380,7 @@ static void unix_sock_destructor(struct sock *sk) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); local_bh_enable(); #ifdef UNIX_REFCNT_DEBUG - printk(KERN_DEBUG "UNIX %p is destroyed, %ld are still alive.\n", sk, + pr_debug("UNIX %p is destroyed, %ld are still alive.\n", sk, atomic_long_read(&unix_nr_socks)); #endif } @@ -1448,7 +1450,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct unix_sock *u = unix_sk(sk); - struct sockaddr_un *sunaddr = msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name); struct sock *other = NULL; int namelen = 0; /* fake GCC */ int err; @@ -1910,7 +1912,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, struct scm_cookie tmp_scm; struct sock *sk = sock->sk; struct unix_sock *u = unix_sk(sk); - struct sockaddr_un *sunaddr = msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name); int copied = 0; int check_creds = 0; int target; @@ -2441,8 +2443,7 @@ static int __init af_unix_init(void) rc = proto_register(&unix_proto, 1); if (rc != 0) { - printk(KERN_CRIT "%s: Cannot create unix_sock SLAB cache!\n", - __func__); + pr_crit("%s: Cannot create unix_sock SLAB cache!\n", __func__); goto out; } diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 687360da62d9..9bb63ffec4f2 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1779,10 +1779,8 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb, goto out; if (msg->msg_name) { - struct sockaddr_vm *vm_addr; - /* Provide the address of the sender. */ - vm_addr = (struct sockaddr_vm *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_vm *, vm_addr, msg->msg_name); vsock_addr_init(vm_addr, dg->src.context, dg->src.resource); msg->msg_namelen = sizeof(*vm_addr); } diff --git a/net/wireless/ap.c b/net/wireless/ap.c index 324e8d851dc4..11ee4ed04f73 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -29,6 +29,7 @@ static int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, wdev->beacon_interval = 0; wdev->channel = NULL; wdev->ssid_len = 0; + rdev_set_qos_map(rdev, dev, NULL); } return err; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 9b8cc877eb19..78559b5bbd1f 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -277,6 +277,32 @@ void cfg80211_set_dfs_state(struct wiphy *wiphy, width, dfs_state); } +static u32 cfg80211_get_start_freq(u32 center_freq, + u32 bandwidth) +{ + u32 start_freq; + + if (bandwidth <= 20) + start_freq = center_freq; + else + start_freq = center_freq - bandwidth/2 + 10; + + return start_freq; +} + +static u32 cfg80211_get_end_freq(u32 center_freq, + u32 bandwidth) +{ + u32 end_freq; + + if (bandwidth <= 20) + end_freq = center_freq; + else + end_freq = center_freq + bandwidth/2 - 10; + + return end_freq; +} + static int cfg80211_get_chans_dfs_required(struct wiphy *wiphy, u32 center_freq, u32 bandwidth) @@ -284,13 +310,8 @@ static int cfg80211_get_chans_dfs_required(struct wiphy *wiphy, struct ieee80211_channel *c; u32 freq, start_freq, end_freq; - if (bandwidth <= 20) { - start_freq = center_freq; - end_freq = center_freq; - } else { - start_freq = center_freq - bandwidth/2 + 10; - end_freq = center_freq + bandwidth/2 - 10; - } + start_freq = cfg80211_get_start_freq(center_freq, bandwidth); + end_freq = cfg80211_get_end_freq(center_freq, bandwidth); for (freq = start_freq; freq <= end_freq; freq += 20) { c = ieee80211_get_channel(wiphy, freq); @@ -330,33 +351,159 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy, } EXPORT_SYMBOL(cfg80211_chandef_dfs_required); -static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy, - u32 center_freq, u32 bandwidth, - u32 prohibited_flags) +static int cfg80211_get_chans_dfs_usable(struct wiphy *wiphy, + u32 center_freq, + u32 bandwidth) { struct ieee80211_channel *c; u32 freq, start_freq, end_freq; + int count = 0; - if (bandwidth <= 20) { - start_freq = center_freq; - end_freq = center_freq; - } else { - start_freq = center_freq - bandwidth/2 + 10; - end_freq = center_freq + bandwidth/2 - 10; + start_freq = cfg80211_get_start_freq(center_freq, bandwidth); + end_freq = cfg80211_get_end_freq(center_freq, bandwidth); + + /* + * Check entire range of channels for the bandwidth. + * Check all channels are DFS channels (DFS_USABLE or + * DFS_AVAILABLE). Return number of usable channels + * (require CAC). Allow DFS and non-DFS channel mix. + */ + for (freq = start_freq; freq <= end_freq; freq += 20) { + c = ieee80211_get_channel(wiphy, freq); + if (!c) + return -EINVAL; + + if (c->flags & IEEE80211_CHAN_DISABLED) + return -EINVAL; + + if (c->flags & IEEE80211_CHAN_RADAR) { + if (c->dfs_state == NL80211_DFS_UNAVAILABLE) + return -EINVAL; + + if (c->dfs_state == NL80211_DFS_USABLE) + count++; + } } + return count; +} + +bool cfg80211_chandef_dfs_usable(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef) +{ + int width; + int r1, r2 = 0; + + if (WARN_ON(!cfg80211_chandef_valid(chandef))) + return false; + + width = cfg80211_chandef_get_width(chandef); + if (width < 0) + return false; + + r1 = cfg80211_get_chans_dfs_usable(wiphy, chandef->center_freq1, + width); + + if (r1 < 0) + return false; + + switch (chandef->width) { + case NL80211_CHAN_WIDTH_80P80: + WARN_ON(!chandef->center_freq2); + r2 = cfg80211_get_chans_dfs_usable(wiphy, + chandef->center_freq2, + width); + if (r2 < 0) + return false; + break; + default: + WARN_ON(chandef->center_freq2); + break; + } + + return (r1 + r2 > 0); +} + + +static bool cfg80211_get_chans_dfs_available(struct wiphy *wiphy, + u32 center_freq, + u32 bandwidth) +{ + struct ieee80211_channel *c; + u32 freq, start_freq, end_freq; + + start_freq = cfg80211_get_start_freq(center_freq, bandwidth); + end_freq = cfg80211_get_end_freq(center_freq, bandwidth); + + /* + * Check entire range of channels for the bandwidth. + * If any channel in between is disabled or has not + * had gone through CAC return false + */ for (freq = start_freq; freq <= end_freq; freq += 20) { c = ieee80211_get_channel(wiphy, freq); if (!c) return false; - /* check for radar flags */ - if ((prohibited_flags & c->flags & IEEE80211_CHAN_RADAR) && + if (c->flags & IEEE80211_CHAN_DISABLED) + return false; + + if ((c->flags & IEEE80211_CHAN_RADAR) && (c->dfs_state != NL80211_DFS_AVAILABLE)) return false; + } + + return true; +} + +static bool cfg80211_chandef_dfs_available(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef) +{ + int width; + int r; + + if (WARN_ON(!cfg80211_chandef_valid(chandef))) + return false; + + width = cfg80211_chandef_get_width(chandef); + if (width < 0) + return false; + + r = cfg80211_get_chans_dfs_available(wiphy, chandef->center_freq1, + width); + + /* If any of channels unavailable for cf1 just return */ + if (!r) + return r; + + switch (chandef->width) { + case NL80211_CHAN_WIDTH_80P80: + WARN_ON(!chandef->center_freq2); + r = cfg80211_get_chans_dfs_available(wiphy, + chandef->center_freq2, + width); + default: + WARN_ON(chandef->center_freq2); + break; + } + + return r; +} - /* check for the other flags */ - if (c->flags & prohibited_flags & ~IEEE80211_CHAN_RADAR) + +static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy, + u32 center_freq, u32 bandwidth, + u32 prohibited_flags) +{ + struct ieee80211_channel *c; + u32 freq, start_freq, end_freq; + + start_freq = cfg80211_get_start_freq(center_freq, bandwidth); + end_freq = cfg80211_get_end_freq(center_freq, bandwidth); + + for (freq = start_freq; freq <= end_freq; freq += 20) { + c = ieee80211_get_channel(wiphy, freq); + if (!c || c->flags & prohibited_flags) return false; } @@ -462,14 +609,19 @@ bool cfg80211_reg_can_beacon(struct wiphy *wiphy, struct cfg80211_chan_def *chandef) { bool res; + u32 prohibited_flags = IEEE80211_CHAN_DISABLED | + IEEE80211_CHAN_NO_IR | + IEEE80211_CHAN_RADAR; trace_cfg80211_reg_can_beacon(wiphy, chandef); - res = cfg80211_chandef_usable(wiphy, chandef, - IEEE80211_CHAN_DISABLED | - IEEE80211_CHAN_PASSIVE_SCAN | - IEEE80211_CHAN_NO_IBSS | - IEEE80211_CHAN_RADAR); + if (cfg80211_chandef_dfs_required(wiphy, chandef) > 0 && + cfg80211_chandef_dfs_available(wiphy, chandef)) { + /* We can skip IEEE80211_CHAN_NO_IR if chandef dfs available */ + prohibited_flags = IEEE80211_CHAN_DISABLED; + } + + res = cfg80211_chandef_usable(wiphy, chandef, prohibited_flags); trace_cfg80211_return_bool(res); return res; @@ -510,6 +662,7 @@ cfg80211_get_chan_state(struct wireless_dev *wdev, : CHAN_MODE_EXCLUSIVE; return; } + break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: if (wdev->current_bss) { diff --git a/net/wireless/core.c b/net/wireless/core.c index 52b865fb7351..010892b81a06 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -204,15 +204,9 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, rdev->opencount--; if (rdev->scan_req && rdev->scan_req->wdev == wdev) { - /* - * If the scan request wasn't notified as done, set it - * to aborted and leak it after a warning. The driver - * should have notified us that it ended at the latest - * during rdev_stop_p2p_device(). - */ if (WARN_ON(!rdev->scan_req->notified)) rdev->scan_req->aborted = true; - ___cfg80211_scan_done(rdev, !rdev->scan_req->notified); + ___cfg80211_scan_done(rdev, false); } } @@ -357,8 +351,6 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) rdev->wiphy.rts_threshold = (u32) -1; rdev->wiphy.coverage_class = 0; - rdev->wiphy.features = NL80211_FEATURE_SCAN_FLUSH; - return &rdev->wiphy; } EXPORT_SYMBOL(wiphy_new); @@ -451,9 +443,6 @@ int wiphy_register(struct wiphy *wiphy) int i; u16 ifmodes = wiphy->interface_modes; - /* support for 5/10 MHz is broken due to nl80211 API mess - disable */ - wiphy->flags &= ~WIPHY_FLAG_SUPPORTS_5_10_MHZ; - /* * There are major locking problems in nl80211/mac80211 for CSA, * disable for all drivers until this has been reworked. @@ -575,6 +564,8 @@ int wiphy_register(struct wiphy *wiphy) /* check and set up bitrates */ ieee80211_set_bitrate_flags(wiphy); + rdev->wiphy.features |= NL80211_FEATURE_SCAN_FLUSH; + rtnl_lock(); res = device_add(&rdev->wiphy.dev); if (res) { @@ -595,7 +586,7 @@ int wiphy_register(struct wiphy *wiphy) if (IS_ERR(rdev->wiphy.debugfsdir)) rdev->wiphy.debugfsdir = NULL; - if (wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY) { + if (wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) { struct regulatory_request request; request.wiphy_idx = get_wiphy_idx(wiphy); @@ -765,13 +756,16 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev, { struct net_device *dev = wdev->netdev; + ASSERT_RTNL(); + switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: cfg80211_leave_ibss(rdev, dev, true); break; case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_STATION: - __cfg80211_stop_sched_scan(rdev, false); + if (rdev->sched_scan_req && dev == rdev->sched_scan_req->dev) + __cfg80211_stop_sched_scan(rdev, false); wdev_lock(wdev); #ifdef CONFIG_CFG80211_WEXT @@ -868,7 +862,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, if (rdev->scan_req && rdev->scan_req->wdev == wdev) { if (WARN_ON(!rdev->scan_req->notified)) rdev->scan_req->aborted = true; - ___cfg80211_scan_done(rdev, true); + ___cfg80211_scan_done(rdev, false); } if (WARN_ON(rdev->sched_scan_req && diff --git a/net/wireless/core.h b/net/wireless/core.h index af10e59af2d8..f1d193b557b6 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -62,14 +62,13 @@ struct cfg80211_registered_device { struct rb_root bss_tree; u32 bss_generation; struct cfg80211_scan_request *scan_req; /* protected by RTNL */ + struct sk_buff *scan_msg; struct cfg80211_sched_scan_request *sched_scan_req; unsigned long suspend_at; struct work_struct scan_done_wk; struct work_struct sched_scan_results_wk; -#ifdef CONFIG_NL80211_TESTMODE - struct genl_info *testmode_info; -#endif + struct genl_info *cur_cmd_info; struct work_struct conn_work; struct work_struct event_work; @@ -317,9 +316,8 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid); void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev); int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, - struct ieee80211_channel *chan, bool offchan, - unsigned int wait, const u8 *buf, size_t len, - bool no_cck, bool dont_wait_for_ack, u64 *cookie); + struct cfg80211_mgmt_tx_params *params, + u64 *cookie); void cfg80211_oper_and_ht_capa(struct ieee80211_ht_cap *ht_capa, const struct ieee80211_ht_cap *ht_capa_mask); void cfg80211_oper_and_vht_capa(struct ieee80211_vht_cap *vht_capa, @@ -364,7 +362,8 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr); void __cfg80211_scan_done(struct work_struct *wk); -void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak); +void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, + bool send_message); void __cfg80211_sched_scan_results(struct work_struct *wk); int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev, bool driver_initiated); @@ -382,6 +381,19 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, enum cfg80211_chan_mode chanmode, u8 radar_detect); +/** + * cfg80211_chandef_dfs_usable - checks if chandef is DFS usable + * @wiphy: the wiphy to validate against + * @chandef: the channel definition to check + * + * Checks if chandef is usable and we can/need start CAC on such channel. + * + * Return: Return true if all channels available and at least + * one channel require CAC (NL80211_DFS_USABLE) + */ +bool cfg80211_chandef_dfs_usable(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef); + void cfg80211_set_dfs_state(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef, enum nl80211_dfs_state dfs_state); diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk index 42ed274e81f4..9a8217d2a908 100644 --- a/net/wireless/genregdb.awk +++ b/net/wireless/genregdb.awk @@ -33,15 +33,7 @@ BEGIN { regdb = "const struct ieee80211_regdomain *reg_regdb[] = {\n" } -/^[ \t]*#/ { - # Ignore -} - -!active && /^[ \t]*$/ { - # Ignore -} - -!active && /country/ { +function parse_country_head() { country=$2 sub(/:/, "", country) printf "static const struct ieee80211_regdomain regdom_%s = {\n", country @@ -57,7 +49,8 @@ BEGIN { regdb = regdb "\t®dom_" country ",\n" } -active && /^[ \t]*\(/ { +function parse_reg_rule() +{ start = $1 sub(/\(/, "", start) end = $3 @@ -107,17 +100,21 @@ active && /^[ \t]*\(/ { } else if (flagarray[arg] == "PTMP-ONLY") { flags = flags "\n\t\t\tNL80211_RRF_PTMP_ONLY | " } else if (flagarray[arg] == "PASSIVE-SCAN") { - flags = flags "\n\t\t\tNL80211_RRF_PASSIVE_SCAN | " + flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " } else if (flagarray[arg] == "NO-IBSS") { - flags = flags "\n\t\t\tNL80211_RRF_NO_IBSS | " + flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " + } else if (flagarray[arg] == "NO-IR") { + flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " } + } flags = flags "0" printf "\t\tREG_RULE(%d, %d, %d, %d, %d, %s),\n", start, end, bw, gain, power, flags rules++ } -active && /^[ \t]*$/ { +function print_tail_country() +{ active = 0 printf "\t},\n" printf "\t.n_reg_rules = %d\n", rules @@ -125,7 +122,29 @@ active && /^[ \t]*$/ { rules = 0; } +/^[ \t]*#/ { + # Ignore +} + +!active && /^[ \t]*$/ { + # Ignore +} + +!active && /country/ { + parse_country_head() +} + +active && /^[ \t]*\(/ { + parse_reg_rule() +} + +active && /^[ \t]*$/ { + print_tail_country() +} + END { + if (active) + print_tail_country() print regdb "};" print "" print "int reg_regdb_size = ARRAY_SIZE(reg_regdb);" diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 89737ee2669a..f911c5f9f903 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -183,6 +183,8 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext) kfree(wdev->connect_keys); wdev->connect_keys = NULL; + rdev_set_qos_map(rdev, dev, NULL); + /* * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. @@ -274,7 +276,7 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, for (i = 0; i < sband->n_channels; i++) { chan = &sband->channels[i]; - if (chan->flags & IEEE80211_CHAN_NO_IBSS) + if (chan->flags & IEEE80211_CHAN_NO_IR) continue; if (chan->flags & IEEE80211_CHAN_DISABLED) continue; @@ -346,7 +348,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, chan = ieee80211_get_channel(wdev->wiphy, freq); if (!chan) return -EINVAL; - if (chan->flags & IEEE80211_CHAN_NO_IBSS || + if (chan->flags & IEEE80211_CHAN_NO_IR || chan->flags & IEEE80211_CHAN_DISABLED) return -EINVAL; } diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index 0553fd4d85ae..885862447b63 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -99,6 +99,7 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, const struct mesh_config *conf) { struct wireless_dev *wdev = dev->ieee80211_ptr; + u8 radar_detect_width = 0; int err; BUILD_BUG_ON(IEEE80211_MAX_SSID_LEN != IEEE80211_MAX_MESH_ID_LEN); @@ -141,8 +142,7 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, for (i = 0; i < sband->n_channels; i++) { chan = &sband->channels[i]; - if (chan->flags & (IEEE80211_CHAN_NO_IBSS | - IEEE80211_CHAN_PASSIVE_SCAN | + if (chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_DISABLED | IEEE80211_CHAN_RADAR)) continue; @@ -178,8 +178,16 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, if (!cfg80211_reg_can_beacon(&rdev->wiphy, &setup->chandef)) return -EINVAL; - err = cfg80211_can_use_chan(rdev, wdev, setup->chandef.chan, - CHAN_MODE_SHARED); + err = cfg80211_chandef_dfs_required(wdev->wiphy, &setup->chandef); + if (err < 0) + return err; + if (err) + radar_detect_width = BIT(setup->chandef.width); + + err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype, + setup->chandef.chan, + CHAN_MODE_SHARED, + radar_detect_width); if (err) return err; @@ -269,6 +277,7 @@ static int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, if (!err) { wdev->mesh_id_len = 0; wdev->channel = NULL; + rdev_set_qos_map(rdev, dev, NULL); } return err; diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 6a6b1c8e907d..52cca05044a8 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -520,9 +520,7 @@ void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev) int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, - struct ieee80211_channel *chan, bool offchan, - unsigned int wait, const u8 *buf, size_t len, - bool no_cck, bool dont_wait_for_ack, u64 *cookie) + struct cfg80211_mgmt_tx_params *params, u64 *cookie) { const struct ieee80211_mgmt *mgmt; u16 stype; @@ -533,10 +531,10 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, if (!rdev->ops->mgmt_tx) return -EOPNOTSUPP; - if (len < 24 + 1) + if (params->len < 24 + 1) return -EINVAL; - mgmt = (const struct ieee80211_mgmt *) buf; + mgmt = (const struct ieee80211_mgmt *)params->buf; if (!ieee80211_is_mgmt(mgmt->frame_control)) return -EINVAL; @@ -615,9 +613,7 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, return -EINVAL; /* Transmit the Action frame as requested by user space */ - return rdev_mgmt_tx(rdev, wdev, chan, offchan, - wait, buf, len, no_cck, dont_wait_for_ack, - cookie); + return rdev_mgmt_tx(rdev, wdev, params, cookie); } bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_mbm, @@ -763,12 +759,12 @@ void cfg80211_radar_event(struct wiphy *wiphy, EXPORT_SYMBOL(cfg80211_radar_event); void cfg80211_cac_event(struct net_device *netdev, + const struct cfg80211_chan_def *chandef, enum nl80211_radar_event event, gfp_t gfp) { struct wireless_dev *wdev = netdev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - struct cfg80211_chan_def chandef; unsigned long timeout; trace_cfg80211_cac_event(netdev, event); @@ -779,14 +775,12 @@ void cfg80211_cac_event(struct net_device *netdev, if (WARN_ON(!wdev->channel)) return; - cfg80211_chandef_create(&chandef, wdev->channel, NL80211_CHAN_NO_HT); - switch (event) { case NL80211_RADAR_CAC_FINISHED: timeout = wdev->cac_start_time + msecs_to_jiffies(IEEE80211_DFS_MIN_CAC_TIME_MS); WARN_ON(!time_after_eq(jiffies, timeout)); - cfg80211_set_dfs_state(wiphy, &chandef, NL80211_DFS_AVAILABLE); + cfg80211_set_dfs_state(wiphy, chandef, NL80211_DFS_AVAILABLE); break; case NL80211_RADAR_CAC_ABORTED: break; @@ -796,6 +790,6 @@ void cfg80211_cac_event(struct net_device *netdev, } wdev->cac_started = false; - nl80211_radar_notify(rdev, &chandef, event, netdev, gfp); + nl80211_radar_notify(rdev, chandef, event, netdev, gfp); } EXPORT_SYMBOL(cfg80211_cac_event); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 138dc3bb8b67..4fe2e6e2bc76 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -53,6 +53,7 @@ enum nl80211_multicast_groups { NL80211_MCGRP_SCAN, NL80211_MCGRP_REGULATORY, NL80211_MCGRP_MLME, + NL80211_MCGRP_VENDOR, NL80211_MCGRP_TESTMODE /* keep last - ifdef! */ }; @@ -61,6 +62,7 @@ static const struct genl_multicast_group nl80211_mcgrps[] = { [NL80211_MCGRP_SCAN] = { .name = "scan", }, [NL80211_MCGRP_REGULATORY] = { .name = "regulatory", }, [NL80211_MCGRP_MLME] = { .name = "mlme", }, + [NL80211_MCGRP_VENDOR] = { .name = "vendor", }, #ifdef CONFIG_NL80211_TESTMODE [NL80211_MCGRP_TESTMODE] = { .name = "testmode", } #endif @@ -163,7 +165,7 @@ __cfg80211_rdev_from_attrs(struct net *netns, struct nlattr **attrs) if (attrs[NL80211_ATTR_IFINDEX]) { int ifindex = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]); - netdev = dev_get_by_index(netns, ifindex); + netdev = __dev_get_by_index(netns, ifindex); if (netdev) { if (netdev->ieee80211_ptr) tmp = wiphy_to_dev( @@ -171,8 +173,6 @@ __cfg80211_rdev_from_attrs(struct net *netns, struct nlattr **attrs) else tmp = NULL; - dev_put(netdev); - /* not wireless device -- return error */ if (!tmp) return ERR_PTR(-EINVAL); @@ -376,6 +376,12 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY }, [NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY }, [NL80211_ATTR_HANDLE_DFS] = { .type = NLA_FLAG }, + [NL80211_ATTR_OPMODE_NOTIF] = { .type = NLA_U8 }, + [NL80211_ATTR_VENDOR_ID] = { .type = NLA_U32 }, + [NL80211_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 }, + [NL80211_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, + [NL80211_ATTR_QOS_MAP] = { .type = NLA_BINARY, + .len = IEEE80211_QOS_MAP_LEN_MAX }, }; /* policy for the key attributes */ @@ -564,12 +570,12 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, if ((chan->flags & IEEE80211_CHAN_DISABLED) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DISABLED)) goto nla_put_failure; - if ((chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) && - nla_put_flag(msg, NL80211_FREQUENCY_ATTR_PASSIVE_SCAN)) - goto nla_put_failure; - if ((chan->flags & IEEE80211_CHAN_NO_IBSS) && - nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_IBSS)) - goto nla_put_failure; + if (chan->flags & IEEE80211_CHAN_NO_IR) { + if (nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_IR)) + goto nla_put_failure; + if (nla_put_flag(msg, __NL80211_FREQUENCY_ATTR_NO_IBSS)) + goto nla_put_failure; + } if (chan->flags & IEEE80211_CHAN_RADAR) { if (nla_put_flag(msg, NL80211_FREQUENCY_ATTR_RADAR)) goto nla_put_failure; @@ -1247,10 +1253,6 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev, if ((dev->wiphy.flags & WIPHY_FLAG_TDLS_EXTERNAL_SETUP) && nla_put_flag(msg, NL80211_ATTR_TDLS_EXTERNAL_SETUP)) goto nla_put_failure; - if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_5_10_MHZ) && - nla_put_flag(msg, WIPHY_FLAG_SUPPORTS_5_10_MHZ)) - goto nla_put_failure; - state->split_start++; if (state->split) break; @@ -1454,6 +1456,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev, if (dev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH) CMD(channel_switch, CHANNEL_SWITCH); } + CMD(set_qos_map, SET_QOS_MAP); #ifdef CONFIG_NL80211_TESTMODE CMD(testmode_cmd, TESTMODE); @@ -1579,6 +1582,46 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev, if (nl80211_send_coalesce(msg, dev)) goto nla_put_failure; + if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_5_10_MHZ) && + (nla_put_flag(msg, NL80211_ATTR_SUPPORT_5_MHZ) || + nla_put_flag(msg, NL80211_ATTR_SUPPORT_10_MHZ))) + goto nla_put_failure; + state->split_start++; + break; + case 11: + if (dev->wiphy.n_vendor_commands) { + const struct nl80211_vendor_cmd_info *info; + struct nlattr *nested; + + nested = nla_nest_start(msg, NL80211_ATTR_VENDOR_DATA); + if (!nested) + goto nla_put_failure; + + for (i = 0; i < dev->wiphy.n_vendor_commands; i++) { + info = &dev->wiphy.vendor_commands[i].info; + if (nla_put(msg, i + 1, sizeof(*info), info)) + goto nla_put_failure; + } + nla_nest_end(msg, nested); + } + + if (dev->wiphy.n_vendor_events) { + const struct nl80211_vendor_cmd_info *info; + struct nlattr *nested; + + nested = nla_nest_start(msg, + NL80211_ATTR_VENDOR_EVENTS); + if (!nested) + goto nla_put_failure; + + for (i = 0; i < dev->wiphy.n_vendor_events; i++) { + info = &dev->wiphy.vendor_events[i]; + if (nla_put(msg, i + 1, sizeof(*info), info)) + goto nla_put_failure; + } + nla_nest_end(msg, nested); + } + /* done */ state->split_start = 0; break; @@ -1611,7 +1654,7 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb, struct cfg80211_registered_device *rdev; int ifidx = nla_get_u32(tb[NL80211_ATTR_IFINDEX]); - netdev = dev_get_by_index(sock_net(skb->sk), ifidx); + netdev = __dev_get_by_index(sock_net(skb->sk), ifidx); if (!netdev) return -ENODEV; if (netdev->ieee80211_ptr) { @@ -1619,7 +1662,6 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb, netdev->ieee80211_ptr->wiphy); state->filter_wiphy = rdev->wiphy_idx; } - dev_put(netdev); } return 0; @@ -1677,9 +1719,10 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) * We can then retry with the larger buffer. */ if ((ret == -ENOBUFS || ret == -EMSGSIZE) && - !skb->len && + !skb->len && !state->split && cb->min_dump_alloc < 4096) { cb->min_dump_alloc = 4096; + state->split_start = 0; rtnl_unlock(); return 1; } @@ -1942,7 +1985,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_IFINDEX]) { int ifindex = nla_get_u32(info->attrs[NL80211_ATTR_IFINDEX]); - netdev = dev_get_by_index(genl_info_net(info), ifindex); + netdev = __dev_get_by_index(genl_info_net(info), ifindex); if (netdev && netdev->ieee80211_ptr) rdev = wiphy_to_dev(netdev->ieee80211_ptr->wiphy); else @@ -1970,32 +2013,24 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rdev, nla_data(info->attrs[NL80211_ATTR_WIPHY_NAME])); if (result) - goto bad_res; + return result; if (info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS]) { struct ieee80211_txq_params txq_params; struct nlattr *tb[NL80211_TXQ_ATTR_MAX + 1]; - if (!rdev->ops->set_txq_params) { - result = -EOPNOTSUPP; - goto bad_res; - } + if (!rdev->ops->set_txq_params) + return -EOPNOTSUPP; - if (!netdev) { - result = -EINVAL; - goto bad_res; - } + if (!netdev) + return -EINVAL; if (netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && - netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) { - result = -EINVAL; - goto bad_res; - } + netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) + return -EINVAL; - if (!netif_running(netdev)) { - result = -ENETDOWN; - goto bad_res; - } + if (!netif_running(netdev)) + return -ENETDOWN; nla_for_each_nested(nl_txq_params, info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS], @@ -2006,12 +2041,12 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) txq_params_policy); result = parse_txq_params(tb, &txq_params); if (result) - goto bad_res; + return result; result = rdev_set_txq_params(rdev, netdev, &txq_params); if (result) - goto bad_res; + return result; } } @@ -2020,7 +2055,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) nl80211_can_set_dev_channel(wdev) ? wdev : NULL, info); if (result) - goto bad_res; + return result; } if (info->attrs[NL80211_ATTR_WIPHY_TX_POWER_SETTING]) { @@ -2031,19 +2066,15 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (!(rdev->wiphy.features & NL80211_FEATURE_VIF_TXPOWER)) txp_wdev = NULL; - if (!rdev->ops->set_tx_power) { - result = -EOPNOTSUPP; - goto bad_res; - } + if (!rdev->ops->set_tx_power) + return -EOPNOTSUPP; idx = NL80211_ATTR_WIPHY_TX_POWER_SETTING; type = nla_get_u32(info->attrs[idx]); if (!info->attrs[NL80211_ATTR_WIPHY_TX_POWER_LEVEL] && - (type != NL80211_TX_POWER_AUTOMATIC)) { - result = -EINVAL; - goto bad_res; - } + (type != NL80211_TX_POWER_AUTOMATIC)) + return -EINVAL; if (type != NL80211_TX_POWER_AUTOMATIC) { idx = NL80211_ATTR_WIPHY_TX_POWER_LEVEL; @@ -2052,7 +2083,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) result = rdev_set_tx_power(rdev, txp_wdev, type, mbm); if (result) - goto bad_res; + return result; } if (info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX] && @@ -2060,10 +2091,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) u32 tx_ant, rx_ant; if ((!rdev->wiphy.available_antennas_tx && !rdev->wiphy.available_antennas_rx) || - !rdev->ops->set_antenna) { - result = -EOPNOTSUPP; - goto bad_res; - } + !rdev->ops->set_antenna) + return -EOPNOTSUPP; tx_ant = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX]); rx_ant = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_ANTENNA_RX]); @@ -2071,17 +2100,15 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) /* reject antenna configurations which don't match the * available antenna masks, except for the "all" mask */ if ((~tx_ant && (tx_ant & ~rdev->wiphy.available_antennas_tx)) || - (~rx_ant && (rx_ant & ~rdev->wiphy.available_antennas_rx))) { - result = -EINVAL; - goto bad_res; - } + (~rx_ant && (rx_ant & ~rdev->wiphy.available_antennas_rx))) + return -EINVAL; tx_ant = tx_ant & rdev->wiphy.available_antennas_tx; rx_ant = rx_ant & rdev->wiphy.available_antennas_rx; result = rdev_set_antenna(rdev, tx_ant, rx_ant); if (result) - goto bad_res; + return result; } changed = 0; @@ -2089,30 +2116,27 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_WIPHY_RETRY_SHORT]) { retry_short = nla_get_u8( info->attrs[NL80211_ATTR_WIPHY_RETRY_SHORT]); - if (retry_short == 0) { - result = -EINVAL; - goto bad_res; - } + if (retry_short == 0) + return -EINVAL; + changed |= WIPHY_PARAM_RETRY_SHORT; } if (info->attrs[NL80211_ATTR_WIPHY_RETRY_LONG]) { retry_long = nla_get_u8( info->attrs[NL80211_ATTR_WIPHY_RETRY_LONG]); - if (retry_long == 0) { - result = -EINVAL; - goto bad_res; - } + if (retry_long == 0) + return -EINVAL; + changed |= WIPHY_PARAM_RETRY_LONG; } if (info->attrs[NL80211_ATTR_WIPHY_FRAG_THRESHOLD]) { frag_threshold = nla_get_u32( info->attrs[NL80211_ATTR_WIPHY_FRAG_THRESHOLD]); - if (frag_threshold < 256) { - result = -EINVAL; - goto bad_res; - } + if (frag_threshold < 256) + return -EINVAL; + if (frag_threshold != (u32) -1) { /* * Fragments (apart from the last one) are required to @@ -2142,10 +2166,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) u32 old_frag_threshold, old_rts_threshold; u8 old_coverage_class; - if (!rdev->ops->set_wiphy_params) { - result = -EOPNOTSUPP; - goto bad_res; - } + if (!rdev->ops->set_wiphy_params) + return -EOPNOTSUPP; old_retry_short = rdev->wiphy.retry_short; old_retry_long = rdev->wiphy.retry_long; @@ -2173,11 +2195,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rdev->wiphy.coverage_class = old_coverage_class; } } - - bad_res: - if (netdev) - dev_put(netdev); - return result; + return 0; } static inline u64 wdev_id(struct wireless_dev *wdev) @@ -2187,7 +2205,7 @@ static inline u64 wdev_id(struct wireless_dev *wdev) } static int nl80211_send_chandef(struct sk_buff *msg, - struct cfg80211_chan_def *chandef) + const struct cfg80211_chan_def *chandef) { WARN_ON(!cfg80211_chandef_valid(chandef)); @@ -3236,6 +3254,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) return PTR_ERR(params.acl); } + wdev_lock(wdev); err = rdev_start_ap(rdev, dev, ¶ms); if (!err) { wdev->preset_chandef = params.chandef; @@ -3244,6 +3263,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) wdev->ssid_len = params.ssid_len; memcpy(wdev->ssid, params.ssid, wdev->ssid_len); } + wdev_unlock(wdev); kfree(params.acl); @@ -3272,7 +3292,11 @@ static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) if (err) return err; - return rdev_change_beacon(rdev, dev, ¶ms); + wdev_lock(wdev); + err = rdev_change_beacon(rdev, dev, ¶ms); + wdev_unlock(wdev); + + return err; } static int nl80211_stop_ap(struct sk_buff *skb, struct genl_info *info) @@ -4144,6 +4168,12 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.vht_capa = nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]); + if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) { + params.opmode_notif_used = true; + params.opmode_notif = + nla_get_u8(info->attrs[NL80211_ATTR_OPMODE_NOTIF]); + } + if (info->attrs[NL80211_ATTR_STA_PLINK_ACTION]) { params.plink_action = nla_get_u8(info->attrs[NL80211_ATTR_STA_PLINK_ACTION]); @@ -4478,7 +4508,9 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; struct bss_parameters params; + int err; memset(¶ms, 0, sizeof(params)); /* default to not changing parameters */ @@ -4544,7 +4576,11 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) return -EOPNOTSUPP; - return rdev_change_bss(rdev, dev, ¶ms); + wdev_lock(wdev); + err = rdev_change_bss(rdev, dev, ¶ms); + wdev_unlock(wdev); + + return err; } static const struct nla_policy reg_rule_policy[NL80211_REG_RULE_ATTR_MAX + 1] = { @@ -5098,7 +5134,7 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) char *alpha2 = NULL; int rem_reg_rules = 0, r = 0; u32 num_rules = 0, rule_idx = 0, size_of_regd; - u8 dfs_region = 0; + enum nl80211_dfs_regions dfs_region = NL80211_DFS_UNSET; struct ieee80211_regdomain *rd = NULL; if (!info->attrs[NL80211_ATTR_REG_ALPHA2]) @@ -5119,6 +5155,9 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } + if (!reg_is_valid_request(alpha2)) + return -EINVAL; + size_of_regd = sizeof(struct ieee80211_regdomain) + num_rules * sizeof(struct ieee80211_reg_rule); @@ -5206,7 +5245,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->scan) return -EOPNOTSUPP; - if (rdev->scan_req) { + if (rdev->scan_req || rdev->scan_msg) { err = -EBUSY; goto unlock; } @@ -5219,12 +5258,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) goto unlock; } } else { - enum ieee80211_band band; - n_channels = 0; - - for (band = 0; band < IEEE80211_NUM_BANDS; band++) - if (wiphy->bands[band]) - n_channels += wiphy->bands[band]->n_channels; + n_channels = ieee80211_get_num_supported_channels(wiphy); } if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) @@ -5365,10 +5399,8 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) { request->flags = nla_get_u32( info->attrs[NL80211_ATTR_SCAN_FLAGS]); - if (((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) || - ((request->flags & NL80211_SCAN_FLAG_FLUSH) && - !(wiphy->features & NL80211_FEATURE_SCAN_FLUSH))) { + if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && + !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) { err = -EOPNOTSUPP; goto out_free; } @@ -5434,11 +5466,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, if (!n_channels) return -EINVAL; } else { - n_channels = 0; - - for (band = 0; band < IEEE80211_NUM_BANDS; band++) - if (wiphy->bands[band]) - n_channels += wiphy->bands[band]->n_channels; + n_channels = ieee80211_get_num_supported_channels(wiphy); } if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) @@ -5608,10 +5636,8 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) { request->flags = nla_get_u32( info->attrs[NL80211_ATTR_SCAN_FLAGS]); - if (((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) || - ((request->flags & NL80211_SCAN_FLAG_FLUSH) && - !(wiphy->features & NL80211_FEATURE_SCAN_FLUSH))) { + if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && + !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) { err = -EOPNOTSUPP; goto out_free; } @@ -5655,8 +5681,13 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_chan_def chandef; + enum nl80211_dfs_regions dfs_region; int err; + dfs_region = reg_get_dfs_region(wdev->wiphy); + if (dfs_region == NL80211_DFS_UNSET) + return -EINVAL; + err = nl80211_parse_chandef(rdev, info, &chandef); if (err) return err; @@ -5674,7 +5705,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, if (err == 0) return -EINVAL; - if (chandef.chan->dfs_state != NL80211_DFS_USABLE) + if (!cfg80211_chandef_dfs_usable(wdev->wiphy, &chandef)) return -EINVAL; if (!rdev->ops->start_radar_detection) @@ -5814,7 +5845,11 @@ skip_beacons: if (info->attrs[NL80211_ATTR_CH_SWITCH_BLOCK_TX]) params.block_tx = true; - return rdev_channel_switch(rdev, dev, ¶ms); + wdev_lock(wdev); + err = rdev_channel_switch(rdev, dev, ¶ms); + wdev_unlock(wdev); + + return err; } static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, @@ -6677,6 +6712,101 @@ static int nl80211_set_mcast_rate(struct sk_buff *skb, struct genl_info *info) return err; } +static struct sk_buff * +__cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev, + int approxlen, u32 portid, u32 seq, + enum nl80211_commands cmd, + enum nl80211_attrs attr, + const struct nl80211_vendor_cmd_info *info, + gfp_t gfp) +{ + struct sk_buff *skb; + void *hdr; + struct nlattr *data; + + skb = nlmsg_new(approxlen + 100, gfp); + if (!skb) + return NULL; + + hdr = nl80211hdr_put(skb, portid, seq, 0, cmd); + if (!hdr) { + kfree_skb(skb); + return NULL; + } + + if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx)) + goto nla_put_failure; + + if (info) { + if (nla_put_u32(skb, NL80211_ATTR_VENDOR_ID, + info->vendor_id)) + goto nla_put_failure; + if (nla_put_u32(skb, NL80211_ATTR_VENDOR_SUBCMD, + info->subcmd)) + goto nla_put_failure; + } + + data = nla_nest_start(skb, attr); + + ((void **)skb->cb)[0] = rdev; + ((void **)skb->cb)[1] = hdr; + ((void **)skb->cb)[2] = data; + + return skb; + + nla_put_failure: + kfree_skb(skb); + return NULL; +} + +struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy, + enum nl80211_commands cmd, + enum nl80211_attrs attr, + int vendor_event_idx, + int approxlen, gfp_t gfp) +{ + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + const struct nl80211_vendor_cmd_info *info; + + switch (cmd) { + case NL80211_CMD_TESTMODE: + if (WARN_ON(vendor_event_idx != -1)) + return NULL; + info = NULL; + break; + case NL80211_CMD_VENDOR: + if (WARN_ON(vendor_event_idx < 0 || + vendor_event_idx >= wiphy->n_vendor_events)) + return NULL; + info = &wiphy->vendor_events[vendor_event_idx]; + break; + default: + WARN_ON(1); + return NULL; + } + + return __cfg80211_alloc_vendor_skb(rdev, approxlen, 0, 0, + cmd, attr, info, gfp); +} +EXPORT_SYMBOL(__cfg80211_alloc_event_skb); + +void __cfg80211_send_event_skb(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]; + enum nl80211_multicast_groups mcgrp = NL80211_MCGRP_TESTMODE; + + nla_nest_end(skb, data); + genlmsg_end(skb, hdr); + + if (data->nla_type == NL80211_ATTR_VENDOR_DATA) + mcgrp = NL80211_MCGRP_VENDOR; + + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), skb, 0, + mcgrp, gfp); +} +EXPORT_SYMBOL(__cfg80211_send_event_skb); #ifdef CONFIG_NL80211_TESTMODE static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info) @@ -6701,11 +6831,11 @@ static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NL80211_ATTR_TESTDATA]) return -EINVAL; - rdev->testmode_info = info; + rdev->cur_cmd_info = info; err = rdev_testmode_cmd(rdev, wdev, nla_data(info->attrs[NL80211_ATTR_TESTDATA]), nla_len(info->attrs[NL80211_ATTR_TESTDATA])); - rdev->testmode_info = NULL; + rdev->cur_cmd_info = NULL; return err; } @@ -6804,93 +6934,6 @@ static int nl80211_testmode_dump(struct sk_buff *skb, rtnl_unlock(); return err; } - -static struct sk_buff * -__cfg80211_testmode_alloc_skb(struct cfg80211_registered_device *rdev, - int approxlen, u32 portid, u32 seq, gfp_t gfp) -{ - struct sk_buff *skb; - void *hdr; - struct nlattr *data; - - skb = nlmsg_new(approxlen + 100, gfp); - if (!skb) - return NULL; - - hdr = nl80211hdr_put(skb, portid, seq, 0, NL80211_CMD_TESTMODE); - if (!hdr) { - kfree_skb(skb); - return NULL; - } - - if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx)) - goto nla_put_failure; - data = nla_nest_start(skb, NL80211_ATTR_TESTDATA); - - ((void **)skb->cb)[0] = rdev; - ((void **)skb->cb)[1] = hdr; - ((void **)skb->cb)[2] = data; - - return skb; - - nla_put_failure: - kfree_skb(skb); - return NULL; -} - -struct sk_buff *cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy, - int approxlen) -{ - struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - - if (WARN_ON(!rdev->testmode_info)) - return NULL; - - return __cfg80211_testmode_alloc_skb(rdev, approxlen, - rdev->testmode_info->snd_portid, - rdev->testmode_info->snd_seq, - GFP_KERNEL); -} -EXPORT_SYMBOL(cfg80211_testmode_alloc_reply_skb); - -int cfg80211_testmode_reply(struct sk_buff *skb) -{ - struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0]; - void *hdr = ((void **)skb->cb)[1]; - struct nlattr *data = ((void **)skb->cb)[2]; - - if (WARN_ON(!rdev->testmode_info)) { - kfree_skb(skb); - return -EINVAL; - } - - nla_nest_end(skb, data); - genlmsg_end(skb, hdr); - return genlmsg_reply(skb, rdev->testmode_info); -} -EXPORT_SYMBOL(cfg80211_testmode_reply); - -struct sk_buff *cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy, - int approxlen, gfp_t gfp) -{ - struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - - return __cfg80211_testmode_alloc_skb(rdev, approxlen, 0, 0, gfp); -} -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]; - - nla_nest_end(skb, data); - genlmsg_end(skb, hdr); - genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), skb, 0, - NL80211_MCGRP_TESTMODE, gfp); -} -EXPORT_SYMBOL(cfg80211_testmode_event); #endif static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) @@ -7312,11 +7355,72 @@ static bool ht_rateset_to_mask(struct ieee80211_supported_band *sband, return true; } +static u16 vht_mcs_map_to_mcs_mask(u8 vht_mcs_map) +{ + u16 mcs_mask = 0; + + switch (vht_mcs_map) { + case IEEE80211_VHT_MCS_NOT_SUPPORTED: + break; + case IEEE80211_VHT_MCS_SUPPORT_0_7: + mcs_mask = 0x00FF; + break; + case IEEE80211_VHT_MCS_SUPPORT_0_8: + mcs_mask = 0x01FF; + break; + case IEEE80211_VHT_MCS_SUPPORT_0_9: + mcs_mask = 0x03FF; + break; + default: + break; + } + + return mcs_mask; +} + +static void vht_build_mcs_mask(u16 vht_mcs_map, + u16 vht_mcs_mask[NL80211_VHT_NSS_MAX]) +{ + u8 nss; + + for (nss = 0; nss < NL80211_VHT_NSS_MAX; nss++) { + vht_mcs_mask[nss] = vht_mcs_map_to_mcs_mask(vht_mcs_map & 0x03); + vht_mcs_map >>= 2; + } +} + +static bool vht_set_mcs_mask(struct ieee80211_supported_band *sband, + struct nl80211_txrate_vht *txrate, + u16 mcs[NL80211_VHT_NSS_MAX]) +{ + u16 tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map); + u16 tx_mcs_mask[NL80211_VHT_NSS_MAX] = {}; + u8 i; + + if (!sband->vht_cap.vht_supported) + return false; + + memset(mcs, 0, sizeof(u16) * NL80211_VHT_NSS_MAX); + + /* Build vht_mcs_mask from VHT capabilities */ + vht_build_mcs_mask(tx_mcs_map, tx_mcs_mask); + + for (i = 0; i < NL80211_VHT_NSS_MAX; i++) { + if ((tx_mcs_mask[i] & txrate->mcs[i]) == txrate->mcs[i]) + mcs[i] = txrate->mcs[i]; + else + return false; + } + + return true; +} + static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = { [NL80211_TXRATE_LEGACY] = { .type = NLA_BINARY, .len = NL80211_MAX_SUPP_RATES }, - [NL80211_TXRATE_MCS] = { .type = NLA_BINARY, - .len = NL80211_MAX_SUPP_HT_RATES }, + [NL80211_TXRATE_HT] = { .type = NLA_BINARY, + .len = NL80211_MAX_SUPP_HT_RATES }, + [NL80211_TXRATE_VHT] = { .len = sizeof(struct nl80211_txrate_vht)}, }; static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, @@ -7329,9 +7433,7 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, struct net_device *dev = info->user_ptr[1]; struct nlattr *tx_rates; struct ieee80211_supported_band *sband; - - if (info->attrs[NL80211_ATTR_TX_RATES] == NULL) - return -EINVAL; + u16 vht_tx_mcs_map; if (!rdev->ops->set_bitrate_mask) return -EOPNOTSUPP; @@ -7340,17 +7442,26 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, /* Default to all rates enabled */ for (i = 0; i < IEEE80211_NUM_BANDS; i++) { sband = rdev->wiphy.bands[i]; - mask.control[i].legacy = - sband ? (1 << sband->n_bitrates) - 1 : 0; - if (sband) - memcpy(mask.control[i].mcs, - sband->ht_cap.mcs.rx_mask, - sizeof(mask.control[i].mcs)); - else - memset(mask.control[i].mcs, 0, - sizeof(mask.control[i].mcs)); + + if (!sband) + continue; + + mask.control[i].legacy = (1 << sband->n_bitrates) - 1; + memcpy(mask.control[i].ht_mcs, + sband->ht_cap.mcs.rx_mask, + sizeof(mask.control[i].ht_mcs)); + + if (!sband->vht_cap.vht_supported) + continue; + + vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map); + vht_build_mcs_mask(vht_tx_mcs_map, mask.control[i].vht_mcs); } + /* if no rates are given set it back to the defaults */ + if (!info->attrs[NL80211_ATTR_TX_RATES]) + goto out; + /* * The nested attribute uses enum nl80211_band as the index. This maps * directly to the enum ieee80211_band values used in cfg80211. @@ -7375,31 +7486,44 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, nla_len(tb[NL80211_TXRATE_LEGACY])) return -EINVAL; } - if (tb[NL80211_TXRATE_MCS]) { + if (tb[NL80211_TXRATE_HT]) { if (!ht_rateset_to_mask( sband, - nla_data(tb[NL80211_TXRATE_MCS]), - nla_len(tb[NL80211_TXRATE_MCS]), - mask.control[band].mcs)) + nla_data(tb[NL80211_TXRATE_HT]), + nla_len(tb[NL80211_TXRATE_HT]), + mask.control[band].ht_mcs)) + return -EINVAL; + } + if (tb[NL80211_TXRATE_VHT]) { + if (!vht_set_mcs_mask( + sband, + nla_data(tb[NL80211_TXRATE_VHT]), + mask.control[band].vht_mcs)) return -EINVAL; } if (mask.control[band].legacy == 0) { - /* don't allow empty legacy rates if HT - * is not even supported. */ - if (!rdev->wiphy.bands[band]->ht_cap.ht_supported) + /* don't allow empty legacy rates if HT or VHT + * are not even supported. + */ + if (!(rdev->wiphy.bands[band]->ht_cap.ht_supported || + rdev->wiphy.bands[band]->vht_cap.vht_supported)) return -EINVAL; for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) - if (mask.control[band].mcs[i]) - break; + if (mask.control[band].ht_mcs[i]) + goto out; + + for (i = 0; i < NL80211_VHT_NSS_MAX; i++) + if (mask.control[band].vht_mcs[i]) + goto out; /* legacy and mcs rates may not be both empty */ - if (i == IEEE80211_HT_MCS_MASK_LEN) - return -EINVAL; + return -EINVAL; } } +out: return rdev_set_bitrate_mask(rdev, dev, NULL, &mask); } @@ -7447,10 +7571,10 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) void *hdr = NULL; u64 cookie; struct sk_buff *msg = NULL; - unsigned int wait = 0; - bool offchan, no_cck, dont_wait_for_ack; - - dont_wait_for_ack = info->attrs[NL80211_ATTR_DONT_WAIT_FOR_ACK]; + struct cfg80211_mgmt_tx_params params = { + .dont_wait_for_ack = + info->attrs[NL80211_ATTR_DONT_WAIT_FOR_ACK], + }; if (!info->attrs[NL80211_ATTR_FRAME]) return -EINVAL; @@ -7477,24 +7601,24 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_DURATION]) { if (!(rdev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX)) return -EINVAL; - wait = nla_get_u32(info->attrs[NL80211_ATTR_DURATION]); + params.wait = nla_get_u32(info->attrs[NL80211_ATTR_DURATION]); /* * We should wait on the channel for at least a minimum amount * of time (10ms) but no longer than the driver supports. */ - if (wait < NL80211_MIN_REMAIN_ON_CHANNEL_TIME || - wait > rdev->wiphy.max_remain_on_channel_duration) + if (params.wait < NL80211_MIN_REMAIN_ON_CHANNEL_TIME || + params.wait > rdev->wiphy.max_remain_on_channel_duration) return -EINVAL; } - offchan = info->attrs[NL80211_ATTR_OFFCHANNEL_TX_OK]; + params.offchan = info->attrs[NL80211_ATTR_OFFCHANNEL_TX_OK]; - if (offchan && !(rdev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX)) + if (params.offchan && !(rdev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX)) return -EINVAL; - no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); + params.no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); /* get the channel if any has been specified, otherwise pass NULL to * the driver. The latter will use the current one @@ -7506,10 +7630,10 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) return err; } - if (!chandef.chan && offchan) + if (!chandef.chan && params.offchan) return -EINVAL; - if (!dont_wait_for_ack) { + if (!params.dont_wait_for_ack) { msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -7522,10 +7646,10 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) } } - err = cfg80211_mlme_mgmt_tx(rdev, wdev, chandef.chan, offchan, wait, - nla_data(info->attrs[NL80211_ATTR_FRAME]), - nla_len(info->attrs[NL80211_ATTR_FRAME]), - no_cck, dont_wait_for_ack, &cookie); + params.buf = nla_data(info->attrs[NL80211_ATTR_FRAME]); + params.len = nla_len(info->attrs[NL80211_ATTR_FRAME]); + params.chan = chandef.chan; + err = cfg80211_mlme_mgmt_tx(rdev, wdev, ¶ms, &cookie); if (err) goto free_msg; @@ -8859,6 +8983,162 @@ static int nl80211_crit_protocol_stop(struct sk_buff *skb, return 0; } +static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev = + __cfg80211_wdev_from_attrs(genl_info_net(info), info->attrs); + int i, err; + u32 vid, subcmd; + + if (!rdev->wiphy.vendor_commands) + return -EOPNOTSUPP; + + if (IS_ERR(wdev)) { + err = PTR_ERR(wdev); + if (err != -EINVAL) + return err; + wdev = NULL; + } else if (wdev->wiphy != &rdev->wiphy) { + return -EINVAL; + } + + if (!info->attrs[NL80211_ATTR_VENDOR_ID] || + !info->attrs[NL80211_ATTR_VENDOR_SUBCMD]) + return -EINVAL; + + vid = nla_get_u32(info->attrs[NL80211_ATTR_VENDOR_ID]); + subcmd = nla_get_u32(info->attrs[NL80211_ATTR_VENDOR_SUBCMD]); + for (i = 0; i < rdev->wiphy.n_vendor_commands; i++) { + const struct wiphy_vendor_command *vcmd; + void *data = NULL; + int len = 0; + + vcmd = &rdev->wiphy.vendor_commands[i]; + + if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd) + continue; + + if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV | + WIPHY_VENDOR_CMD_NEED_NETDEV)) { + if (!wdev) + return -EINVAL; + if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV && + !wdev->netdev) + return -EINVAL; + + if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) { + if (wdev->netdev && + !netif_running(wdev->netdev)) + return -ENETDOWN; + if (!wdev->netdev && !wdev->p2p_started) + return -ENETDOWN; + } + } else { + wdev = NULL; + } + + if (info->attrs[NL80211_ATTR_VENDOR_DATA]) { + data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]); + len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]); + } + + rdev->cur_cmd_info = info; + err = rdev->wiphy.vendor_commands[i].doit(&rdev->wiphy, wdev, + data, len); + rdev->cur_cmd_info = NULL; + return err; + } + + return -EOPNOTSUPP; +} + +struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy, + enum nl80211_commands cmd, + enum nl80211_attrs attr, + int approxlen) +{ + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + if (WARN_ON(!rdev->cur_cmd_info)) + return NULL; + + return __cfg80211_alloc_vendor_skb(rdev, approxlen, + rdev->cur_cmd_info->snd_portid, + rdev->cur_cmd_info->snd_seq, + cmd, attr, NULL, GFP_KERNEL); +} +EXPORT_SYMBOL(__cfg80211_alloc_reply_skb); + +int cfg80211_vendor_cmd_reply(struct sk_buff *skb) +{ + struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0]; + void *hdr = ((void **)skb->cb)[1]; + struct nlattr *data = ((void **)skb->cb)[2]; + + if (WARN_ON(!rdev->cur_cmd_info)) { + kfree_skb(skb); + return -EINVAL; + } + + nla_nest_end(skb, data); + genlmsg_end(skb, hdr); + return genlmsg_reply(skb, rdev->cur_cmd_info); +} +EXPORT_SYMBOL_GPL(cfg80211_vendor_cmd_reply); + + +static int nl80211_set_qos_map(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_qos_map *qos_map = NULL; + struct net_device *dev = info->user_ptr[1]; + u8 *pos, len, num_des, des_len, des; + int ret; + + if (!rdev->ops->set_qos_map) + return -EOPNOTSUPP; + + if (info->attrs[NL80211_ATTR_QOS_MAP]) { + pos = nla_data(info->attrs[NL80211_ATTR_QOS_MAP]); + len = nla_len(info->attrs[NL80211_ATTR_QOS_MAP]); + + if (len % 2 || len < IEEE80211_QOS_MAP_LEN_MIN || + len > IEEE80211_QOS_MAP_LEN_MAX) + return -EINVAL; + + qos_map = kzalloc(sizeof(struct cfg80211_qos_map), GFP_KERNEL); + if (!qos_map) + return -ENOMEM; + + num_des = (len - IEEE80211_QOS_MAP_LEN_MIN) >> 1; + if (num_des) { + des_len = num_des * + sizeof(struct cfg80211_dscp_exception); + memcpy(qos_map->dscp_exception, pos, des_len); + qos_map->num_des = num_des; + for (des = 0; des < num_des; des++) { + if (qos_map->dscp_exception[des].up > 7) { + kfree(qos_map); + return -EINVAL; + } + } + pos += des_len; + } + memcpy(qos_map->up, pos, IEEE80211_QOS_MAP_LEN_MIN); + } + + wdev_lock(dev->ieee80211_ptr); + ret = nl80211_key_allowed(dev->ieee80211_ptr); + if (!ret) + ret = rdev_set_qos_map(rdev, dev, qos_map); + wdev_unlock(dev->ieee80211_ptr); + + kfree(qos_map); + return ret; +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -9583,6 +9863,22 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_VENDOR, + .doit = nl80211_vendor_cmd, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_WIPHY | + NL80211_FLAG_NEED_RTNL, + }, + { + .cmd = NL80211_CMD_SET_QOS_MAP, + .doit = nl80211_set_qos_map, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, }; /* notification functions */ @@ -9716,40 +10012,31 @@ void nl80211_send_scan_start(struct cfg80211_registered_device *rdev, NL80211_MCGRP_SCAN, GFP_KERNEL); } -void nl80211_send_scan_done(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev) +struct sk_buff *nl80211_build_scan_msg(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, bool aborted) { struct sk_buff *msg; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) - return; + return NULL; if (nl80211_send_scan_msg(msg, rdev, wdev, 0, 0, 0, - NL80211_CMD_NEW_SCAN_RESULTS) < 0) { + aborted ? NL80211_CMD_SCAN_ABORTED : + NL80211_CMD_NEW_SCAN_RESULTS) < 0) { nlmsg_free(msg); - return; + return NULL; } - genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, - NL80211_MCGRP_SCAN, GFP_KERNEL); + return msg; } -void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev) +void nl80211_send_scan_result(struct cfg80211_registered_device *rdev, + struct sk_buff *msg) { - struct sk_buff *msg; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; - if (nl80211_send_scan_msg(msg, rdev, wdev, 0, 0, 0, - NL80211_CMD_SCAN_ABORTED) < 0) { - nlmsg_free(msg); - return; - } - genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, NL80211_MCGRP_SCAN, GFP_KERNEL); } @@ -10810,21 +11097,18 @@ void cfg80211_ch_switch_notify(struct net_device *dev, struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - trace_cfg80211_ch_switch_notify(dev, chandef); + ASSERT_WDEV_LOCK(wdev); - wdev_lock(wdev); + trace_cfg80211_ch_switch_notify(dev, chandef); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP && wdev->iftype != NL80211_IFTYPE_P2P_GO && wdev->iftype != NL80211_IFTYPE_ADHOC && wdev->iftype != NL80211_IFTYPE_MESH_POINT)) - goto out; + return; wdev->channel = chandef->chan; nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL); -out: - wdev_unlock(wdev); - return; } EXPORT_SYMBOL(cfg80211_ch_switch_notify); @@ -10883,7 +11167,7 @@ EXPORT_SYMBOL(cfg80211_cqm_txe_notify); void nl80211_radar_notify(struct cfg80211_registered_device *rdev, - struct cfg80211_chan_def *chandef, + const struct cfg80211_chan_def *chandef, enum nl80211_radar_event event, struct net_device *netdev, gfp_t gfp) { diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 2c0f2b3c07cb..75799746d845 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -8,10 +8,10 @@ void nl80211_exit(void); void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev); void nl80211_send_scan_start(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); -void nl80211_send_scan_done(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev); -void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev); +struct sk_buff *nl80211_build_scan_msg(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, bool aborted); +void nl80211_send_scan_result(struct cfg80211_registered_device *rdev, + struct sk_buff *msg); void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev, struct net_device *netdev, u32 cmd); void nl80211_send_sched_scan_results(struct cfg80211_registered_device *rdev, @@ -70,7 +70,7 @@ int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, void nl80211_radar_notify(struct cfg80211_registered_device *rdev, - struct cfg80211_chan_def *chandef, + const struct cfg80211_chan_def *chandef, enum nl80211_radar_event event, struct net_device *netdev, gfp_t gfp); diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 37ce9fdfe934..c8e225947adb 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -624,16 +624,12 @@ rdev_cancel_remain_on_channel(struct cfg80211_registered_device *rdev, static inline int rdev_mgmt_tx(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, - struct ieee80211_channel *chan, bool offchan, - unsigned int wait, const u8 *buf, size_t len, - bool no_cck, bool dont_wait_for_ack, u64 *cookie) + struct cfg80211_mgmt_tx_params *params, + u64 *cookie) { int ret; - trace_rdev_mgmt_tx(&rdev->wiphy, wdev, chan, offchan, - wait, no_cck, dont_wait_for_ack); - ret = rdev->ops->mgmt_tx(&rdev->wiphy, wdev, chan, offchan, - wait, buf, len, no_cck, - dont_wait_for_ack, cookie); + trace_rdev_mgmt_tx(&rdev->wiphy, wdev, params); + ret = rdev->ops->mgmt_tx(&rdev->wiphy, wdev, params, cookie); trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); return ret; } @@ -936,4 +932,19 @@ static inline int rdev_channel_switch(struct cfg80211_registered_device *rdev, return ret; } +static inline int rdev_set_qos_map(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_qos_map *qos_map) +{ + int ret = -EOPNOTSUPP; + + if (rdev->ops->set_qos_map) { + trace_rdev_set_qos_map(&rdev->wiphy, dev, qos_map); + ret = rdev->ops->set_qos_map(&rdev->wiphy, dev, qos_map); + trace_rdev_return_int(&rdev->wiphy, ret); + } + + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 7da67fd0b418..9b897fca7487 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -120,6 +120,48 @@ static const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy) return rtnl_dereference(wiphy->regd); } +static const char *reg_dfs_region_str(enum nl80211_dfs_regions dfs_region) +{ + switch (dfs_region) { + case NL80211_DFS_UNSET: + return "unset"; + case NL80211_DFS_FCC: + return "FCC"; + case NL80211_DFS_ETSI: + return "ETSI"; + case NL80211_DFS_JP: + return "JP"; + } + return "Unknown"; +} + +enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy) +{ + const struct ieee80211_regdomain *regd = NULL; + const struct ieee80211_regdomain *wiphy_regd = NULL; + + regd = get_cfg80211_regdom(); + if (!wiphy) + goto out; + + wiphy_regd = get_wiphy_regdom(wiphy); + if (!wiphy_regd) + goto out; + + if (wiphy_regd->dfs_region == regd->dfs_region) + goto out; + + REG_DBG_PRINT("%s: device specific dfs_region " + "(%s) disagrees with cfg80211's " + "central dfs_region (%s)\n", + dev_name(&wiphy->dev), + reg_dfs_region_str(wiphy_regd->dfs_region), + reg_dfs_region_str(regd->dfs_region)); + +out: + return regd->dfs_region; +} + static void rcu_free_regdom(const struct ieee80211_regdomain *r) { if (!r) @@ -163,35 +205,29 @@ static const struct ieee80211_regdomain world_regdom = { REG_RULE(2412-10, 2462+10, 40, 6, 20, 0), /* IEEE 802.11b/g, channels 12..13. */ REG_RULE(2467-10, 2472+10, 40, 6, 20, - NL80211_RRF_PASSIVE_SCAN | - NL80211_RRF_NO_IBSS), + NL80211_RRF_NO_IR), /* IEEE 802.11 channel 14 - Only JP enables * this and for 802.11b only */ REG_RULE(2484-10, 2484+10, 20, 6, 20, - NL80211_RRF_PASSIVE_SCAN | - NL80211_RRF_NO_IBSS | + NL80211_RRF_NO_IR | NL80211_RRF_NO_OFDM), /* IEEE 802.11a, channel 36..48 */ REG_RULE(5180-10, 5240+10, 160, 6, 20, - NL80211_RRF_PASSIVE_SCAN | - NL80211_RRF_NO_IBSS), + NL80211_RRF_NO_IR), /* IEEE 802.11a, channel 52..64 - DFS required */ REG_RULE(5260-10, 5320+10, 160, 6, 20, - NL80211_RRF_PASSIVE_SCAN | - NL80211_RRF_NO_IBSS | + NL80211_RRF_NO_IR | NL80211_RRF_DFS), /* IEEE 802.11a, channel 100..144 - DFS required */ REG_RULE(5500-10, 5720+10, 160, 6, 20, - NL80211_RRF_PASSIVE_SCAN | - NL80211_RRF_NO_IBSS | + NL80211_RRF_NO_IR | NL80211_RRF_DFS), /* IEEE 802.11a, channel 149..165 */ REG_RULE(5745-10, 5825+10, 80, 6, 20, - NL80211_RRF_PASSIVE_SCAN | - NL80211_RRF_NO_IBSS), + NL80211_RRF_NO_IR), /* IEEE 802.11ad (60gHz), channels 1..3 */ REG_RULE(56160+2160*1-1080, 56160+2160*3+1080, 2160, 0, 0, 0), @@ -208,11 +244,26 @@ static char user_alpha2[2]; module_param(ieee80211_regdom, charp, 0444); MODULE_PARM_DESC(ieee80211_regdom, "IEEE 802.11 regulatory domain code"); +static void reg_kfree_last_request(void) +{ + struct regulatory_request *lr; + + lr = get_last_request(); + + if (lr != &core_request_world && lr) + kfree_rcu(lr, rcu_head); +} + +static void reg_update_last_request(struct regulatory_request *request) +{ + reg_kfree_last_request(); + rcu_assign_pointer(last_request, request); +} + static void reset_regdomains(bool full_reset, const struct ieee80211_regdomain *new_regdom) { const struct ieee80211_regdomain *r; - struct regulatory_request *lr; ASSERT_RTNL(); @@ -235,10 +286,7 @@ static void reset_regdomains(bool full_reset, if (!full_reset) return; - lr = get_last_request(); - if (lr != &core_request_world && lr) - kfree_rcu(lr, rcu_head); - rcu_assign_pointer(last_request, &core_request_world); + reg_update_last_request(&core_request_world); } /* @@ -456,7 +504,15 @@ static int call_crda(const char *alpha2) return kobject_uevent(®_pdev->dev.kobj, KOBJ_CHANGE); } -static bool reg_is_valid_request(const char *alpha2) +static enum reg_request_treatment +reg_call_crda(struct regulatory_request *request) +{ + if (call_crda(request->alpha2)) + return REG_REQ_IGNORE; + return REG_REQ_OK; +} + +bool reg_is_valid_request(const char *alpha2) { struct regulatory_request *lr = get_last_request(); @@ -557,6 +613,20 @@ static bool freq_in_rule_band(const struct ieee80211_freq_range *freq_range, } /* + * Later on we can perhaps use the more restrictive DFS + * region but we don't have information for that yet so + * for now simply disallow conflicts. + */ +static enum nl80211_dfs_regions +reg_intersect_dfs_region(const enum nl80211_dfs_regions dfs_region1, + const enum nl80211_dfs_regions dfs_region2) +{ + if (dfs_region1 != dfs_region2) + return NL80211_DFS_UNSET; + return dfs_region1; +} + +/* * Helper for regdom_intersect(), this does the real * mathematical intersection fun */ @@ -687,6 +757,8 @@ regdom_intersect(const struct ieee80211_regdomain *rd1, rd->n_reg_rules = num_rules; rd->alpha2[0] = '9'; rd->alpha2[1] = '8'; + rd->dfs_region = reg_intersect_dfs_region(rd1->dfs_region, + rd2->dfs_region); return rd; } @@ -698,10 +770,8 @@ regdom_intersect(const struct ieee80211_regdomain *rd1, static u32 map_regdom_flags(u32 rd_flags) { u32 channel_flags = 0; - if (rd_flags & NL80211_RRF_PASSIVE_SCAN) - channel_flags |= IEEE80211_CHAN_PASSIVE_SCAN; - if (rd_flags & NL80211_RRF_NO_IBSS) - channel_flags |= IEEE80211_CHAN_NO_IBSS; + if (rd_flags & NL80211_RRF_NO_IR_ALL) + channel_flags |= IEEE80211_CHAN_NO_IR; if (rd_flags & NL80211_RRF_DFS) channel_flags |= IEEE80211_CHAN_RADAR; if (rd_flags & NL80211_RRF_NO_OFDM) @@ -854,8 +924,18 @@ static void handle_channel(struct wiphy *wiphy, PTR_ERR(reg_rule) == -ERANGE) return; - REG_DBG_PRINT("Disabling freq %d MHz\n", chan->center_freq); - chan->flags |= IEEE80211_CHAN_DISABLED; + if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && + request_wiphy && request_wiphy == wiphy && + request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { + REG_DBG_PRINT("Disabling freq %d MHz for good\n", + chan->center_freq); + chan->orig_flags |= IEEE80211_CHAN_DISABLED; + chan->flags = chan->orig_flags; + } else { + REG_DBG_PRINT("Disabling freq %d MHz\n", + chan->center_freq); + chan->flags |= IEEE80211_CHAN_DISABLED; + } return; } @@ -873,7 +953,7 @@ static void handle_channel(struct wiphy *wiphy, if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && request_wiphy && request_wiphy == wiphy && - request_wiphy->flags & WIPHY_FLAG_STRICT_REGULATORY) { + request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { /* * This guarantees the driver's requested regulatory domain * will always be used as a base for further regulatory @@ -899,13 +979,11 @@ static void handle_channel(struct wiphy *wiphy, chan->max_reg_power = (int) MBM_TO_DBM(power_rule->max_eirp); if (chan->orig_mpwr) { /* - * Devices that have their own custom regulatory domain - * but also use WIPHY_FLAG_STRICT_REGULATORY will follow the - * passed country IE power settings. + * Devices that use REGULATORY_COUNTRY_IE_FOLLOW_POWER + * will always follow the passed country IE power settings. */ if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && - wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY && - wiphy->flags & WIPHY_FLAG_STRICT_REGULATORY) + wiphy->regulatory_flags & REGULATORY_COUNTRY_IE_FOLLOW_POWER) chan->max_power = chan->max_reg_power; else chan->max_power = min(chan->orig_mpwr, @@ -975,8 +1053,8 @@ static bool reg_dev_ignore_cell_hint(struct wiphy *wiphy) static bool wiphy_strict_alpha2_regd(struct wiphy *wiphy) { - if (wiphy->flags & WIPHY_FLAG_STRICT_REGULATORY && - !(wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY)) + if (wiphy->regulatory_flags & REGULATORY_STRICT_REG && + !(wiphy->regulatory_flags & REGULATORY_CUSTOM_REG)) return true; return false; } @@ -994,7 +1072,7 @@ static bool ignore_reg_update(struct wiphy *wiphy, } if (initiator == NL80211_REGDOM_SET_BY_CORE && - wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY) { + wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) { REG_DBG_PRINT("Ignoring regulatory request set by %s " "since the driver uses its own custom " "regulatory domain\n", @@ -1032,7 +1110,7 @@ static bool reg_is_world_roaming(struct wiphy *wiphy) return true; if (lr && lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && - wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY) + wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) return true; return false; @@ -1060,19 +1138,14 @@ static void handle_reg_beacon(struct wiphy *wiphy, unsigned int chan_idx, if (!reg_is_world_roaming(wiphy)) return; - if (wiphy->flags & WIPHY_FLAG_DISABLE_BEACON_HINTS) + if (wiphy->regulatory_flags & REGULATORY_DISABLE_BEACON_HINTS) return; chan_before.center_freq = chan->center_freq; chan_before.flags = chan->flags; - if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) { - chan->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN; - channel_changed = true; - } - - if (chan->flags & IEEE80211_CHAN_NO_IBSS) { - chan->flags &= ~IEEE80211_CHAN_NO_IBSS; + if (chan->flags & IEEE80211_CHAN_NO_IR) { + chan->flags &= ~IEEE80211_CHAN_NO_IR; channel_changed = true; } @@ -1205,14 +1278,30 @@ static void reg_process_ht_flags(struct wiphy *wiphy) reg_process_ht_flags_band(wiphy, wiphy->bands[band]); } +static void reg_call_notifier(struct wiphy *wiphy, + struct regulatory_request *request) +{ + if (wiphy->reg_notifier) + wiphy->reg_notifier(wiphy, request); +} + static void wiphy_update_regulatory(struct wiphy *wiphy, enum nl80211_reg_initiator initiator) { enum ieee80211_band band; struct regulatory_request *lr = get_last_request(); - if (ignore_reg_update(wiphy, initiator)) + if (ignore_reg_update(wiphy, initiator)) { + /* + * Regulatory updates set by CORE are ignored for custom + * regulatory cards. Let us notify the changes to the driver, + * as some drivers used this to restore its orig_* reg domain. + */ + if (initiator == NL80211_REGDOM_SET_BY_CORE && + wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) + reg_call_notifier(wiphy, lr); return; + } lr->dfs_region = get_cfg80211_regdom()->dfs_region; @@ -1221,9 +1310,7 @@ static void wiphy_update_regulatory(struct wiphy *wiphy, reg_process_beacons(wiphy); reg_process_ht_flags(wiphy); - - if (wiphy->reg_notifier) - wiphy->reg_notifier(wiphy, lr); + reg_call_notifier(wiphy, lr); } static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator) @@ -1236,15 +1323,6 @@ static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator) list_for_each_entry(rdev, &cfg80211_rdev_list, list) { wiphy = &rdev->wiphy; wiphy_update_regulatory(wiphy, initiator); - /* - * Regulatory updates set by CORE are ignored for custom - * regulatory cards. Let us notify the changes to the driver, - * as some drivers used this to restore its orig_* reg domain. - */ - if (initiator == NL80211_REGDOM_SET_BY_CORE && - wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY && - wiphy->reg_notifier) - wiphy->reg_notifier(wiphy, get_last_request()); } } @@ -1263,7 +1341,8 @@ static void handle_channel_custom(struct wiphy *wiphy, if (IS_ERR(reg_rule)) { REG_DBG_PRINT("Disabling freq %d MHz as custom regd has no rule that fits it\n", chan->center_freq); - chan->flags = IEEE80211_CHAN_DISABLED; + chan->orig_flags |= IEEE80211_CHAN_DISABLED; + chan->flags = chan->orig_flags; return; } @@ -1305,6 +1384,10 @@ void wiphy_apply_custom_regulatory(struct wiphy *wiphy, enum ieee80211_band band; unsigned int bands_set = 0; + WARN(!(wiphy->regulatory_flags & REGULATORY_CUSTOM_REG), + "wiphy should have REGULATORY_CUSTOM_REG\n"); + wiphy->regulatory_flags |= REGULATORY_CUSTOM_REG; + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { if (!wiphy->bands[band]) continue; @@ -1320,225 +1403,285 @@ void wiphy_apply_custom_regulatory(struct wiphy *wiphy, } EXPORT_SYMBOL(wiphy_apply_custom_regulatory); -/* This has the logic which determines when a new request - * should be ignored. */ -static enum reg_request_treatment -get_reg_request_treatment(struct wiphy *wiphy, - struct regulatory_request *pending_request) +static void reg_set_request_processed(void) { - struct wiphy *last_wiphy = NULL; + bool need_more_processing = false; struct regulatory_request *lr = get_last_request(); - /* All initial requests are respected */ - if (!lr) - return REG_REQ_OK; + lr->processed = true; - switch (pending_request->initiator) { - case NL80211_REGDOM_SET_BY_CORE: - return REG_REQ_OK; - case NL80211_REGDOM_SET_BY_COUNTRY_IE: - if (reg_request_cell_base(lr)) { - /* Trust a Cell base station over the AP's country IE */ - if (regdom_changes(pending_request->alpha2)) - return REG_REQ_IGNORE; - return REG_REQ_ALREADY_SET; - } + spin_lock(®_requests_lock); + if (!list_empty(®_requests_list)) + need_more_processing = true; + spin_unlock(®_requests_lock); - last_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); + if (lr->initiator == NL80211_REGDOM_SET_BY_USER) + cancel_delayed_work(®_timeout); - if (unlikely(!is_an_alpha2(pending_request->alpha2))) - return -EINVAL; - if (lr->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE) { - if (last_wiphy != wiphy) { - /* - * Two cards with two APs claiming different - * Country IE alpha2s. We could - * intersect them, but that seems unlikely - * to be correct. Reject second one for now. - */ - if (regdom_changes(pending_request->alpha2)) - return REG_REQ_IGNORE; - return REG_REQ_ALREADY_SET; - } - /* - * Two consecutive Country IE hints on the same wiphy. - * This should be picked up early by the driver/stack - */ - if (WARN_ON(regdom_changes(pending_request->alpha2))) - return REG_REQ_OK; - return REG_REQ_ALREADY_SET; - } - return REG_REQ_OK; - case NL80211_REGDOM_SET_BY_DRIVER: - if (lr->initiator == NL80211_REGDOM_SET_BY_CORE) { - if (regdom_changes(pending_request->alpha2)) - return REG_REQ_OK; - return REG_REQ_ALREADY_SET; - } + if (need_more_processing) + schedule_work(®_work); +} - /* - * This would happen if you unplug and plug your card - * back in or if you add a new device for which the previously - * loaded card also agrees on the regulatory domain. - */ - if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && - !regdom_changes(pending_request->alpha2)) - return REG_REQ_ALREADY_SET; +/** + * reg_process_hint_core - process core regulatory requests + * @pending_request: a pending core regulatory request + * + * The wireless subsystem can use this function to process + * a regulatory request issued by the regulatory core. + * + * Returns one of the different reg request treatment values. + */ +static enum reg_request_treatment +reg_process_hint_core(struct regulatory_request *core_request) +{ + + core_request->intersect = false; + core_request->processed = false; + + reg_update_last_request(core_request); + + return reg_call_crda(core_request); +} +static enum reg_request_treatment +__reg_process_hint_user(struct regulatory_request *user_request) +{ + struct regulatory_request *lr = get_last_request(); + + if (reg_request_cell_base(user_request)) + return reg_ignore_cell_hint(user_request); + + if (reg_request_cell_base(lr)) + return REG_REQ_IGNORE; + + if (lr->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE) return REG_REQ_INTERSECT; - case NL80211_REGDOM_SET_BY_USER: - if (reg_request_cell_base(pending_request)) - return reg_ignore_cell_hint(pending_request); + /* + * If the user knows better the user should set the regdom + * to their country before the IE is picked up + */ + if (lr->initiator == NL80211_REGDOM_SET_BY_USER && + lr->intersect) + return REG_REQ_IGNORE; + /* + * Process user requests only after previous user/driver/core + * requests have been processed + */ + if ((lr->initiator == NL80211_REGDOM_SET_BY_CORE || + lr->initiator == NL80211_REGDOM_SET_BY_DRIVER || + lr->initiator == NL80211_REGDOM_SET_BY_USER) && + regdom_changes(lr->alpha2)) + return REG_REQ_IGNORE; - if (reg_request_cell_base(lr)) - return REG_REQ_IGNORE; + if (!regdom_changes(user_request->alpha2)) + return REG_REQ_ALREADY_SET; - if (lr->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE) - return REG_REQ_INTERSECT; - /* - * If the user knows better the user should set the regdom - * to their country before the IE is picked up - */ - if (lr->initiator == NL80211_REGDOM_SET_BY_USER && - lr->intersect) - return REG_REQ_IGNORE; - /* - * Process user requests only after previous user/driver/core - * requests have been processed - */ - if ((lr->initiator == NL80211_REGDOM_SET_BY_CORE || - lr->initiator == NL80211_REGDOM_SET_BY_DRIVER || - lr->initiator == NL80211_REGDOM_SET_BY_USER) && - regdom_changes(lr->alpha2)) - return REG_REQ_IGNORE; + return REG_REQ_OK; +} - if (!regdom_changes(pending_request->alpha2)) - return REG_REQ_ALREADY_SET; +/** + * reg_process_hint_user - process user regulatory requests + * @user_request: a pending user regulatory request + * + * The wireless subsystem can use this function to process + * a regulatory request initiated by userspace. + * + * Returns one of the different reg request treatment values. + */ +static enum reg_request_treatment +reg_process_hint_user(struct regulatory_request *user_request) +{ + enum reg_request_treatment treatment; - return REG_REQ_OK; + treatment = __reg_process_hint_user(user_request); + if (treatment == REG_REQ_IGNORE || + treatment == REG_REQ_ALREADY_SET) { + kfree(user_request); + return treatment; } - return REG_REQ_IGNORE; + user_request->intersect = treatment == REG_REQ_INTERSECT; + user_request->processed = false; + + reg_update_last_request(user_request); + + user_alpha2[0] = user_request->alpha2[0]; + user_alpha2[1] = user_request->alpha2[1]; + + return reg_call_crda(user_request); } -static void reg_set_request_processed(void) +static enum reg_request_treatment +__reg_process_hint_driver(struct regulatory_request *driver_request) { - bool need_more_processing = false; struct regulatory_request *lr = get_last_request(); - lr->processed = true; - - spin_lock(®_requests_lock); - if (!list_empty(®_requests_list)) - need_more_processing = true; - spin_unlock(®_requests_lock); + if (lr->initiator == NL80211_REGDOM_SET_BY_CORE) { + if (regdom_changes(driver_request->alpha2)) + return REG_REQ_OK; + return REG_REQ_ALREADY_SET; + } - if (lr->initiator == NL80211_REGDOM_SET_BY_USER) - cancel_delayed_work(®_timeout); + /* + * This would happen if you unplug and plug your card + * back in or if you add a new device for which the previously + * loaded card also agrees on the regulatory domain. + */ + if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && + !regdom_changes(driver_request->alpha2)) + return REG_REQ_ALREADY_SET; - if (need_more_processing) - schedule_work(®_work); + return REG_REQ_INTERSECT; } /** - * __regulatory_hint - hint to the wireless core a regulatory domain - * @wiphy: if the hint comes from country information from an AP, this - * is required to be set to the wiphy that received the information - * @pending_request: the regulatory request currently being processed + * reg_process_hint_driver - process driver regulatory requests + * @driver_request: a pending driver regulatory request * - * The Wireless subsystem can use this function to hint to the wireless core - * what it believes should be the current regulatory domain. + * The wireless subsystem can use this function to process + * a regulatory request issued by an 802.11 driver. * * Returns one of the different reg request treatment values. */ static enum reg_request_treatment -__regulatory_hint(struct wiphy *wiphy, - struct regulatory_request *pending_request) +reg_process_hint_driver(struct wiphy *wiphy, + struct regulatory_request *driver_request) { const struct ieee80211_regdomain *regd; - bool intersect = false; enum reg_request_treatment treatment; - struct regulatory_request *lr; - treatment = get_reg_request_treatment(wiphy, pending_request); + treatment = __reg_process_hint_driver(driver_request); switch (treatment) { - case REG_REQ_INTERSECT: - if (pending_request->initiator == - NL80211_REGDOM_SET_BY_DRIVER) { - regd = reg_copy_regd(get_cfg80211_regdom()); - if (IS_ERR(regd)) { - kfree(pending_request); - return PTR_ERR(regd); - } - rcu_assign_pointer(wiphy->regd, regd); - } - intersect = true; - break; case REG_REQ_OK: break; - default: - /* - * If the regulatory domain being requested by the - * driver has already been set just copy it to the - * wiphy - */ - if (treatment == REG_REQ_ALREADY_SET && - pending_request->initiator == NL80211_REGDOM_SET_BY_DRIVER) { - regd = reg_copy_regd(get_cfg80211_regdom()); - if (IS_ERR(regd)) { - kfree(pending_request); - return REG_REQ_IGNORE; - } - treatment = REG_REQ_ALREADY_SET; - rcu_assign_pointer(wiphy->regd, regd); - goto new_request; - } - kfree(pending_request); + case REG_REQ_IGNORE: + kfree(driver_request); return treatment; + case REG_REQ_INTERSECT: + /* fall through */ + case REG_REQ_ALREADY_SET: + regd = reg_copy_regd(get_cfg80211_regdom()); + if (IS_ERR(regd)) { + kfree(driver_request); + return REG_REQ_IGNORE; + } + rcu_assign_pointer(wiphy->regd, regd); } -new_request: - lr = get_last_request(); - if (lr != &core_request_world && lr) - kfree_rcu(lr, rcu_head); - pending_request->intersect = intersect; - pending_request->processed = false; - rcu_assign_pointer(last_request, pending_request); - lr = pending_request; + driver_request->intersect = treatment == REG_REQ_INTERSECT; + driver_request->processed = false; + + reg_update_last_request(driver_request); + + /* + * Since CRDA will not be called in this case as we already + * have applied the requested regulatory domain before we just + * inform userspace we have processed the request + */ + if (treatment == REG_REQ_ALREADY_SET) { + nl80211_send_reg_change_event(driver_request); + reg_set_request_processed(); + return treatment; + } + + return reg_call_crda(driver_request); +} - pending_request = NULL; +static enum reg_request_treatment +__reg_process_hint_country_ie(struct wiphy *wiphy, + struct regulatory_request *country_ie_request) +{ + struct wiphy *last_wiphy = NULL; + struct regulatory_request *lr = get_last_request(); - if (lr->initiator == NL80211_REGDOM_SET_BY_USER) { - user_alpha2[0] = lr->alpha2[0]; - user_alpha2[1] = lr->alpha2[1]; + if (reg_request_cell_base(lr)) { + /* Trust a Cell base station over the AP's country IE */ + if (regdom_changes(country_ie_request->alpha2)) + return REG_REQ_IGNORE; + return REG_REQ_ALREADY_SET; + } else { + if (wiphy->regulatory_flags & REGULATORY_COUNTRY_IE_IGNORE) + return REG_REQ_IGNORE; } - /* When r == REG_REQ_INTERSECT we do need to call CRDA */ - if (treatment != REG_REQ_OK && treatment != REG_REQ_INTERSECT) { + if (unlikely(!is_an_alpha2(country_ie_request->alpha2))) + return -EINVAL; + + if (lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE) + return REG_REQ_OK; + + last_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); + + if (last_wiphy != wiphy) { /* - * Since CRDA will not be called in this case as we already - * have applied the requested regulatory domain before we just - * inform userspace we have processed the request + * Two cards with two APs claiming different + * Country IE alpha2s. We could + * intersect them, but that seems unlikely + * to be correct. Reject second one for now. */ - if (treatment == REG_REQ_ALREADY_SET) { - nl80211_send_reg_change_event(lr); - reg_set_request_processed(); - } - return treatment; + if (regdom_changes(country_ie_request->alpha2)) + return REG_REQ_IGNORE; + return REG_REQ_ALREADY_SET; } + /* + * Two consecutive Country IE hints on the same wiphy. + * This should be picked up early by the driver/stack + */ + if (WARN_ON(regdom_changes(country_ie_request->alpha2))) + return REG_REQ_OK; + return REG_REQ_ALREADY_SET; +} - if (call_crda(lr->alpha2)) +/** + * reg_process_hint_country_ie - process regulatory requests from country IEs + * @country_ie_request: a regulatory request from a country IE + * + * The wireless subsystem can use this function to process + * a regulatory request issued by a country Information Element. + * + * Returns one of the different reg request treatment values. + */ +static enum reg_request_treatment +reg_process_hint_country_ie(struct wiphy *wiphy, + struct regulatory_request *country_ie_request) +{ + enum reg_request_treatment treatment; + + treatment = __reg_process_hint_country_ie(wiphy, country_ie_request); + + switch (treatment) { + case REG_REQ_OK: + break; + case REG_REQ_IGNORE: + /* fall through */ + case REG_REQ_ALREADY_SET: + kfree(country_ie_request); + return treatment; + case REG_REQ_INTERSECT: + kfree(country_ie_request); + /* + * This doesn't happen yet, not sure we + * ever want to support it for this case. + */ + WARN_ONCE(1, "Unexpected intersection for country IEs"); return REG_REQ_IGNORE; - return REG_REQ_OK; + } + + country_ie_request->intersect = false; + country_ie_request->processed = false; + + reg_update_last_request(country_ie_request); + + return reg_call_crda(country_ie_request); } /* This processes *all* regulatory hints */ -static void reg_process_hint(struct regulatory_request *reg_request, - enum nl80211_reg_initiator reg_initiator) +static void reg_process_hint(struct regulatory_request *reg_request) { struct wiphy *wiphy = NULL; + enum reg_request_treatment treatment; if (WARN_ON(!reg_request->alpha2)) return; @@ -1546,23 +1689,37 @@ static void reg_process_hint(struct regulatory_request *reg_request, if (reg_request->wiphy_idx != WIPHY_IDX_INVALID) wiphy = wiphy_idx_to_wiphy(reg_request->wiphy_idx); - if (reg_initiator == NL80211_REGDOM_SET_BY_DRIVER && !wiphy) { + if (reg_request->initiator == NL80211_REGDOM_SET_BY_DRIVER && !wiphy) { kfree(reg_request); return; } - switch (__regulatory_hint(wiphy, reg_request)) { - case REG_REQ_ALREADY_SET: - /* This is required so that the orig_* parameters are saved */ - if (wiphy && wiphy->flags & WIPHY_FLAG_STRICT_REGULATORY) - wiphy_update_regulatory(wiphy, reg_initiator); + switch (reg_request->initiator) { + case NL80211_REGDOM_SET_BY_CORE: + reg_process_hint_core(reg_request); + return; + case NL80211_REGDOM_SET_BY_USER: + treatment = reg_process_hint_user(reg_request); + if (treatment == REG_REQ_OK || + treatment == REG_REQ_ALREADY_SET) + return; + schedule_delayed_work(®_timeout, msecs_to_jiffies(3142)); + return; + case NL80211_REGDOM_SET_BY_DRIVER: + treatment = reg_process_hint_driver(wiphy, reg_request); break; - default: - if (reg_initiator == NL80211_REGDOM_SET_BY_USER) - schedule_delayed_work(®_timeout, - msecs_to_jiffies(3142)); + case NL80211_REGDOM_SET_BY_COUNTRY_IE: + treatment = reg_process_hint_country_ie(wiphy, reg_request); break; + default: + WARN(1, "invalid initiator %d\n", reg_request->initiator); + return; } + + /* This is required so that the orig_* parameters are saved */ + if (treatment == REG_REQ_ALREADY_SET && wiphy && + wiphy->regulatory_flags & REGULATORY_STRICT_REG) + wiphy_update_regulatory(wiphy, reg_request->initiator); } /* @@ -1596,7 +1753,7 @@ static void reg_process_pending_hints(void) spin_unlock(®_requests_lock); - reg_process_hint(reg_request, reg_request->initiator); + reg_process_hint(reg_request); } /* Processes beacon hints -- this has nothing to do with country IEs */ @@ -1696,6 +1853,8 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2) if (WARN_ON(!alpha2 || !wiphy)) return -EINVAL; + wiphy->regulatory_flags &= ~REGULATORY_CUSTOM_REG; + request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) return -ENOMEM; @@ -1888,7 +2047,7 @@ static void restore_regulatory_settings(bool reset_user) world_alpha2[1] = cfg80211_world_regdom->alpha2[1]; list_for_each_entry(rdev, &cfg80211_rdev_list, list) { - if (rdev->wiphy.flags & WIPHY_FLAG_CUSTOM_REGULATORY) + if (rdev->wiphy.regulatory_flags & REGULATORY_CUSTOM_REG) restore_custom_reg_settings(&rdev->wiphy); } @@ -2016,7 +2175,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) } } -bool reg_supported_dfs_region(u8 dfs_region) +bool reg_supported_dfs_region(enum nl80211_dfs_regions dfs_region) { switch (dfs_region) { case NL80211_DFS_UNSET: @@ -2031,27 +2190,6 @@ bool reg_supported_dfs_region(u8 dfs_region) } } -static void print_dfs_region(u8 dfs_region) -{ - if (!dfs_region) - return; - - switch (dfs_region) { - case NL80211_DFS_FCC: - pr_info(" DFS Master region FCC"); - break; - case NL80211_DFS_ETSI: - pr_info(" DFS Master region ETSI"); - break; - case NL80211_DFS_JP: - pr_info(" DFS Master region JP"); - break; - default: - pr_info(" DFS Master region Unknown"); - break; - } -} - static void print_regdomain(const struct ieee80211_regdomain *rd) { struct regulatory_request *lr = get_last_request(); @@ -2083,7 +2221,7 @@ static void print_regdomain(const struct ieee80211_regdomain *rd) } } - print_dfs_region(rd->dfs_region); + pr_info(" DFS Master region: %s", reg_dfs_region_str(rd->dfs_region)); print_rd_rules(rd); } @@ -2093,48 +2231,60 @@ static void print_regdomain_info(const struct ieee80211_regdomain *rd) print_rd_rules(rd); } -/* Takes ownership of rd only if it doesn't fail */ -static int __set_regdom(const struct ieee80211_regdomain *rd) +static int reg_set_rd_core(const struct ieee80211_regdomain *rd) +{ + if (!is_world_regdom(rd->alpha2)) + return -EINVAL; + update_world_regdomain(rd); + return 0; +} + +static int reg_set_rd_user(const struct ieee80211_regdomain *rd, + struct regulatory_request *user_request) { - const struct ieee80211_regdomain *regd; const struct ieee80211_regdomain *intersected_rd = NULL; - struct wiphy *request_wiphy; - struct regulatory_request *lr = get_last_request(); - /* Some basic sanity checks first */ + if (is_world_regdom(rd->alpha2)) + return -EINVAL; + + if (!regdom_changes(rd->alpha2)) + return -EALREADY; - if (!reg_is_valid_request(rd->alpha2)) + if (!is_valid_rd(rd)) { + pr_err("Invalid regulatory domain detected:\n"); + print_regdomain_info(rd); return -EINVAL; + } - if (is_world_regdom(rd->alpha2)) { - update_world_regdomain(rd); + if (!user_request->intersect) { + reset_regdomains(false, rd); return 0; } - if (!is_alpha2_set(rd->alpha2) && !is_an_alpha2(rd->alpha2) && - !is_unknown_alpha2(rd->alpha2)) + intersected_rd = regdom_intersect(rd, get_cfg80211_regdom()); + if (!intersected_rd) return -EINVAL; - /* - * Lets only bother proceeding on the same alpha2 if the current - * rd is non static (it means CRDA was present and was used last) - * and the pending request came in from a country IE - */ - if (lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE) { - /* - * If someone else asked us to change the rd lets only bother - * checking if the alpha2 changes if CRDA was already called - */ - if (!regdom_changes(rd->alpha2)) - return -EALREADY; - } + kfree(rd); + rd = NULL; + reset_regdomains(false, intersected_rd); - /* - * Now lets set the regulatory domain, update all driver channels - * and finally inform them of what we have done, in case they want - * to review or adjust their own settings based on their own - * internal EEPROM data - */ + return 0; +} + +static int reg_set_rd_driver(const struct ieee80211_regdomain *rd, + struct regulatory_request *driver_request) +{ + const struct ieee80211_regdomain *regd; + const struct ieee80211_regdomain *intersected_rd = NULL; + const struct ieee80211_regdomain *tmp; + struct wiphy *request_wiphy; + + if (is_world_regdom(rd->alpha2)) + return -EINVAL; + + if (!regdom_changes(rd->alpha2)) + return -EALREADY; if (!is_valid_rd(rd)) { pr_err("Invalid regulatory domain detected:\n"); @@ -2142,29 +2292,13 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) return -EINVAL; } - request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); - if (!request_wiphy && - (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER || - lr->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE)) { + request_wiphy = wiphy_idx_to_wiphy(driver_request->wiphy_idx); + if (!request_wiphy) { schedule_delayed_work(®_timeout, 0); return -ENODEV; } - if (!lr->intersect) { - if (lr->initiator != NL80211_REGDOM_SET_BY_DRIVER) { - reset_regdomains(false, rd); - return 0; - } - - /* - * For a driver hint, lets copy the regulatory domain the - * driver wanted to the wiphy to deal with conflicts - */ - - /* - * Userspace could have sent two replies with only - * one kernel request. - */ + if (!driver_request->intersect) { if (request_wiphy->regd) return -EALREADY; @@ -2177,38 +2311,59 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) return 0; } - /* Intersection requires a bit more work */ + intersected_rd = regdom_intersect(rd, get_cfg80211_regdom()); + if (!intersected_rd) + return -EINVAL; - if (lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE) { - intersected_rd = regdom_intersect(rd, get_cfg80211_regdom()); - if (!intersected_rd) - return -EINVAL; + /* + * We can trash what CRDA provided now. + * However if a driver requested this specific regulatory + * domain we keep it for its private use + */ + tmp = get_wiphy_regdom(request_wiphy); + rcu_assign_pointer(request_wiphy->regd, rd); + rcu_free_regdom(tmp); - /* - * We can trash what CRDA provided now. - * However if a driver requested this specific regulatory - * domain we keep it for its private use - */ - if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER) { - const struct ieee80211_regdomain *tmp; + rd = NULL; - tmp = get_wiphy_regdom(request_wiphy); - rcu_assign_pointer(request_wiphy->regd, rd); - rcu_free_regdom(tmp); - } else { - kfree(rd); - } + reset_regdomains(false, intersected_rd); + + return 0; +} - rd = NULL; +static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd, + struct regulatory_request *country_ie_request) +{ + struct wiphy *request_wiphy; - reset_regdomains(false, intersected_rd); + if (!is_alpha2_set(rd->alpha2) && !is_an_alpha2(rd->alpha2) && + !is_unknown_alpha2(rd->alpha2)) + return -EINVAL; - return 0; + /* + * Lets only bother proceeding on the same alpha2 if the current + * rd is non static (it means CRDA was present and was used last) + * and the pending request came in from a country IE + */ + + if (!is_valid_rd(rd)) { + pr_err("Invalid regulatory domain detected:\n"); + print_regdomain_info(rd); + return -EINVAL; } - return -EINVAL; -} + request_wiphy = wiphy_idx_to_wiphy(country_ie_request->wiphy_idx); + if (!request_wiphy) { + schedule_delayed_work(®_timeout, 0); + return -ENODEV; + } + + if (country_ie_request->intersect) + return -EINVAL; + reset_regdomains(false, rd); + return 0; +} /* * Use this call to set the current regulatory domain. Conflicts with @@ -2220,10 +2375,32 @@ int set_regdom(const struct ieee80211_regdomain *rd) struct regulatory_request *lr; int r; + if (!reg_is_valid_request(rd->alpha2)) { + kfree(rd); + return -EINVAL; + } + lr = get_last_request(); /* Note that this doesn't update the wiphys, this is done below */ - r = __set_regdom(rd); + switch (lr->initiator) { + case NL80211_REGDOM_SET_BY_CORE: + r = reg_set_rd_core(rd); + break; + case NL80211_REGDOM_SET_BY_USER: + r = reg_set_rd_user(rd, lr); + break; + case NL80211_REGDOM_SET_BY_DRIVER: + r = reg_set_rd_driver(rd, lr); + break; + case NL80211_REGDOM_SET_BY_COUNTRY_IE: + r = reg_set_rd_country_ie(rd, lr); + break; + default: + WARN(1, "invalid initiator %d\n", lr->initiator); + return -EINVAL; + } + if (r) { if (r == -EALREADY) reg_set_request_processed(); diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 9677e3c13da9..02bd8f4b0921 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -18,8 +18,10 @@ extern const struct ieee80211_regdomain __rcu *cfg80211_regdomain; +bool reg_is_valid_request(const char *alpha2); bool is_world_regdom(const char *alpha2); -bool reg_supported_dfs_region(u8 dfs_region); +bool reg_supported_dfs_region(enum nl80211_dfs_regions dfs_region); +enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy); int regulatory_hint_user(const char *alpha2, enum nl80211_user_reg_hint_type user_reg_hint_type); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d4397eba5408..d1ed4aebbbb7 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -161,18 +161,25 @@ static void __cfg80211_bss_expire(struct cfg80211_registered_device *dev, dev->bss_generation++; } -void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) +void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, + bool send_message) { struct cfg80211_scan_request *request; struct wireless_dev *wdev; + struct sk_buff *msg; #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif ASSERT_RTNL(); - request = rdev->scan_req; + if (rdev->scan_msg) { + nl80211_send_scan_result(rdev, rdev->scan_msg); + rdev->scan_msg = NULL; + return; + } + request = rdev->scan_req; if (!request) return; @@ -186,18 +193,16 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) if (wdev->netdev) cfg80211_sme_scan_done(wdev->netdev); - if (request->aborted) { - nl80211_send_scan_aborted(rdev, wdev); - } else { - if (request->flags & NL80211_SCAN_FLAG_FLUSH) { - /* flush entries from previous scans */ - spin_lock_bh(&rdev->bss_lock); - __cfg80211_bss_expire(rdev, request->scan_start); - spin_unlock_bh(&rdev->bss_lock); - } - nl80211_send_scan_done(rdev, wdev); + if (!request->aborted && + request->flags & NL80211_SCAN_FLAG_FLUSH) { + /* flush entries from previous scans */ + spin_lock_bh(&rdev->bss_lock); + __cfg80211_bss_expire(rdev, request->scan_start); + spin_unlock_bh(&rdev->bss_lock); } + msg = nl80211_build_scan_msg(rdev, wdev, request->aborted); + #ifdef CONFIG_CFG80211_WEXT if (wdev->netdev && !request->aborted) { memset(&wrqu, 0, sizeof(wrqu)); @@ -210,17 +215,12 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) dev_put(wdev->netdev); rdev->scan_req = NULL; + kfree(request); - /* - * OK. If this is invoked with "leak" then we can't - * free this ... but we've cleaned it up anyway. The - * driver failed to call the scan_done callback, so - * all bets are off, it might still be trying to use - * the scan request or not ... if it accesses the dev - * in there (it shouldn't anyway) then it may crash. - */ - if (!leak) - kfree(request); + if (!send_message) + rdev->scan_msg = msg; + else + nl80211_send_scan_result(rdev, msg); } void __cfg80211_scan_done(struct work_struct *wk) @@ -231,7 +231,7 @@ void __cfg80211_scan_done(struct work_struct *wk) scan_done_wk); rtnl_lock(); - ___cfg80211_scan_done(rdev, false); + ___cfg80211_scan_done(rdev, true); rtnl_unlock(); } @@ -1089,7 +1089,7 @@ int cfg80211_wext_siwscan(struct net_device *dev, if (IS_ERR(rdev)) return PTR_ERR(rdev); - if (rdev->scan_req) { + if (rdev->scan_req || rdev->scan_msg) { err = -EBUSY; goto out; } @@ -1099,11 +1099,8 @@ int cfg80211_wext_siwscan(struct net_device *dev, /* Determine number of channels, needed to allocate creq */ if (wreq && wreq->num_channels) n_channels = wreq->num_channels; - else { - for (band = 0; band < IEEE80211_NUM_BANDS; band++) - if (wiphy->bands[band]) - n_channels += wiphy->bands[band]->n_channels; - } + else + n_channels = ieee80211_get_num_supported_channels(wiphy); creq = kzalloc(sizeof(*creq) + sizeof(struct cfg80211_ssid) + n_channels * sizeof(void *), @@ -1494,7 +1491,7 @@ int cfg80211_wext_giwscan(struct net_device *dev, if (IS_ERR(rdev)) return PTR_ERR(rdev); - if (rdev->scan_req) + if (rdev->scan_req || rdev->scan_msg) return -EAGAIN; res = ieee80211_scan_results(rdev, info, extra, data->length); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index d3c5bd7c6b51..f04d4c32e96e 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -67,21 +67,14 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) ASSERT_RDEV_LOCK(rdev); ASSERT_WDEV_LOCK(wdev); - if (rdev->scan_req) + if (rdev->scan_req || rdev->scan_msg) return -EBUSY; - if (wdev->conn->params.channel) { + if (wdev->conn->params.channel) n_channels = 1; - } else { - enum ieee80211_band band; - n_channels = 0; + else + n_channels = ieee80211_get_num_supported_channels(wdev->wiphy); - for (band = 0; band < IEEE80211_NUM_BANDS; band++) { - if (!wdev->wiphy->bands[band]) - continue; - n_channels += wdev->wiphy->bands[band]->n_channels; - } - } request = kzalloc(sizeof(*request) + sizeof(request->ssids[0]) + sizeof(request->channels[0]) * n_channels, GFP_KERNEL); @@ -872,6 +865,8 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, for (i = 0; i < 6; i++) rdev_del_key(rdev, dev, i, false, NULL); + rdev_set_qos_map(rdev, dev, NULL); + #ifdef CONFIG_CFG80211_WEXT memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index ba5f0d6614d5..fbcc23edee54 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -186,6 +186,28 @@ #define BOOL_TO_STR(bo) (bo) ? "true" : "false" +#define QOS_MAP_ENTRY __field(u8, num_des) \ + __array(u8, dscp_exception, \ + 2 * IEEE80211_QOS_MAP_MAX_EX) \ + __array(u8, up, IEEE80211_QOS_MAP_LEN_MIN) +#define QOS_MAP_ASSIGN(qos_map) \ + do { \ + if ((qos_map)) { \ + __entry->num_des = (qos_map)->num_des; \ + memcpy(__entry->dscp_exception, \ + &(qos_map)->dscp_exception, \ + 2 * IEEE80211_QOS_MAP_MAX_EX); \ + memcpy(__entry->up, &(qos_map)->up, \ + IEEE80211_QOS_MAP_LEN_MIN); \ + } else { \ + __entry->num_des = 0; \ + memset(__entry->dscp_exception, 0, \ + 2 * IEEE80211_QOS_MAP_MAX_EX); \ + memset(__entry->up, 0, \ + IEEE80211_QOS_MAP_LEN_MIN); \ + } \ + } while (0) + /************************************************************* * rdev->ops traces * *************************************************************/ @@ -1653,9 +1675,8 @@ TRACE_EVENT(rdev_cancel_remain_on_channel, TRACE_EVENT(rdev_mgmt_tx, TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev, - struct ieee80211_channel *chan, bool offchan, - unsigned int wait, bool no_cck, bool dont_wait_for_ack), - TP_ARGS(wiphy, wdev, chan, offchan, wait, no_cck, dont_wait_for_ack), + struct cfg80211_mgmt_tx_params *params), + TP_ARGS(wiphy, wdev, params), TP_STRUCT__entry( WIPHY_ENTRY WDEV_ENTRY @@ -1668,11 +1689,11 @@ TRACE_EVENT(rdev_mgmt_tx, TP_fast_assign( WIPHY_ASSIGN; WDEV_ASSIGN; - CHAN_ASSIGN(chan); - __entry->offchan = offchan; - __entry->wait = wait; - __entry->no_cck = no_cck; - __entry->dont_wait_for_ack = dont_wait_for_ack; + CHAN_ASSIGN(params->chan); + __entry->offchan = params->offchan; + __entry->wait = params->wait; + __entry->no_cck = params->no_cck; + __entry->dont_wait_for_ack = params->dont_wait_for_ack; ), TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT ", " CHAN_PR_FMT ", offchan: %s," " wait: %u, no cck: %s, dont wait for ack: %s", @@ -1876,6 +1897,24 @@ TRACE_EVENT(rdev_channel_switch, __entry->counter_offset_presp) ); +TRACE_EVENT(rdev_set_qos_map, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_qos_map *qos_map), + TP_ARGS(wiphy, netdev, qos_map), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + QOS_MAP_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + QOS_MAP_ASSIGN(qos_map); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", num_des: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->num_des) +); + /************************************************************* * cfg80211 exported functions traces * *************************************************************/ diff --git a/net/wireless/util.c b/net/wireless/util.c index 935dea9485da..d39c37104ae2 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -689,7 +689,8 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, EXPORT_SYMBOL(ieee80211_amsdu_to_8023s); /* Given a data frame determine the 802.1p/1d tag to use. */ -unsigned int cfg80211_classify8021d(struct sk_buff *skb) +unsigned int cfg80211_classify8021d(struct sk_buff *skb, + struct cfg80211_qos_map *qos_map) { unsigned int dscp; unsigned char vlan_priority; @@ -720,6 +721,21 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb) return 0; } + if (qos_map) { + unsigned int i, tmp_dscp = dscp >> 2; + + for (i = 0; i < qos_map->num_des; i++) { + if (tmp_dscp == qos_map->dscp_exception[i].dscp) + return qos_map->dscp_exception[i].up; + } + + for (i = 0; i < 8; i++) { + if (tmp_dscp >= qos_map->up[i].low && + tmp_dscp <= qos_map->up[i].high) + return i; + } + } + return dscp >> 5; } EXPORT_SYMBOL(cfg80211_classify8021d); @@ -863,6 +879,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, dev->ieee80211_ptr->use_4addr = false; dev->ieee80211_ptr->mesh_id_up_len = 0; + wdev_lock(dev->ieee80211_ptr); + rdev_set_qos_map(rdev, dev, NULL); + wdev_unlock(dev->ieee80211_ptr); switch (otype) { case NL80211_IFTYPE_AP: @@ -1462,6 +1481,19 @@ int ieee80211_get_ratemask(struct ieee80211_supported_band *sband, return 0; } +unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy) +{ + enum ieee80211_band band; + unsigned int n_channels = 0; + + for (band = 0; band < IEEE80211_NUM_BANDS; band++) + if (wiphy->bands[band]) + n_channels += wiphy->bands[band]->n_channels; + + return n_channels; +} +EXPORT_SYMBOL(ieee80211_get_num_supported_channels); + /* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */ /* Ethernet-II snap header (RFC1042 for most EtherTypes) */ const unsigned char rfc1042_header[] __aligned(2) = diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index e7c6e862580d..5661a54ac7ee 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -370,7 +370,7 @@ static int cfg80211_wext_siwretry(struct net_device *dev, u8 oshort = wdev->wiphy->retry_short; int err; - if (retry->disabled || + if (retry->disabled || retry->value < 1 || retry->value > 255 || (retry->flags & IW_RETRY_TYPE) != IW_RETRY_LIMIT) return -EINVAL; @@ -412,9 +412,9 @@ int cfg80211_wext_giwretry(struct net_device *dev, * First return short value, iwconfig will ask long value * later if needed */ - retry->flags |= IW_RETRY_LIMIT; + retry->flags |= IW_RETRY_LIMIT | IW_RETRY_SHORT; retry->value = wdev->wiphy->retry_short; - if (wdev->wiphy->retry_long != wdev->wiphy->retry_short) + if (wdev->wiphy->retry_long == wdev->wiphy->retry_short) retry->flags |= IW_RETRY_LONG; return 0; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 7622789d3750..6177479c7de9 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -35,6 +35,8 @@ * response */ +#define pr_fmt(fmt) "X25: " fmt + #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> @@ -1080,7 +1082,7 @@ static int x25_sendmsg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct x25_sock *x25 = x25_sk(sk); - struct sockaddr_x25 *usx25 = (struct sockaddr_x25 *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_x25 *, usx25, msg->msg_name); struct sockaddr_x25 sx25; struct sk_buff *skb; unsigned char *asmptr; @@ -1256,7 +1258,7 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, { struct sock *sk = sock->sk; struct x25_sock *x25 = x25_sk(sk); - struct sockaddr_x25 *sx25 = (struct sockaddr_x25 *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_x25 *, sx25, msg->msg_name); size_t copied; int qbit, header_len; struct sk_buff *skb; @@ -1809,7 +1811,7 @@ static int __init x25_init(void) if (rc != 0) goto out_sock; - printk(KERN_INFO "X.25 for Linux Version 0.2\n"); + pr_info("Linux Version 0.2\n"); x25_register_sysctl(); rc = x25_proc_init(); diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index a8a236338e61..39231237e1c3 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -17,6 +17,8 @@ * 2000-09-04 Henner Eisen Prevent freeing a dangling skb. */ +#define pr_fmt(fmt) "X25: " fmt + #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/skbuff.h> @@ -89,7 +91,7 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb) */ if (frametype != X25_CLEAR_CONFIRMATION) - printk(KERN_DEBUG "x25_receive_data(): unknown frame type %2x\n",frametype); + pr_debug("x25_receive_data(): unknown frame type %2x\n",frametype); return 0; } @@ -114,7 +116,7 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, */ nb = x25_get_neigh(dev); if (!nb) { - printk(KERN_DEBUG "X.25: unknown neighbour - %s\n", dev->name); + pr_debug("unknown neighbour - %s\n", dev->name); goto drop; } @@ -154,7 +156,7 @@ void x25_establish_link(struct x25_neigh *nb) switch (nb->dev->type) { case ARPHRD_X25: if ((skb = alloc_skb(1, GFP_ATOMIC)) == NULL) { - printk(KERN_ERR "x25_dev: out of memory\n"); + pr_err("x25_dev: out of memory\n"); return; } ptr = skb_put(skb, 1); @@ -189,7 +191,7 @@ void x25_terminate_link(struct x25_neigh *nb) skb = alloc_skb(1, GFP_ATOMIC); if (!skb) { - printk(KERN_ERR "x25_dev: out of memory\n"); + pr_err("x25_dev: out of memory\n"); return; } diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index b8253250d723..7ecd04c21360 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -21,6 +21,8 @@ * on response. */ +#define pr_fmt(fmt) "X25: " fmt + #include <linux/kernel.h> #include <linux/string.h> #include <linux/skbuff.h> @@ -109,7 +111,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, case X25_MARKER: break; default: - printk(KERN_DEBUG "X.25: unknown facility " + pr_debug("unknown facility " "%02X, value %02X\n", p[0], p[1]); break; @@ -132,7 +134,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, *vc_fac_mask |= X25_MASK_WINDOW_SIZE; break; default: - printk(KERN_DEBUG "X.25: unknown facility " + pr_debug("unknown facility " "%02X, values %02X, %02X\n", p[0], p[1], p[2]); break; @@ -143,7 +145,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, case X25_FAC_CLASS_C: if (len < 4) return -1; - printk(KERN_DEBUG "X.25: unknown facility %02X, " + pr_debug("unknown facility %02X, " "values %02X, %02X, %02X\n", p[0], p[1], p[2], p[3]); p += 4; @@ -172,7 +174,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, *vc_fac_mask |= X25_MASK_CALLED_AE; break; default: - printk(KERN_DEBUG "X.25: unknown facility %02X," + pr_debug("unknown facility %02X," "length %d\n", p[0], p[1]); break; } @@ -341,12 +343,12 @@ void x25_limit_facilities(struct x25_facilities *facilities, if (!nb->extended) { if (facilities->winsize_in > 7) { - printk(KERN_DEBUG "X.25: incoming winsize limited to 7\n"); + pr_debug("incoming winsize limited to 7\n"); facilities->winsize_in = 7; } if (facilities->winsize_out > 7) { facilities->winsize_out = 7; - printk( KERN_DEBUG "X.25: outgoing winsize limited to 7\n"); + pr_debug("outgoing winsize limited to 7\n"); } } } diff --git a/net/x25/x25_forward.c b/net/x25/x25_forward.c index c541b622ae16..cf561f1613e1 100644 --- a/net/x25/x25_forward.c +++ b/net/x25/x25_forward.c @@ -8,6 +8,9 @@ * History * 03-01-2007 Added forwarding for x.25 Andrew Hendry */ + +#define pr_fmt(fmt) "X25: " fmt + #include <linux/if_arp.h> #include <linux/init.h> #include <linux/slab.h> @@ -51,7 +54,7 @@ int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from, list_for_each(entry, &x25_forward_list) { x25_frwd = list_entry(entry, struct x25_forward, node); if (x25_frwd->lci == lci) { - printk(KERN_WARNING "X.25: call request for lci which is already registered!, transmitting but not registering new pair\n"); + pr_warn("call request for lci which is already registered!, transmitting but not registering new pair\n"); same_lci = 1; } } diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index a49cd4ec551a..d1b0dc79bb6f 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -23,6 +23,8 @@ * i-frames. */ +#define pr_fmt(fmt) "X25: " fmt + #include <linux/slab.h> #include <linux/errno.h> #include <linux/kernel.h> @@ -317,7 +319,7 @@ static int x25_state3_machine(struct sock *sk, struct sk_buff *skb, int frametyp break; default: - printk(KERN_WARNING "x25: unknown %02X in state 3\n", frametype); + pr_warn("unknown %02X in state 3\n", frametype); break; } diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 4acacf3c6617..fd5ffb25873f 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -21,6 +21,8 @@ * 2000-09-04 Henner Eisen dev_hold() / dev_put() for x25_neigh. */ +#define pr_fmt(fmt) "X25: " fmt + #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/timer.h> @@ -93,13 +95,13 @@ void x25_link_control(struct sk_buff *skb, struct x25_neigh *nb, if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 4)) break; - printk(KERN_WARNING "x25: diagnostic #%d - %02X %02X %02X\n", + pr_warn("diagnostic #%d - %02X %02X %02X\n", skb->data[3], skb->data[4], skb->data[5], skb->data[6]); break; default: - printk(KERN_WARNING "x25: received unknown %02X with LCI 000\n", + pr_warn("received unknown %02X with LCI 000\n", frametype); break; } diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 5170d52bfd96..6b5af65f491f 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -23,6 +23,8 @@ * restriction on response. */ +#define pr_fmt(fmt) "X25: " fmt + #include <linux/slab.h> #include <linux/kernel.h> #include <linux/string.h> @@ -148,7 +150,7 @@ void x25_write_internal(struct sock *sk, int frametype) case X25_RESET_CONFIRMATION: break; default: - printk(KERN_ERR "X.25: invalid frame type %02X\n", frametype); + pr_err("invalid frame type %02X\n", frametype); return; } @@ -338,7 +340,7 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, } } - printk(KERN_DEBUG "X.25: invalid PLP frame %02X %02X %02X\n", + pr_debug("invalid PLP frame %02X %02X %02X\n", frame[0], frame[1], frame[2]); return X25_ILLEGAL; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 88843996f935..6c7ac016ce3a 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -67,7 +67,7 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) case IPPROTO_COMP: if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr))) return -EINVAL; - *spi = htonl(ntohs(*(__be16*)(skb_transport_header(skb) + 2))); + *spi = htonl(ntohs(*(__be16 *)(skb_transport_header(skb) + 2))); *seq = 0; return 0; default: @@ -77,8 +77,8 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) if (!pskb_may_pull(skb, hlen)) return -EINVAL; - *spi = *(__be32*)(skb_transport_header(skb) + offset); - *seq = *(__be32*)(skb_transport_header(skb) + offset_seq); + *spi = *(__be32 *)(skb_transport_header(skb) + offset); + *seq = *(__be32 *)(skb_transport_header(skb) + offset_seq); return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9a91f7431c41..4b98b25793c5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -39,12 +39,7 @@ #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ)) #define XFRM_MAX_QUEUE_LEN 100 -DEFINE_MUTEX(xfrm_cfg_mutex); -EXPORT_SYMBOL(xfrm_cfg_mutex); - -static DEFINE_SPINLOCK(xfrm_policy_sk_bundle_lock); static struct dst_entry *xfrm_policy_sk_bundles; -static DEFINE_RWLOCK(xfrm_policy_lock); static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO] @@ -176,7 +171,7 @@ static inline unsigned long make_jiffies(long secs) static void xfrm_policy_timer(unsigned long data) { - struct xfrm_policy *xp = (struct xfrm_policy*)data; + struct xfrm_policy *xp = (struct xfrm_policy *)data; unsigned long now = get_seconds(); long next = LONG_MAX; int warn = 0; @@ -438,7 +433,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) if (!ndst) return; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); for (i = hmask; i >= 0; i--) xfrm_dst_hash_transfer(odst + i, ndst, nhashmask); @@ -446,7 +441,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) net->xfrm.policy_bydst[dir].table = ndst; net->xfrm.policy_bydst[dir].hmask = nhashmask; - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head)); } @@ -463,7 +458,7 @@ static void xfrm_byidx_resize(struct net *net, int total) if (!nidx) return; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); for (i = hmask; i >= 0; i--) xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask); @@ -471,7 +466,7 @@ static void xfrm_byidx_resize(struct net *net, int total) net->xfrm.policy_byidx = nidx; net->xfrm.policy_idx_hmask = nhashmask; - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head)); } @@ -504,7 +499,7 @@ static inline int xfrm_byidx_should_resize(struct net *net, int total) void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) { - read_lock_bh(&xfrm_policy_lock); + read_lock_bh(&net->xfrm.xfrm_policy_lock); si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN]; si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT]; si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD]; @@ -513,7 +508,7 @@ void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; si->spdhcnt = net->xfrm.policy_idx_hmask; si->spdhmcnt = xfrm_policy_hashmax; - read_unlock_bh(&xfrm_policy_lock); + read_unlock_bh(&net->xfrm.xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_spd_getinfo); @@ -538,7 +533,7 @@ static void xfrm_hash_resize(struct work_struct *work) /* Generate new index... KAME seems to generate them ordered by cost * of an absolute inpredictability of ordering of rules. This will not pass. */ -static u32 xfrm_gen_index(struct net *net, int dir) +static u32 xfrm_gen_index(struct net *net, int dir, u32 index) { static u32 idx_generator; @@ -548,8 +543,14 @@ static u32 xfrm_gen_index(struct net *net, int dir) u32 idx; int found; - idx = (idx_generator | dir); - idx_generator += 8; + if (!index) { + idx = (idx_generator | dir); + idx_generator += 8; + } else { + idx = index; + index = 0; + } + if (idx == 0) idx = 8; list = net->xfrm.policy_byidx + idx_hash(net, idx); @@ -630,7 +631,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct hlist_head *chain; struct hlist_node *newpos; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); delpol = NULL; newpos = NULL; @@ -641,7 +642,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) { - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return -EEXIST; } delpol = pol; @@ -672,14 +673,14 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) xfrm_policy_requeue(delpol, policy); __xfrm_policy_unlink(delpol, dir); } - policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir); + policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index); hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index)); policy->curlft.add_time = get_seconds(); policy->curlft.use_time = 0; if (!mod_timer(&policy->timer, jiffies + HZ)) xfrm_pol_hold(policy); list_add(&policy->walk.all, &net->xfrm.policy_all); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (delpol) xfrm_policy_kill(delpol); @@ -699,7 +700,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, struct hlist_head *chain; *err = 0; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, sel, sel->family, dir); ret = NULL; hlist_for_each_entry(pol, chain, bydst) { @@ -712,7 +713,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, *err = security_xfrm_policy_delete( pol->security); if (*err) { - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); @@ -721,7 +722,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, break; } } - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); @@ -740,7 +741,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, return NULL; *err = 0; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); chain = net->xfrm.policy_byidx + idx_hash(net, id); ret = NULL; hlist_for_each_entry(pol, chain, byidx) { @@ -751,7 +752,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, *err = security_xfrm_policy_delete( pol->security); if (*err) { - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); @@ -760,7 +761,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, break; } } - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); @@ -823,7 +824,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) { int dir, err = 0, cnt = 0; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); err = xfrm_policy_flush_secctx_check(net, type, audit_info); if (err) @@ -839,7 +840,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) if (pol->type != type) continue; __xfrm_policy_unlink(pol, dir); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, audit_info->loginuid, @@ -848,7 +849,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) xfrm_policy_kill(pol); - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); goto again1; } @@ -860,7 +861,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) if (pol->type != type) continue; __xfrm_policy_unlink(pol, dir); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, @@ -869,7 +870,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) audit_info->secid); xfrm_policy_kill(pol); - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); goto again2; } } @@ -878,7 +879,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) if (!cnt) err = -ESRCH; out: - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; } EXPORT_SYMBOL(xfrm_policy_flush); @@ -898,7 +899,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, if (list_empty(&walk->walk.all) && walk->seq != 0) return 0; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); if (list_empty(&walk->walk.all)) x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all); else @@ -924,7 +925,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, } list_del_init(&walk->walk.all); out: - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return error; } EXPORT_SYMBOL(xfrm_policy_walk); @@ -938,14 +939,14 @@ void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type) } EXPORT_SYMBOL(xfrm_policy_walk_init); -void xfrm_policy_walk_done(struct xfrm_policy_walk *walk) +void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net) { if (list_empty(&walk->walk.all)) return; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */ list_del(&walk->walk.all); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_policy_walk_done); @@ -990,7 +991,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if (unlikely(!daddr || !saddr)) return NULL; - read_lock_bh(&xfrm_policy_lock); + read_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_direct(net, daddr, saddr, family, dir); ret = NULL; hlist_for_each_entry(pol, chain, bydst) { @@ -1026,7 +1027,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if (ret) xfrm_pol_hold(ret); fail: - read_unlock_bh(&xfrm_policy_lock); + read_unlock_bh(&net->xfrm.xfrm_policy_lock); return ret; } @@ -1103,8 +1104,9 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, const struct flowi *fl) { struct xfrm_policy *pol; + struct net *net = sock_net(sk); - read_lock_bh(&xfrm_policy_lock); + read_lock_bh(&net->xfrm.xfrm_policy_lock); if ((pol = sk->sk_policy[dir]) != NULL) { bool match = xfrm_selector_match(&pol->selector, fl, sk->sk_family); @@ -1128,7 +1130,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, pol = NULL; } out: - read_unlock_bh(&xfrm_policy_lock); + read_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } @@ -1166,9 +1168,11 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int xfrm_policy_delete(struct xfrm_policy *pol, int dir) { - write_lock_bh(&xfrm_policy_lock); + struct net *net = xp_net(pol); + + write_lock_bh(&net->xfrm.xfrm_policy_lock); pol = __xfrm_policy_unlink(pol, dir); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (pol) { xfrm_policy_kill(pol); return 0; @@ -1187,12 +1191,12 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) return -EINVAL; #endif - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); old_pol = sk->sk_policy[dir]; sk->sk_policy[dir] = pol; if (pol) { pol->curlft.add_time = get_seconds(); - pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir); + pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0); __xfrm_policy_link(pol, XFRM_POLICY_MAX+dir); } if (old_pol) { @@ -1204,7 +1208,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) */ __xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir); } - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (old_pol) { xfrm_policy_kill(old_pol); @@ -1215,6 +1219,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) { struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC); + struct net *net = xp_net(old); if (newp) { newp->selector = old->selector; @@ -1233,9 +1238,9 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) newp->type = old->type; memcpy(newp->xfrm_vec, old->xfrm_vec, newp->xfrm_nr*sizeof(struct xfrm_tmpl)); - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); __xfrm_policy_link(newp, XFRM_POLICY_MAX+dir); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_pol_put(newp); } return newp; @@ -1281,7 +1286,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family); xfrm_address_t tmp; - for (nx=0, i = 0; i < policy->xfrm_nr; i++) { + for (nx = 0, i = 0; i < policy->xfrm_nr; i++) { struct xfrm_state *x; xfrm_address_t *remote = daddr; xfrm_address_t *local = saddr; @@ -1311,9 +1316,9 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, error = (x->km.state == XFRM_STATE_ERROR ? -EINVAL : -EAGAIN); xfrm_state_put(x); - } - else if (error == -ESRCH) + } else if (error == -ESRCH) { error = -EAGAIN; + } if (!tmpl->optional) goto fail; @@ -1321,7 +1326,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, return nx; fail: - for (nx--; nx>=0; nx--) + for (nx--; nx >= 0; nx--) xfrm_state_put(xfrm[nx]); return error; } @@ -1358,7 +1363,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, return cnx; fail: - for (cnx--; cnx>=0; cnx--) + for (cnx--; cnx >= 0; cnx--) xfrm_state_put(tpp[cnx]); return error; @@ -1636,20 +1641,22 @@ free_dst: goto out; } -static int inline -xfrm_dst_alloc_copy(void **target, const void *src, int size) +#ifdef CONFIG_XFRM_SUB_POLICY +static int xfrm_dst_alloc_copy(void **target, const void *src, int size) { if (!*target) { *target = kmalloc(size, GFP_ATOMIC); if (!*target) return -ENOMEM; } + memcpy(*target, src, size); return 0; } +#endif -static int inline -xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel) +static int xfrm_dst_update_parent(struct dst_entry *dst, + const struct xfrm_selector *sel) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_dst *xdst = (struct xfrm_dst *)dst; @@ -1660,8 +1667,8 @@ xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel) #endif } -static int inline -xfrm_dst_update_origin(struct dst_entry *dst, const struct flowi *fl) +static int xfrm_dst_update_origin(struct dst_entry *dst, + const struct flowi *fl) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_dst *xdst = (struct xfrm_dst *)dst; @@ -1699,7 +1706,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, xfrm_pols_put(pols, *num_pols); return PTR_ERR(pols[1]); } - (*num_pols) ++; + (*num_pols)++; (*num_xfrms) += pols[1]->xfrm_nr; } } @@ -1753,7 +1760,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, } xdst->num_pols = num_pols; - memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols); + memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); xdst->policy_genid = atomic_read(&pols[0]->genid); return xdst; @@ -1896,8 +1903,7 @@ static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, if (IS_ERR(xdst)) return xdst; - if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0 || - (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP)) + if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0) return xdst; dst1 = &xdst->u.dst; @@ -2023,7 +2029,7 @@ make_dummy_bundle: } xdst->num_pols = num_pols; xdst->num_xfrms = num_xfrms; - memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols); + memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); dst_hold(&xdst->u.dst); return &xdst->flo; @@ -2072,7 +2078,6 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT); int i, err, num_pols, num_xfrms = 0, drop_pols = 0; -restart: dst = NULL; xdst = NULL; route = NULL; @@ -2106,10 +2111,10 @@ restart: dst_hold(&xdst->u.dst); - spin_lock_bh(&xfrm_policy_sk_bundle_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); xdst->u.dst.next = xfrm_policy_sk_bundles; xfrm_policy_sk_bundles = &xdst->u.dst; - spin_unlock_bh(&xfrm_policy_sk_bundle_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); route = xdst->route; } @@ -2133,7 +2138,7 @@ restart: num_pols = xdst->num_pols; num_xfrms = xdst->num_xfrms; - memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols); + memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols); route = xdst->route; } @@ -2152,23 +2157,8 @@ restart: return make_blackhole(net, family, dst_orig); } - if (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP) { - DECLARE_WAITQUEUE(wait, current); - add_wait_queue(&net->xfrm.km_waitq, &wait); - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - set_current_state(TASK_RUNNING); - remove_wait_queue(&net->xfrm.km_waitq, &wait); - - if (!signal_pending(current)) { - dst_release(dst); - goto restart; - } - - err = -ERESTART; - } else - err = -EAGAIN; + err = -EAGAIN; XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); goto error; @@ -2344,7 +2334,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (skb->sp) { int i; - for (i=skb->sp->len-1; i>=0; i--) { + for (i = skb->sp->len-1; i >= 0; i--) { struct xfrm_state *x = skb->sp->xvec[i]; if (!xfrm_selector_match(&x->sel, &fl, family)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); @@ -2390,7 +2380,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol->curlft.use_time = get_seconds(); pols[0] = pol; - npols ++; + npols++; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, @@ -2402,7 +2392,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 0; } pols[1]->curlft.use_time = get_seconds(); - npols ++; + npols++; } } #endif @@ -2434,7 +2424,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } xfrm_nr = ti; if (npols > 1) { - xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); + xfrm_tmpl_sort(stp, tpp, xfrm_nr, family, net); tpp = stp; } @@ -2563,10 +2553,10 @@ static void __xfrm_garbage_collect(struct net *net) { struct dst_entry *head, *next; - spin_lock_bh(&xfrm_policy_sk_bundle_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); head = xfrm_policy_sk_bundles; xfrm_policy_sk_bundles = NULL; - spin_unlock_bh(&xfrm_policy_sk_bundle_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); while (head) { next = head->next; @@ -2906,12 +2896,12 @@ static void xfrm_policy_fini(struct net *net) flush_work(&net->xfrm.policy_hash_work); #ifdef CONFIG_XFRM_SUB_POLICY audit_info.loginuid = INVALID_UID; - audit_info.sessionid = -1; + audit_info.sessionid = (unsigned int)-1; audit_info.secid = 0; xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, &audit_info); #endif audit_info.loginuid = INVALID_UID; - audit_info.sessionid = -1; + audit_info.sessionid = (unsigned int)-1; audit_info.secid = 0; xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, &audit_info); @@ -2950,6 +2940,13 @@ static int __net_init xfrm_net_init(struct net *net) rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; + + /* Initialize the per-net locks here */ + spin_lock_init(&net->xfrm.xfrm_state_lock); + rwlock_init(&net->xfrm.xfrm_policy_lock); + spin_lock_init(&net->xfrm.xfrm_policy_sk_bundle_lock); + mutex_init(&net->xfrm.xfrm_cfg_mutex); + return 0; out_sysctl: @@ -2992,7 +2989,7 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp, audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); - switch(sel->family) { + switch (sel->family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4); if (sel->prefixlen_s != 32) @@ -3017,7 +3014,7 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp, } void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, - kuid_t auid, u32 sessionid, u32 secid) + kuid_t auid, unsigned int sessionid, u32 secid) { struct audit_buffer *audit_buf; @@ -3032,7 +3029,7 @@ void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, EXPORT_SYMBOL_GPL(xfrm_audit_policy_add); void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, - kuid_t auid, u32 sessionid, u32 secid) + kuid_t auid, unsigned int sessionid, u32 secid) { struct audit_buffer *audit_buf; @@ -3069,15 +3066,15 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, return false; } -static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel, - u8 dir, u8 type) +static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel, + u8 dir, u8 type, struct net *net) { struct xfrm_policy *pol, *ret = NULL; struct hlist_head *chain; u32 priority = ~0U; - read_lock_bh(&xfrm_policy_lock); - chain = policy_hash_direct(&init_net, &sel->daddr, &sel->saddr, sel->family, dir); + read_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME*/ + chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir); hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { @@ -3086,7 +3083,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector break; } } - chain = &init_net.xfrm.policy_inexact[dir]; + chain = &net->xfrm.policy_inexact[dir]; hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type && @@ -3099,7 +3096,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector if (ret) xfrm_pol_hold(ret); - read_unlock_bh(&xfrm_policy_lock); + read_unlock_bh(&net->xfrm.xfrm_policy_lock); return ret; } @@ -3210,7 +3207,7 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, - struct xfrm_kmaddress *k) + struct xfrm_kmaddress *k, struct net *net) { int i, err, nx_cur = 0, nx_new = 0; struct xfrm_policy *pol = NULL; @@ -3223,14 +3220,14 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, goto out; /* Stage 1 - find policy */ - if ((pol = xfrm_migrate_policy_find(sel, dir, type)) == NULL) { + if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) { err = -ENOENT; goto out; } /* Stage 2 - find and update state(s) */ for (i = 0, mp = m; i < num_migrate; i++, mp++) { - if ((x = xfrm_migrate_state_find(mp))) { + if ((x = xfrm_migrate_state_find(mp, net))) { x_cur[nx_cur] = x; nx_cur++; if ((xc = xfrm_state_migrate(x, mp))) { diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index 80cd1e55b834..fc5abd0b456f 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -52,7 +52,7 @@ static int xfrm_statistics_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; int i; - for (i=0; xfrm_mib_list[i].name; i++) + for (i = 0; xfrm_mib_list[i].name; i++) seq_printf(seq, "%-24s\t%lu\n", xfrm_mib_list[i].name, snmp_fold_field((void __percpu **) net->mib.xfrm_statistics, diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 68c2f357a183..a26b7aa79475 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -35,8 +35,6 @@ destination/tunnel endpoint. (output) */ -static DEFINE_SPINLOCK(xfrm_state_lock); - static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; static inline unsigned int xfrm_dst_hash(struct net *net, @@ -127,7 +125,7 @@ static void xfrm_hash_resize(struct work_struct *work) goto out_unlock; } - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; for (i = net->xfrm.state_hmask; i >= 0; i--) @@ -144,7 +142,7 @@ static void xfrm_hash_resize(struct work_struct *work) net->xfrm.state_byspi = nspi; net->xfrm.state_hmask = nhashmask; - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); osize = (ohashmask + 1) * sizeof(struct hlist_head); xfrm_hash_free(odst, osize); @@ -374,8 +372,6 @@ static void xfrm_state_gc_task(struct work_struct *work) hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) xfrm_state_gc_destroy(x); - - wake_up(&net->xfrm.km_waitq); } static inline unsigned long make_jiffies(long secs) @@ -386,11 +382,10 @@ static inline unsigned long make_jiffies(long secs) return secs*HZ; } -static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me) +static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) { struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer); struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer); - struct net *net = xs_net(x); unsigned long now = get_seconds(); long next = LONG_MAX; int warn = 0; @@ -453,19 +448,15 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me) if (warn) km_state_expired(x, 0, 0); resched: - if (next != LONG_MAX){ + if (next != LONG_MAX) { tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL); } goto out; expired: - if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) { + if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) x->km.state = XFRM_STATE_EXPIRED; - wake_up(&net->xfrm.km_waitq); - next = 2; - goto resched; - } err = __xfrm_state_delete(x); if (!err) @@ -535,14 +526,14 @@ int __xfrm_state_delete(struct xfrm_state *x) if (x->km.state != XFRM_STATE_DEAD) { x->km.state = XFRM_STATE_DEAD; - spin_lock(&xfrm_state_lock); + spin_lock(&net->xfrm.xfrm_state_lock); list_del(&x->km.all); hlist_del(&x->bydst); hlist_del(&x->bysrc); if (x->id.spi) hlist_del(&x->byspi); net->xfrm.state_num--; - spin_unlock(&xfrm_state_lock); + spin_unlock(&net->xfrm.xfrm_state_lock); /* All xfrm_state objects are created by xfrm_state_alloc. * The xfrm_state_alloc call gives a reference, and that @@ -603,7 +594,7 @@ int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info) { int i, err = 0, cnt = 0; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_flush_secctx_check(net, proto, audit_info); if (err) goto out; @@ -616,7 +607,7 @@ restart: if (!xfrm_state_kern(x) && xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, @@ -627,7 +618,7 @@ restart: if (!err) cnt++; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); goto restart; } } @@ -636,19 +627,18 @@ restart: err = 0; out: - spin_unlock_bh(&xfrm_state_lock); - wake_up(&net->xfrm.km_waitq); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } EXPORT_SYMBOL(xfrm_state_flush); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); si->sadcnt = net->xfrm.state_num; si->sadhcnt = net->xfrm.state_hmask; si->sadhmcnt = xfrm_state_hashmax; - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_sad_getinfo); @@ -801,7 +791,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, to_put = NULL; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == encap_family && @@ -886,7 +876,7 @@ out: xfrm_state_hold(x); else *err = acquire_in_progress ? -EAGAIN : error; - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (to_put) xfrm_state_put(to_put); return x; @@ -900,7 +890,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, unsigned int h; struct xfrm_state *rx = NULL, *x = NULL; - spin_lock(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && @@ -918,13 +908,35 @@ xfrm_stateonly_find(struct net *net, u32 mark, if (rx) xfrm_state_hold(rx); - spin_unlock(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return rx; } EXPORT_SYMBOL(xfrm_stateonly_find); +struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, + unsigned short family) +{ + struct xfrm_state *x; + struct xfrm_state_walk *w; + + spin_lock_bh(&net->xfrm.xfrm_state_lock); + list_for_each_entry(w, &net->xfrm.state_all, all) { + x = container_of(w, struct xfrm_state, km); + if (x->props.family != family || + x->id.spi != spi) + continue; + + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + xfrm_state_hold(x); + return x; + } + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + return NULL; +} +EXPORT_SYMBOL(xfrm_state_lookup_byspi); + static void __xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -950,14 +962,12 @@ static void __xfrm_state_insert(struct xfrm_state *x) if (x->replay_maxage) mod_timer(&x->rtimer, jiffies + x->replay_maxage); - wake_up(&net->xfrm.km_waitq); - net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); } -/* xfrm_state_lock is held */ +/* net->xfrm.xfrm_state_lock is held */ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) { struct net *net = xs_net(xnew); @@ -980,14 +990,16 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) void xfrm_state_insert(struct xfrm_state *x) { - spin_lock_bh(&xfrm_state_lock); + struct net *net = xs_net(x); + + spin_lock_bh(&net->xfrm.xfrm_state_lock); __xfrm_state_bump_genids(x); __xfrm_state_insert(x); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_insert); -/* xfrm_state_lock is held */ +/* net->xfrm.xfrm_state_lock is held */ static struct xfrm_state *__find_acq_core(struct net *net, const struct xfrm_mark *m, unsigned short family, u8 mode, @@ -1079,7 +1091,7 @@ int xfrm_state_add(struct xfrm_state *x) to_put = NULL; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, family); if (x1) { @@ -1108,7 +1120,7 @@ int xfrm_state_add(struct xfrm_state *x) err = 0; out: - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (x1) { xfrm_state_delete(x1); @@ -1203,16 +1215,16 @@ out: return NULL; } -/* xfrm_state_lock is held */ -struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) +/* net->xfrm.xfrm_state_lock is held */ +struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net) { unsigned int h; struct xfrm_state *x; if (m->reqid) { - h = xfrm_dst_hash(&init_net, &m->old_daddr, &m->old_saddr, + h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr, m->reqid, m->old_family); - hlist_for_each_entry(x, init_net.xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -1227,9 +1239,9 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) return x; } } else { - h = xfrm_src_hash(&init_net, &m->old_daddr, &m->old_saddr, + h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr, m->old_family); - hlist_for_each_entry(x, init_net.xfrm.state_bysrc+h, bysrc) { + hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -1247,8 +1259,8 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) } EXPORT_SYMBOL(xfrm_migrate_state_find); -struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x, - struct xfrm_migrate *m) +struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, + struct xfrm_migrate *m) { struct xfrm_state *xc; int err; @@ -1283,10 +1295,11 @@ int xfrm_state_update(struct xfrm_state *x) struct xfrm_state *x1, *to_put; int err; int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); + struct net *net = xs_net(x); to_put = NULL; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, x->props.family); err = -ESRCH; @@ -1306,7 +1319,7 @@ int xfrm_state_update(struct xfrm_state *x) err = 0; out: - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (to_put) xfrm_state_put(to_put); @@ -1357,7 +1370,7 @@ int xfrm_state_check_expire(struct xfrm_state *x) if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { x->km.state = XFRM_STATE_EXPIRED; - tasklet_hrtimer_start(&x->mtimer, ktime_set(0,0), HRTIMER_MODE_REL); + tasklet_hrtimer_start(&x->mtimer, ktime_set(0, 0), HRTIMER_MODE_REL); return -EINVAL; } @@ -1377,9 +1390,9 @@ xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 { struct xfrm_state *x; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_state_lookup); @@ -1391,9 +1404,9 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark, { struct xfrm_state *x; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_state_lookup_byaddr); @@ -1405,9 +1418,9 @@ xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, { struct xfrm_state *x; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } @@ -1416,17 +1429,17 @@ EXPORT_SYMBOL(xfrm_find_acq); #ifdef CONFIG_XFRM_SUB_POLICY int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, - unsigned short family) + unsigned short family, struct net *net) { int err = 0; struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (!afinfo) return -EAFNOSUPPORT; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); /*FIXME*/ if (afinfo->tmpl_sort) err = afinfo->tmpl_sort(dst, src, n); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); xfrm_state_put_afinfo(afinfo); return err; } @@ -1438,13 +1451,15 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, { int err = 0; struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); + struct net *net = xs_net(*dst); + if (!afinfo) return -EAFNOSUPPORT; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); if (afinfo->state_sort) err = afinfo->state_sort(dst, src, n); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); xfrm_state_put_afinfo(afinfo); return err; } @@ -1476,9 +1491,9 @@ struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq) { struct xfrm_state *x; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_find_acq_byseq(net, mark, seq); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_find_acq_byseq); @@ -1496,6 +1511,30 @@ u32 xfrm_get_acqseq(void) } EXPORT_SYMBOL(xfrm_get_acqseq); +int verify_spi_info(u8 proto, u32 min, u32 max) +{ + switch (proto) { + case IPPROTO_AH: + case IPPROTO_ESP: + break; + + case IPPROTO_COMP: + /* IPCOMP spi is 16-bits. */ + if (max >= 0x10000) + return -EINVAL; + break; + + default: + return -EINVAL; + } + + if (min > max) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL(verify_spi_info); + int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) { struct net *net = xs_net(x); @@ -1525,8 +1564,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) x->id.spi = minspi; } else { u32 spi = 0; - for (h=0; h<high-low+1; h++) { - spi = low + net_random()%(high-low+1); + for (h = 0; h < high-low+1; h++) { + spi = low + prandom_u32()%(high-low+1); x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { x->id.spi = htonl(spi); @@ -1536,10 +1575,10 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) } } if (x->id.spi) { - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); hlist_add_head(&x->byspi, net->xfrm.state_byspi+h); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = 0; } @@ -1562,7 +1601,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, if (walk->seq != 0 && list_empty(&walk->all)) return 0; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); if (list_empty(&walk->all)) x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all); else @@ -1586,7 +1625,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, } list_del_init(&walk->all); out: - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } EXPORT_SYMBOL(xfrm_state_walk); @@ -1600,20 +1639,20 @@ void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto) } EXPORT_SYMBOL(xfrm_state_walk_init); -void xfrm_state_walk_done(struct xfrm_state_walk *walk) +void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net) { if (list_empty(&walk->all)) return; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); list_del(&walk->all); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_walk_done); static void xfrm_replay_timer_handler(unsigned long data) { - struct xfrm_state *x = (struct xfrm_state*)data; + struct xfrm_state *x = (struct xfrm_state *)data; spin_lock(&x->lock); @@ -1655,16 +1694,12 @@ EXPORT_SYMBOL(km_state_notify); void km_state_expired(struct xfrm_state *x, int hard, u32 portid) { - struct net *net = xs_net(x); struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_EXPIRE; km_state_notify(x, &c); - - if (hard) - wake_up(&net->xfrm.km_waitq); } EXPORT_SYMBOL(km_state_expired); @@ -1707,16 +1742,12 @@ EXPORT_SYMBOL(km_new_mapping); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid) { - struct net *net = xp_net(pol); struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_POLEXPIRE; km_policy_notify(pol, dir, &c); - - if (hard) - wake_up(&net->xfrm.km_waitq); } EXPORT_SYMBOL(km_policy_expired); @@ -2025,7 +2056,7 @@ int __net_init xfrm_state_init(struct net *net) INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize); INIT_HLIST_HEAD(&net->xfrm.state_gc_list); INIT_WORK(&net->xfrm.state_gc_work, xfrm_state_gc_task); - init_waitqueue_head(&net->xfrm.km_waitq); + spin_lock_init(&net->xfrm.xfrm_state_lock); return 0; out_byspi: @@ -2043,7 +2074,7 @@ void xfrm_state_fini(struct net *net) flush_work(&net->xfrm.state_hash_work); audit_info.loginuid = INVALID_UID; - audit_info.sessionid = -1; + audit_info.sessionid = (unsigned int)-1; audit_info.secid = 0; xfrm_state_flush(net, IPSEC_PROTO_ANY, &audit_info); flush_work(&net->xfrm.state_gc_work); @@ -2070,7 +2101,7 @@ static void xfrm_audit_helper_sainfo(struct xfrm_state *x, audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); - switch(x->props.family) { + switch (x->props.family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4 dst=%pI4", &x->props.saddr.a4, &x->id.daddr.a4); @@ -2100,7 +2131,7 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family, iph6 = ipv6_hdr(skb); audit_log_format(audit_buf, " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x", - &iph6->saddr,&iph6->daddr, + &iph6->saddr, &iph6->daddr, iph6->flow_lbl[0] & 0x0f, iph6->flow_lbl[1], iph6->flow_lbl[2]); @@ -2109,7 +2140,7 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family, } void xfrm_audit_state_add(struct xfrm_state *x, int result, - kuid_t auid, u32 sessionid, u32 secid) + kuid_t auid, unsigned int sessionid, u32 secid) { struct audit_buffer *audit_buf; @@ -2124,7 +2155,7 @@ void xfrm_audit_state_add(struct xfrm_state *x, int result, EXPORT_SYMBOL_GPL(xfrm_audit_state_add); void xfrm_audit_state_delete(struct xfrm_state *x, int result, - kuid_t auid, u32 sessionid, u32 secid) + kuid_t auid, unsigned int sessionid, u32 secid) { struct audit_buffer *audit_buf; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index f964d4c00ffb..1ae3ec7c18b0 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -181,7 +181,9 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_CRYPT] || attrs[XFRMA_ALG_COMP] || - attrs[XFRMA_TFCPAD]) + attrs[XFRMA_TFCPAD] || + (ntohl(p->id.spi) >= 0x10000)) + goto out; break; @@ -600,7 +602,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, int err; struct km_event c; kuid_t loginuid = audit_get_loginuid(current); - u32 sessionid = audit_get_sessionid(current); + unsigned int sessionid = audit_get_sessionid(current); u32 sid; err = verify_newsa_info(p, attrs); @@ -679,7 +681,7 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct km_event c; struct xfrm_usersa_id *p = nlmsg_data(nlh); kuid_t loginuid = audit_get_loginuid(current); - u32 sessionid = audit_get_sessionid(current); + unsigned int sessionid = audit_get_sessionid(current); u32 sid; x = xfrm_user_state_lookup(net, p, attrs, &err); @@ -877,7 +879,10 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr) static int xfrm_dump_sa_done(struct netlink_callback *cb) { struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1]; - xfrm_state_walk_done(walk); + struct sock *sk = cb->skb->sk; + struct net *net = sock_net(sk); + + xfrm_state_walk_done(walk, net); return 0; } @@ -1074,29 +1079,6 @@ out_noput: return err; } -static int verify_userspi_info(struct xfrm_userspi_info *p) -{ - switch (p->info.id.proto) { - case IPPROTO_AH: - case IPPROTO_ESP: - break; - - case IPPROTO_COMP: - /* IPCOMP spi is 16-bits. */ - if (p->max >= 0x10000) - return -EINVAL; - break; - - default: - return -EINVAL; - } - - if (p->min > p->max) - return -EINVAL; - - return 0; -} - static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { @@ -1111,7 +1093,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_mark m; p = nlmsg_data(nlh); - err = verify_userspi_info(p); + err = verify_spi_info(p->info.id.proto, p->min, p->max); if (err) goto out_noput; @@ -1189,6 +1171,8 @@ static int verify_policy_type(u8 type) static int verify_newpolicy_info(struct xfrm_userpolicy_info *p) { + int ret; + switch (p->share) { case XFRM_SHARE_ANY: case XFRM_SHARE_SESSION: @@ -1224,7 +1208,13 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p) return -EINVAL; } - return verify_policy_dir(p->dir); + ret = verify_policy_dir(p->dir); + if (ret) + return ret; + if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir)) + return -EINVAL; + + return 0; } static int copy_from_user_sec_ctx(struct xfrm_policy *pol, struct nlattr **attrs) @@ -1405,7 +1395,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, int err; int excl; kuid_t loginuid = audit_get_loginuid(current); - u32 sessionid = audit_get_sessionid(current); + unsigned int sessionid = audit_get_sessionid(current); u32 sid; err = verify_newpolicy_info(p); @@ -1547,8 +1537,9 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr static int xfrm_dump_policy_done(struct netlink_callback *cb) { struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1]; + struct net *net = sock_net(cb->skb->sk); - xfrm_policy_walk_done(walk); + xfrm_policy_walk_done(walk, net); return 0; } @@ -1663,7 +1654,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, } } else { kuid_t loginuid = audit_get_loginuid(current); - u32 sessionid = audit_get_sessionid(current); + unsigned int sessionid = audit_get_sessionid(current); u32 sid; security_task_getsecid(current, &sid); @@ -1740,11 +1731,11 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct return -EMSGSIZE; id = nlmsg_data(nlh); - memcpy(&id->sa_id.daddr, &x->id.daddr,sizeof(x->id.daddr)); + memcpy(&id->sa_id.daddr, &x->id.daddr, sizeof(x->id.daddr)); id->sa_id.spi = x->id.spi; id->sa_id.family = x->props.family; id->sa_id.proto = x->id.proto; - memcpy(&id->saddr, &x->props.saddr,sizeof(x->props.saddr)); + memcpy(&id->saddr, &x->props.saddr, sizeof(x->props.saddr)); id->reqid = x->props.reqid; id->flags = c->data.aevent; @@ -1833,7 +1824,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct xfrm_state *x; struct km_event c; - int err = - EINVAL; + int err = -EINVAL; u32 mark = 0; struct xfrm_mark m; struct xfrm_aevent_id *p = nlmsg_data(nlh); @@ -1959,7 +1950,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, err = 0; if (up->hard) { kuid_t loginuid = audit_get_loginuid(current); - u32 sessionid = audit_get_sessionid(current); + unsigned int sessionid = audit_get_sessionid(current); u32 sid; security_task_getsecid(current, &sid); @@ -2002,7 +1993,7 @@ static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (ue->hard) { kuid_t loginuid = audit_get_loginuid(current); - u32 sessionid = audit_get_sessionid(current); + unsigned int sessionid = audit_get_sessionid(current); u32 sid; security_task_getsecid(current, &sid); @@ -2129,6 +2120,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, u8 type; int err; int n = 0; + struct net *net = sock_net(skb->sk); if (attrs[XFRMA_MIGRATE] == NULL) return -EINVAL; @@ -2146,7 +2138,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, if (!n) return 0; - xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp); + xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net); return 0; } @@ -2394,9 +2386,11 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) static void xfrm_netlink_rcv(struct sk_buff *skb) { - mutex_lock(&xfrm_cfg_mutex); + struct net *net = sock_net(skb->sk); + + mutex_lock(&net->xfrm.xfrm_cfg_mutex); netlink_rcv_skb(skb, &xfrm_user_rcv_msg); - mutex_unlock(&xfrm_cfg_mutex); + mutex_unlock(&net->xfrm.xfrm_cfg_mutex); } static inline size_t xfrm_expire_msgsize(void) |