diff options
Diffstat (limited to 'net')
220 files changed, 6327 insertions, 3790 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a292e8050ef..babfde9f734 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -105,6 +105,8 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) */ unregister_netdevice_queue(dev, head); + netdev_upper_dev_unlink(real_dev, dev); + if (grp->nr_vlan_devs == 0) vlan_gvrp_uninit_applicant(real_dev); @@ -162,9 +164,13 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_applicant; + err = netdev_upper_dev_link(real_dev, dev); + if (err) + goto out_uninit_applicant; + err = register_netdevice(dev); if (err < 0) - goto out_uninit_applicant; + goto out_upper_dev_unlink; /* Account for reference in struct vlan_dev_priv */ dev_hold(real_dev); @@ -180,6 +186,8 @@ int register_vlan_dev(struct net_device *dev) return 0; +out_upper_dev_unlink: + netdev_upper_dev_unlink(real_dev, dev); out_uninit_applicant: if (grp->nr_vlan_devs == 0) vlan_gvrp_uninit_applicant(real_dev); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 65e06abe023..380440b8ea8 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -60,21 +60,25 @@ bool vlan_do_receive(struct sk_buff **skbp) return true; } -/* Must be invoked with rcu_read_lock or with RTNL. */ -struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, +/* Must be invoked with rcu_read_lock. */ +struct net_device *__vlan_find_dev_deep(struct net_device *dev, u16 vlan_id) { - struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info); + struct vlan_info *vlan_info = rcu_dereference(dev->vlan_info); if (vlan_info) { return vlan_group_get_device(&vlan_info->grp, vlan_id); } else { /* - * Bonding slaves do not have grp assigned to themselves. - * Grp is assigned to bonding master instead. + * Lower devices of master uppers (bonding, team) do not have + * grp assigned to themselves. Grp is assigned to upper device + * instead. */ - if (netif_is_bond_slave(real_dev)) - return __vlan_find_dev_deep(real_dev->master, vlan_id); + struct net_device *upper_dev; + + upper_dev = netdev_master_upper_dev_get_rcu(dev); + if (upper_dev) + return __vlan_find_dev_deep(upper_dev, vlan_id); } return NULL; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 4a6d31a082b..09f9108d468 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -640,9 +640,9 @@ static int vlan_ethtool_get_settings(struct net_device *dev, static void vlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strcpy(info->driver, vlan_fullname); - strcpy(info->version, vlan_version); - strcpy(info->fw_version, "N/A"); + strlcpy(info->driver, vlan_fullname, sizeof(info->driver)); + strlcpy(info->version, vlan_version, sizeof(info->version)); + strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); } static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) diff --git a/net/Kconfig b/net/Kconfig index 30b48f52313..3cc5be0fe42 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -232,7 +232,7 @@ config RFS_ACCEL config XPS boolean - depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS + depends on SMP && USE_GENERIC_SMP_HELPERS default y config NETPRIO_CGROUP diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index a0ba3bff9b3..a4808c29ea3 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 7d02ebd11a7..72fe1bbf772 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -123,7 +123,7 @@ batadv_iv_ogm_emit_send_time(const struct batadv_priv *bat_priv) unsigned int msecs; msecs = atomic_read(&bat_priv->orig_interval) - BATADV_JITTER; - msecs += random32() % (2 * BATADV_JITTER); + msecs += prandom_u32() % (2 * BATADV_JITTER); return jiffies + msecs_to_jiffies(msecs); } @@ -131,7 +131,7 @@ batadv_iv_ogm_emit_send_time(const struct batadv_priv *bat_priv) /* when do we schedule a ogm packet to be sent */ static unsigned long batadv_iv_ogm_fwd_send_time(void) { - return jiffies + msecs_to_jiffies(random32() % (BATADV_JITTER / 2)); + return jiffies + msecs_to_jiffies(prandom_u32() % (BATADV_JITTER / 2)); } /* apply hop penalty for a normal link */ @@ -183,7 +183,6 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, /* adjust all flags and log packets */ while (batadv_iv_ogm_aggr_packet(buff_pos, forw_packet->packet_len, batadv_ogm_packet->tt_num_changes)) { - /* we might have aggregated direct link packets with an * ordinary base packet */ @@ -261,7 +260,6 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) */ if ((directlink && (batadv_ogm_packet->header.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", @@ -325,7 +323,6 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, if (time_before(send_time, forw_packet->send_time) && time_after_eq(aggregation_end_time, forw_packet->send_time) && (aggregated_bytes <= BATADV_MAX_AGGREGATION_BYTES)) { - /* check aggregation compatibility * -> direct link packets are broadcasted on * their interface only @@ -815,7 +812,6 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_node, node, &orig_neigh_node->neigh_list, list) { - if (!batadv_compare_eth(tmp_neigh_node->addr, orig_neigh_node->orig)) continue; @@ -949,7 +945,6 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_node, node, &orig_node->neigh_list, list) { - is_duplicate |= batadv_test_bit(tmp_neigh_node->real_bits, orig_node->last_real_seqno, seqno); @@ -1033,7 +1028,7 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, 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, ttvn %u, crc %u, changes %u, td %d, TTL %d, V %d, IDF %d)\n", + "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, ttvn %u, crc %#.4x, changes %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, @@ -1223,7 +1218,6 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, /* is single hop (direct) neighbor */ if (is_single_hop_neigh) { - /* mark direct link on incoming interface */ batadv_iv_ogm_forward(orig_node, ethhdr, batadv_ogm_packet, is_single_hop_neigh, diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 5453b17d8df..973982414d5 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index cebaae7e148..a81b9322e38 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 5aebe9327d6..30f46526cbb 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich * @@ -34,13 +34,14 @@ static const uint8_t batadv_announce_mac[4] = {0x43, 0x05, 0x43, 0x05}; static void batadv_bla_periodic_work(struct work_struct *work); -static void batadv_bla_send_announce(struct batadv_priv *bat_priv, - struct batadv_backbone_gw *backbone_gw); +static void +batadv_bla_send_announce(struct batadv_priv *bat_priv, + struct batadv_bla_backbone_gw *backbone_gw); /* return the index of the claim */ static inline uint32_t batadv_choose_claim(const void *data, uint32_t size) { - struct batadv_claim *claim = (struct batadv_claim *)data; + struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data; uint32_t hash = 0; hash = batadv_hash_bytes(hash, &claim->addr, sizeof(claim->addr)); @@ -57,7 +58,7 @@ static inline uint32_t batadv_choose_claim(const void *data, uint32_t size) static inline uint32_t batadv_choose_backbone_gw(const void *data, uint32_t size) { - struct batadv_claim *claim = (struct batadv_claim *)data; + const struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data; uint32_t hash = 0; hash = batadv_hash_bytes(hash, &claim->addr, sizeof(claim->addr)); @@ -75,9 +76,9 @@ static inline uint32_t batadv_choose_backbone_gw(const void *data, static int batadv_compare_backbone_gw(const struct hlist_node *node, const void *data2) { - const void *data1 = container_of(node, struct batadv_backbone_gw, + const void *data1 = container_of(node, struct batadv_bla_backbone_gw, hash_entry); - const struct batadv_backbone_gw *gw1 = data1, *gw2 = data2; + const struct batadv_bla_backbone_gw *gw1 = data1, *gw2 = data2; if (!batadv_compare_eth(gw1->orig, gw2->orig)) return 0; @@ -92,9 +93,9 @@ static int batadv_compare_backbone_gw(const struct hlist_node *node, static int batadv_compare_claim(const struct hlist_node *node, const void *data2) { - const void *data1 = container_of(node, struct batadv_claim, + const void *data1 = container_of(node, struct batadv_bla_claim, hash_entry); - const struct batadv_claim *cl1 = data1, *cl2 = data2; + const struct batadv_bla_claim *cl1 = data1, *cl2 = data2; if (!batadv_compare_eth(cl1->addr, cl2->addr)) return 0; @@ -106,7 +107,8 @@ static int batadv_compare_claim(const struct hlist_node *node, } /* free a backbone gw */ -static void batadv_backbone_gw_free_ref(struct batadv_backbone_gw *backbone_gw) +static void +batadv_backbone_gw_free_ref(struct batadv_bla_backbone_gw *backbone_gw) { if (atomic_dec_and_test(&backbone_gw->refcount)) kfree_rcu(backbone_gw, rcu); @@ -115,16 +117,16 @@ static void batadv_backbone_gw_free_ref(struct batadv_backbone_gw *backbone_gw) /* finally deinitialize the claim */ static void batadv_claim_free_rcu(struct rcu_head *rcu) { - struct batadv_claim *claim; + struct batadv_bla_claim *claim; - claim = container_of(rcu, struct batadv_claim, rcu); + claim = container_of(rcu, struct batadv_bla_claim, rcu); batadv_backbone_gw_free_ref(claim->backbone_gw); kfree(claim); } /* free a claim, call claim_free_rcu if its the last reference */ -static void batadv_claim_free_ref(struct batadv_claim *claim) +static void batadv_claim_free_ref(struct batadv_bla_claim *claim) { if (atomic_dec_and_test(&claim->refcount)) call_rcu(&claim->rcu, batadv_claim_free_rcu); @@ -136,14 +138,15 @@ static void batadv_claim_free_ref(struct batadv_claim *claim) * looks for a claim in the hash, and returns it if found * or NULL otherwise. */ -static struct batadv_claim *batadv_claim_hash_find(struct batadv_priv *bat_priv, - struct batadv_claim *data) +static struct batadv_bla_claim +*batadv_claim_hash_find(struct batadv_priv *bat_priv, + struct batadv_bla_claim *data) { struct batadv_hashtable *hash = bat_priv->bla.claim_hash; struct hlist_head *head; struct hlist_node *node; - struct batadv_claim *claim; - struct batadv_claim *claim_tmp = NULL; + struct batadv_bla_claim *claim; + struct batadv_bla_claim *claim_tmp = NULL; int index; if (!hash) @@ -176,15 +179,15 @@ static struct batadv_claim *batadv_claim_hash_find(struct batadv_priv *bat_priv, * * Returns claim if found or NULL otherwise. */ -static struct batadv_backbone_gw * +static struct batadv_bla_backbone_gw * batadv_backbone_hash_find(struct batadv_priv *bat_priv, uint8_t *addr, short vid) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; struct hlist_node *node; - struct batadv_backbone_gw search_entry, *backbone_gw; - struct batadv_backbone_gw *backbone_gw_tmp = NULL; + struct batadv_bla_backbone_gw search_entry, *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw_tmp = NULL; int index; if (!hash) @@ -215,12 +218,12 @@ batadv_backbone_hash_find(struct batadv_priv *bat_priv, /* delete all claims for a backbone */ static void -batadv_bla_del_backbone_claims(struct batadv_backbone_gw *backbone_gw) +batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) { struct batadv_hashtable *hash; struct hlist_node *node, *node_tmp; struct hlist_head *head; - struct batadv_claim *claim; + struct batadv_bla_claim *claim; int i; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -235,7 +238,6 @@ batadv_bla_del_backbone_claims(struct batadv_backbone_gw *backbone_gw) spin_lock_bh(list_lock); hlist_for_each_entry_safe(claim, node, node_tmp, head, hash_entry) { - if (claim->backbone_gw != backbone_gw) continue; @@ -338,7 +340,6 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, "bla_send_claim(): REQUEST of %pM to %pMon vid %d\n", ethhdr->h_source, ethhdr->h_dest, vid); break; - } if (vid != -1) @@ -366,11 +367,11 @@ out: * searches for the backbone gw or creates a new one if it could not * be found. */ -static struct batadv_backbone_gw * +static struct batadv_bla_backbone_gw * batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig, short vid, bool own_backbone) { - struct batadv_backbone_gw *entry; + struct batadv_bla_backbone_gw *entry; struct batadv_orig_node *orig_node; int hash_added; @@ -437,7 +438,7 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, short vid) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; backbone_gw = batadv_bla_get_backbone_gw(bat_priv, primary_if->net_dev->dev_addr, @@ -462,8 +463,8 @@ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; - struct batadv_claim *claim; - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_claim *claim; + struct batadv_bla_backbone_gw *backbone_gw; int i; batadv_dbg(BATADV_DBG_BLA, bat_priv, @@ -502,7 +503,7 @@ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, * After the request, it will repeat all of his own claims and finally * send an announcement claim with which we can check again. */ -static void batadv_bla_send_request(struct batadv_backbone_gw *backbone_gw) +static void batadv_bla_send_request(struct batadv_bla_backbone_gw *backbone_gw) { /* first, remove all old entries */ batadv_bla_del_backbone_claims(backbone_gw); @@ -528,7 +529,7 @@ static void batadv_bla_send_request(struct batadv_backbone_gw *backbone_gw) * places. */ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, - struct batadv_backbone_gw *backbone_gw) + struct batadv_bla_backbone_gw *backbone_gw) { uint8_t mac[ETH_ALEN]; __be16 crc; @@ -539,7 +540,6 @@ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, batadv_bla_send_claim(bat_priv, mac, backbone_gw->vid, BATADV_CLAIM_TYPE_ANNOUNCE); - } /** @@ -551,10 +551,10 @@ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, */ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, const uint8_t *mac, const short vid, - struct batadv_backbone_gw *backbone_gw) + struct batadv_bla_backbone_gw *backbone_gw) { - struct batadv_claim *claim; - struct batadv_claim search_claim; + struct batadv_bla_claim *claim; + struct batadv_bla_claim search_claim; int hash_added; memcpy(search_claim.addr, mac, ETH_ALEN); @@ -598,7 +598,6 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); batadv_backbone_gw_free_ref(claim->backbone_gw); - } /* set (new) backbone gw */ atomic_inc(&backbone_gw->refcount); @@ -617,7 +616,7 @@ claim_free_ref: static void batadv_bla_del_claim(struct batadv_priv *bat_priv, const uint8_t *mac, const short vid) { - struct batadv_claim search_claim, *claim; + struct batadv_bla_claim search_claim, *claim; memcpy(search_claim.addr, mac, ETH_ALEN); search_claim.vid = vid; @@ -643,7 +642,7 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, uint8_t *an_addr, uint8_t *backbone_addr, short vid) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; uint16_t crc; if (memcmp(an_addr, batadv_announce_mac, 4) != 0) @@ -661,12 +660,12 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, crc = ntohs(*((__be16 *)(&an_addr[4]))); batadv_dbg(BATADV_DBG_BLA, bat_priv, - "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %04x\n", + "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n", vid, backbone_gw->orig, crc); if (backbone_gw->crc != crc) { batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, - "handle_announce(): CRC FAILED for %pM/%d (my = %04x, sent = %04x)\n", + "handle_announce(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n", backbone_gw->orig, backbone_gw->vid, backbone_gw->crc, crc); @@ -715,7 +714,7 @@ static int batadv_handle_unclaim(struct batadv_priv *bat_priv, uint8_t *backbone_addr, uint8_t *claim_addr, short vid) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; /* unclaim in any case if it is our own */ if (primary_if && batadv_compare_eth(backbone_addr, @@ -744,7 +743,7 @@ static int batadv_handle_claim(struct batadv_priv *bat_priv, uint8_t *backbone_addr, uint8_t *claim_addr, short vid) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; /* register the gateway if not yet available, and add the claim. */ @@ -835,7 +834,7 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv, /* if our mesh friends mac is bigger, use it for ourselves. */ if (ntohs(bla_dst->group) > ntohs(bla_dst_own->group)) { batadv_dbg(BATADV_DBG_BLA, bat_priv, - "taking other backbones claim group: %04x\n", + "taking other backbones claim group: %#.4x\n", ntohs(bla_dst->group)); bla_dst_own->group = bla_dst->group; } @@ -958,7 +957,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, */ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; struct hlist_node *node, *node_tmp; struct hlist_head *head; struct batadv_hashtable *hash; @@ -1013,7 +1012,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, int now) { - struct batadv_claim *claim; + struct batadv_bla_claim *claim; struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; @@ -1062,7 +1061,7 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, struct batadv_hard_iface *oldif) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; @@ -1104,16 +1103,6 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, } } - - -/* (re)start the timer */ -static void batadv_bla_start_timer(struct batadv_priv *bat_priv) -{ - INIT_DELAYED_WORK(&bat_priv->bla.work, batadv_bla_periodic_work); - queue_delayed_work(batadv_event_workqueue, &bat_priv->bla.work, - msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); -} - /* periodic work to do: * * purge structures when they are too old * * send announcements @@ -1125,7 +1114,7 @@ static void batadv_bla_periodic_work(struct work_struct *work) struct batadv_priv_bla *priv_bla; struct hlist_node *node; struct hlist_head *head; - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hashtable *hash; struct batadv_hard_iface *primary_if; int i; @@ -1184,7 +1173,8 @@ out: if (primary_if) batadv_hardif_free_ref(primary_if); - batadv_bla_start_timer(bat_priv); + queue_delayed_work(batadv_event_workqueue, &bat_priv->bla.work, + msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); } /* The hash for claim and backbone hash receive the same key because they @@ -1242,7 +1232,10 @@ int batadv_bla_init(struct batadv_priv *bat_priv) batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla hashes initialized\n"); - batadv_bla_start_timer(bat_priv); + INIT_DELAYED_WORK(&bat_priv->bla.work, batadv_bla_periodic_work); + + queue_delayed_work(batadv_event_workqueue, &bat_priv->bla.work, + msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); return 0; } @@ -1330,7 +1323,7 @@ int batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig) struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; struct hlist_node *node; - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; int i; if (!atomic_read(&bat_priv->bridge_loop_avoidance)) @@ -1371,7 +1364,7 @@ int batadv_bla_is_backbone_gw(struct sk_buff *skb, { struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; short vid = -1; if (!atomic_read(&orig_node->bat_priv->bridge_loop_avoidance)) @@ -1442,7 +1435,7 @@ int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid, bool is_bcast) { struct ethhdr *ethhdr; - struct batadv_claim search_claim, *claim = NULL; + struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_hard_iface *primary_if; int ret; @@ -1536,7 +1529,7 @@ out: int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid) { struct ethhdr *ethhdr; - struct batadv_claim search_claim, *claim = NULL; + struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_hard_iface *primary_if; int ret = 0; @@ -1612,7 +1605,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) struct net_device *net_dev = (struct net_device *)seq->private; struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hashtable *hash = bat_priv->bla.claim_hash; - struct batadv_claim *claim; + struct batadv_bla_claim *claim; struct batadv_hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; @@ -1626,10 +1619,10 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) primary_addr = primary_if->net_dev->dev_addr; seq_printf(seq, - "Claims announced for the mesh %s (orig %pM, group id %04x)\n", + "Claims announced for the mesh %s (orig %pM, group id %#.4x)\n", net_dev->name, primary_addr, ntohs(bat_priv->bla.claim_dest.group)); - seq_printf(seq, " %-17s %-5s %-17s [o] (%-4s)\n", + seq_printf(seq, " %-17s %-5s %-17s [o] (%-6s)\n", "Client", "VID", "Originator", "CRC"); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1638,7 +1631,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) hlist_for_each_entry_rcu(claim, node, head, hash_entry) { is_own = batadv_compare_eth(claim->backbone_gw->orig, primary_addr); - seq_printf(seq, " * %pM on % 5d by %pM [%c] (%04x)\n", + seq_printf(seq, " * %pM on % 5d by %pM [%c] (%#.4x)\n", claim->addr, claim->vid, claim->backbone_gw->orig, (is_own ? 'x' : ' '), @@ -1657,7 +1650,7 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) struct net_device *net_dev = (struct net_device *)seq->private; struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; @@ -1672,10 +1665,10 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) primary_addr = primary_if->net_dev->dev_addr; seq_printf(seq, - "Backbones announced for the mesh %s (orig %pM, group id %04x)\n", + "Backbones announced for the mesh %s (orig %pM, group id %#.4x)\n", net_dev->name, primary_addr, ntohs(bat_priv->bla.claim_dest.group)); - seq_printf(seq, " %-17s %-5s %-9s (%-4s)\n", + seq_printf(seq, " %-17s %-5s %-9s (%-6s)\n", "Originator", "VID", "last seen", "CRC"); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1693,7 +1686,7 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) continue; seq_printf(seq, - " * %pM on % 5d % 4i.%03is (%04x)\n", + " * %pM on % 5d % 4i.%03is (%#.4x)\n", backbone_gw->orig, backbone_gw->vid, secs, msecs, backbone_gw->crc); } diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 196d9a0254b..dea2fbc5d98 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 6f58ddd53bf..6ae86516db4 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -40,13 +40,14 @@ static struct dentry *batadv_debugfs; static const int batadv_log_buff_len = BATADV_LOG_BUF_LEN; -static char *batadv_log_char_addr(struct batadv_debug_log *debug_log, +static char *batadv_log_char_addr(struct batadv_priv_debug_log *debug_log, size_t idx) { return &debug_log->log_buff[idx & BATADV_LOG_BUFF_MASK]; } -static void batadv_emit_log_char(struct batadv_debug_log *debug_log, char c) +static void batadv_emit_log_char(struct batadv_priv_debug_log *debug_log, + char c) { char *char_addr; @@ -59,7 +60,7 @@ static void batadv_emit_log_char(struct batadv_debug_log *debug_log, char c) } __printf(2, 3) -static int batadv_fdebug_log(struct batadv_debug_log *debug_log, +static int batadv_fdebug_log(struct batadv_priv_debug_log *debug_log, const char *fmt, ...) { va_list args; @@ -114,7 +115,7 @@ static int batadv_log_release(struct inode *inode, struct file *file) return 0; } -static int batadv_log_empty(struct batadv_debug_log *debug_log) +static int batadv_log_empty(struct batadv_priv_debug_log *debug_log) { return !(debug_log->log_start - debug_log->log_end); } @@ -123,7 +124,7 @@ static ssize_t batadv_log_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct batadv_priv *bat_priv = file->private_data; - struct batadv_debug_log *debug_log = bat_priv->debug_log; + struct batadv_priv_debug_log *debug_log = bat_priv->debug_log; int error, i = 0; char *char_addr; char c; @@ -164,7 +165,6 @@ static ssize_t batadv_log_read(struct file *file, char __user *buf, buf++; i++; - } spin_unlock_bh(&debug_log->lock); @@ -178,7 +178,7 @@ static ssize_t batadv_log_read(struct file *file, char __user *buf, static unsigned int batadv_log_poll(struct file *file, poll_table *wait) { struct batadv_priv *bat_priv = file->private_data; - struct batadv_debug_log *debug_log = bat_priv->debug_log; + struct batadv_priv_debug_log *debug_log = bat_priv->debug_log; poll_wait(file, &debug_log->queue_wait, wait); @@ -230,7 +230,6 @@ static void batadv_debug_log_cleanup(struct batadv_priv *bat_priv) #else /* CONFIG_BATMAN_ADV_DEBUG */ static int batadv_debug_log_setup(struct batadv_priv *bat_priv) { - bat_priv->debug_log = NULL; return 0; } @@ -397,10 +396,8 @@ err: void batadv_debugfs_destroy(void) { - if (batadv_debugfs) { - debugfs_remove_recursive(batadv_debugfs); - batadv_debugfs = NULL; - } + debugfs_remove_recursive(batadv_debugfs); + batadv_debugfs = NULL; } int batadv_debugfs_add_meshif(struct net_device *dev) diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 3319e1f21f5..f8c3849edff 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 183f97a86bb..ea0bd31d41c 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index d060c033e7d..125c8c6fcfa 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index dd07c7e3654..074107f2cfa 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index f0d129e323c..039902dca4a 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 9001208d175..84bb2b18d71 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index 13697f6e711..509b2bf8c2f 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index f1d37cd8181..368219e026a 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -457,6 +457,24 @@ out: batadv_hardif_free_ref(primary_if); } +/** + * batadv_hardif_remove_interface_finish - cleans up the remains of a hardif + * @work: work queue item + * + * Free the parts of the hard interface which can not be removed under + * rtnl lock (to prevent deadlock situations). + */ +static void batadv_hardif_remove_interface_finish(struct work_struct *work) +{ + struct batadv_hard_iface *hard_iface; + + hard_iface = container_of(work, struct batadv_hard_iface, + cleanup_work); + + batadv_sysfs_del_hardif(&hard_iface->hardif_obj); + batadv_hardif_free_ref(hard_iface); +} + static struct batadv_hard_iface * batadv_hardif_add_interface(struct net_device *net_dev) { @@ -484,6 +502,9 @@ batadv_hardif_add_interface(struct net_device *net_dev) hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; INIT_LIST_HEAD(&hard_iface->list); + INIT_WORK(&hard_iface->cleanup_work, + batadv_hardif_remove_interface_finish); + /* extra reference for return */ atomic_set(&hard_iface->refcount, 2); @@ -518,8 +539,7 @@ static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface) return; hard_iface->if_status = BATADV_IF_TO_BE_REMOVED; - batadv_sysfs_del_hardif(&hard_iface->hardif_obj); - batadv_hardif_free_ref(hard_iface); + queue_work(batadv_event_workqueue, &hard_iface->cleanup_work); } void batadv_hardif_remove_interfaces(void) diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 3732366e744..308437d52e2 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 15a849c2d41..7198dafd3bf 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index e05333905af..1b4da72f209 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -89,7 +89,7 @@ static inline void batadv_hash_delete(struct batadv_hashtable *hash, * * Returns the new hash value. */ -static inline uint32_t batadv_hash_bytes(uint32_t hash, void *data, +static inline uint32_t batadv_hash_bytes(uint32_t hash, const void *data, uint32_t size) { const unsigned char *key = data; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 87ca8095b01..0ba6c899b2d 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 29443a1dbb5..1fcca37b622 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index f65a222b7b8..21fe6987733 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 2f85577086a..ced08b936a9 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -26,7 +26,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2012.5.0" +#define BATADV_SOURCE_VERSION "2013.1.0" #endif /* B.A.T.M.A.N. parameters */ @@ -41,9 +41,11 @@ * -> TODO: check influence on BATADV_TQ_LOCAL_WINDOW_SIZE */ #define BATADV_PURGE_TIMEOUT 200000 /* 200 seconds */ -#define BATADV_TT_LOCAL_TIMEOUT 3600000 /* in milliseconds */ +#define BATADV_TT_LOCAL_TIMEOUT 600000 /* in milliseconds */ #define BATADV_TT_CLIENT_ROAM_TIMEOUT 600000 /* in milliseconds */ #define BATADV_TT_CLIENT_TEMP_TIMEOUT 600000 /* in milliseconds */ +#define BATADV_TT_WORK_PERIOD 5000 /* 5 seconds */ +#define BATADV_ORIG_WORK_PERIOD 1000 /* 1 second */ #define BATADV_DAT_ENTRY_TIMEOUT (5*60000) /* 5 mins in milliseconds */ /* sliding packet range of received originator messages in sequence numbers * (should be a multiple of our word size) @@ -276,9 +278,7 @@ static inline bool batadv_has_timed_out(unsigned long timestamp, static inline void batadv_add_counter(struct batadv_priv *bat_priv, size_t idx, size_t count) { - int cpu = get_cpu(); - per_cpu_ptr(bat_priv->bat_counters, cpu)[idx] += count; - put_cpu(); + this_cpu_add(bat_priv->bat_counters[idx], count); } #define batadv_inc_counter(b, i) batadv_add_counter(b, i, 1) diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 8c32cf1c2de..457ea445217 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -29,14 +29,10 @@ #include "soft-interface.h" #include "bridge_loop_avoidance.h" -static void batadv_purge_orig(struct work_struct *work); +/* hash class keys */ +static struct lock_class_key batadv_orig_hash_lock_class_key; -static void batadv_start_purge_timer(struct batadv_priv *bat_priv) -{ - INIT_DELAYED_WORK(&bat_priv->orig_work, batadv_purge_orig); - queue_delayed_work(batadv_event_workqueue, - &bat_priv->orig_work, msecs_to_jiffies(1000)); -} +static void batadv_purge_orig(struct work_struct *work); /* returns 1 if they are the same originator */ static int batadv_compare_orig(const struct hlist_node *node, const void *data2) @@ -57,7 +53,14 @@ int batadv_originator_init(struct batadv_priv *bat_priv) if (!bat_priv->orig_hash) goto err; - batadv_start_purge_timer(bat_priv); + batadv_hash_set_lock_class(bat_priv->orig_hash, + &batadv_orig_hash_lock_class_key); + + INIT_DELAYED_WORK(&bat_priv->orig_work, batadv_purge_orig); + queue_delayed_work(batadv_event_workqueue, + &bat_priv->orig_work, + msecs_to_jiffies(BATADV_ORIG_WORK_PERIOD)); + return 0; err: @@ -178,7 +181,6 @@ void batadv_originator_free(struct batadv_priv *bat_priv) spin_lock_bh(list_lock); hlist_for_each_entry_safe(orig_node, node, node_tmp, head, hash_entry) { - hlist_del_rcu(node); batadv_orig_node_free_ref(orig_node); } @@ -285,7 +287,6 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node, node_tmp, &orig_node->neigh_list, list) { - last_seen = neigh_node->last_seen; if_incoming = neigh_node->if_incoming; @@ -293,7 +294,6 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, (if_incoming->if_status == BATADV_IF_INACTIVE) || (if_incoming->if_status == BATADV_IF_NOT_IN_USE) || (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) { - if ((if_incoming->if_status == BATADV_IF_INACTIVE) || (if_incoming->if_status == BATADV_IF_NOT_IN_USE) || (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) @@ -393,7 +393,9 @@ static void batadv_purge_orig(struct work_struct *work) delayed_work = container_of(work, struct delayed_work, work); bat_priv = container_of(delayed_work, struct batadv_priv, orig_work); _batadv_purge_orig(bat_priv); - batadv_start_purge_timer(bat_priv); + queue_delayed_work(batadv_event_workqueue, + &bat_priv->orig_work, + msecs_to_jiffies(BATADV_ORIG_WORK_PERIOD)); } void batadv_purge_orig_ref(struct batadv_priv *bat_priv) diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 9778e656dec..286bf743e76 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index cb6405bf755..ed0aa89bbf8 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/ring_buffer.c b/net/batman-adv/ring_buffer.c index c8f61e395b7..ccab0bbdbb5 100644 --- a/net/batman-adv/ring_buffer.c +++ b/net/batman-adv/ring_buffer.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/ring_buffer.h b/net/batman-adv/ring_buffer.h index fda8c17df27..3f92ae248e8 100644 --- a/net/batman-adv/ring_buffer.h +++ b/net/batman-adv/ring_buffer.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 1aa1722d018..60ba03fc839 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -80,7 +80,6 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, /* route added */ } else if ((!curr_router) && (neigh_node)) { - batadv_dbg(BATADV_DBG_ROUTES, bat_priv, "Adding route towards: %pM (via %pM)\n", orig_node->orig, neigh_node->addr); @@ -172,7 +171,6 @@ void batadv_bonding_candidate_add(struct batadv_orig_node *orig_node, */ hlist_for_each_entry_rcu(tmp_neigh_node, node, &orig_node->neigh_list, list) { - if (tmp_neigh_node == neigh_node) continue; @@ -836,7 +834,6 @@ static int batadv_route_unicast_packet(struct sk_buff *skb, if (unicast_packet->header.packet_type == BATADV_UNICAST_FRAG && batadv_frag_can_reassemble(skb, neigh_node->if_incoming->net_dev->mtu)) { - ret = batadv_frag_reassemble_skb(skb, bat_priv, &new_skb); if (ret == NET_RX_DROP) @@ -1103,7 +1100,6 @@ int batadv_recv_ucast_frag_packet(struct sk_buff *skb, /* packet for me */ if (batadv_is_my_mac(unicast_packet->dest)) { - ret = batadv_frag_reassemble_skb(skb, bat_priv, &new_skb); if (ret == NET_RX_DROP) diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 9262279ea66..99eeafaba40 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 4425af9dad4..80ca65fc89a 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -155,8 +155,6 @@ _batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, spin_unlock_bh(&bat_priv->forw_bcast_list_lock); /* start timer for this packet */ - INIT_DELAYED_WORK(&forw_packet->delayed_work, - batadv_send_outstanding_bcast_packet); queue_delayed_work(batadv_event_workqueue, &forw_packet->delayed_work, send_time); } @@ -210,6 +208,9 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, /* how often did we send the bcast packet ? */ forw_packet->num_packets = 0; + INIT_DELAYED_WORK(&forw_packet->delayed_work, + batadv_send_outstanding_bcast_packet); + _batadv_add_bcast_packet_to_list(bat_priv, forw_packet, delay); return NETDEV_TX_OK; @@ -330,7 +331,6 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, spin_lock_bh(&bat_priv->forw_bcast_list_lock); hlist_for_each_entry_safe(forw_packet, tmp_node, safe_tmp_node, &bat_priv->forw_bcast_list, list) { - /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ @@ -357,7 +357,6 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, spin_lock_bh(&bat_priv->forw_bat_list_lock); hlist_for_each_entry_safe(forw_packet, tmp_node, safe_tmp_node, &bat_priv->forw_bat_list, list) { - /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 0078dece1ab..38e662f619a 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 6b548fde8e0..2711e870f55 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -124,7 +124,6 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) batadv_tt_local_add(dev, addr->sa_data, BATADV_NULL_IFINDEX); } - dev->addr_assign_type &= ~NET_ADDR_RANDOM; return 0; } @@ -181,7 +180,8 @@ static int batadv_interface_tx(struct sk_buff *skb, goto dropped; /* Register the client MAC in the transtable */ - batadv_tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif); + if (!is_multicast_ether_addr(ethhdr->h_source)) + batadv_tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif); /* don't accept stp packets. STP does not help in meshes. * better use the bridge loop avoidance ... @@ -449,6 +449,30 @@ static void batadv_interface_setup(struct net_device *dev) memset(priv, 0, sizeof(*priv)); } +/** + * batadv_softif_destroy_finish - cleans up the remains of a softif + * @work: work queue item + * + * Free the parts of the soft interface which can not be removed under + * rtnl lock (to prevent deadlock situations). + */ +static void batadv_softif_destroy_finish(struct work_struct *work) +{ + struct batadv_priv *bat_priv; + struct net_device *soft_iface; + + bat_priv = container_of(work, struct batadv_priv, + cleanup_work); + soft_iface = bat_priv->soft_iface; + + batadv_debugfs_del_meshif(soft_iface); + batadv_sysfs_del_meshif(soft_iface); + + rtnl_lock(); + unregister_netdevice(soft_iface); + rtnl_unlock(); +} + struct net_device *batadv_softif_create(const char *name) { struct net_device *soft_iface; @@ -463,6 +487,8 @@ struct net_device *batadv_softif_create(const char *name) goto out; bat_priv = netdev_priv(soft_iface); + bat_priv->soft_iface = soft_iface; + INIT_WORK(&bat_priv->cleanup_work, batadv_softif_destroy_finish); /* batadv_interface_stats() needs to be available as soon as * register_netdevice() has been called @@ -480,7 +506,9 @@ struct net_device *batadv_softif_create(const char *name) atomic_set(&bat_priv->aggregated_ogms, 1); atomic_set(&bat_priv->bonding, 0); +#ifdef CONFIG_BATMAN_ADV_BLA atomic_set(&bat_priv->bridge_loop_avoidance, 0); +#endif #ifdef CONFIG_BATMAN_ADV_DAT atomic_set(&bat_priv->distributed_arp_table, 1); #endif @@ -491,7 +519,9 @@ struct net_device *batadv_softif_create(const char *name) atomic_set(&bat_priv->gw_bandwidth, 41); atomic_set(&bat_priv->orig_interval, 1000); atomic_set(&bat_priv->hop_penalty, 30); +#ifdef CONFIG_BATMAN_ADV_DEBUG atomic_set(&bat_priv->log_level, 0); +#endif atomic_set(&bat_priv->fragmentation, 1); atomic_set(&bat_priv->bcast_queue_left, BATADV_BCAST_QUEUE_LEN); atomic_set(&bat_priv->batman_queue_left, BATADV_BATMAN_QUEUE_LEN); @@ -547,10 +577,10 @@ out: void batadv_softif_destroy(struct net_device *soft_iface) { - batadv_debugfs_del_meshif(soft_iface); - batadv_sysfs_del_meshif(soft_iface); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + batadv_mesh_free(soft_iface); - unregister_netdevice(soft_iface); + queue_work(batadv_event_workqueue, &bat_priv->cleanup_work); } int batadv_softif_is_valid(const struct net_device *net_dev) @@ -581,10 +611,10 @@ static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) static void batadv_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strcpy(info->driver, "B.A.T.M.A.N. advanced"); - strcpy(info->version, BATADV_SOURCE_VERSION); - strcpy(info->fw_version, "N/A"); - strcpy(info->bus_info, "batman"); + strlcpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver)); + strlcpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version)); + strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); + strlcpy(info->bus_info, "batman", sizeof(info->bus_info)); } static u32 batadv_get_msglevel(struct net_device *dev) diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 07a08fed28b..43182e5e603 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 84a55cb19b0..afbba319d73 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index 3fd1412b062..479acf4c16f 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 22457a7952b..fb15b4c076f 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * @@ -29,6 +29,10 @@ #include <linux/crc16.h> +/* hash class keys */ +static struct lock_class_key batadv_tt_local_hash_lock_class_key; +static struct lock_class_key batadv_tt_global_hash_lock_class_key; + static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client, struct batadv_orig_node *orig_node); static void batadv_tt_purge(struct work_struct *work); @@ -48,13 +52,6 @@ static int batadv_compare_tt(const struct hlist_node *node, const void *data2) return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } -static void batadv_tt_start_timer(struct batadv_priv *bat_priv) -{ - INIT_DELAYED_WORK(&bat_priv->tt.work, batadv_tt_purge); - queue_delayed_work(batadv_event_workqueue, &bat_priv->tt.work, - msecs_to_jiffies(5000)); -} - static struct batadv_tt_common_entry * batadv_tt_hash_find(struct batadv_hashtable *hash, const void *data) { @@ -112,7 +109,6 @@ batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const void *data) struct batadv_tt_global_entry, common); return tt_global_entry; - } static void @@ -235,6 +231,9 @@ static int batadv_tt_local_init(struct batadv_priv *bat_priv) if (!bat_priv->tt.local_hash) return -ENOMEM; + batadv_hash_set_lock_class(bat_priv->tt.local_hash, + &batadv_tt_local_hash_lock_class_key); + return 0; } @@ -249,7 +248,6 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv, batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt, batadv_choose_orig, tt_global->common.addr); batadv_tt_global_entry_free_ref(tt_global); - } void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, @@ -305,7 +303,11 @@ void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, (uint8_t)atomic_read(&bat_priv->tt.vn)); memcpy(tt_local->common.addr, addr, ETH_ALEN); - tt_local->common.flags = BATADV_NO_FLAGS; + /* The local entry has to be marked as NEW to avoid to send it in + * a full table response going out before the next ttvn increment + * (consistency check) + */ + tt_local->common.flags = BATADV_TT_CLIENT_NEW; if (batadv_is_wifi_iface(ifindex)) tt_local->common.flags |= BATADV_TT_CLIENT_WIFI; atomic_set(&tt_local->common.refcount, 2); @@ -316,12 +318,6 @@ void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, if (batadv_compare_eth(addr, soft_iface->dev_addr)) tt_local->common.flags |= BATADV_TT_CLIENT_NOPURGE; - /* The local entry has to be marked as NEW to avoid to send it in - * a full table response going out before the next ttvn increment - * (consistency check) - */ - tt_local->common.flags |= BATADV_TT_CLIENT_NEW; - hash_added = batadv_hash_add(bat_priv->tt.local_hash, batadv_compare_tt, batadv_choose_orig, &tt_local->common, &tt_local->common.hash_entry); @@ -472,18 +468,27 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common_entry; + struct batadv_tt_local_entry *tt_local; struct batadv_hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; uint32_t i; + int last_seen_secs; + int last_seen_msecs; + unsigned long last_seen_jiffies; + bool no_purge; + uint16_t np_flag = BATADV_TT_CLIENT_NOPURGE; primary_if = batadv_seq_print_text_primary_if_get(seq); if (!primary_if) goto out; 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)); + "Locally retrieved addresses (from %s) announced via TT (TTVN: %u CRC: %#.4x):\n", + net_dev->name, (uint8_t)atomic_read(&bat_priv->tt.vn), + bat_priv->tt.local_crc); + seq_printf(seq, " %-13s %-7s %-10s\n", "Client", "Flags", + "Last seen"); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -491,18 +496,29 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(tt_common_entry, node, head, hash_entry) { - seq_printf(seq, " * %pM [%c%c%c%c%c]\n", + tt_local = container_of(tt_common_entry, + struct batadv_tt_local_entry, + common); + last_seen_jiffies = jiffies - tt_local->last_seen; + last_seen_msecs = jiffies_to_msecs(last_seen_jiffies); + last_seen_secs = last_seen_msecs / 1000; + last_seen_msecs = last_seen_msecs % 1000; + + no_purge = tt_common_entry->flags & np_flag; + + seq_printf(seq, " * %pM [%c%c%c%c%c] %3u.%03u\n", tt_common_entry->addr, (tt_common_entry->flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'), - (tt_common_entry->flags & - BATADV_TT_CLIENT_NOPURGE ? 'P' : '.'), + no_purge ? 'P' : '.', (tt_common_entry->flags & BATADV_TT_CLIENT_NEW ? 'N' : '.'), (tt_common_entry->flags & BATADV_TT_CLIENT_PENDING ? 'X' : '.'), (tt_common_entry->flags & - BATADV_TT_CLIENT_WIFI ? 'W' : '.')); + BATADV_TT_CLIENT_WIFI ? 'W' : '.'), + no_purge ? last_seen_secs : 0, + no_purge ? last_seen_msecs : 0); } rcu_read_unlock(); } @@ -627,7 +643,6 @@ static void batadv_tt_local_purge(struct batadv_priv *bat_priv) batadv_tt_local_purge_list(bat_priv, head); spin_unlock_bh(list_lock); } - } static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) @@ -676,6 +691,9 @@ static int batadv_tt_global_init(struct batadv_priv *bat_priv) if (!bat_priv->tt.global_hash) return -ENOMEM; + batadv_hash_set_lock_class(bat_priv->tt.global_hash, + &batadv_tt_global_hash_lock_class_key); + return 0; } @@ -967,10 +985,11 @@ batadv_tt_global_print_entry(struct batadv_tt_global_entry *tt_global_entry, best_entry = batadv_transtable_best_orig(tt_global_entry); if (best_entry) { last_ttvn = atomic_read(&best_entry->orig_node->last_ttvn); - seq_printf(seq, " %c %pM (%3u) via %pM (%3u) [%c%c%c]\n", + seq_printf(seq, + " %c %pM (%3u) via %pM (%3u) (%#.4x) [%c%c%c]\n", '*', tt_global_entry->common.addr, best_entry->ttvn, best_entry->orig_node->orig, - last_ttvn, + last_ttvn, best_entry->orig_node->tt_crc, (flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'), (flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.'), (flags & BATADV_TT_CLIENT_TEMP ? 'T' : '.')); @@ -1012,8 +1031,9 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset) seq_printf(seq, "Globally announced TT entries received via the mesh %s\n", net_dev->name); - seq_printf(seq, " %-13s %s %-15s %s %s\n", - "Client", "(TTVN)", "Originator", "(Curr TTVN)", "Flags"); + seq_printf(seq, " %-13s %s %-15s %s (%-6s) %s\n", + "Client", "(TTVN)", "Originator", "(Curr TTVN)", "CRC", + "Flags"); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1049,7 +1069,6 @@ batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry) batadv_tt_orig_list_entry_free_ref(orig_entry); } spin_unlock_bh(&tt_global_entry->list_lock); - } static void @@ -1825,7 +1844,6 @@ out: if (!ret) kfree_skb(skb); return ret; - } static bool @@ -2111,7 +2129,9 @@ int batadv_tt_init(struct batadv_priv *bat_priv) if (ret < 0) return ret; - batadv_tt_start_timer(bat_priv); + INIT_DELAYED_WORK(&bat_priv->tt.work, batadv_tt_purge); + queue_delayed_work(batadv_event_workqueue, &bat_priv->tt.work, + msecs_to_jiffies(BATADV_TT_WORK_PERIOD)); return 1; } @@ -2261,7 +2281,8 @@ static void batadv_tt_purge(struct work_struct *work) batadv_tt_req_purge(bat_priv); batadv_tt_roam_purge(bat_priv); - batadv_tt_start_timer(bat_priv); + queue_delayed_work(batadv_event_workqueue, &bat_priv->tt.work, + msecs_to_jiffies(BATADV_TT_WORK_PERIOD)); } void batadv_tt_free(struct batadv_priv *bat_priv) @@ -2352,7 +2373,6 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) } spin_unlock_bh(list_lock); } - } static int batadv_tt_commit_changes(struct batadv_priv *bat_priv, @@ -2496,7 +2516,7 @@ void batadv_tt_update_orig(struct batadv_priv *bat_priv, orig_node->tt_crc != tt_crc) { request_table: batadv_dbg(BATADV_DBG_TT, bat_priv, - "TT inconsistency for %pM. Need to retrieve the correct information (ttvn: %u last_ttvn: %u crc: %u last_crc: %u num_changes: %u)\n", + "TT inconsistency for %pM. Need to retrieve the correct information (ttvn: %u last_ttvn: %u crc: %#.4x last_crc: %#.4x num_changes: %u)\n", orig_node->orig, ttvn, orig_ttvn, tt_crc, orig_node->tt_crc, tt_num_changes); batadv_send_tt_request(bat_priv, orig_node, ttvn, @@ -2549,7 +2569,6 @@ bool batadv_tt_local_client_is_roaming(struct batadv_priv *bat_priv, batadv_tt_local_entry_free_ref(tt_local_entry); out: return ret; - } bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv, diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 46d4451a59e..ab8e683b402 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ae9ac9aca8c..4cd87a0b5b8 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -24,6 +24,9 @@ #include "bitarray.h" #include <linux/kernel.h> +/** + * Maximum overhead for the encapsulation for a payload packet + */ #define BATADV_HEADER_LEN \ (ETH_HLEN + max(sizeof(struct batadv_unicast_packet), \ sizeof(struct batadv_bcast_packet))) @@ -51,6 +54,22 @@ struct batadv_hard_iface_bat_iv { atomic_t ogm_seqno; }; +/** + * struct batadv_hard_iface - network device known to batman-adv + * @list: list node for batadv_hardif_list + * @if_num: identificator of the interface + * @if_status: status of the interface for batman-adv + * @net_dev: pointer to the net_device + * @frag_seqno: last fragment sequence number sent by this interface + * @hardif_obj: kobject of the per interface sysfs "mesh" directory + * @refcount: number of contexts the object is used + * @batman_adv_ptype: packet type describing packets that should be processed by + * batman-adv for this interface + * @soft_iface: the batman-adv interface which uses this network interface + * @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 + */ struct batadv_hard_iface { struct list_head list; int16_t if_num; @@ -63,22 +82,52 @@ struct batadv_hard_iface { struct net_device *soft_iface; struct rcu_head rcu; struct batadv_hard_iface_bat_iv bat_iv; + struct work_struct cleanup_work; }; /** - * struct batadv_orig_node - structure for orig_list maintaining nodes of mesh - * @primary_addr: hosts primary interface address - * @last_seen: 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 - * @gw_flags: flags related to gateway class - * @flags: for now only VIS_SERVER flag - * @last_real_seqno: last and best known sequence number - * @last_ttl: ttl of last received packet - * @last_bcast_seqno: last broadcast sequence number received by this host - * - * @candidates: how many candidates are available - * @selected: next bonding candidate + * 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 + * @batadv_dat_addr_t: address of the orig node in the distributed hash + * @bcast_own: bitfield containing the number of our OGMs this orig_node + * rebroadcasted "back" to us (relative to last_real_seqno) + * @bcast_own_sum: counted result of bcast_own + * @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 + * @gw_flags: flags related to gateway class + * @flags: for now only VIS_SERVER flag + * @last_ttvn: last seen translation table version number + * @tt_crc: CRC of the translation table + * @tt_buff: last tt changeset this node received from the orig node + * @tt_buff_len: length of the last tt changeset this node received from the + * orig node + * @tt_buff_lock: lock that protects tt_buff and tt_buff_len + * @tt_size: number of global TT entries announced by the orig node + * @tt_initialised: bool keeping track of whether or not this node have received + * any translation table information from the orig node yet + * @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 + * @frag_list: fragmentation buffer list for fragment re-assembly + * @last_frag_packet: time when last fragmented packet from this node was + * received + * @neigh_list_lock: lock protecting neigh_list, router and bonding_list + * @hash_entry: hlist node for batadv_priv::orig_hash + * @bat_priv: pointer to soft_iface this orig node belongs to + * @ogm_cnt_lock: lock protecting bcast_own, bcast_own_sum, + * neigh_node->real_bits & neigh_node->real_packet_count + * @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 */ struct batadv_orig_node { uint8_t orig[ETH_ALEN]; @@ -94,11 +143,11 @@ struct batadv_orig_node { unsigned long batman_seqno_reset; uint8_t gw_flags; uint8_t flags; - atomic_t last_ttvn; /* last seen translation table version number */ + atomic_t last_ttvn; uint16_t tt_crc; unsigned char *tt_buff; int16_t tt_buff_len; - spinlock_t tt_buff_lock; /* protects tt_buff */ + spinlock_t tt_buff_lock; /* protects tt_buff & tt_buff_len */ atomic_t tt_size; bool tt_initialised; uint32_t last_real_seqno; @@ -107,23 +156,31 @@ struct batadv_orig_node { uint32_t last_bcast_seqno; struct hlist_head neigh_list; struct list_head frag_list; - spinlock_t neigh_list_lock; /* protects neigh_list and router */ - atomic_t refcount; - struct rcu_head rcu; + unsigned long last_frag_packet; + /* neigh_list_lock protects: neigh_list, router & bonding_list */ + spinlock_t neigh_list_lock; struct hlist_node hash_entry; struct batadv_priv *bat_priv; - unsigned long last_frag_packet; /* ogm_cnt_lock protects: bcast_own, bcast_own_sum, - * neigh_node->real_bits, neigh_node->real_packet_count + * neigh_node->real_bits & neigh_node->real_packet_count */ spinlock_t ogm_cnt_lock; - /* bcast_seqno_lock protects bcast_bits, last_bcast_seqno */ + /* bcast_seqno_lock protects: bcast_bits & last_bcast_seqno */ spinlock_t bcast_seqno_lock; - spinlock_t tt_list_lock; /* protects tt_list */ atomic_t bond_candidates; struct list_head bond_list; + atomic_t refcount; + struct rcu_head rcu; }; +/** + * struct batadv_gw_node - structure for orig nodes announcing gw capabilities + * @list: list node for batadv_priv_gw::list + * @orig_node: pointer to corresponding orig node + * @deleted: this struct is scheduled for deletion + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ struct batadv_gw_node { struct hlist_node list; struct batadv_orig_node *orig_node; @@ -132,13 +189,28 @@ struct batadv_gw_node { struct rcu_head rcu; }; -/* batadv_neigh_node - * @last_seen: when last packet via this neighbor was received +/** + * struct batadv_neigh_node - structure for single hop neighbors + * @list: list node for batadv_orig_node::neigh_list + * @addr: mac address of neigh node + * @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) + * @last_ttl: last received ttl from this neigh node + * @bonding_list: list node for batadv_orig_node::bond_list + * @last_seen: when last packet via this neighbor was received + * @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 + * @orig_node: pointer to corresponding orig_node + * @if_incoming: pointer to incoming hard interface + * @lq_update_lock: lock protecting tq_recv & tq_index + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner */ struct batadv_neigh_node { struct hlist_node list; uint8_t addr[ETH_ALEN]; - uint8_t real_packet_count; uint8_t tq_recv[BATADV_TQ_GLOBAL_WINDOW_SIZE]; uint8_t tq_index; uint8_t tq_avg; @@ -146,13 +218,20 @@ struct batadv_neigh_node { struct list_head bonding_list; unsigned long last_seen; DECLARE_BITMAP(real_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); - atomic_t refcount; - struct rcu_head rcu; + uint8_t real_packet_count; struct batadv_orig_node *orig_node; struct batadv_hard_iface *if_incoming; - spinlock_t lq_update_lock; /* protects: tq_recv, tq_index */ + spinlock_t lq_update_lock; /* protects tq_recv & tq_index */ + atomic_t refcount; + struct rcu_head rcu; }; +/** + * struct batadv_bcast_duplist_entry - structure for LAN broadcast suppression + * @orig[ETH_ALEN]: mac address of orig node orginating the broadcast + * @crc: crc32 checksum of broadcast payload + * @entrytime: time when the broadcast packet was received + */ #ifdef CONFIG_BATMAN_ADV_BLA struct batadv_bcast_duplist_entry { uint8_t orig[ETH_ALEN]; @@ -161,6 +240,33 @@ struct batadv_bcast_duplist_entry { }; #endif +/** + * enum batadv_counters - indices for traffic counters + * @BATADV_CNT_TX: transmitted payload traffic packet counter + * @BATADV_CNT_TX_BYTES: transmitted payload traffic bytes counter + * @BATADV_CNT_TX_DROPPED: dropped transmission payload traffic packet counter + * @BATADV_CNT_RX: received payload traffic packet counter + * @BATADV_CNT_RX_BYTES: received payload traffic bytes counter + * @BATADV_CNT_FORWARD: forwarded payload traffic packet counter + * @BATADV_CNT_FORWARD_BYTES: forwarded payload traffic bytes counter + * @BATADV_CNT_MGMT_TX: transmitted routing protocol traffic packet counter + * @BATADV_CNT_MGMT_TX_BYTES: transmitted routing protocol traffic bytes counter + * @BATADV_CNT_MGMT_RX: received routing protocol traffic packet counter + * @BATADV_CNT_MGMT_RX_BYTES: received routing protocol traffic bytes counter + * @BATADV_CNT_TT_REQUEST_TX: transmitted tt req traffic packet counter + * @BATADV_CNT_TT_REQUEST_RX: received tt req traffic packet counter + * @BATADV_CNT_TT_RESPONSE_TX: transmitted tt resp traffic packet counter + * @BATADV_CNT_TT_RESPONSE_RX: received tt resp traffic packet counter + * @BATADV_CNT_TT_ROAM_ADV_TX: transmitted tt roam traffic packet counter + * @BATADV_CNT_TT_ROAM_ADV_RX: received tt roam traffic packet counter + * @BATADV_CNT_DAT_GET_TX: transmitted dht GET traffic packet counter + * @BATADV_CNT_DAT_GET_RX: received dht GET traffic packet counter + * @BATADV_CNT_DAT_PUT_TX: transmitted dht PUT traffic packet counter + * @BATADV_CNT_DAT_PUT_RX: received dht PUT traffic packet counter + * @BATADV_CNT_DAT_CACHED_REPLY_TX: transmitted dat cache reply traffic packet + * counter + * @BATADV_CNT_NUM: number of traffic counters + */ enum batadv_counters { BATADV_CNT_TX, BATADV_CNT_TX_BYTES, @@ -192,14 +298,23 @@ enum batadv_counters { /** * struct batadv_priv_tt - per mesh interface translation table data * @vn: translation table version number + * @ogm_append_cnt: counter of number of OGMs containing the local tt diff * @local_changes: changes registered in an originator interval - * @poss_change: Detect an ongoing roaming phase. If true, then this node - * received a roaming_adv and has to inspect every packet directed to it to - * check whether it still is the true destination or not. This flag will be - * reset to false as soon as the this node's ttvn is increased * @changes_list: tracks tt local changes within an originator interval - * @req_list: list of pending tt_requests + * @local_hash: local translation table hash table + * @global_hash: global translation table hash table + * @req_list: list of pending & unanswered tt_requests + * @roam_list: list of the last roaming events of each client limiting the + * number of roaming events to avoid route flapping + * @changes_list_lock: lock protecting changes_list + * @req_list_lock: lock protecting req_list + * @roam_list_lock: lock protecting roam_list + * @local_entry_num: number of entries in the local hash table * @local_crc: Checksum of the local table, recomputed before sending a new OGM + * @last_changeset: last tt changeset this host has generated + * @last_changeset_len: length of last tt changeset this host has generated + * @last_changeset_lock: lock protecting last_changeset & last_changeset_len + * @work: work queue callback item for translation table purging */ struct batadv_priv_tt { atomic_t vn; @@ -217,36 +332,83 @@ struct batadv_priv_tt { uint16_t local_crc; unsigned char *last_changeset; int16_t last_changeset_len; - spinlock_t last_changeset_lock; /* protects last_changeset */ + /* protects last_changeset & last_changeset_len */ + spinlock_t last_changeset_lock; struct delayed_work work; }; +/** + * struct batadv_priv_bla - per mesh interface bridge loope avoidance data + * @num_requests; number of bla requests in flight + * @claim_hash: hash table containing mesh nodes this host has claimed + * @backbone_hash: hash table containing all detected backbone gateways + * @bcast_duplist: recently received broadcast packets array (for broadcast + * duplicate suppression) + * @bcast_duplist_curr: index of last broadcast packet added to bcast_duplist + * @bcast_duplist_lock: lock protecting bcast_duplist & bcast_duplist_curr + * @claim_dest: local claim data (e.g. claim group) + * @work: work queue callback item for cleanups & bla announcements + */ #ifdef CONFIG_BATMAN_ADV_BLA struct batadv_priv_bla { - atomic_t num_requests; /* number of bla requests in flight */ + atomic_t num_requests; struct batadv_hashtable *claim_hash; struct batadv_hashtable *backbone_hash; struct batadv_bcast_duplist_entry bcast_duplist[BATADV_DUPLIST_SIZE]; int bcast_duplist_curr; - /* protects bcast_duplist and bcast_duplist_curr */ + /* protects bcast_duplist & bcast_duplist_curr */ spinlock_t bcast_duplist_lock; struct batadv_bla_claim_dst claim_dest; struct delayed_work work; }; #endif +/** + * struct batadv_debug_log - debug logging data + * @log_buff: buffer holding the logs (ring bufer) + * @log_start: index of next character to read + * @log_end: index of next character to write + * @lock: lock protecting log_buff, log_start & log_end + * @queue_wait: log reader's wait queue + */ +#ifdef CONFIG_BATMAN_ADV_DEBUG +struct batadv_priv_debug_log { + char log_buff[BATADV_LOG_BUF_LEN]; + unsigned long log_start; + unsigned long log_end; + spinlock_t lock; /* protects log_buff, log_start and log_end */ + wait_queue_head_t queue_wait; +}; +#endif + +/** + * struct batadv_priv_gw - per mesh interface gateway data + * @list: list of available gateway nodes + * @list_lock: lock protecting gw_list & curr_gw + * @curr_gw: pointer to currently selected gateway node + * @reselect: bool indicating a gateway re-selection is in progress + */ struct batadv_priv_gw { struct hlist_head list; - spinlock_t list_lock; /* protects gw_list and curr_gw */ + spinlock_t list_lock; /* protects gw_list & curr_gw */ struct batadv_gw_node __rcu *curr_gw; /* rcu protected pointer */ atomic_t reselect; }; +/** + * struct batadv_priv_vis - per mesh interface vis data + * @send_list: list of batadv_vis_info packets to sent + * @hash: hash table containing vis data from other nodes in the network + * @hash_lock: lock protecting the hash table + * @list_lock: lock protecting my_info::recv_list + * @work: work queue callback item for vis packet sending + * @my_info: holds this node's vis data sent on a regular basis + */ struct batadv_priv_vis { struct list_head send_list; struct batadv_hashtable *hash; spinlock_t hash_lock; /* protects hash */ - spinlock_t list_lock; /* protects info::recv_list */ + spinlock_t list_lock; /* protects my_info::recv_list */ struct delayed_work work; struct batadv_vis_info *my_info; }; @@ -265,30 +427,78 @@ struct batadv_priv_dat { }; #endif +/** + * struct batadv_priv - per mesh interface data + * @mesh_state: current status of the mesh (inactive/active/deactivating) + * @soft_iface: net device which holds this struct as private data + * @stats: structure holding the data for the ndo_get_stats() call + * @bat_counters: mesh internal traffic statistic counters (see batadv_counters) + * @aggregated_ogms: bool indicating whether OGM aggregation is enabled + * @bonding: bool indicating whether traffic bonding is enabled + * @fragmentation: bool indicating whether traffic fragmentation is enabled + * @ap_isolation: bool indicating whether ap isolation is enabled + * @bridge_loop_avoidance: bool indicating whether bridge loop avoidance is + * enabled + * @distributed_arp_table: bool indicating whether distributed ARP table is + * enabled + * @vis_mode: vis operation: client or server (see batadv_vis_packettype) + * @gw_mode: gateway operation: off, client or server (see batadv_gw_modes) + * @gw_sel_class: gateway selection class (applies if gw_mode client) + * @gw_bandwidth: gateway announced bandwidth (applies if gw_mode server) + * @orig_interval: OGM broadcast interval in milliseconds + * @hop_penalty: penalty which will be applied to an OGM's tq-field on every hop + * @log_level: configured log level (see batadv_dbg_level) + * @bcast_seqno: last sent broadcast packet sequence number + * @bcast_queue_left: number of remaining buffered broadcast packet slots + * @batman_queue_left: number of remaining OGM packet slots + * @num_ifaces: number of interfaces assigned to this mesh interface + * @mesh_obj: kobject for sysfs mesh subdirectory + * @debug_dir: dentry for debugfs batman-adv subdirectory + * @forw_bat_list: list of aggregated OGMs that will be forwarded + * @forw_bcast_list: list of broadcast packets that will be rebroadcasted + * @orig_hash: hash table containing mesh participants (orig nodes) + * @forw_bat_list_lock: lock protecting forw_bat_list + * @forw_bcast_list_lock: lock protecting forw_bcast_list + * @orig_work: work queue callback item for orig node purging + * @cleanup_work: work queue callback item for soft interface deinit + * @primary_if: one of the hard interfaces assigned to this mesh interface + * becomes the primary interface + * @bat_algo_ops: routing algorithm used by this mesh interface + * @bla: bridge loope avoidance data + * @debug_log: holding debug logging relevant data + * @gw: gateway data + * @tt: translation table data + * @vis: vis data + * @dat: distributed arp table data + */ struct batadv_priv { atomic_t mesh_state; + struct net_device *soft_iface; struct net_device_stats stats; uint64_t __percpu *bat_counters; /* Per cpu counters */ - atomic_t aggregated_ogms; /* boolean */ - atomic_t bonding; /* boolean */ - atomic_t fragmentation; /* boolean */ - atomic_t ap_isolation; /* boolean */ - atomic_t bridge_loop_avoidance; /* boolean */ + atomic_t aggregated_ogms; + atomic_t bonding; + atomic_t fragmentation; + atomic_t ap_isolation; +#ifdef CONFIG_BATMAN_ADV_BLA + atomic_t bridge_loop_avoidance; +#endif #ifdef CONFIG_BATMAN_ADV_DAT - atomic_t distributed_arp_table; /* boolean */ + atomic_t distributed_arp_table; +#endif + atomic_t vis_mode; + atomic_t gw_mode; + atomic_t gw_sel_class; + atomic_t gw_bandwidth; + atomic_t orig_interval; + atomic_t hop_penalty; +#ifdef CONFIG_BATMAN_ADV_DEBUG + atomic_t log_level; #endif - atomic_t vis_mode; /* VIS_TYPE_* */ - atomic_t gw_mode; /* GW_MODE_* */ - atomic_t gw_sel_class; /* uint */ - atomic_t gw_bandwidth; /* gw bandwidth */ - atomic_t orig_interval; /* uint */ - atomic_t hop_penalty; /* uint */ - atomic_t log_level; /* uint */ atomic_t bcast_seqno; atomic_t bcast_queue_left; atomic_t batman_queue_left; char num_ifaces; - struct batadv_debug_log *debug_log; struct kobject *mesh_obj; struct dentry *debug_dir; struct hlist_head forw_bat_list; @@ -297,11 +507,15 @@ struct batadv_priv { spinlock_t forw_bat_list_lock; /* protects forw_bat_list */ spinlock_t forw_bcast_list_lock; /* protects forw_bcast_list */ struct delayed_work orig_work; + struct work_struct cleanup_work; struct batadv_hard_iface __rcu *primary_if; /* rcu protected pointer */ struct batadv_algo_ops *bat_algo_ops; #ifdef CONFIG_BATMAN_ADV_BLA struct batadv_priv_bla bla; #endif +#ifdef CONFIG_BATMAN_ADV_DEBUG + struct batadv_priv_debug_log *debug_log; +#endif struct batadv_priv_gw gw; struct batadv_priv_tt tt; struct batadv_priv_vis vis; @@ -310,21 +524,97 @@ struct batadv_priv { #endif }; +/** + * struct batadv_socket_client - layer2 icmp socket client data + * @queue_list: packet queue for packets destined for this socket client + * @queue_len: number of packets in the packet queue (queue_list) + * @index: socket client's index in the batadv_socket_client_hash + * @lock: lock protecting queue_list, queue_len & index + * @queue_wait: socket client's wait queue + * @bat_priv: pointer to soft_iface this client belongs to + */ struct batadv_socket_client { struct list_head queue_list; unsigned int queue_len; unsigned char index; - spinlock_t lock; /* protects queue_list, queue_len, index */ + spinlock_t lock; /* protects queue_list, queue_len & index */ wait_queue_head_t queue_wait; struct batadv_priv *bat_priv; }; +/** + * struct batadv_socket_packet - layer2 icmp packet for socket client + * @list: list node for batadv_socket_client::queue_list + * @icmp_len: size of the layer2 icmp packet + * @icmp_packet: layer2 icmp packet + */ struct batadv_socket_packet { struct list_head list; size_t icmp_len; struct batadv_icmp_packet_rr icmp_packet; }; +/** + * struct batadv_bla_backbone_gw - batman-adv gateway bridged into the LAN + * @orig: originator address of backbone node (mac address of primary iface) + * @vid: vlan id this gateway was detected on + * @hash_entry: hlist node for batadv_priv_bla::backbone_hash + * @bat_priv: pointer to soft_iface this backbone gateway belongs to + * @lasttime: last time we heard of this backbone gw + * @wait_periods: grace time for bridge forward delays and bla group forming at + * bootup phase - no bcast traffic is formwared until it has elapsed + * @request_sent: if this bool is set to true we are out of sync with this + * backbone gateway - no bcast traffic is formwared until the situation was + * resolved + * @crc: crc16 checksum over all claims + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ +#ifdef CONFIG_BATMAN_ADV_BLA +struct batadv_bla_backbone_gw { + uint8_t orig[ETH_ALEN]; + short vid; + struct hlist_node hash_entry; + struct batadv_priv *bat_priv; + unsigned long lasttime; + atomic_t wait_periods; + atomic_t request_sent; + uint16_t crc; + atomic_t refcount; + struct rcu_head rcu; +}; + +/** + * struct batadv_bla_claim - claimed non-mesh client structure + * @addr: mac address of claimed non-mesh client + * @vid: vlan id this client was detected on + * @batadv_bla_backbone_gw: pointer to backbone gw claiming this client + * @lasttime: last time we heard of claim (locals only) + * @hash_entry: hlist node for batadv_priv_bla::claim_hash + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ +struct batadv_bla_claim { + uint8_t addr[ETH_ALEN]; + short vid; + struct batadv_bla_backbone_gw *backbone_gw; + unsigned long lasttime; + struct hlist_node hash_entry; + struct rcu_head rcu; + atomic_t refcount; +}; +#endif + +/** + * struct batadv_tt_common_entry - tt local & tt global common data + * @addr: mac address of non-mesh client + * @hash_entry: hlist node for batadv_priv_tt::local_hash or for + * batadv_priv_tt::global_hash + * @flags: various state handling flags (see batadv_tt_client_flags) + * @added_at: timestamp used for purging stale tt common entries + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ struct batadv_tt_common_entry { uint8_t addr[ETH_ALEN]; struct hlist_node hash_entry; @@ -334,62 +624,76 @@ struct batadv_tt_common_entry { struct rcu_head rcu; }; +/** + * struct batadv_tt_local_entry - translation table local entry data + * @common: general translation table data + * @last_seen: timestamp used for purging stale tt local entries + */ struct batadv_tt_local_entry { struct batadv_tt_common_entry common; unsigned long last_seen; }; +/** + * struct batadv_tt_global_entry - translation table global entry data + * @common: general translation table data + * @orig_list: list of orig nodes announcing this non-mesh client + * @list_lock: lock protecting orig_list + * @roam_at: time at which TT_GLOBAL_ROAM was set + */ struct batadv_tt_global_entry { struct batadv_tt_common_entry common; struct hlist_head orig_list; - spinlock_t list_lock; /* protects the list */ - unsigned long roam_at; /* time at which TT_GLOBAL_ROAM was set */ + spinlock_t list_lock; /* protects orig_list */ + unsigned long roam_at; }; +/** + * struct batadv_tt_orig_list_entry - orig node announcing a non-mesh client + * @orig_node: pointer to orig node announcing this non-mesh client + * @ttvn: translation table version number which added the non-mesh client + * @list: list node for batadv_tt_global_entry::orig_list + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ struct batadv_tt_orig_list_entry { struct batadv_orig_node *orig_node; uint8_t ttvn; - atomic_t refcount; - struct rcu_head rcu; struct hlist_node list; -}; - -#ifdef CONFIG_BATMAN_ADV_BLA -struct batadv_backbone_gw { - uint8_t orig[ETH_ALEN]; - short vid; /* used VLAN ID */ - struct hlist_node hash_entry; - struct batadv_priv *bat_priv; - unsigned long lasttime; /* last time we heard of this backbone gw */ - atomic_t wait_periods; - atomic_t request_sent; atomic_t refcount; struct rcu_head rcu; - uint16_t crc; /* crc checksum over all claims */ -}; - -struct batadv_claim { - uint8_t addr[ETH_ALEN]; - short vid; - struct batadv_backbone_gw *backbone_gw; - unsigned long lasttime; /* last time we heard of claim (locals only) */ - struct rcu_head rcu; - atomic_t refcount; - struct hlist_node hash_entry; }; -#endif +/** + * struct batadv_tt_change_node - structure for tt changes occured + * @list: list node for batadv_priv_tt::changes_list + * @change: holds the actual translation table diff data + */ struct batadv_tt_change_node { struct list_head list; struct batadv_tt_change change; }; +/** + * struct batadv_tt_req_node - data to keep track of the tt requests in flight + * @addr: mac address address of the originator this request was sent to + * @issued_at: timestamp used for purging stale tt requests + * @list: list node for batadv_priv_tt::req_list + */ struct batadv_tt_req_node { uint8_t addr[ETH_ALEN]; unsigned long issued_at; struct list_head list; }; +/** + * struct batadv_tt_roam_node - roaming client data + * @addr: mac address of the client in the roaming phase + * @counter: number of allowed roaming events per client within a single + * OGM interval (changes are committed with each OGM) + * @first_time: timestamp used for purging stale roaming node entries + * @list: list node for batadv_priv_tt::roam_list + */ struct batadv_tt_roam_node { uint8_t addr[ETH_ALEN]; atomic_t counter; @@ -397,8 +701,19 @@ struct batadv_tt_roam_node { struct list_head list; }; -/* forw_packet - structure for forw_list maintaining packets to be - * send/forwarded +/** + * struct batadv_forw_packet - structure for bcast packets to be sent/forwarded + * @list: list node for batadv_socket_client::queue_list + * @send_time: execution time for delayed_work (packet sending) + * @own: bool for locally generated packets (local OGMs are re-scheduled after + * sending) + * @skb: bcast packet's skb buffer + * @packet_len: size of aggregated OGM packet inside the skb buffer + * @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 */ struct batadv_forw_packet { struct hlist_node list; @@ -412,72 +727,98 @@ struct batadv_forw_packet { struct batadv_hard_iface *if_incoming; }; -/* While scanning for vis-entries of a particular vis-originator - * this list collects its interfaces to create a subgraph/cluster - * out of them later +/** + * struct batadv_frag_packet_list_entry - storage for fragment packet + * @list: list node for orig_node::frag_list + * @seqno: sequence number of the fragment + * @skb: fragment's skb buffer */ -struct batadv_if_list_entry { - uint8_t addr[ETH_ALEN]; - bool primary; - struct hlist_node list; -}; - -struct batadv_debug_log { - char log_buff[BATADV_LOG_BUF_LEN]; - unsigned long log_start; - unsigned long log_end; - spinlock_t lock; /* protects log_buff, log_start and log_end */ - wait_queue_head_t queue_wait; -}; - struct batadv_frag_packet_list_entry { struct list_head list; uint16_t seqno; struct sk_buff *skb; }; +/** + * struct batadv_vis_info - local data for vis information + * @first_seen: timestamp used for purging stale vis info entries + * @recv_list: List of server-neighbors we have received this packet from. This + * packet should not be re-forward to them again. List elements are struct + * batadv_vis_recvlist_node + * @send_list: list of packets to be forwarded + * @refcount: number of contexts the object is used + * @hash_entry: hlist node for batadv_priv_vis::hash + * @bat_priv: pointer to soft_iface this orig node belongs to + * @skb_packet: contains the vis packet + */ struct batadv_vis_info { unsigned long first_seen; - /* list of server-neighbors we received a vis-packet - * from. we should not reply to them. - */ struct list_head recv_list; struct list_head send_list; struct kref refcount; struct hlist_node hash_entry; struct batadv_priv *bat_priv; - /* this packet might be part of the vis send queue. */ struct sk_buff *skb_packet; - /* vis_info may follow here */ } __packed; +/** + * struct batadv_vis_info_entry - contains link information for vis + * @src: source MAC of the link, all zero for local TT entry + * @dst: destination MAC of the link, client mac address for local TT entry + * @quality: transmission quality of the link, or 0 for local TT entry + */ struct batadv_vis_info_entry { uint8_t src[ETH_ALEN]; uint8_t dest[ETH_ALEN]; - uint8_t quality; /* quality = 0 client */ + uint8_t quality; } __packed; -struct batadv_recvlist_node { +/** + * struct batadv_vis_recvlist_node - list entry for batadv_vis_info::recv_list + * @list: list node for batadv_vis_info::recv_list + * @mac: MAC address of the originator from where the vis_info was received + */ +struct batadv_vis_recvlist_node { struct list_head list; uint8_t mac[ETH_ALEN]; }; +/** + * struct batadv_vis_if_list_entry - auxiliary data for vis data generation + * @addr: MAC address of the interface + * @primary: true if this interface is the primary interface + * @list: list node the interface list + * + * While scanning for vis-entries of a particular vis-originator + * this list collects its interfaces to create a subgraph/cluster + * out of them later + */ +struct batadv_vis_if_list_entry { + uint8_t addr[ETH_ALEN]; + bool primary; + struct hlist_node list; +}; + +/** + * struct batadv_algo_ops - mesh algorithm callbacks + * @list: list node for the batadv_algo_list + * @name: name of the algorithm + * @bat_iface_enable: init routing info when hard-interface is enabled + * @bat_iface_disable: de-init routing info when hard-interface is disabled + * @bat_iface_update_mac: (re-)init mac addresses of the protocol information + * belonging to this hard-interface + * @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 + */ struct batadv_algo_ops { struct hlist_node list; char *name; - /* init routing info when hard-interface is enabled */ int (*bat_iface_enable)(struct batadv_hard_iface *hard_iface); - /* de-init routing info when hard-interface is disabled */ void (*bat_iface_disable)(struct batadv_hard_iface *hard_iface); - /* (re-)init mac addresses of the protocol information - * belonging to this hard-interface - */ void (*bat_iface_update_mac)(struct batadv_hard_iface *hard_iface); - /* called when primary interface is selected / changed */ void (*bat_primary_iface_set)(struct batadv_hard_iface *hard_iface); - /* prepare a new outgoing OGM for the send queue */ void (*bat_ogm_schedule)(struct batadv_hard_iface *hard_iface); - /* send scheduled OGM */ void (*bat_ogm_emit)(struct batadv_forw_packet *forw_packet); }; diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index 10aff49fcf2..50e079f00be 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Andreas Langer * @@ -133,7 +133,6 @@ batadv_frag_search_packet(struct list_head *head, is_head = !!(up->flags & BATADV_UNI_FRAG_HEAD); list_for_each_entry(tfp, head, list) { - if (!tfp->skb) continue; @@ -162,7 +161,6 @@ void batadv_frag_list_free(struct list_head *head) struct batadv_frag_packet_list_entry *pf, *tmp_pf; if (!list_empty(head)) { - list_for_each_entry_safe(pf, tmp_pf, head, list) { kfree_skb(pf->skb); list_del(&pf->list); diff --git a/net/batman-adv/unicast.h b/net/batman-adv/unicast.h index 61abba58bd8..429cf8a4a31 100644 --- a/net/batman-adv/unicast.h +++ b/net/batman-adv/unicast.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Andreas Langer * diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index 0f65a9de5f7..22d2785177d 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2008-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2008-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich * @@ -28,14 +28,15 @@ #define BATADV_MAX_VIS_PACKET_SIZE 1000 -static void batadv_start_vis_timer(struct batadv_priv *bat_priv); +/* hash class keys */ +static struct lock_class_key batadv_vis_hash_lock_class_key; /* free the info */ static void batadv_free_info(struct kref *ref) { struct batadv_vis_info *info; struct batadv_priv *bat_priv; - struct batadv_recvlist_node *entry, *tmp; + struct batadv_vis_recvlist_node *entry, *tmp; info = container_of(ref, struct batadv_vis_info, refcount); bat_priv = info->bat_priv; @@ -126,7 +127,7 @@ static void batadv_vis_data_insert_interface(const uint8_t *interface, struct hlist_head *if_list, bool primary) { - struct batadv_if_list_entry *entry; + struct batadv_vis_if_list_entry *entry; struct hlist_node *pos; hlist_for_each_entry(entry, pos, if_list, list) { @@ -146,7 +147,7 @@ static void batadv_vis_data_insert_interface(const uint8_t *interface, static void batadv_vis_data_read_prim_sec(struct seq_file *seq, const struct hlist_head *if_list) { - struct batadv_if_list_entry *entry; + struct batadv_vis_if_list_entry *entry; struct hlist_node *pos; hlist_for_each_entry(entry, pos, if_list, list) { @@ -196,7 +197,7 @@ static void batadv_vis_data_read_entries(struct seq_file *seq, struct batadv_vis_info_entry *entries) { int i; - struct batadv_if_list_entry *entry; + struct batadv_vis_if_list_entry *entry; struct hlist_node *pos; hlist_for_each_entry(entry, pos, list, list) { @@ -222,7 +223,7 @@ static void batadv_vis_seq_print_text_bucket(struct seq_file *seq, struct batadv_vis_packet *packet; uint8_t *entries_pos; struct batadv_vis_info_entry *entries; - struct batadv_if_list_entry *entry; + struct batadv_vis_if_list_entry *entry; struct hlist_node *pos, *n; HLIST_HEAD(vis_if_list); @@ -304,7 +305,7 @@ static void batadv_send_list_del(struct batadv_vis_info *info) static void batadv_recv_list_add(struct batadv_priv *bat_priv, struct list_head *recv_list, const char *mac) { - struct batadv_recvlist_node *entry; + struct batadv_vis_recvlist_node *entry; entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) @@ -321,7 +322,7 @@ static int batadv_recv_list_is_in(struct batadv_priv *bat_priv, const struct list_head *recv_list, const char *mac) { - const struct batadv_recvlist_node *entry; + const struct batadv_vis_recvlist_node *entry; spin_lock_bh(&bat_priv->vis.list_lock); list_for_each_entry(entry, recv_list, list) { @@ -827,7 +828,9 @@ static void batadv_send_vis_packets(struct work_struct *work) kref_put(&info->refcount, batadv_free_info); } spin_unlock_bh(&bat_priv->vis.hash_lock); - batadv_start_vis_timer(bat_priv); + + queue_delayed_work(batadv_event_workqueue, &bat_priv->vis.work, + msecs_to_jiffies(BATADV_VIS_INTERVAL)); } /* init the vis server. this may only be called when if_list is already @@ -852,6 +855,9 @@ int batadv_vis_init(struct batadv_priv *bat_priv) goto err; } + batadv_hash_set_lock_class(bat_priv->vis.hash, + &batadv_vis_hash_lock_class_key); + bat_priv->vis.my_info = kmalloc(BATADV_MAX_VIS_PACKET_SIZE, GFP_ATOMIC); if (!bat_priv->vis.my_info) goto err; @@ -894,7 +900,11 @@ int batadv_vis_init(struct batadv_priv *bat_priv) } spin_unlock_bh(&bat_priv->vis.hash_lock); - batadv_start_vis_timer(bat_priv); + + INIT_DELAYED_WORK(&bat_priv->vis.work, batadv_send_vis_packets); + queue_delayed_work(batadv_event_workqueue, &bat_priv->vis.work, + msecs_to_jiffies(BATADV_VIS_INTERVAL)); + return 0; free_info: @@ -931,11 +941,3 @@ void batadv_vis_quit(struct batadv_priv *bat_priv) bat_priv->vis.my_info = NULL; spin_unlock_bh(&bat_priv->vis.hash_lock); } - -/* schedule packets for (re)transmission */ -static void batadv_start_vis_timer(struct batadv_priv *bat_priv) -{ - INIT_DELAYED_WORK(&bat_priv->vis.work, batadv_send_vis_packets); - queue_delayed_work(batadv_event_workqueue, &bat_priv->vis.work, - msecs_to_jiffies(BATADV_VIS_INTERVAL)); -} diff --git a/net/batman-adv/vis.h b/net/batman-adv/vis.h index 873282fa86d..ad92b0e3c23 100644 --- a/net/batman-adv/vis.h +++ b/net/batman-adv/vis.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2008-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2008-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 7c78e264019..e1bc090bc00 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -172,7 +172,6 @@ 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)) { - dev->addr_assign_type &= ~NET_ADDR_RANDOM; memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); br_fdb_change_mac_address(br, addr->sa_data); br_stp_change_bridge_id(br, addr->sa_data); @@ -185,10 +184,10 @@ static int br_set_mac_address(struct net_device *dev, void *p) static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strcpy(info->driver, "bridge"); - strcpy(info->version, BR_VERSION); - strcpy(info->fw_version, "N/A"); - strcpy(info->bus_info, "N/A"); + strlcpy(info->driver, "bridge", sizeof(info->driver)); + strlcpy(info->version, BR_VERSION, sizeof(info->version)); + strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); + strlcpy(info->bus_info, "N/A", sizeof(info->bus_info)); } static netdev_features_t br_fix_features(struct net_device *dev, diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 37fe693471a..2148d474a04 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -66,14 +66,14 @@ void br_port_carrier_check(struct net_bridge_port *p) struct net_device *dev = p->dev; struct net_bridge *br = p->br; - if (netif_running(dev) && netif_carrier_ok(dev)) + if (netif_running(dev) && netif_oper_up(dev)) p->path_cost = port_cost(dev); if (!netif_running(br->dev)) return; spin_lock_bh(&br->lock); - if (netif_running(dev) && netif_carrier_ok(dev)) { + if (netif_running(dev) && netif_oper_up(dev)) { if (p->state == BR_STATE_DISABLED) br_stp_enable_port(p); } else { @@ -148,7 +148,7 @@ static void del_nbp(struct net_bridge_port *p) netdev_rx_handler_unregister(dev); synchronize_net(); - netdev_set_master(dev, NULL); + netdev_upper_dev_unlink(dev, br->dev); br_multicast_del_port(p); @@ -364,7 +364,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (br_netpoll_info(br) && ((err = br_netpoll_enable(p, GFP_KERNEL)))) goto err3; - err = netdev_set_master(dev, br->dev); + err = netdev_master_upper_dev_link(dev, br->dev); if (err) goto err4; @@ -383,7 +383,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); - if ((dev->flags & IFF_UP) && netif_carrier_ok(dev) && + if (netif_running(dev) && netif_oper_up(dev) && (br->dev->flags & IFF_UP)) br_stp_enable_port(p); spin_unlock_bh(&br->lock); @@ -403,7 +403,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) return 0; err5: - netdev_set_master(dev, NULL); + netdev_upper_dev_unlink(dev, br->dev); err4: br_netpoll_disable(p); err3: diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 5dc66abcc9e..39ca9796f3f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -181,8 +181,11 @@ static int br_set_port_state(struct net_bridge_port *p, u8 state) if (p->br->stp_enabled == BR_KERNEL_STP) return -EBUSY; + /* if device is not up, change is not allowed + * if link is not present, only allowable state is disabled + */ if (!netif_running(p->dev) || - (!netif_carrier_ok(p->dev) && state != BR_STATE_DISABLED)) + (!netif_oper_up(p->dev) && state != BR_STATE_DISABLED)) return -ENETDOWN; p->state = state; diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c index a76b6213555..1644b3e1f94 100644 --- a/net/bridge/br_notify.c +++ b/net/bridge/br_notify.c @@ -82,7 +82,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v break; case NETDEV_UP: - if (netif_carrier_ok(dev) && (br->dev->flags & IFF_UP)) { + if (netif_running(br->dev) && netif_oper_up(dev)) { spin_lock_bh(&br->lock); br_stp_enable_port(p); spin_unlock_bh(&br->lock); diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 9d5a414a394..7b5197c7de1 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -54,7 +54,7 @@ void br_stp_enable_bridge(struct net_bridge *br) br_config_bpdu_generation(br); list_for_each_entry(p, &br->port_list, list) { - if ((p->dev->flags & IFF_UP) && netif_carrier_ok(p->dev)) + if (netif_running(p->dev) && netif_oper_up(p->dev)) br_stp_enable_port(p); } diff --git a/net/can/Kconfig b/net/can/Kconfig index 03200699d27..a15c0e0d1fc 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -16,10 +16,11 @@ menuconfig CAN If you want CAN support you should say Y here and also to the specific driver for your controller(s) below. +if CAN + config CAN_RAW tristate "Raw CAN Protocol (raw access with CAN-ID filtering)" - depends on CAN - default N + default y ---help--- The raw CAN protocol option offers access to the CAN bus via the BSD socket API. You probably want to use the raw socket in @@ -29,8 +30,7 @@ config CAN_RAW config CAN_BCM tristate "Broadcast Manager CAN Protocol (with content filtering)" - depends on CAN - default N + default y ---help--- The Broadcast Manager offers content filtering, timeout monitoring, sending of RTR frames, and cyclic CAN messages without permanent user @@ -42,8 +42,7 @@ config CAN_BCM config CAN_GW tristate "CAN Gateway/Router (with netlink configuration)" - depends on CAN - default N + default y ---help--- The CAN Gateway/Router is used to route (and modify) CAN frames. It is based on the PF_CAN core infrastructure for msg filtering and @@ -53,3 +52,5 @@ config CAN_GW by the netlink configuration interface known e.g. from iptables. source "drivers/net/can/Kconfig" + +endif diff --git a/net/can/bcm.c b/net/can/bcm.c index 969b7cdff59..28e12d18f0f 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -54,6 +54,7 @@ #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> +#include <linux/can/skb.h> #include <linux/can/bcm.h> #include <linux/slab.h> #include <net/sock.h> @@ -256,10 +257,13 @@ static void bcm_can_tx(struct bcm_op *op) return; } - skb = alloc_skb(CFSIZ, gfp_any()); + skb = alloc_skb(CFSIZ + sizeof(struct can_skb_priv), gfp_any()); if (!skb) goto out; + can_skb_reserve(skb); + can_skb_prv(skb)->ifindex = dev->ifindex; + memcpy(skb_put(skb, CFSIZ), cf, CFSIZ); /* send with loopback */ @@ -1199,11 +1203,12 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk) if (!ifindex) return -ENODEV; - skb = alloc_skb(CFSIZ, GFP_KERNEL); - + skb = alloc_skb(CFSIZ + sizeof(struct can_skb_priv), GFP_KERNEL); if (!skb) return -ENOMEM; + can_skb_reserve(skb); + err = memcpy_fromiovec(skb_put(skb, CFSIZ), msg->msg_iov, CFSIZ); if (err < 0) { kfree_skb(skb); @@ -1216,6 +1221,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk) return -ENODEV; } + can_skb_prv(skb)->ifindex = dev->ifindex; skb->dev = dev; skb->sk = sk; err = can_send(skb, 1); /* send with loopback */ diff --git a/net/can/gw.c b/net/can/gw.c index 574dda78eb0..c185fcd5e82 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -42,6 +42,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/types.h> +#include <linux/kernel.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> @@ -52,19 +53,31 @@ #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> +#include <linux/can/skb.h> #include <linux/can/gw.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> -#define CAN_GW_VERSION "20101209" -static __initconst const char banner[] = - KERN_INFO "can: netlink gateway (rev " CAN_GW_VERSION ")\n"; +#define CAN_GW_VERSION "20130117" +#define CAN_GW_NAME "can-gw" MODULE_DESCRIPTION("PF_CAN netlink gateway"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); -MODULE_ALIAS("can-gw"); +MODULE_ALIAS(CAN_GW_NAME); + +#define CGW_MIN_HOPS 1 +#define CGW_MAX_HOPS 6 +#define CGW_DEFAULT_HOPS 1 + +static unsigned int max_hops __read_mostly = CGW_DEFAULT_HOPS; +module_param(max_hops, uint, S_IRUGO); +MODULE_PARM_DESC(max_hops, + "maximum " CAN_GW_NAME " routing hops for CAN frames " + "(valid values: " __stringify(CGW_MIN_HOPS) "-" + __stringify(CGW_MAX_HOPS) " hops, " + "default: " __stringify(CGW_DEFAULT_HOPS) ")"); static HLIST_HEAD(cgw_list); static struct notifier_block notifier; @@ -118,6 +131,7 @@ struct cgw_job { struct rcu_head rcu; u32 handled_frames; u32 dropped_frames; + u32 deleted_frames; struct cf_mod mod; union { /* CAN frame data source */ @@ -338,15 +352,38 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) struct sk_buff *nskb; int modidx = 0; - /* do not handle already routed frames - see comment below */ - if (skb_mac_header_was_set(skb)) + /* + * Do not handle CAN frames routed more than 'max_hops' times. + * In general we should never catch this delimiter which is intended + * to cover a misconfiguration protection (e.g. circular CAN routes). + * + * The Controller Area Network controllers only accept CAN frames with + * correct CRCs - which are not visible in the controller registers. + * According to skbuff.h documentation the csum_start element for IP + * checksums is undefined/unsued when ip_summed == CHECKSUM_UNNECESSARY. + * Only CAN skbs can be processed here which already have this property. + */ + +#define cgw_hops(skb) ((skb)->csum_start) + + BUG_ON(skb->ip_summed != CHECKSUM_UNNECESSARY); + + if (cgw_hops(skb) >= max_hops) { + /* indicate deleted frames due to misconfiguration */ + gwj->deleted_frames++; return; + } if (!(gwj->dst.dev->flags & IFF_UP)) { gwj->dropped_frames++; return; } + /* is sending the skb back to the incoming interface not allowed? */ + if (!(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK) && + can_skb_prv(skb)->ifindex == gwj->dst.dev->ifindex) + return; + /* * clone the given skb, which has not been done in can_rcv() * @@ -363,15 +400,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) return; } - /* - * Mark routed frames by setting some mac header length which is - * not relevant for the CAN frames located in the skb->data section. - * - * As dev->header_ops is not set in CAN netdevices no one is ever - * accessing the various header offsets in the CAN skbuffs anyway. - * E.g. using the packet socket to read CAN frames is still working. - */ - skb_set_mac_header(nskb, 8); + /* put the incremented hop counter in the cloned skb */ + cgw_hops(nskb) = cgw_hops(skb) + 1; nskb->dev = gwj->dst.dev; /* pointer to modifiable CAN frame */ @@ -472,6 +502,11 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, goto cancel; } + if (gwj->deleted_frames) { + if (nla_put_u32(skb, CGW_DELETED, gwj->deleted_frames) < 0) + goto cancel; + } + /* check non default settings of attributes */ if (gwj->mod.modtype.and) { @@ -771,6 +806,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, gwj->handled_frames = 0; gwj->dropped_frames = 0; + gwj->deleted_frames = 0; gwj->flags = r->flags; gwj->gwtype = r->gwtype; @@ -895,7 +931,11 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) static __init int cgw_module_init(void) { - printk(banner); + /* sanitize given module parameter */ + max_hops = clamp_t(unsigned int, max_hops, CGW_MIN_HOPS, CGW_MAX_HOPS); + + pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n", + max_hops); cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), 0, 0, NULL); diff --git a/net/can/raw.c b/net/can/raw.c index 5b0e3e330d9..c1764e41dda 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -50,6 +50,7 @@ #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> +#include <linux/can/skb.h> #include <linux/can/raw.h> #include <net/sock.h> #include <net/net_namespace.h> @@ -699,11 +700,14 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, if (!dev) return -ENXIO; - skb = sock_alloc_send_skb(sk, size, msg->msg_flags & MSG_DONTWAIT, - &err); + skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv), + msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) goto put_dev; + can_skb_reserve(skb); + can_skb_prv(skb)->ifindex = dev->ifindex; + err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size); if (err < 0) goto free_skb; diff --git a/net/core/dev.c b/net/core/dev.c index f64e439b4a0..a83375d3af7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -134,7 +134,6 @@ #include <linux/cpu_rmap.h> #include <linux/net_tstamp.h> #include <linux/static_key.h> -#include <net/flow_keys.h> #include "net-sysfs.h" @@ -1857,6 +1856,228 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq) } } +#ifdef CONFIG_XPS +static DEFINE_MUTEX(xps_map_mutex); +#define xmap_dereference(P) \ + rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) + +static struct xps_map *remove_xps_queue(struct xps_dev_maps *dev_maps, + int cpu, u16 index) +{ + struct xps_map *map = NULL; + int pos; + + if (dev_maps) + map = xmap_dereference(dev_maps->cpu_map[cpu]); + + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] == index) { + if (map->len > 1) { + map->queues[pos] = map->queues[--map->len]; + } else { + RCU_INIT_POINTER(dev_maps->cpu_map[cpu], NULL); + kfree_rcu(map, rcu); + map = NULL; + } + break; + } + } + + return map; +} + +static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) +{ + struct xps_dev_maps *dev_maps; + int cpu, i; + bool active = false; + + mutex_lock(&xps_map_mutex); + dev_maps = xmap_dereference(dev->xps_maps); + + if (!dev_maps) + goto out_no_maps; + + for_each_possible_cpu(cpu) { + for (i = index; i < dev->num_tx_queues; i++) { + if (!remove_xps_queue(dev_maps, cpu, i)) + break; + } + if (i == dev->num_tx_queues) + active = true; + } + + if (!active) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + + for (i = index; i < dev->num_tx_queues; i++) + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i), + NUMA_NO_NODE); + +out_no_maps: + mutex_unlock(&xps_map_mutex); +} + +static struct xps_map *expand_xps_map(struct xps_map *map, + int cpu, u16 index) +{ + struct xps_map *new_map; + int alloc_len = XPS_MIN_MAP_ALLOC; + int i, pos; + + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] != index) + continue; + return map; + } + + /* Need to add queue to this CPU's existing map */ + if (map) { + if (pos < map->alloc_len) + return map; + + alloc_len = map->alloc_len * 2; + } + + /* Need to allocate new map to store queue on this CPU's map */ + new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, + cpu_to_node(cpu)); + if (!new_map) + return NULL; + + for (i = 0; i < pos; i++) + new_map->queues[i] = map->queues[i]; + new_map->alloc_len = alloc_len; + new_map->len = pos; + + return new_map; +} + +int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index) +{ + struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; + struct xps_map *map, *new_map; + int maps_sz = max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES); + int cpu, numa_node_id = -2; + bool active = false; + + mutex_lock(&xps_map_mutex); + + dev_maps = xmap_dereference(dev->xps_maps); + + /* allocate memory for queue storage */ + for_each_online_cpu(cpu) { + if (!cpumask_test_cpu(cpu, mask)) + continue; + + if (!new_dev_maps) + new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); + if (!new_dev_maps) + return -ENOMEM; + + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + + map = expand_xps_map(map, cpu, index); + if (!map) + goto error; + + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + } + + if (!new_dev_maps) + goto out_no_new_maps; + + for_each_possible_cpu(cpu) { + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) { + /* add queue to CPU maps */ + int pos = 0; + + map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + while ((pos < map->len) && (map->queues[pos] != index)) + pos++; + + if (pos == map->len) + map->queues[map->len++] = index; +#ifdef CONFIG_NUMA + if (numa_node_id == -2) + numa_node_id = cpu_to_node(cpu); + else if (numa_node_id != cpu_to_node(cpu)) + numa_node_id = -1; +#endif + } else if (dev_maps) { + /* fill in the new device map from the old device map */ + map = xmap_dereference(dev_maps->cpu_map[cpu]); + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + } + + } + + rcu_assign_pointer(dev->xps_maps, new_dev_maps); + + /* Cleanup old maps */ + if (dev_maps) { + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = xmap_dereference(dev_maps->cpu_map[cpu]); + if (map && map != new_map) + kfree_rcu(map, rcu); + } + + kfree_rcu(dev_maps, rcu); + } + + dev_maps = new_dev_maps; + active = true; + +out_no_new_maps: + /* update Tx queue numa node */ + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), + (numa_node_id >= 0) ? numa_node_id : + NUMA_NO_NODE); + + if (!dev_maps) + goto out_no_maps; + + /* removes queue from unused CPUs */ + for_each_possible_cpu(cpu) { + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) + continue; + + if (remove_xps_queue(dev_maps, cpu, index)) + active = true; + } + + /* free map if not active */ + if (!active) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + +out_no_maps: + mutex_unlock(&xps_map_mutex); + + return 0; +error: + /* remove any maps that we added */ + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + if (new_map && new_map != map) + kfree(new_map); + } + + mutex_unlock(&xps_map_mutex); + + kfree(new_dev_maps); + return -ENOMEM; +} +EXPORT_SYMBOL(netif_set_xps_queue); + +#endif /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. @@ -1880,8 +2101,12 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (dev->num_tc) netif_setup_tc(dev, txq); - if (txq < dev->real_num_tx_queues) + if (txq < dev->real_num_tx_queues) { qdisc_reset_all_tx_gt(dev, txq); +#ifdef CONFIG_XPS + netif_reset_xps_queues_gt(dev, txq); +#endif + } } dev->real_num_tx_queues = txq; @@ -2046,6 +2271,15 @@ int skb_checksum_help(struct sk_buff *skb) return -EINVAL; } + /* Before computing a checksum, we should make sure no frag could + * be modified by an external entity : checksum could be wrong. + */ + if (skb_has_shared_frag(skb)) { + ret = __skb_linearize(skb); + if (ret) + goto out; + } + offset = skb_checksum_start_offset(skb); BUG_ON(offset >= skb_headlen(skb)); csum = skb_checksum(skb, offset, skb->len - offset, 0); @@ -2410,126 +2644,28 @@ out: return rc; } -static u32 hashrnd __read_mostly; - -/* - * Returns a Tx hash based on the given packet descriptor a Tx queues' number - * to be used as a distribution range. - */ -u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, - unsigned int num_tx_queues) -{ - u32 hash; - u16 qoffset = 0; - u16 qcount = num_tx_queues; - - if (skb_rx_queue_recorded(skb)) { - hash = skb_get_rx_queue(skb); - while (unlikely(hash >= num_tx_queues)) - hash -= num_tx_queues; - return hash; - } - - if (dev->num_tc) { - u8 tc = netdev_get_prio_tc_map(dev, skb->priority); - qoffset = dev->tc_to_txq[tc].offset; - qcount = dev->tc_to_txq[tc].count; - } - - if (skb->sk && skb->sk->sk_hash) - hash = skb->sk->sk_hash; - else - hash = (__force u16) skb->protocol; - hash = jhash_1word(hash, hashrnd); - - return (u16) (((u64) hash * qcount) >> 32) + qoffset; -} -EXPORT_SYMBOL(__skb_tx_hash); - -static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) +static void qdisc_pkt_len_init(struct sk_buff *skb) { - 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 - struct xps_dev_maps *dev_maps; - struct xps_map *map; - int queue_index = -1; + const struct skb_shared_info *shinfo = skb_shinfo(skb); - rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_maps); - if (dev_maps) { - map = rcu_dereference( - dev_maps->cpu_map[raw_smp_processor_id()]); - if (map) { - if (map->len == 1) - queue_index = map->queues[0]; - else { - u32 hash; - if (skb->sk && skb->sk->sk_hash) - hash = skb->sk->sk_hash; - else - hash = (__force u16) skb->protocol ^ - skb->rxhash; - hash = jhash_1word(hash, hashrnd); - queue_index = map->queues[ - ((u64)hash * map->len) >> 32]; - } - if (unlikely(queue_index >= dev->real_num_tx_queues)) - queue_index = -1; - } - } - rcu_read_unlock(); - - return queue_index; -#else - return -1; -#endif -} - -struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb) -{ - int queue_index; - const struct net_device_ops *ops = dev->netdev_ops; - - if (dev->real_num_tx_queues == 1) - queue_index = 0; - else if (ops->ndo_select_queue) { - queue_index = ops->ndo_select_queue(dev, skb); - queue_index = dev_cap_txqueue(dev, queue_index); - } else { - struct sock *sk = skb->sk; - queue_index = sk_tx_queue_get(sk); - - if (queue_index < 0 || skb->ooo_okay || - queue_index >= dev->real_num_tx_queues) { - int old_index = queue_index; + qdisc_skb_cb(skb)->pkt_len = skb->len; - queue_index = get_xps_queue(dev, skb); - if (queue_index < 0) - queue_index = skb_tx_hash(dev, skb); + /* To get more precise estimation of bytes sent on wire, + * we add to pkt_len the headers size of all segments + */ + if (shinfo->gso_size) { + unsigned int hdr_len; - if (queue_index != old_index && sk) { - struct dst_entry *dst = - rcu_dereference_check(sk->sk_dst_cache, 1); + /* mac layer + network layer */ + hdr_len = skb_transport_header(skb) - skb_mac_header(skb); - if (dst && skb_dst(skb) == dst) - sk_tx_queue_set(sk, queue_index); - } - } + /* + transport layer */ + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + hdr_len += tcp_hdrlen(skb); + else + hdr_len += sizeof(struct udphdr); + qdisc_skb_cb(skb)->pkt_len += (shinfo->gso_segs - 1) * hdr_len; } - - skb_set_queue_mapping(skb, queue_index); - return netdev_get_tx_queue(dev, queue_index); } static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, @@ -2540,7 +2676,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, bool contended; int rc; - qdisc_skb_cb(skb)->pkt_len = skb->len; + qdisc_pkt_len_init(skb); qdisc_calculate_pkt_len(skb, q); /* * Heuristic to force contended enqueues to serialize on a @@ -2757,41 +2893,6 @@ static inline void ____napi_schedule(struct softnet_data *sd, __raise_softirq_irqoff(NET_RX_SOFTIRQ); } -/* - * __skb_get_rxhash: 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) -{ - struct flow_keys keys; - u32 hash; - - if (!skb_flow_dissect(skb, &keys)) - return; - - if (keys.ports) - skb->l4_rxhash = 1; - - /* get a consistent hash (same value on both flow directions) */ - if (((__force u32)keys.dst < (__force u32)keys.src) || - (((__force u32)keys.dst == (__force u32)keys.src) && - ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) { - swap(keys.dst, keys.src); - swap(keys.port16[0], keys.port16[1]); - } - - hash = jhash_3words((__force u32)keys.dst, - (__force u32)keys.src, - (__force u32)keys.ports, hashrnd); - if (!hash) - hash = 1; - - skb->rxhash = hash; -} -EXPORT_SYMBOL(__skb_get_rxhash); - #ifdef CONFIG_RPS /* One global table that all flow-based protocols share. */ @@ -3352,7 +3453,8 @@ static int __netif_receive_skb(struct sk_buff *skb) orig_dev = skb->dev; skb_reset_network_header(skb); - skb_reset_transport_header(skb); + if (!skb_transport_header_was_set(skb)) + skb_reset_transport_header(skb); skb_reset_mac_len(skb); pt_prev = NULL; @@ -4600,64 +4702,231 @@ static int __init dev_proc_init(void) #endif /* CONFIG_PROC_FS */ +struct netdev_upper { + struct net_device *dev; + bool master; + struct list_head list; + struct rcu_head rcu; + struct list_head search_list; +}; + +static void __append_search_uppers(struct list_head *search_list, + struct net_device *dev) +{ + struct netdev_upper *upper; + + list_for_each_entry(upper, &dev->upper_dev_list, list) { + /* check if this upper is not already in search list */ + if (list_empty(&upper->search_list)) + list_add_tail(&upper->search_list, search_list); + } +} + +static bool __netdev_search_upper_dev(struct net_device *dev, + struct net_device *upper_dev) +{ + LIST_HEAD(search_list); + struct netdev_upper *upper; + struct netdev_upper *tmp; + bool ret = false; + + __append_search_uppers(&search_list, dev); + list_for_each_entry(upper, &search_list, search_list) { + if (upper->dev == upper_dev) { + ret = true; + break; + } + __append_search_uppers(&search_list, upper->dev); + } + list_for_each_entry_safe(upper, tmp, &search_list, search_list) + INIT_LIST_HEAD(&upper->search_list); + return ret; +} + +static struct netdev_upper *__netdev_find_upper(struct net_device *dev, + struct net_device *upper_dev) +{ + struct netdev_upper *upper; + + list_for_each_entry(upper, &dev->upper_dev_list, list) { + if (upper->dev == upper_dev) + return upper; + } + return NULL; +} + /** - * netdev_set_master - set up master pointer - * @slave: slave device - * @master: new master device - * - * Changes the master device of the slave. Pass %NULL to break the - * bonding. The caller must hold the RTNL semaphore. On a failure - * a negative errno code is returned. On success the reference counts - * are adjusted and the function returns zero. + * netdev_has_upper_dev - Check if device is linked to an upper device + * @dev: device + * @upper_dev: upper device to check + * + * Find out if a device is linked to specified upper device and return true + * in case it is. Note that this checks only immediate upper device, + * not through a complete stack of devices. The caller must hold the RTNL lock. */ -int netdev_set_master(struct net_device *slave, struct net_device *master) +bool netdev_has_upper_dev(struct net_device *dev, + struct net_device *upper_dev) { - struct net_device *old = slave->master; + ASSERT_RTNL(); + + return __netdev_find_upper(dev, upper_dev); +} +EXPORT_SYMBOL(netdev_has_upper_dev); +/** + * netdev_has_any_upper_dev - Check if device is linked to some device + * @dev: device + * + * 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) +{ ASSERT_RTNL(); - if (master) { - if (old) - return -EBUSY; - dev_hold(master); - } + return !list_empty(&dev->upper_dev_list); +} +EXPORT_SYMBOL(netdev_has_any_upper_dev); + +/** + * netdev_master_upper_dev_get - Get master upper device + * @dev: device + * + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RTNL lock. + */ +struct net_device *netdev_master_upper_dev_get(struct net_device *dev) +{ + struct netdev_upper *upper; - slave->master = master; + ASSERT_RTNL(); - if (old) - dev_put(old); - return 0; + if (list_empty(&dev->upper_dev_list)) + return NULL; + + upper = list_first_entry(&dev->upper_dev_list, + struct netdev_upper, list); + if (likely(upper->master)) + return upper->dev; + return NULL; } -EXPORT_SYMBOL(netdev_set_master); +EXPORT_SYMBOL(netdev_master_upper_dev_get); /** - * netdev_set_bond_master - set up bonding master/slave pair - * @slave: slave device - * @master: new master device - * - * Changes the master device of the slave. Pass %NULL to break the - * bonding. The caller must hold the RTNL semaphore. On a failure - * a negative errno code is returned. On success %RTM_NEWLINK is sent - * to the routing socket and the function returns zero. + * netdev_master_upper_dev_get_rcu - Get master upper device + * @dev: device + * + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RCU read lock. */ -int netdev_set_bond_master(struct net_device *slave, struct net_device *master) +struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) { - int err; + struct netdev_upper *upper; + + upper = list_first_or_null_rcu(&dev->upper_dev_list, + struct netdev_upper, list); + if (upper && likely(upper->master)) + return upper->dev; + return NULL; +} +EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); + +static int __netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev, bool master) +{ + struct netdev_upper *upper; ASSERT_RTNL(); - err = netdev_set_master(slave, master); - if (err) - return err; + if (dev == upper_dev) + return -EBUSY; + + /* To prevent loops, check if dev is not upper device to upper_dev. */ + if (__netdev_search_upper_dev(upper_dev, dev)) + return -EBUSY; + + if (__netdev_find_upper(dev, upper_dev)) + return -EEXIST; + + if (master && netdev_master_upper_dev_get(dev)) + return -EBUSY; + + upper = kmalloc(sizeof(*upper), GFP_KERNEL); + if (!upper) + return -ENOMEM; + + upper->dev = upper_dev; + upper->master = master; + INIT_LIST_HEAD(&upper->search_list); + + /* Ensure that master upper link is always the first item in list. */ if (master) - slave->flags |= IFF_SLAVE; + list_add_rcu(&upper->list, &dev->upper_dev_list); else - slave->flags &= ~IFF_SLAVE; + list_add_tail_rcu(&upper->list, &dev->upper_dev_list); + dev_hold(upper_dev); - rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE); return 0; } -EXPORT_SYMBOL(netdev_set_bond_master); + +/** + * netdev_upper_dev_link - Add a link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. The caller must hold + * the RTNL lock. On a failure a negative errno code is returned. + * On success the reference counts are adjusted and the function + * returns zero. + */ +int netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) +{ + return __netdev_upper_dev_link(dev, upper_dev, false); +} +EXPORT_SYMBOL(netdev_upper_dev_link); + +/** + * netdev_master_upper_dev_link - Add a master link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. In this case, only + * one master upper device can be linked, although other non-master devices + * might be linked as well. The caller must hold the RTNL lock. + * On a failure a negative errno code is returned. On success the reference + * counts are adjusted and the function returns zero. + */ +int netdev_master_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) +{ + return __netdev_upper_dev_link(dev, upper_dev, true); +} +EXPORT_SYMBOL(netdev_master_upper_dev_link); + +/** + * netdev_upper_dev_unlink - Removes a link to upper device + * @dev: device + * @upper_dev: new upper device + * + * Removes a link to device which is upper to this one. The caller must hold + * the RTNL lock. + */ +void netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) +{ + struct netdev_upper *upper; + + ASSERT_RTNL(); + + upper = __netdev_find_upper(dev, upper_dev); + if (!upper) + return; + list_del_rcu(&upper->list); + dev_put(upper_dev); + kfree_rcu(upper, rcu); +} +EXPORT_SYMBOL(netdev_upper_dev_unlink); static void dev_change_rx_flags(struct net_device *dev, int flags) { @@ -5020,13 +5289,34 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) if (!netif_device_present(dev)) return -ENODEV; err = ops->ndo_set_mac_address(dev, sa); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + if (err) + return err; + dev->addr_assign_type = NET_ADDR_SET; + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); add_device_randomness(dev->dev_addr, dev->addr_len); - return err; + return 0; } EXPORT_SYMBOL(dev_set_mac_address); +/** + * dev_change_carrier - Change device carrier + * @dev: device + * @new_carries: new value + * + * Change device carrier + */ +int dev_change_carrier(struct net_device *dev, bool new_carrier) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_change_carrier) + return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_change_carrier(dev, new_carrier); +} +EXPORT_SYMBOL(dev_change_carrier); + /* * Perform the SIOCxIFxxx calls, inside rcu_read_lock() */ @@ -5482,11 +5772,15 @@ static void rollback_registered_many(struct list_head *head) if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); - /* Notifier chain MUST detach us from master device. */ - WARN_ON(dev->master); + /* Notifier chain MUST detach us all upper devices. */ + WARN_ON(netdev_has_any_upper_dev(dev)); /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); +#ifdef CONFIG_XPS + /* Remove XPS queueing entries */ + netif_reset_xps_queues_gt(dev, 0); +#endif } synchronize_net(); @@ -5815,6 +6109,13 @@ int register_netdevice(struct net_device *dev) list_netdevice(dev); add_device_randomness(dev->dev_addr, dev->addr_len); + /* If the device has permanent device address, driver should + * set dev_addr and also addr_assign_type should be set to + * NET_ADDR_PERM (default value). + */ + if (dev->addr_assign_type == NET_ADDR_PERM) + memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); + /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); ret = notifier_to_errno(ret); @@ -6199,6 +6500,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->link_watch_list); + INIT_LIST_HEAD(&dev->upper_dev_list); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); @@ -6849,12 +7151,3 @@ out: } subsys_initcall(net_dev_init); - -static int __init initialize_hashrnd(void) -{ - get_random_bytes(&hashrnd, sizeof(hashrnd)); - return 0; -} - -late_initcall_sync(initialize_hashrnd); - diff --git a/net/core/ethtool.c b/net/core/ethtool.c index a8705432e4b..d9d55209db6 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -175,7 +175,7 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset) if (sset == ETH_SS_FEATURES) return ARRAY_SIZE(netdev_features_strings); - if (ops && ops->get_sset_count && ops->get_strings) + if (ops->get_sset_count && ops->get_strings) return ops->get_sset_count(dev, sset); else return -EOPNOTSUPP; @@ -311,7 +311,7 @@ int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { ASSERT_RTNL(); - if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings) + if (!dev->ethtool_ops->get_settings) return -EOPNOTSUPP; memset(cmd, 0, sizeof(struct ethtool_cmd)); @@ -355,7 +355,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GDRVINFO; - if (ops && ops->get_drvinfo) { + if (ops->get_drvinfo) { ops->get_drvinfo(dev, &info); } else if (dev->dev.parent && dev->dev.parent->driver) { strlcpy(info.bus_info, dev_name(dev->dev.parent), @@ -370,7 +370,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, * this method of obtaining string set info is deprecated; * Use ETHTOOL_GSSET_INFO instead. */ - if (ops && ops->get_sset_count) { + if (ops->get_sset_count) { int rc; rc = ops->get_sset_count(dev, ETH_SS_TEST); @@ -383,9 +383,9 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, if (rc >= 0) info.n_priv_flags = rc; } - if (ops && ops->get_regs_len) + if (ops->get_regs_len) info.regdump_len = ops->get_regs_len(dev); - if (ops && ops->get_eeprom_len) + if (ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); if (copy_to_user(useraddr, &info, sizeof(info))) @@ -590,13 +590,14 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, struct ethtool_rxnfc rx_rings; u32 user_size, dev_size, i; u32 *indir; + const struct ethtool_ops *ops = dev->ethtool_ops; int ret; - if (!dev->ethtool_ops->get_rxfh_indir_size || - !dev->ethtool_ops->set_rxfh_indir || - !dev->ethtool_ops->get_rxnfc) + if (!ops->get_rxfh_indir_size || !ops->set_rxfh_indir || + !ops->get_rxnfc) return -EOPNOTSUPP; - dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); + + dev_size = ops->get_rxfh_indir_size(dev); if (dev_size == 0) return -EOPNOTSUPP; @@ -613,7 +614,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, return -ENOMEM; rx_rings.cmd = ETHTOOL_GRXRINGS; - ret = dev->ethtool_ops->get_rxnfc(dev, &rx_rings, NULL); + ret = ops->get_rxnfc(dev, &rx_rings, NULL); if (ret) goto out; @@ -639,7 +640,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, } } - ret = dev->ethtool_ops->set_rxfh_indir(dev, indir); + ret = ops->set_rxfh_indir(dev, indir); out: kfree(indir); @@ -1082,9 +1083,10 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) { struct ethtool_value id; static bool busy; + const struct ethtool_ops *ops = dev->ethtool_ops; int rc; - if (!dev->ethtool_ops->set_phys_id) + if (!ops->set_phys_id) return -EOPNOTSUPP; if (busy) @@ -1093,7 +1095,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) if (copy_from_user(&id, useraddr, sizeof(id))) return -EFAULT; - rc = dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE); + rc = ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE); if (rc < 0) return rc; @@ -1118,7 +1120,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) i = n; do { rtnl_lock(); - rc = dev->ethtool_ops->set_phys_id(dev, + rc = ops->set_phys_id(dev, (i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); rtnl_unlock(); if (rc) @@ -1133,7 +1135,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) dev_put(dev); busy = false; - (void)dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); + (void) ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); return rc; } @@ -1275,7 +1277,7 @@ static int ethtool_get_dump_flag(struct net_device *dev, struct ethtool_dump dump; const struct ethtool_ops *ops = dev->ethtool_ops; - if (!dev->ethtool_ops->get_dump_flag) + if (!ops->get_dump_flag) return -EOPNOTSUPP; if (copy_from_user(&dump, useraddr, sizeof(dump))) @@ -1299,8 +1301,7 @@ static int ethtool_get_dump_data(struct net_device *dev, const struct ethtool_ops *ops = dev->ethtool_ops; void *data = NULL; - if (!dev->ethtool_ops->get_dump_data || - !dev->ethtool_ops->get_dump_flag) + if (!ops->get_dump_data || !ops->get_dump_flag) return -EOPNOTSUPP; if (copy_from_user(&dump, useraddr, sizeof(dump))) @@ -1346,13 +1347,9 @@ static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) info.cmd = ETHTOOL_GET_TS_INFO; if (phydev && phydev->drv && phydev->drv->ts_info) { - err = phydev->drv->ts_info(phydev, &info); - - } else if (dev->ethtool_ops && dev->ethtool_ops->get_ts_info) { - + } else if (ops->get_ts_info) { err = ops->get_ts_info(dev, &info); - } else { info.so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | diff --git a/net/core/filter.c b/net/core/filter.c index c23543cba13..2e20b55a783 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -532,6 +532,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) [BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X, }; int pc; + bool anc_found; if (flen == 0 || flen > BPF_MAXINSNS) return -EINVAL; @@ -592,8 +593,10 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) case BPF_S_LD_W_ABS: case BPF_S_LD_H_ABS: case BPF_S_LD_B_ABS: + anc_found = false; #define ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ code = BPF_S_ANC_##CODE; \ + anc_found = true; \ break switch (ftest->k) { ANCILLARY(PROTOCOL); @@ -610,6 +613,10 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) ANCILLARY(VLAN_TAG); ANCILLARY(VLAN_TAG_PRESENT); } + + /* ancillary operation unknown or unsupported */ + if (anc_found == false && ftest->k >= SKF_AD_OFF) + return -EINVAL; } ftest->code = code; } @@ -714,6 +721,9 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) unsigned int fsize = sizeof(struct sock_filter) * fprog->len; int err; + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) return -EINVAL; @@ -750,6 +760,9 @@ int sk_detach_filter(struct sock *sk) int ret = -ENOENT; struct sk_filter *filter; + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + filter = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); if (filter) { diff --git a/net/core/flow.c b/net/core/flow.c index b0901ee5a00..43f7495df27 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -286,7 +286,7 @@ nocache: else fle->genid--; } else { - if (flo && !IS_ERR(flo)) + if (!IS_ERR_OR_NULL(flo)) flo->ops->delete(flo); } ret_object: diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 466820b6e34..9d4c7201400 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -143,3 +143,176 @@ ipv6: return true; } EXPORT_SYMBOL(skb_flow_dissect); + +static u32 hashrnd __read_mostly; + +/* + * __skb_get_rxhash: 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) +{ + struct flow_keys keys; + u32 hash; + + if (!skb_flow_dissect(skb, &keys)) + return; + + if (keys.ports) + skb->l4_rxhash = 1; + + /* get a consistent hash (same value on both flow directions) */ + if (((__force u32)keys.dst < (__force u32)keys.src) || + (((__force u32)keys.dst == (__force u32)keys.src) && + ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) { + swap(keys.dst, keys.src); + swap(keys.port16[0], keys.port16[1]); + } + + hash = jhash_3words((__force u32)keys.dst, + (__force u32)keys.src, + (__force u32)keys.ports, hashrnd); + if (!hash) + hash = 1; + + skb->rxhash = hash; +} +EXPORT_SYMBOL(__skb_get_rxhash); + +/* + * Returns a Tx hash based on the given packet descriptor a Tx queues' number + * to be used as a distribution range. + */ +u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, + unsigned int num_tx_queues) +{ + u32 hash; + u16 qoffset = 0; + u16 qcount = num_tx_queues; + + if (skb_rx_queue_recorded(skb)) { + hash = skb_get_rx_queue(skb); + while (unlikely(hash >= num_tx_queues)) + hash -= num_tx_queues; + return hash; + } + + if (dev->num_tc) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + qoffset = dev->tc_to_txq[tc].offset; + qcount = dev->tc_to_txq[tc].count; + } + + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol; + hash = jhash_1word(hash, hashrnd); + + return (u16) (((u64) hash * qcount) >> 32) + qoffset; +} +EXPORT_SYMBOL(__skb_tx_hash); + +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 + struct xps_dev_maps *dev_maps; + struct xps_map *map; + int queue_index = -1; + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + map = rcu_dereference( + dev_maps->cpu_map[raw_smp_processor_id()]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else { + u32 hash; + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol ^ + skb->rxhash; + hash = jhash_1word(hash, hashrnd); + queue_index = map->queues[ + ((u64)hash * map->len) >> 32]; + } + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + } + rcu_read_unlock(); + + return queue_index; +#else + return -1; +#endif +} + +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); + + if (queue_index < 0 || skb->ooo_okay || + queue_index >= dev->real_num_tx_queues) { + int new_index = get_xps_queue(dev, skb); + if (new_index < 0) + new_index = skb_tx_hash(dev, skb); + + if (queue_index != new_index && sk) { + struct dst_entry *dst = + rcu_dereference_check(sk->sk_dst_cache, 1); + + if (dst && skb_dst(skb) == dst) + sk_tx_queue_set(sk, queue_index); + + } + + queue_index = new_index; + } + + return queue_index; +} +EXPORT_SYMBOL(__netdev_pick_tx); + +struct netdev_queue *netdev_pick_tx(struct net_device *dev, + struct sk_buff *skb) +{ + int queue_index = 0; + + 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); + else + queue_index = __netdev_pick_tx(dev, skb); + queue_index = dev_cap_txqueue(dev, queue_index); + } + + skb_set_queue_mapping(skb, queue_index); + return netdev_get_tx_queue(dev, queue_index); +} + +static int __init initialize_hashrnd(void) +{ + get_random_bytes(&hashrnd, sizeof(hashrnd)); + return 0; +} + +late_initcall_sync(initialize_hashrnd); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index c815f285e5a..3863b8f639c 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -290,15 +290,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device goto out_entries; } - if (tbl->entry_size) - n = kzalloc(tbl->entry_size, GFP_ATOMIC); - else { - int sz = sizeof(*n) + tbl->key_len; - - sz = ALIGN(sz, NEIGH_PRIV_ALIGN); - sz += dev->neigh_priv_len; - n = kzalloc(sz, GFP_ATOMIC); - } + n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC); if (!n) goto out_entries; @@ -778,6 +770,9 @@ static void neigh_periodic_work(struct work_struct *work) nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); + if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + goto out; + /* * periodically recompute ReachableTime from random function */ @@ -832,6 +827,7 @@ next_elt: nht = rcu_dereference_protected(tbl->nht, 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. @@ -1542,6 +1538,12 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl) if (!tbl->nht || !tbl->phash_buckets) panic("cannot allocate neighbour cache hashes"); + if (!tbl->entry_size) + tbl->entry_size = ALIGN(offsetof(struct neighbour, primary_key) + + tbl->key_len, NEIGH_PRIV_ALIGN); + else + WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); + rwlock_init(&tbl->lock); INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 28c5f5aa7ca..a5b89a6fec6 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -126,6 +126,19 @@ static ssize_t show_broadcast(struct device *dev, return -EINVAL; } +static int change_carrier(struct net_device *net, unsigned long new_carrier) +{ + if (!netif_running(net)) + return -EINVAL; + return dev_change_carrier(net, (bool) new_carrier); +} + +static ssize_t store_carrier(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, change_carrier); +} + static ssize_t show_carrier(struct device *dev, struct device_attribute *attr, char *buf) { @@ -331,7 +344,7 @@ static struct device_attribute net_class_attributes[] = { __ATTR(link_mode, S_IRUGO, show_link_mode, NULL), __ATTR(address, S_IRUGO, show_address, NULL), __ATTR(broadcast, S_IRUGO, show_broadcast, NULL), - __ATTR(carrier, S_IRUGO, show_carrier, NULL), + __ATTR(carrier, S_IRUGO | S_IWUSR, show_carrier, store_carrier), __ATTR(speed, S_IRUGO, show_speed, NULL), __ATTR(duplex, S_IRUGO, show_duplex, NULL), __ATTR(dormant, S_IRUGO, show_dormant, NULL), @@ -989,68 +1002,14 @@ static ssize_t show_xps_map(struct netdev_queue *queue, return len; } -static DEFINE_MUTEX(xps_map_mutex); -#define xmap_dereference(P) \ - rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) - -static void xps_queue_release(struct netdev_queue *queue) -{ - struct net_device *dev = queue->dev; - struct xps_dev_maps *dev_maps; - struct xps_map *map; - unsigned long index; - int i, pos, nonempty = 0; - - index = get_netdev_queue_index(queue); - - mutex_lock(&xps_map_mutex); - dev_maps = xmap_dereference(dev->xps_maps); - - if (dev_maps) { - for_each_possible_cpu(i) { - map = xmap_dereference(dev_maps->cpu_map[i]); - if (!map) - continue; - - for (pos = 0; pos < map->len; pos++) - if (map->queues[pos] == index) - break; - - if (pos < map->len) { - if (map->len > 1) - map->queues[pos] = - map->queues[--map->len]; - else { - RCU_INIT_POINTER(dev_maps->cpu_map[i], - NULL); - kfree_rcu(map, rcu); - map = NULL; - } - } - if (map) - nonempty = 1; - } - - if (!nonempty) { - RCU_INIT_POINTER(dev->xps_maps, NULL); - kfree_rcu(dev_maps, rcu); - } - } - mutex_unlock(&xps_map_mutex); -} - static ssize_t store_xps_map(struct netdev_queue *queue, struct netdev_queue_attribute *attribute, const char *buf, size_t len) { struct net_device *dev = queue->dev; - cpumask_var_t mask; - int err, i, cpu, pos, map_len, alloc_len, need_set; unsigned long index; - struct xps_map *map, *new_map; - struct xps_dev_maps *dev_maps, *new_dev_maps; - int nonempty = 0; - int numa_node_id = -2; + cpumask_var_t mask; + int err; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -1066,105 +1025,11 @@ static ssize_t store_xps_map(struct netdev_queue *queue, return err; } - new_dev_maps = kzalloc(max_t(unsigned int, - XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES), GFP_KERNEL); - if (!new_dev_maps) { - free_cpumask_var(mask); - return -ENOMEM; - } - - mutex_lock(&xps_map_mutex); - - dev_maps = xmap_dereference(dev->xps_maps); - - for_each_possible_cpu(cpu) { - map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; - new_map = map; - if (map) { - for (pos = 0; pos < map->len; pos++) - if (map->queues[pos] == index) - break; - map_len = map->len; - alloc_len = map->alloc_len; - } else - pos = map_len = alloc_len = 0; - - need_set = cpumask_test_cpu(cpu, mask) && cpu_online(cpu); -#ifdef CONFIG_NUMA - if (need_set) { - if (numa_node_id == -2) - numa_node_id = cpu_to_node(cpu); - else if (numa_node_id != cpu_to_node(cpu)) - numa_node_id = -1; - } -#endif - if (need_set && pos >= map_len) { - /* Need to add queue to this CPU's map */ - if (map_len >= alloc_len) { - alloc_len = alloc_len ? - 2 * alloc_len : XPS_MIN_MAP_ALLOC; - new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), - GFP_KERNEL, - cpu_to_node(cpu)); - if (!new_map) - goto error; - new_map->alloc_len = alloc_len; - for (i = 0; i < map_len; i++) - new_map->queues[i] = map->queues[i]; - new_map->len = map_len; - } - new_map->queues[new_map->len++] = index; - } else if (!need_set && pos < map_len) { - /* Need to remove queue from this CPU's map */ - if (map_len > 1) - new_map->queues[pos] = - new_map->queues[--new_map->len]; - else - new_map = NULL; - } - RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], new_map); - } - - /* Cleanup old maps */ - for_each_possible_cpu(cpu) { - map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; - if (map && xmap_dereference(new_dev_maps->cpu_map[cpu]) != map) - kfree_rcu(map, rcu); - if (new_dev_maps->cpu_map[cpu]) - nonempty = 1; - } - - if (nonempty) { - rcu_assign_pointer(dev->xps_maps, new_dev_maps); - } else { - kfree(new_dev_maps); - RCU_INIT_POINTER(dev->xps_maps, NULL); - } - - if (dev_maps) - kfree_rcu(dev_maps, rcu); - - netdev_queue_numa_node_write(queue, (numa_node_id >= 0) ? numa_node_id : - NUMA_NO_NODE); - - mutex_unlock(&xps_map_mutex); + err = netif_set_xps_queue(dev, mask, index); free_cpumask_var(mask); - return len; -error: - mutex_unlock(&xps_map_mutex); - - if (new_dev_maps) - for_each_possible_cpu(i) - kfree(rcu_dereference_protected( - new_dev_maps->cpu_map[i], - 1)); - kfree(new_dev_maps); - free_cpumask_var(mask); - return -ENOMEM; + return err ? : len; } static struct netdev_queue_attribute xps_cpus_attribute = @@ -1183,10 +1048,6 @@ static void netdev_queue_release(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); -#ifdef CONFIG_XPS - xps_queue_release(queue); -#endif - memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 3151acf5ec1..331ccb90f91 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -29,6 +29,9 @@ #include <linux/if_vlan.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/addrconf.h> +#include <net/ndisc.h> +#include <net/ip6_checksum.h> #include <asm/unaligned.h> #include <trace/events/napi.h> @@ -55,7 +58,7 @@ static atomic_t trapped; MAX_UDP_CHUNK) static void zap_completion_queue(void); -static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo); +static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); @@ -181,13 +184,13 @@ static void poll_napi(struct net_device *dev) } } -static void service_arp_queue(struct netpoll_info *npi) +static void service_neigh_queue(struct netpoll_info *npi) { if (npi) { struct sk_buff *skb; - while ((skb = skb_dequeue(&npi->arp_tx))) - netpoll_arp_reply(skb, npi); + while ((skb = skb_dequeue(&npi->neigh_tx))) + netpoll_neigh_reply(skb, npi); } } @@ -210,17 +213,20 @@ static void netpoll_poll_dev(struct net_device *dev) if (dev->flags & IFF_SLAVE) { if (ni) { - struct net_device *bond_dev = dev->master; + struct net_device *bond_dev; struct sk_buff *skb; - struct netpoll_info *bond_ni = rcu_dereference_bh(bond_dev->npinfo); - while ((skb = skb_dequeue(&ni->arp_tx))) { + struct netpoll_info *bond_ni; + + bond_dev = netdev_master_upper_dev_get_rcu(dev); + bond_ni = rcu_dereference_bh(bond_dev->npinfo); + while ((skb = skb_dequeue(&ni->neigh_tx))) { skb->dev = bond_dev; - skb_queue_tail(&bond_ni->arp_tx, skb); + skb_queue_tail(&bond_ni->neigh_tx, skb); } } } - service_arp_queue(ni); + service_neigh_queue(ni); zap_completion_queue(); } @@ -381,9 +387,14 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) struct iphdr *iph; struct ethhdr *eth; static atomic_t ip_ident; + struct ipv6hdr *ip6h; udp_len = len + sizeof(*udph); - ip_len = udp_len + sizeof(*iph); + if (np->ipv6) + ip_len = udp_len + sizeof(*ip6h); + else + ip_len = udp_len + sizeof(*iph); + total_len = ip_len + LL_RESERVED_SPACE(np->dev); skb = find_skb(np, total_len + np->dev->needed_tailroom, @@ -400,34 +411,66 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) udph->source = htons(np->local_port); udph->dest = htons(np->remote_port); udph->len = htons(udp_len); - udph->check = 0; - udph->check = csum_tcpudp_magic(np->local_ip, - np->remote_ip, - udp_len, IPPROTO_UDP, - csum_partial(udph, udp_len, 0)); - if (udph->check == 0) - udph->check = CSUM_MANGLED_0; - - skb_push(skb, sizeof(*iph)); - skb_reset_network_header(skb); - iph = ip_hdr(skb); - - /* iph->version = 4; iph->ihl = 5; */ - put_unaligned(0x45, (unsigned char *)iph); - iph->tos = 0; - put_unaligned(htons(ip_len), &(iph->tot_len)); - iph->id = htons(atomic_inc_return(&ip_ident)); - iph->frag_off = 0; - iph->ttl = 64; - iph->protocol = IPPROTO_UDP; - iph->check = 0; - put_unaligned(np->local_ip, &(iph->saddr)); - put_unaligned(np->remote_ip, &(iph->daddr)); - iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); - - eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); - skb_reset_mac_header(skb); - skb->protocol = eth->h_proto = htons(ETH_P_IP); + + if (np->ipv6) { + udph->check = 0; + udph->check = csum_ipv6_magic(&np->local_ip.in6, + &np->remote_ip.in6, + udp_len, IPPROTO_UDP, + csum_partial(udph, udp_len, 0)); + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + + skb_push(skb, sizeof(*ip6h)); + skb_reset_network_header(skb); + ip6h = ipv6_hdr(skb); + + /* ip6h->version = 6; ip6h->priority = 0; */ + put_unaligned(0x60, (unsigned char *)ip6h); + ip6h->flow_lbl[0] = 0; + ip6h->flow_lbl[1] = 0; + ip6h->flow_lbl[2] = 0; + + ip6h->payload_len = htons(sizeof(struct udphdr) + len); + ip6h->nexthdr = IPPROTO_UDP; + ip6h->hop_limit = 32; + ip6h->saddr = np->local_ip.in6; + ip6h->daddr = np->remote_ip.in6; + + eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth->h_proto = htons(ETH_P_IPV6); + } else { + udph->check = 0; + udph->check = csum_tcpudp_magic(np->local_ip.ip, + np->remote_ip.ip, + udp_len, IPPROTO_UDP, + csum_partial(udph, udp_len, 0)); + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + + skb_push(skb, sizeof(*iph)); + skb_reset_network_header(skb); + iph = ip_hdr(skb); + + /* iph->version = 4; iph->ihl = 5; */ + put_unaligned(0x45, (unsigned char *)iph); + iph->tos = 0; + put_unaligned(htons(ip_len), &(iph->tot_len)); + iph->id = htons(atomic_inc_return(&ip_ident)); + iph->frag_off = 0; + iph->ttl = 64; + iph->protocol = IPPROTO_UDP; + iph->check = 0; + put_unaligned(np->local_ip.ip, &(iph->saddr)); + put_unaligned(np->remote_ip.ip, &(iph->daddr)); + iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + + eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + 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); @@ -437,18 +480,16 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) } EXPORT_SYMBOL(netpoll_send_udp); -static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo) +static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo) { - struct arphdr *arp; - unsigned char *arp_ptr; - int size, type = ARPOP_REPLY, ptype = ETH_P_ARP; + int size, type = ARPOP_REPLY; __be32 sip, tip; unsigned char *sha; struct sk_buff *send_skb; struct netpoll *np, *tmp; unsigned long flags; int hlen, tlen; - int hits = 0; + int hits = 0, proto; if (list_empty(&npinfo->rx_np)) return; @@ -466,94 +507,214 @@ static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo) if (!hits) return; - /* No arp on this interface */ - if (skb->dev->flags & IFF_NOARP) - return; - - if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) - return; + proto = ntohs(eth_hdr(skb)->h_proto); + if (proto == ETH_P_IP) { + struct arphdr *arp; + unsigned char *arp_ptr; + /* No arp on this interface */ + if (skb->dev->flags & IFF_NOARP) + return; - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - arp = arp_hdr(skb); + if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) + return; - if ((arp->ar_hrd != htons(ARPHRD_ETHER) && - arp->ar_hrd != htons(ARPHRD_IEEE802)) || - arp->ar_pro != htons(ETH_P_IP) || - arp->ar_op != htons(ARPOP_REQUEST)) - return; + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + arp = arp_hdr(skb); - arp_ptr = (unsigned char *)(arp+1); - /* save the location of the src hw addr */ - sha = arp_ptr; - arp_ptr += skb->dev->addr_len; - memcpy(&sip, arp_ptr, 4); - arp_ptr += 4; - /* If we actually cared about dst hw addr, - it would get copied here */ - arp_ptr += skb->dev->addr_len; - memcpy(&tip, arp_ptr, 4); - - /* Should we ignore arp? */ - if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) - return; + if ((arp->ar_hrd != htons(ARPHRD_ETHER) && + arp->ar_hrd != htons(ARPHRD_IEEE802)) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_op != htons(ARPOP_REQUEST)) + return; - size = arp_hdr_len(skb->dev); + arp_ptr = (unsigned char *)(arp+1); + /* save the location of the src hw addr */ + sha = arp_ptr; + arp_ptr += skb->dev->addr_len; + memcpy(&sip, arp_ptr, 4); + arp_ptr += 4; + /* If we actually cared about dst hw addr, + it would get copied here */ + arp_ptr += skb->dev->addr_len; + memcpy(&tip, arp_ptr, 4); - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (tip != np->local_ip) - continue; + /* Should we ignore arp? */ + if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) + return; - hlen = LL_RESERVED_SPACE(np->dev); - tlen = np->dev->needed_tailroom; - send_skb = find_skb(np, size + hlen + tlen, hlen); - if (!send_skb) - continue; + size = arp_hdr_len(skb->dev); - skb_reset_network_header(send_skb); - arp = (struct arphdr *) skb_put(send_skb, size); - send_skb->dev = skb->dev; - send_skb->protocol = htons(ETH_P_ARP); + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (tip != np->local_ip.ip) + continue; + + hlen = LL_RESERVED_SPACE(np->dev); + tlen = np->dev->needed_tailroom; + send_skb = find_skb(np, size + hlen + tlen, hlen); + if (!send_skb) + continue; + + skb_reset_network_header(send_skb); + arp = (struct arphdr *) skb_put(send_skb, size); + send_skb->dev = skb->dev; + send_skb->protocol = htons(ETH_P_ARP); + + /* Fill the device header for the ARP frame */ + if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP, + sha, np->dev->dev_addr, + send_skb->len) < 0) { + kfree_skb(send_skb); + continue; + } - /* Fill the device header for the ARP frame */ - if (dev_hard_header(send_skb, skb->dev, ptype, - sha, np->dev->dev_addr, - send_skb->len) < 0) { - kfree_skb(send_skb); - continue; + /* + * Fill out the arp protocol part. + * + * we only support ethernet device type, + * which (according to RFC 1390) should + * always equal 1 (Ethernet). + */ + + arp->ar_hrd = htons(np->dev->type); + arp->ar_pro = htons(ETH_P_IP); + arp->ar_hln = np->dev->addr_len; + arp->ar_pln = 4; + arp->ar_op = htons(type); + + arp_ptr = (unsigned char *)(arp + 1); + memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); + arp_ptr += np->dev->addr_len; + memcpy(arp_ptr, &tip, 4); + arp_ptr += 4; + memcpy(arp_ptr, sha, np->dev->addr_len); + arp_ptr += np->dev->addr_len; + memcpy(arp_ptr, &sip, 4); + + netpoll_send_skb(np, send_skb); + + /* If there are several rx_hooks for the same address, + we're fine by sending a single reply */ + break; } + spin_unlock_irqrestore(&npinfo->rx_lock, flags); + } else if( proto == ETH_P_IPV6) { +#if IS_ENABLED(CONFIG_IPV6) + struct nd_msg *msg; + u8 *lladdr = NULL; + struct ipv6hdr *hdr; + struct icmp6hdr *icmp6h; + const struct in6_addr *saddr; + const struct in6_addr *daddr; + struct inet6_dev *in6_dev = NULL; + struct in6_addr *target; + + in6_dev = in6_dev_get(skb->dev); + if (!in6_dev || !in6_dev->cnf.accept_ra) + return; - /* - * Fill out the arp protocol part. - * - * we only support ethernet device type, - * which (according to RFC 1390) should - * always equal 1 (Ethernet). - */ + if (!pskb_may_pull(skb, skb->len)) + return; - arp->ar_hrd = htons(np->dev->type); - arp->ar_pro = htons(ETH_P_IP); - arp->ar_hln = np->dev->addr_len; - arp->ar_pln = 4; - arp->ar_op = htons(type); + msg = (struct nd_msg *)skb_transport_header(skb); - arp_ptr = (unsigned char *)(arp + 1); - memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &tip, 4); - arp_ptr += 4; - memcpy(arp_ptr, sha, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &sip, 4); + __skb_push(skb, skb->data - skb_transport_header(skb)); + + if (ipv6_hdr(skb)->hop_limit != 255) + return; + if (msg->icmph.icmp6_code != 0) + return; + if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) + return; + + saddr = &ipv6_hdr(skb)->saddr; + daddr = &ipv6_hdr(skb)->daddr; - netpoll_send_skb(np, send_skb); + size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); - /* If there are several rx_hooks for the same address, - we're fine by sending a single reply */ - break; + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (!ipv6_addr_equal(daddr, &np->local_ip.in6)) + continue; + + hlen = LL_RESERVED_SPACE(np->dev); + tlen = np->dev->needed_tailroom; + send_skb = find_skb(np, size + hlen + tlen, hlen); + if (!send_skb) + continue; + + send_skb->protocol = htons(ETH_P_IPV6); + send_skb->dev = skb->dev; + + skb_reset_network_header(send_skb); + skb_put(send_skb, sizeof(struct ipv6hdr)); + hdr = ipv6_hdr(send_skb); + + *(__be32*)hdr = htonl(0x60000000); + + hdr->payload_len = htons(size); + hdr->nexthdr = IPPROTO_ICMPV6; + hdr->hop_limit = 255; + hdr->saddr = *saddr; + hdr->daddr = *daddr; + + send_skb->transport_header = send_skb->tail; + skb_put(send_skb, size); + + icmp6h = (struct icmp6hdr *)skb_transport_header(skb); + icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; + icmp6h->icmp6_router = 0; + icmp6h->icmp6_solicited = 1; + target = (struct in6_addr *)skb_transport_header(send_skb) + sizeof(struct icmp6hdr); + *target = msg->target; + icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size, + IPPROTO_ICMPV6, + csum_partial(icmp6h, + size, 0)); + + if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6, + lladdr, np->dev->dev_addr, + send_skb->len) < 0) { + kfree_skb(send_skb); + continue; + } + + netpoll_send_skb(np, send_skb); + + /* If there are several rx_hooks for the same address, + we're fine by sending a single reply */ + break; + } + spin_unlock_irqrestore(&npinfo->rx_lock, flags); +#endif } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); +} + +static bool pkt_is_ns(struct sk_buff *skb) +{ + struct nd_msg *msg; + struct ipv6hdr *hdr; + + if (skb->protocol != htons(ETH_P_ARP)) + return false; + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg))) + return false; + + msg = (struct nd_msg *)skb_transport_header(skb); + __skb_push(skb, skb->data - skb_transport_header(skb)); + hdr = ipv6_hdr(skb); + + if (hdr->nexthdr != IPPROTO_ICMPV6) + return false; + if (hdr->hop_limit != 255) + return false; + if (msg->icmph.icmp6_code != 0) + return false; + if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) + return false; + + return true; } int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) @@ -571,9 +732,11 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) goto out; /* check if netpoll clients need ARP */ - if (skb->protocol == htons(ETH_P_ARP) && - atomic_read(&trapped)) { - skb_queue_tail(&npinfo->arp_tx, skb); + if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) { + skb_queue_tail(&npinfo->neigh_tx, skb); + return 1; + } else if (pkt_is_ns(skb) && atomic_read(&trapped)) { + skb_queue_tail(&npinfo->neigh_tx, skb); return 1; } @@ -584,60 +747,100 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) } proto = ntohs(eth_hdr(skb)->h_proto); - if (proto != ETH_P_IP) + if (proto != ETH_P_IP && proto != ETH_P_IPV6) goto out; if (skb->pkt_type == PACKET_OTHERHOST) goto out; if (skb_shared(skb)) goto out; - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto out; - iph = (struct iphdr *)skb->data; - if (iph->ihl < 5 || iph->version != 4) - goto out; - if (!pskb_may_pull(skb, iph->ihl*4)) - goto out; - iph = (struct iphdr *)skb->data; - if (ip_fast_csum((u8 *)iph, iph->ihl) != 0) - goto out; - - len = ntohs(iph->tot_len); - if (skb->len < len || len < iph->ihl*4) - goto out; + if (proto == ETH_P_IP) { + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto out; + iph = (struct iphdr *)skb->data; + if (iph->ihl < 5 || iph->version != 4) + goto out; + if (!pskb_may_pull(skb, iph->ihl*4)) + goto out; + iph = (struct iphdr *)skb->data; + if (ip_fast_csum((u8 *)iph, iph->ihl) != 0) + goto out; - /* - * Our transport medium may have padded the buffer out. - * Now We trim to the true length of the frame. - */ - if (pskb_trim_rcsum(skb, len)) - goto out; + len = ntohs(iph->tot_len); + if (skb->len < len || len < iph->ihl*4) + goto out; - iph = (struct iphdr *)skb->data; - if (iph->protocol != IPPROTO_UDP) - goto out; + /* + * Our transport medium may have padded the buffer out. + * Now We trim to the true length of the frame. + */ + if (pskb_trim_rcsum(skb, len)) + goto out; - len -= iph->ihl*4; - uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); - ulen = ntohs(uh->len); + iph = (struct iphdr *)skb->data; + if (iph->protocol != IPPROTO_UDP) + goto out; - if (ulen != len) - goto out; - if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) - goto out; + len -= iph->ihl*4; + uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); + ulen = ntohs(uh->len); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (np->local_ip && np->local_ip != iph->daddr) - continue; - if (np->remote_ip && np->remote_ip != iph->saddr) - continue; - if (np->local_port && np->local_port != ntohs(uh->dest)) - continue; + if (ulen != len) + goto out; + if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) + goto out; + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (np->local_ip.ip && np->local_ip.ip != iph->daddr) + continue; + if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr) + continue; + if (np->local_port && np->local_port != ntohs(uh->dest)) + continue; + + np->rx_hook(np, ntohs(uh->source), + (char *)(uh+1), + ulen - sizeof(struct udphdr)); + hits++; + } + } else { +#if IS_ENABLED(CONFIG_IPV6) + const struct ipv6hdr *ip6h; - np->rx_hook(np, ntohs(uh->source), - (char *)(uh+1), - ulen - sizeof(struct udphdr)); - hits++; + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + goto out; + ip6h = (struct ipv6hdr *)skb->data; + if (ip6h->version != 6) + goto out; + len = ntohs(ip6h->payload_len); + if (!len) + goto out; + if (len + sizeof(struct ipv6hdr) > skb->len) + goto out; + if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr))) + goto out; + ip6h = ipv6_hdr(skb); + if (!pskb_may_pull(skb, sizeof(struct udphdr))) + goto out; + uh = udp_hdr(skb); + ulen = ntohs(uh->len); + if (ulen != skb->len) + goto out; + if (udp6_csum_init(skb, uh, IPPROTO_UDP)) + goto out; + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr)) + continue; + if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr)) + continue; + if (np->local_port && np->local_port != ntohs(uh->dest)) + continue; + + np->rx_hook(np, ntohs(uh->source), + (char *)(uh+1), + ulen - sizeof(struct udphdr)); + hits++; + } +#endif } if (!hits) @@ -658,17 +861,44 @@ out: void netpoll_print_options(struct netpoll *np) { np_info(np, "local port %d\n", np->local_port); - np_info(np, "local IP %pI4\n", &np->local_ip); + if (np->ipv6) + np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6); + else + np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); np_info(np, "interface '%s'\n", np->dev_name); np_info(np, "remote port %d\n", np->remote_port); - np_info(np, "remote IP %pI4\n", &np->remote_ip); + if (np->ipv6) + np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6); + else + np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip); np_info(np, "remote ethernet address %pM\n", np->remote_mac); } EXPORT_SYMBOL(netpoll_print_options); +static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) +{ + const char *end; + + if (!strchr(str, ':') && + in4_pton(str, -1, (void *)addr, -1, &end) > 0) { + if (!*end) + return 0; + } + if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) { +#if IS_ENABLED(CONFIG_IPV6) + if (!*end) + return 1; +#else + return -1; +#endif + } + return -1; +} + int netpoll_parse_options(struct netpoll *np, char *opt) { char *cur=opt, *delim; + int ipv6; if (*cur != '@') { if ((delim = strchr(cur, '@')) == NULL) @@ -684,7 +914,11 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; - np->local_ip = in_aton(cur); + ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip); + if (ipv6 < 0) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; cur = delim; } cur++; @@ -716,7 +950,13 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; - np->remote_ip = in_aton(cur); + ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); + if (ipv6 < 0) + goto parse_failed; + else if (np->ipv6 != (bool)ipv6) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; cur = delim + 1; if (*cur != 0) { @@ -764,7 +1004,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) INIT_LIST_HEAD(&npinfo->rx_np); spin_lock_init(&npinfo->rx_lock); - skb_queue_head_init(&npinfo->arp_tx); + skb_queue_head_init(&npinfo->neigh_tx); skb_queue_head_init(&npinfo->txq); INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); @@ -808,14 +1048,19 @@ int netpoll_setup(struct netpoll *np) struct in_device *in_dev; int err; - if (np->dev_name) - ndev = dev_get_by_name(&init_net, np->dev_name); + rtnl_lock(); + if (np->dev_name) { + struct net *net = current->nsproxy->net_ns; + ndev = __dev_get_by_name(net, np->dev_name); + } if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); - return -ENODEV; + err = -ENODEV; + goto unlock; } + dev_hold(ndev); - if (ndev->master) { + if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; goto put; @@ -826,15 +1071,14 @@ int netpoll_setup(struct netpoll *np) np_info(np, "device %s not up yet, forcing it\n", np->dev_name); - rtnl_lock(); err = dev_open(ndev); - rtnl_unlock(); if (err) { np_err(np, "failed to open %s\n", ndev->name); goto put; } + rtnl_unlock(); atleast = jiffies + HZ/10; atmost = jiffies + carrier_timeout * HZ; while (!netif_carrier_ok(ndev)) { @@ -854,39 +1098,70 @@ int netpoll_setup(struct netpoll *np) np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n"); msleep(4000); } + rtnl_lock(); } - if (!np->local_ip) { - rcu_read_lock(); - in_dev = __in_dev_get_rcu(ndev); + if (!np->local_ip.ip) { + if (!np->ipv6) { + in_dev = __in_dev_get_rtnl(ndev); + + if (!in_dev || !in_dev->ifa_list) { + np_err(np, "no IP address for %s, aborting\n", + np->dev_name); + err = -EDESTADDRREQ; + goto put; + } + + np->local_ip.ip = in_dev->ifa_list->ifa_local; + np_info(np, "local IP %pI4\n", &np->local_ip.ip); + } else { +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_dev *idev; - if (!in_dev || !in_dev->ifa_list) { - rcu_read_unlock(); - np_err(np, "no IP address for %s, aborting\n", - np->dev_name); err = -EDESTADDRREQ; + idev = __in6_dev_get(ndev); + if (idev) { + struct inet6_ifaddr *ifp; + + read_lock_bh(&idev->lock); + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) + continue; + np->local_ip.in6 = ifp->addr; + err = 0; + break; + } + read_unlock_bh(&idev->lock); + } + if (err) { + np_err(np, "no IPv6 address for %s, aborting\n", + np->dev_name); + goto put; + } else + np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6); +#else + np_err(np, "IPv6 is not supported %s, aborting\n", + np->dev_name); + err = -EINVAL; goto put; +#endif } - - np->local_ip = in_dev->ifa_list->ifa_local; - rcu_read_unlock(); - np_info(np, "local IP %pI4\n", &np->local_ip); } /* fill up the skb queue */ refill_skbs(); - rtnl_lock(); err = __netpoll_setup(np, ndev, GFP_KERNEL); - rtnl_unlock(); - if (err) goto put; + rtnl_unlock(); return 0; put: dev_put(ndev); +unlock: + rtnl_unlock(); return err; } EXPORT_SYMBOL(netpoll_setup); @@ -903,7 +1178,7 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) struct netpoll_info *npinfo = container_of(rcu_head, struct netpoll_info, rcu); - skb_queue_purge(&npinfo->arp_tx); + skb_queue_purge(&npinfo->neigh_tx); skb_queue_purge(&npinfo->txq); /* we can't call cancel_delayed_work_sync here, as we are in softirq */ diff --git a/net/core/pktgen.c b/net/core/pktgen.c index b29dacf900f..797769551b9 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -164,6 +164,7 @@ #ifdef CONFIG_XFRM #include <net/xfrm.h> #endif +#include <net/netns/generic.h> #include <asm/byteorder.h> #include <linux/rcupdate.h> #include <linux/bitops.h> @@ -212,7 +213,6 @@ #define PKTGEN_MAGIC 0xbe9be955 #define PG_PROC_DIR "pktgen" #define PGCTRL "pgctrl" -static struct proc_dir_entry *pg_proc_dir; #define MAX_CFLOWS 65536 @@ -397,7 +397,15 @@ struct pktgen_hdr { __be32 tv_usec; }; -static bool pktgen_exiting __read_mostly; + +static int pg_net_id __read_mostly; + +struct pktgen_net { + struct net *net; + struct proc_dir_entry *proc_dir; + struct list_head pktgen_threads; + bool pktgen_exiting; +}; struct pktgen_thread { spinlock_t if_lock; /* for list of devices */ @@ -414,6 +422,7 @@ struct pktgen_thread { wait_queue_head_t queue; struct completion start_done; + struct pktgen_net *net; }; #define REMOVE 1 @@ -428,9 +437,9 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, const char *ifname, bool exact); static int pktgen_device_event(struct notifier_block *, unsigned long, void *); -static void pktgen_run_all_threads(void); -static void pktgen_reset_all_threads(void); -static void pktgen_stop_all_threads_ifs(void); +static void pktgen_run_all_threads(struct pktgen_net *pn); +static void pktgen_reset_all_threads(struct pktgen_net *pn); +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn); static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); @@ -442,7 +451,6 @@ static int pg_clone_skb_d __read_mostly; static int debug __read_mostly; static DEFINE_MUTEX(pktgen_thread_lock); -static LIST_HEAD(pktgen_threads); static struct notifier_block pktgen_notifier_block = { .notifier_call = pktgen_device_event, @@ -464,6 +472,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, { int err = 0; char data[128]; + struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id); if (!capable(CAP_NET_ADMIN)) { err = -EPERM; @@ -480,13 +489,13 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, data[count - 1] = 0; /* Make string */ if (!strcmp(data, "stop")) - pktgen_stop_all_threads_ifs(); + pktgen_stop_all_threads_ifs(pn); else if (!strcmp(data, "start")) - pktgen_run_all_threads(); + pktgen_run_all_threads(pn); else if (!strcmp(data, "reset")) - pktgen_reset_all_threads(); + pktgen_reset_all_threads(pn); else pr_warning("Unknown command: %s\n", data); @@ -1824,13 +1833,14 @@ static const struct file_operations pktgen_thread_fops = { }; /* Think find or remove for NN */ -static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) +static struct pktgen_dev *__pktgen_NN_threads(const struct pktgen_net *pn, + const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; bool exact = (remove == FIND); - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { if (remove) { @@ -1848,7 +1858,7 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) /* * mark a device for removal */ -static void pktgen_mark_device(const char *ifname) +static void pktgen_mark_device(const struct pktgen_net *pn, const char *ifname) { struct pktgen_dev *pkt_dev = NULL; const int max_tries = 10, msec_per_try = 125; @@ -1859,7 +1869,7 @@ static void pktgen_mark_device(const char *ifname) while (1) { - pkt_dev = __pktgen_NN_threads(ifname, REMOVE); + pkt_dev = __pktgen_NN_threads(pn, ifname, REMOVE); if (pkt_dev == NULL) break; /* success */ @@ -1880,21 +1890,21 @@ static void pktgen_mark_device(const char *ifname) mutex_unlock(&pktgen_thread_lock); } -static void pktgen_change_name(struct net_device *dev) +static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *dev) { struct pktgen_thread *t; - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { struct pktgen_dev *pkt_dev; list_for_each_entry(pkt_dev, &t->if_list, list) { if (pkt_dev->odev != dev) continue; - remove_proc_entry(pkt_dev->entry->name, pg_proc_dir); + remove_proc_entry(pkt_dev->entry->name, pn->proc_dir); pkt_dev->entry = proc_create_data(dev->name, 0600, - pg_proc_dir, + pn->proc_dir, &pktgen_if_fops, pkt_dev); if (!pkt_dev->entry) @@ -1909,8 +1919,9 @@ static int pktgen_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = ptr; + struct pktgen_net *pn = net_generic(dev_net(dev), pg_net_id); - if (!net_eq(dev_net(dev), &init_net) || pktgen_exiting) + if (pn->pktgen_exiting) return NOTIFY_DONE; /* It is OK that we do not hold the group lock right now, @@ -1919,18 +1930,19 @@ static int pktgen_device_event(struct notifier_block *unused, switch (event) { case NETDEV_CHANGENAME: - pktgen_change_name(dev); + pktgen_change_name(pn, dev); break; case NETDEV_UNREGISTER: - pktgen_mark_device(dev->name); + pktgen_mark_device(pn, dev->name); break; } return NOTIFY_DONE; } -static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, +static struct net_device *pktgen_dev_get_by_name(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, const char *ifname) { char b[IFNAMSIZ+5]; @@ -1944,13 +1956,14 @@ static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, } b[i] = 0; - return dev_get_by_name(&init_net, b); + return dev_get_by_name(pn->net, b); } /* Associate pktgen_dev with a device. */ -static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) +static int pktgen_setup_dev(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, const char *ifname) { struct net_device *odev; int err; @@ -1961,7 +1974,7 @@ static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) pkt_dev->odev = NULL; } - odev = pktgen_dev_get_by_name(pkt_dev, ifname); + odev = pktgen_dev_get_by_name(pn, pkt_dev, ifname); if (!odev) { pr_err("no such netdevice: \"%s\"\n", ifname); return -ENODEV; @@ -2203,9 +2216,10 @@ static inline int f_pick(struct pktgen_dev *pkt_dev) 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(&init_net, DUMMY_MARK, + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, (xfrm_address_t *)&pkt_dev->cur_daddr, (xfrm_address_t *)&pkt_dev->cur_saddr, AF_INET, @@ -2912,7 +2926,7 @@ static void pktgen_run(struct pktgen_thread *t) t->control &= ~(T_STOP); } -static void pktgen_stop_all_threads_ifs(void) +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -2920,7 +2934,7 @@ static void pktgen_stop_all_threads_ifs(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= T_STOP; mutex_unlock(&pktgen_thread_lock); @@ -2956,28 +2970,28 @@ signal: return 0; } -static int pktgen_wait_all_threads_run(void) +static int pktgen_wait_all_threads_run(struct pktgen_net *pn) { struct pktgen_thread *t; int sig = 1; mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { sig = pktgen_wait_thread_run(t); if (sig == 0) break; } if (sig == 0) - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_STOP); mutex_unlock(&pktgen_thread_lock); return sig; } -static void pktgen_run_all_threads(void) +static void pktgen_run_all_threads(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -2985,7 +2999,7 @@ static void pktgen_run_all_threads(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_RUN); mutex_unlock(&pktgen_thread_lock); @@ -2993,10 +3007,10 @@ static void pktgen_run_all_threads(void) /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); - pktgen_wait_all_threads_run(); + pktgen_wait_all_threads_run(pn); } -static void pktgen_reset_all_threads(void) +static void pktgen_reset_all_threads(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -3004,7 +3018,7 @@ static void pktgen_reset_all_threads(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_REMDEVALL); mutex_unlock(&pktgen_thread_lock); @@ -3012,7 +3026,7 @@ static void pktgen_reset_all_threads(void) /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); - pktgen_wait_all_threads_run(); + pktgen_wait_all_threads_run(pn); } static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) @@ -3154,9 +3168,7 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t) static void pktgen_rem_thread(struct pktgen_thread *t) { /* Remove from the thread list */ - - remove_proc_entry(t->tsk->comm, pg_proc_dir); - + remove_proc_entry(t->tsk->comm, t->net->proc_dir); } static void pktgen_resched(struct pktgen_dev *pkt_dev) @@ -3302,7 +3314,7 @@ static int pktgen_thread_worker(void *arg) pkt_dev = next_to_run(t); if (unlikely(!pkt_dev && t->control == 0)) { - if (pktgen_exiting) + if (t->net->pktgen_exiting) break; wait_event_interruptible_timeout(t->queue, t->control != 0, @@ -3424,7 +3436,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) /* We don't allow a device to be on several threads */ - pkt_dev = __pktgen_NN_threads(ifname, FIND); + pkt_dev = __pktgen_NN_threads(t->net, ifname, FIND); if (pkt_dev) { pr_err("ERROR: interface already used\n"); return -EBUSY; @@ -3459,13 +3471,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->svlan_id = 0xffff; pkt_dev->node = -1; - err = pktgen_setup_dev(pkt_dev, ifname); + err = pktgen_setup_dev(t->net, pkt_dev, ifname); if (err) goto out1; if (pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING) pkt_dev->clone_skb = pg_clone_skb_d; - pkt_dev->entry = proc_create_data(ifname, 0600, pg_proc_dir, + pkt_dev->entry = proc_create_data(ifname, 0600, t->net->proc_dir, &pktgen_if_fops, pkt_dev); if (!pkt_dev->entry) { pr_err("cannot create %s/%s procfs entry\n", @@ -3490,7 +3502,7 @@ out1: return err; } -static int __init pktgen_create_thread(int cpu) +static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) { struct pktgen_thread *t; struct proc_dir_entry *pe; @@ -3508,7 +3520,7 @@ static int __init pktgen_create_thread(int cpu) INIT_LIST_HEAD(&t->if_list); - list_add_tail(&t->th_list, &pktgen_threads); + list_add_tail(&t->th_list, &pn->pktgen_threads); init_completion(&t->start_done); p = kthread_create_on_node(pktgen_thread_worker, @@ -3524,7 +3536,7 @@ static int __init pktgen_create_thread(int cpu) kthread_bind(p, cpu); t->tsk = p; - pe = proc_create_data(t->tsk->comm, 0600, pg_proc_dir, + pe = proc_create_data(t->tsk->comm, 0600, pn->proc_dir, &pktgen_thread_fops, t); if (!pe) { pr_err("cannot create %s/%s procfs entry\n", @@ -3535,6 +3547,7 @@ static int __init pktgen_create_thread(int cpu) return -EINVAL; } + t->net = pn; wake_up_process(p); wait_for_completion(&t->start_done); @@ -3560,6 +3573,7 @@ static void _rem_dev_from_if_list(struct pktgen_thread *t, static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) { + struct pktgen_net *pn = t->net; pr_debug("remove_device pkt_dev=%p\n", pkt_dev); @@ -3580,7 +3594,7 @@ static int pktgen_remove_device(struct pktgen_thread *t, _rem_dev_from_if_list(t, pkt_dev); if (pkt_dev->entry) - remove_proc_entry(pkt_dev->entry->name, pg_proc_dir); + remove_proc_entry(pkt_dev->entry->name, pn->proc_dir); #ifdef CONFIG_XFRM free_SAs(pkt_dev); @@ -3592,63 +3606,63 @@ static int pktgen_remove_device(struct pktgen_thread *t, return 0; } -static int __init pg_init(void) +static int __net_init pg_net_init(struct net *net) { - int cpu; + struct pktgen_net *pn = net_generic(net, pg_net_id); struct proc_dir_entry *pe; - int ret = 0; - - pr_info("%s", version); - - pg_proc_dir = proc_mkdir(PG_PROC_DIR, init_net.proc_net); - if (!pg_proc_dir) + int cpu, ret = 0; + + pn->net = net; + INIT_LIST_HEAD(&pn->pktgen_threads); + pn->pktgen_exiting = false; + pn->proc_dir = proc_mkdir(PG_PROC_DIR, pn->net->proc_net); + if (!pn->proc_dir) { + pr_warn("cannot create /proc/net/%s\n", PG_PROC_DIR); return -ENODEV; - - pe = proc_create(PGCTRL, 0600, pg_proc_dir, &pktgen_fops); + } + pe = proc_create(PGCTRL, 0600, pn->proc_dir, &pktgen_fops); if (pe == NULL) { - pr_err("ERROR: cannot create %s procfs entry\n", PGCTRL); + pr_err("cannot create %s procfs entry\n", PGCTRL); ret = -EINVAL; - goto remove_dir; + goto remove; } - register_netdevice_notifier(&pktgen_notifier_block); - for_each_online_cpu(cpu) { int err; - err = pktgen_create_thread(cpu); + err = pktgen_create_thread(cpu, pn); if (err) - pr_warning("WARNING: Cannot create thread for cpu %d (%d)\n", + pr_warn("Cannot create thread for cpu %d (%d)\n", cpu, err); } - if (list_empty(&pktgen_threads)) { - pr_err("ERROR: Initialization failed for all threads\n"); + if (list_empty(&pn->pktgen_threads)) { + pr_err("Initialization failed for all threads\n"); ret = -ENODEV; - goto unregister; + goto remove_entry; } return 0; - unregister: - unregister_netdevice_notifier(&pktgen_notifier_block); - remove_proc_entry(PGCTRL, pg_proc_dir); - remove_dir: - proc_net_remove(&init_net, PG_PROC_DIR); +remove_entry: + remove_proc_entry(PGCTRL, pn->proc_dir); +remove: + proc_net_remove(pn->net, PG_PROC_DIR); return ret; } -static void __exit pg_cleanup(void) +static void __net_exit pg_net_exit(struct net *net) { + struct pktgen_net *pn = net_generic(net, pg_net_id); struct pktgen_thread *t; struct list_head *q, *n; LIST_HEAD(list); /* Stop all interfaces & threads */ - pktgen_exiting = true; + pn->pktgen_exiting = true; mutex_lock(&pktgen_thread_lock); - list_splice_init(&pktgen_threads, &list); + list_splice_init(&pn->pktgen_threads, &list); mutex_unlock(&pktgen_thread_lock); list_for_each_safe(q, n, &list) { @@ -3658,12 +3672,36 @@ static void __exit pg_cleanup(void) kfree(t); } - /* Un-register us from receiving netdevice events */ - unregister_netdevice_notifier(&pktgen_notifier_block); + remove_proc_entry(PGCTRL, pn->proc_dir); + proc_net_remove(pn->net, PG_PROC_DIR); +} + +static struct pernet_operations pg_net_ops = { + .init = pg_net_init, + .exit = pg_net_exit, + .id = &pg_net_id, + .size = sizeof(struct pktgen_net), +}; + +static int __init pg_init(void) +{ + int ret = 0; - /* Clean up proc file system */ - remove_proc_entry(PGCTRL, pg_proc_dir); - proc_net_remove(&init_net, PG_PROC_DIR); + pr_info("%s", version); + ret = register_pernet_subsys(&pg_net_ops); + if (ret) + return ret; + ret = register_netdevice_notifier(&pktgen_notifier_block); + if (ret) + unregister_pernet_subsys(&pg_net_ops); + + return ret; +} + +static void __exit pg_cleanup(void) +{ + unregister_netdevice_notifier(&pktgen_notifier_block); + unregister_pernet_subsys(&pg_net_ops); } module_init(pg_init); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1868625af25..9a419b09948 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -780,6 +780,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(4) /* IFLA_MASTER */ + + nla_total_size(1) /* IFLA_CARRIER */ + nla_total_size(4) /* IFLA_PROMISCUITY */ + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ @@ -879,6 +880,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, const struct rtnl_link_stats64 *stats; struct nlattr *attr, *af_spec; struct rtnl_af_ops *af_ops; + struct net_device *upper_dev = netdev_master_upper_dev_get(dev); ASSERT_RTNL(); nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); @@ -907,8 +909,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, #endif (dev->ifindex != dev->iflink && nla_put_u32(skb, IFLA_LINK, dev->iflink)) || - (dev->master && - nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) || + (upper_dev && + nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) || + nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || (dev->qdisc && nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || (dev->ifalias && @@ -1108,6 +1111,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_MTU] = { .type = NLA_U32 }, [IFLA_LINK] = { .type = NLA_U32 }, [IFLA_MASTER] = { .type = NLA_U32 }, + [IFLA_CARRIER] = { .type = NLA_U8 }, [IFLA_TXQLEN] = { .type = NLA_U32 }, [IFLA_WEIGHT] = { .type = NLA_U32 }, [IFLA_OPERSTATE] = { .type = NLA_U8 }, @@ -1270,16 +1274,16 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) static int do_set_master(struct net_device *dev, int ifindex) { - struct net_device *master_dev; + struct net_device *upper_dev = netdev_master_upper_dev_get(dev); const struct net_device_ops *ops; int err; - if (dev->master) { - if (dev->master->ifindex == ifindex) + if (upper_dev) { + if (upper_dev->ifindex == ifindex) return 0; - ops = dev->master->netdev_ops; + ops = upper_dev->netdev_ops; if (ops->ndo_del_slave) { - err = ops->ndo_del_slave(dev->master, dev); + err = ops->ndo_del_slave(upper_dev, dev); if (err) return err; } else { @@ -1288,12 +1292,12 @@ static int do_set_master(struct net_device *dev, int ifindex) } if (ifindex) { - master_dev = __dev_get_by_index(dev_net(dev), ifindex); - if (!master_dev) + upper_dev = __dev_get_by_index(dev_net(dev), ifindex); + if (!upper_dev) return -EINVAL; - ops = master_dev->netdev_ops; + ops = upper_dev->netdev_ops; if (ops->ndo_add_slave) { - err = ops->ndo_add_slave(master_dev, dev); + err = ops->ndo_add_slave(upper_dev, dev); if (err) return err; } else { @@ -1307,7 +1311,6 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { const struct net_device_ops *ops = dev->netdev_ops; - int send_addr_notify = 0; int err; if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]) { @@ -1360,16 +1363,6 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, struct sockaddr *sa; int len; - if (!ops->ndo_set_mac_address) { - err = -EOPNOTSUPP; - goto errout; - } - - if (!netif_device_present(dev)) { - err = -ENODEV; - goto errout; - } - len = sizeof(sa_family_t) + dev->addr_len; sa = kmalloc(len, GFP_KERNEL); if (!sa) { @@ -1379,13 +1372,11 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, sa->sa_family = dev->type; memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]), dev->addr_len); - err = ops->ndo_set_mac_address(dev, sa); + err = dev_set_mac_address(dev, sa); kfree(sa); if (err) goto errout; - send_addr_notify = 1; modified = 1; - add_device_randomness(dev->dev_addr, dev->addr_len); } if (tb[IFLA_MTU]) { @@ -1422,7 +1413,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, if (tb[IFLA_BROADCAST]) { nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len); - send_addr_notify = 1; + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); } if (ifm->ifi_flags || ifm->ifi_change) { @@ -1438,6 +1429,13 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, modified = 1; } + if (tb[IFLA_CARRIER]) { + err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER])); + if (err) + goto errout; + modified = 1; + } + if (tb[IFLA_TXQLEN]) dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]); @@ -1536,9 +1534,6 @@ errout: net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n", dev->name); - if (send_addr_notify) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return err; } @@ -1672,9 +1667,11 @@ struct net_device *rtnl_create_link(struct net *net, if (tb[IFLA_MTU]) dev->mtu = nla_get_u32(tb[IFLA_MTU]); - if (tb[IFLA_ADDRESS]) + if (tb[IFLA_ADDRESS]) { memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]), nla_len(tb[IFLA_ADDRESS])); + dev->addr_assign_type = NET_ADDR_SET; + } if (tb[IFLA_BROADCAST]) memcpy(dev->broadcast, nla_data(tb[IFLA_BROADCAST]), nla_len(tb[IFLA_BROADCAST])); @@ -1992,6 +1989,7 @@ errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_LINK, err); } +EXPORT_SYMBOL(rtmsg_ifinfo); static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, @@ -2054,7 +2052,6 @@ errout: static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); - struct net_device *master = NULL; struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; struct net_device *dev; @@ -2096,10 +2093,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) /* Support fdb on master device the net/bridge default case */ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && (dev->priv_flags & IFF_BRIDGE_PORT)) { - master = dev->master; - err = master->netdev_ops->ndo_fdb_add(ndm, tb, - dev, addr, - nlh->nlmsg_flags); + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops = br_dev->netdev_ops; + + err = ops->ndo_fdb_add(ndm, tb, dev, addr, nlh->nlmsg_flags); if (err) goto out; else @@ -2160,10 +2157,11 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) /* Support fdb on master device the net/bridge default case */ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && (dev->priv_flags & IFF_BRIDGE_PORT)) { - struct net_device *master = dev->master; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops = br_dev->netdev_ops; - if (master->netdev_ops->ndo_fdb_del) - err = master->netdev_ops->ndo_fdb_del(ndm, dev, addr); + if (ops->ndo_fdb_del) + err = ops->ndo_fdb_del(ndm, dev, addr); if (err) goto out; @@ -2247,9 +2245,11 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (dev->priv_flags & IFF_BRIDGE_PORT) { - struct net_device *master = dev->master; - const struct net_device_ops *ops = master->netdev_ops; + struct net_device *br_dev; + const struct net_device_ops *ops; + br_dev = netdev_master_upper_dev_get(dev); + ops = br_dev->netdev_ops; if (ops->ndo_fdb_dump) idx = ops->ndo_fdb_dump(skb, cb, dev, idx); } @@ -2270,6 +2270,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct ifinfomsg *ifm; struct nlattr *br_afspec; u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI); if (nlh == NULL) @@ -2287,8 +2288,8 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || nla_put_u8(skb, IFLA_OPERSTATE, operstate) || - (dev->master && - nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) || + (br_dev && + nla_put_u32(skb, IFLA_MASTER, br_dev->ifindex)) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || (dev->ifindex != dev->iflink && @@ -2324,11 +2325,11 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); for_each_netdev_rcu(net, dev) { const struct net_device_ops *ops = dev->netdev_ops; - struct net_device *master = dev->master; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); - if (master && master->netdev_ops->ndo_bridge_getlink) { + if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && - master->netdev_ops->ndo_bridge_getlink( + br_dev->netdev_ops->ndo_bridge_getlink( skb, portid, seq, dev) < 0) break; idx++; @@ -2365,7 +2366,7 @@ static inline size_t bridge_nlmsg_size(void) static int rtnl_bridge_notify(struct net_device *dev, u16 flags) { struct net *net = dev_net(dev); - struct net_device *master = dev->master; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); struct sk_buff *skb; int err = -EOPNOTSUPP; @@ -2376,8 +2377,8 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags) } if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) && - master && master->netdev_ops->ndo_bridge_getlink) { - err = master->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev); + br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { + err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev); if (err < 0) goto errout; } @@ -2436,13 +2437,14 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, oflags = flags; if (!flags || (flags & BRIDGE_FLAGS_MASTER)) { - if (!dev->master || - !dev->master->netdev_ops->ndo_bridge_setlink) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + if (!br_dev || !br_dev->netdev_ops->ndo_bridge_setlink) { err = -EOPNOTSUPP; goto out; } - err = dev->master->netdev_ops->ndo_bridge_setlink(dev, nlh); + err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh); if (err) goto out; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a9a2ae3e221..bddc1dd2e7f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -155,8 +155,9 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) */ #define kmalloc_reserve(size, gfp, node, pfmemalloc) \ __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) -void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip, - bool *pfmemalloc) + +static void *__kmalloc_reserve(size_t size, gfp_t flags, int node, + unsigned long ip, bool *pfmemalloc) { void *obj; bool ret_pfmemalloc = false; @@ -259,6 +260,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, skb->end = skb->tail + size; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->mac_header = ~0U; + skb->transport_header = ~0U; #endif /* make sure we initialize shinfo sequentially */ @@ -327,6 +329,7 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) skb->end = skb->tail + size; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->mac_header = ~0U; + skb->transport_header = ~0U; #endif /* make sure we initialize shinfo sequentially */ @@ -2337,6 +2340,8 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); + skb_shinfo(skb1)->gso_type = skb_shinfo(skb)->gso_type; + if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ @@ -2668,48 +2673,37 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, int len, int odd, struct sk_buff *skb), void *from, int length) { - int frg_cnt = 0; - skb_frag_t *frag = NULL; - struct page *page = NULL; - int copy, left; + int frg_cnt = skb_shinfo(skb)->nr_frags; + int copy; int offset = 0; int ret; + struct page_frag *pfrag = ¤t->task_frag; do { /* Return error if we don't have space for new frag */ - frg_cnt = skb_shinfo(skb)->nr_frags; if (frg_cnt >= MAX_SKB_FRAGS) - return -EFAULT; - - /* allocate a new page for next frag */ - page = alloc_pages(sk->sk_allocation, 0); + return -EMSGSIZE; - /* If alloc_page fails just return failure and caller will - * free previous allocated pages by doing kfree_skb() - */ - if (page == NULL) + if (!sk_page_frag_refill(sk, pfrag)) return -ENOMEM; - /* initialize the next frag */ - skb_fill_page_desc(skb, frg_cnt, page, 0, 0); - skb->truesize += PAGE_SIZE; - atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc); - - /* get the new initialized frag */ - frg_cnt = skb_shinfo(skb)->nr_frags; - frag = &skb_shinfo(skb)->frags[frg_cnt - 1]; - /* copy the user data to page */ - left = PAGE_SIZE - frag->page_offset; - copy = (length > left)? left : length; + copy = min_t(int, length, pfrag->size - pfrag->offset); - ret = getfrag(from, skb_frag_address(frag) + skb_frag_size(frag), - offset, copy, 0, skb); + ret = getfrag(from, page_address(pfrag->page) + pfrag->offset, + offset, copy, 0, skb); if (ret < 0) return -EFAULT; /* copy was successful so update the size parameters */ - skb_frag_size_add(frag, copy); + skb_fill_page_desc(skb, frg_cnt, pfrag->page, pfrag->offset, + copy); + frg_cnt++; + pfrag->offset += copy; + get_page(pfrag->page); + + skb->truesize += copy; + atomic_add(copy, &sk->sk_wmem_alloc); skb->len += copy; skb->data_len += copy; offset += copy; @@ -2853,6 +2847,8 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_copy_from_linear_data_offset(skb, offset, skb_put(nskb, hsize), hsize); + skb_shinfo(nskb)->gso_type = skb_shinfo(skb)->gso_type; + while (pos < offset + len && i < nfrags) { *frag = skb_shinfo(skb)->frags[i]; __skb_frag_ref(frag); diff --git a/net/core/sock.c b/net/core/sock.c index bc131d41968..235fb89e897 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -665,6 +665,9 @@ int sock_setsockopt(struct socket *sock, int level, int optname, case SO_REUSEADDR: sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; + case SO_REUSEPORT: + sk->sk_reuseport = valbool; + break; case SO_TYPE: case SO_PROTOCOL: case SO_DOMAIN: @@ -861,6 +864,13 @@ set_rcvbuf: ret = sk_detach_filter(sk); break; + case SO_LOCK_FILTER: + if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool) + ret = -EPERM; + else + sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool); + break; + case SO_PASSSEC: if (valbool) set_bit(SOCK_PASSSEC, &sock->flags); @@ -965,6 +975,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_reuse; break; + case SO_REUSEPORT: + v.val = sk->sk_reuseport; + break; + case SO_KEEPALIVE: v.val = sock_flag(sk, SOCK_KEEPOPEN); break; @@ -1140,6 +1154,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, goto lenout; + case SO_LOCK_FILTER: + v.val = sock_flag(sk, SOCK_FILTER_LOCKED); + break; + default: return -ENOPROTOOPT; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index d1b08045a9d..cfdb46ab3a7 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -20,6 +20,8 @@ #include <net/sock.h> #include <net/net_ratelimit.h> +static int one = 1; + #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -92,28 +94,32 @@ static struct ctl_table net_core_table[] = { .data = &sysctl_wmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "rmem_max", .data = &sysctl_rmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "wmem_default", .data = &sysctl_wmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "rmem_default", .data = &sysctl_rmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "dev_weight", diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 307c322d53b..64d9843f9e0 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -909,6 +909,7 @@ static int __dn_connect(struct sock *sk, struct sockaddr_dn *addr, int addrlen, struct dn_scp *scp = DN_SK(sk); int err = -EISCONN; struct flowidn fld; + struct dst_entry *dst; if (sock->state == SS_CONNECTED) goto out; @@ -955,10 +956,11 @@ static int __dn_connect(struct sock *sk, struct sockaddr_dn *addr, int addrlen, fld.flowidn_proto = DNPROTO_NSP; if (dn_route_output_sock(&sk->sk_dst_cache, &fld, sk, flags) < 0) goto out; - sk->sk_route_caps = sk->sk_dst_cache->dev->features; + dst = __sk_dst_get(sk); + sk->sk_route_caps = dst->dev->features; sock->state = SS_CONNECTING; scp->state = DN_CI; - scp->segsize_loc = dst_metric_advmss(sk->sk_dst_cache); + scp->segsize_loc = dst_metric_advmss(dst); dn_nsp_send_conninit(sk, NSP_CI); err = -EINPROGRESS; diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 8a96047c7c9..1aaa51ebbda 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -598,7 +598,7 @@ void dn_nsp_send_disc(struct sock *sk, unsigned char msgflg, if (reason == 0) reason = le16_to_cpu(scp->discdata_out.opt_status); - dn_nsp_do_disc(sk, msgflg, reason, gfp, sk->sk_dst_cache, ddl, + dn_nsp_do_disc(sk, msgflg, reason, gfp, __sk_dst_get(sk), ddl, scp->discdata_out.opt_data, scp->addrrem, scp->addrloc); } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index b57419cc41a..1550028fcd8 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1282,7 +1282,7 @@ static int dn_route_output_key(struct dst_entry **pprt, struct flowidn *flp, int return err; } -int dn_route_output_sock(struct dst_entry **pprt, struct flowidn *fl, struct sock *sk, int flags) +int dn_route_output_sock(struct dst_entry __rcu **pprt, struct flowidn *fl, struct sock *sk, int flags) { int err; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 45295ca0957..2bc62ea857c 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -80,6 +80,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, int ret; char *name; int i; + bool valid_name_found = false; /* * Probe for switch model. @@ -131,8 +132,13 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, } else { ds->phys_port_mask |= 1 << i; } + valid_name_found = true; } + if (!valid_name_found && i == DSA_MAX_PORTS) { + ret = -EINVAL; + goto out; + } /* * If the CPU connects to this switch, set the switch tree diff --git a/net/dsa/slave.c b/net/dsa/slave.c index e32083d5d8f..6ebd8fbd928 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -41,8 +41,8 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds) ds->slave_mii_bus->name = "dsa slave smi"; ds->slave_mii_bus->read = dsa_slave_phy_read; ds->slave_mii_bus->write = dsa_slave_phy_write; - snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "%s:%.2x", - ds->master_mii_bus->id, ds->pd->sw_addr); + snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d:%.2x", + ds->index, ds->pd->sw_addr); ds->slave_mii_bus->parent = &ds->master_mii_bus->dev; } @@ -203,10 +203,10 @@ dsa_slave_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) static void dsa_slave_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { - strncpy(drvinfo->driver, "dsa", 32); - strncpy(drvinfo->version, dsa_driver_version, 32); - strncpy(drvinfo->fw_version, "N/A", 32); - strncpy(drvinfo->bus_info, "platform", 32); + strlcpy(drvinfo->driver, "dsa", sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, dsa_driver_version, sizeof(drvinfo->version)); + strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); + strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); } static int dsa_slave_nway_reset(struct net_device *dev) @@ -391,7 +391,7 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent, if (p->phy != NULL) { phy_attach(slave_dev, dev_name(&p->phy->dev), - 0, PHY_INTERFACE_MODE_GMII); + PHY_INTERFACE_MODE_GMII); p->phy->autoneg = AUTONEG_ENABLE; p->phy->speed = 0; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 4efad533e5f..a36c85eab5b 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -272,6 +272,36 @@ void eth_header_cache_update(struct hh_cache *hh, EXPORT_SYMBOL(eth_header_cache_update); /** + * eth_prepare_mac_addr_change - prepare for mac change + * @dev: network device + * @p: socket address + */ +int eth_prepare_mac_addr_change(struct net_device *dev, void *p) +{ + struct sockaddr *addr = p; + + if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) + return -EBUSY; + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + return 0; +} +EXPORT_SYMBOL(eth_prepare_mac_addr_change); + +/** + * eth_commit_mac_addr_change - commit mac change + * @dev: network device + * @p: socket address + */ +void eth_commit_mac_addr_change(struct net_device *dev, void *p) +{ + struct sockaddr *addr = p; + + memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); +} +EXPORT_SYMBOL(eth_commit_mac_addr_change); + +/** * eth_mac_addr - set new Ethernet hardware address * @dev: network device * @p: socket address @@ -283,15 +313,12 @@ EXPORT_SYMBOL(eth_header_cache_update); */ int eth_mac_addr(struct net_device *dev, void *p) { - struct sockaddr *addr = p; + int ret; - if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) - return -EBUSY; - if (!is_valid_ether_addr(addr->sa_data)) - return -EADDRNOTAVAIL; - memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); - /* if device marked as NET_ADDR_RANDOM, reset it */ - dev->addr_assign_type &= ~NET_ADDR_RANDOM; + ret = eth_prepare_mac_addr_change(dev, p); + if (ret < 0) + return ret; + eth_commit_mac_addr_change(dev, p); return 0; } EXPORT_SYMBOL(eth_mac_addr); diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index f651da60f16..09cba81d2c4 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -594,10 +594,32 @@ static int lowpan_header_create(struct sk_buff *skb, } } +static int lowpan_give_skb_to_devices(struct sk_buff *skb) +{ + struct lowpan_dev_record *entry; + struct sk_buff *skb_cp; + int stat = NET_RX_SUCCESS; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &lowpan_devices, list) + if (lowpan_dev_info(entry->ldev)->real_dev == skb->dev) { + skb_cp = skb_copy(skb, GFP_ATOMIC); + if (!skb_cp) { + stat = -ENOMEM; + break; + } + + skb_cp->dev = entry->ldev; + stat = netif_rx(skb_cp); + } + rcu_read_unlock(); + + return stat; +} + static int lowpan_skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr) { struct sk_buff *new; - struct lowpan_dev_record *entry; int stat = NET_RX_SUCCESS; new = skb_copy_expand(skb, sizeof(struct ipv6hdr), skb_tailroom(skb), @@ -614,19 +636,7 @@ static int lowpan_skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr) new->protocol = htons(ETH_P_IPV6); new->pkt_type = PACKET_HOST; - rcu_read_lock(); - list_for_each_entry_rcu(entry, &lowpan_devices, list) - if (lowpan_dev_info(entry->ldev)->real_dev == new->dev) { - skb = skb_copy(new, GFP_ATOMIC); - if (!skb) { - stat = -ENOMEM; - break; - } - - skb->dev = entry->ldev; - stat = netif_rx(skb); - } - rcu_read_unlock(); + stat = lowpan_give_skb_to_devices(new); kfree_skb(new); @@ -1137,19 +1147,42 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, goto drop; /* check that it's our buffer */ - switch (skb->data[0] & 0xe0) { - case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ - case LOWPAN_DISPATCH_FRAG1: /* first fragment header */ - case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */ - local_skb = skb_clone(skb, GFP_ATOMIC); + 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; - lowpan_process_data(local_skb); + local_skb->protocol = htons(ETH_P_IPV6); + local_skb->pkt_type = PACKET_HOST; + + /* Pull off the 1-byte of 6lowpan header. */ + skb_pull(local_skb, 1); + skb_reset_network_header(local_skb); + skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); + + lowpan_give_skb_to_devices(local_skb); + + kfree_skb(local_skb); kfree_skb(skb); - break; - default: - break; + } else { + switch (skb->data[0] & 0xe0) { + case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ + case LOWPAN_DISPATCH_FRAG1: /* first fragment header */ + case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */ + local_skb = skb_clone(skb, GFP_ATOMIC); + if (!local_skb) + goto drop; + lowpan_process_data(local_skb); + + kfree_skb(skb); + break; + default: + break; + } } return NET_RX_SUCCESS; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 24b384b7903..49ddca31c4d 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1306,6 +1306,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_SHARED_FRAG | 0))) goto out; @@ -1333,7 +1334,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ops->callbacks.gso_segment(skb, features); rcu_read_unlock(); - if (!segs || IS_ERR(segs)) + if (IS_ERR_OR_NULL(segs)) goto out; skb = segs; @@ -1705,12 +1706,11 @@ static struct packet_type ip_packet_type __read_mostly = { static int __init inet_init(void) { - struct sk_buff *dummy_skb; struct inet_protosw *q; struct list_head *r; int rc = -EINVAL; - BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct inet_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb)); sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL); if (!sysctl_local_reserved_ports) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a8e4f2665d5..5281314886c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -63,6 +63,7 @@ #include <net/ip_fib.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> +#include <net/addrconf.h> #include "fib_lookup.h" @@ -93,6 +94,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, + [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, }; #define IN4_ADDR_HSIZE_SHIFT 8 @@ -417,6 +419,10 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); } +static void check_lifetime(struct work_struct *work); + +static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime); + static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { @@ -462,6 +468,9 @@ 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); + /* Send message first, then call notifier. Notifier will trigger FIB update, so that listeners of netlink will know about new ifaddr */ @@ -573,7 +582,107 @@ errout: return err; } -static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh) +#define INFINITY_LIFE_TIME 0xFFFFFFFF + +static void check_lifetime(struct work_struct *work) +{ + unsigned long now, next, next_sec, next_sched; + struct in_ifaddr *ifa; + struct hlist_node *node; + int i; + + now = jiffies; + next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); + + rcu_read_lock(); + for (i = 0; i < IN4_ADDR_HSIZE; i++) { + hlist_for_each_entry_rcu(ifa, node, + &inet_addr_lst[i], hash) { + unsigned long age; + + if (ifa->ifa_flags & IFA_F_PERMANENT) + continue; + + /* We try to batch several events at once. */ + age = (now - ifa->ifa_tstamp + + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + + if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && + age >= ifa->ifa_valid_lft) { + struct in_ifaddr **ifap ; + + rtnl_lock(); + for (ifap = &ifa->ifa_dev->ifa_list; + *ifap != NULL; ifap = &ifa->ifa_next) { + if (*ifap == ifa) + inet_del_ifa(ifa->ifa_dev, + ifap, 1); + } + rtnl_unlock(); + } else if (ifa->ifa_preferred_lft == + INFINITY_LIFE_TIME) { + continue; + } else if (age >= ifa->ifa_preferred_lft) { + if (time_before(ifa->ifa_tstamp + + ifa->ifa_valid_lft * HZ, next)) + next = ifa->ifa_tstamp + + ifa->ifa_valid_lft * HZ; + + if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) { + ifa->ifa_flags |= IFA_F_DEPRECATED; + rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); + } + } else if (time_before(ifa->ifa_tstamp + + ifa->ifa_preferred_lft * HZ, + next)) { + next = ifa->ifa_tstamp + + ifa->ifa_preferred_lft * HZ; + } + } + } + rcu_read_unlock(); + + next_sec = round_jiffies_up(next); + next_sched = next; + + /* If rounded timeout is accurate enough, accept it. */ + if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) + next_sched = next_sec; + + now = jiffies; + /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ + 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); +} + +static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, + __u32 prefered_lft) +{ + unsigned long timeout; + + ifa->ifa_flags &= ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); + + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) + ifa->ifa_valid_lft = timeout; + else + ifa->ifa_flags |= IFA_F_PERMANENT; + + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa->ifa_flags |= IFA_F_DEPRECATED; + ifa->ifa_preferred_lft = timeout; + } + ifa->ifa_tstamp = jiffies; + if (!ifa->ifa_cstamp) + ifa->ifa_cstamp = ifa->ifa_tstamp; +} + +static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, + __u32 *pvalid_lft, __u32 *pprefered_lft) { struct nlattr *tb[IFA_MAX+1]; struct in_ifaddr *ifa; @@ -633,24 +742,73 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh) else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); + if (tb[IFA_CACHEINFO]) { + struct ifa_cacheinfo *ci; + + ci = nla_data(tb[IFA_CACHEINFO]); + if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { + err = -EINVAL; + goto errout; + } + *pvalid_lft = ci->ifa_valid; + *pprefered_lft = ci->ifa_prefered; + } + return ifa; errout: return ERR_PTR(err); } +static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa) +{ + struct in_device *in_dev = ifa->ifa_dev; + struct in_ifaddr *ifa1, **ifap; + + if (!ifa->ifa_local) + return NULL; + + for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; + ifap = &ifa1->ifa_next) { + if (ifa1->ifa_mask == ifa->ifa_mask && + inet_ifa_match(ifa1->ifa_address, ifa) && + ifa1->ifa_local == ifa->ifa_local) + return ifa1; + } + return NULL; +} + static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); struct in_ifaddr *ifa; + struct in_ifaddr *ifa_existing; + __u32 valid_lft = INFINITY_LIFE_TIME; + __u32 prefered_lft = INFINITY_LIFE_TIME; ASSERT_RTNL(); - ifa = rtm_to_ifaddr(net, nlh); + ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft); if (IS_ERR(ifa)) return PTR_ERR(ifa); - return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); + ifa_existing = find_matching_ifa(ifa); + if (!ifa_existing) { + /* It would be best to check for !NLM_F_CREATE here but + * userspace alreay relies on not having to provide this. + */ + set_ifa_lifetime(ifa, valid_lft, prefered_lft); + return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); + } else { + inet_free_ifa(ifa); + + if (nlh->nlmsg_flags & NLM_F_EXCL || + !(nlh->nlmsg_flags & NLM_F_REPLACE)) + return -EEXIST; + + set_ifa_lifetime(ifa_existing, valid_lft, prefered_lft); + } + return 0; } /* @@ -852,6 +1010,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) ifa->ifa_prefixlen = 32; ifa->ifa_mask = inet_make_mask(32); } + set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ret = inet_set_ifa(dev, ifa); break; @@ -1190,6 +1349,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, ifa->ifa_dev = in_dev; ifa->ifa_scope = RT_SCOPE_HOST; memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); + set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, + INFINITY_LIFE_TIME); inet_insert_ifa(ifa); } } @@ -1246,11 +1407,30 @@ static size_t inet_nlmsg_size(void) + nla_total_size(IFNAMSIZ); /* IFA_LABEL */ } +static inline u32 cstamp_delta(unsigned long cstamp) +{ + return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; +} + +static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, + unsigned long tstamp, u32 preferred, u32 valid) +{ + struct ifa_cacheinfo ci; + + ci.cstamp = cstamp_delta(cstamp); + ci.tstamp = cstamp_delta(tstamp); + ci.ifa_prefered = preferred; + ci.ifa_valid = valid; + + return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); +} + static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, u32 portid, u32 seq, int event, unsigned int flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; + u32 preferred, valid; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); if (nlh == NULL) @@ -1259,10 +1439,31 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; - ifm->ifa_flags = ifa->ifa_flags|IFA_F_PERMANENT; + ifm->ifa_flags = ifa->ifa_flags; ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; + if (!(ifm->ifa_flags & IFA_F_PERMANENT)) { + preferred = ifa->ifa_preferred_lft; + valid = ifa->ifa_valid_lft; + if (preferred != INFINITY_LIFE_TIME) { + long tval = (jiffies - ifa->ifa_tstamp) / HZ; + + if (preferred > tval) + preferred -= tval; + else + preferred = 0; + if (valid != INFINITY_LIFE_TIME) { + if (valid > tval) + valid -= tval; + else + valid = 0; + } + } + } else { + preferred = INFINITY_LIFE_TIME; + valid = INFINITY_LIFE_TIME; + } if ((ifa->ifa_address && nla_put_be32(skb, IFA_ADDRESS, ifa->ifa_address)) || (ifa->ifa_local && @@ -1270,7 +1471,9 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, (ifa->ifa_broadcast && nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && - nla_put_string(skb, IFA_LABEL, ifa->ifa_label))) + nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || + put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp, + preferred, valid)) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -1988,6 +2191,8 @@ void __init devinet_init(void) register_gifconf(PF_INET, inet_gifconf); register_netdevice_notifier(&ip_netdev_notifier); + schedule_delayed_work(&check_lifetime_work, 0); + rtnl_af_register(&inet_af_ops); rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 5cd75e2dab2..99f00d39d10 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -974,7 +974,7 @@ static void nl_fib_input(struct sk_buff *skb) nl_fib_lookup(frn, tb); - portid = NETLINK_CB(skb).portid; /* pid of sending process */ + portid = NETLINK_CB(skb).portid; /* netlink portid */ NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d0670f00d52..11cb4979a46 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -59,6 +59,8 @@ int inet_csk_bind_conflict(const struct sock *sk, struct sock *sk2; struct hlist_node *node; int reuse = sk->sk_reuse; + int reuseport = sk->sk_reuseport; + kuid_t uid = sock_i_uid((struct sock *)sk); /* * Unlike other sk lookup places we do not check @@ -73,8 +75,11 @@ int inet_csk_bind_conflict(const struct sock *sk, (!sk->sk_bound_dev_if || !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { - if (!reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) { + if ((!reuse || !sk2->sk_reuse || + sk2->sk_state == TCP_LISTEN) && + (!reuseport || !sk2->sk_reuseport || + (sk2->sk_state != TCP_TIME_WAIT && + !uid_eq(uid, sock_i_uid(sk2))))) { const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) || sk2_rcv_saddr == sk_rcv_saddr(sk)) @@ -106,6 +111,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) int ret, attempts = 5; struct net *net = sock_net(sk); int smallest_size = -1, smallest_rover; + kuid_t uid = sock_i_uid(sk); local_bh_disable(); if (!snum) { @@ -125,9 +131,12 @@ again: spin_lock(&head->lock); inet_bind_bucket_for_each(tb, node, &head->chain) if (net_eq(ib_net(tb), net) && tb->port == rover) { - if (tb->fastreuse > 0 && - sk->sk_reuse && - sk->sk_state != TCP_LISTEN && + if (((tb->fastreuse > 0 && + sk->sk_reuse && + sk->sk_state != TCP_LISTEN) || + (tb->fastreuseport > 0 && + sk->sk_reuseport && + uid_eq(tb->fastuid, uid))) && (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; smallest_rover = rover; @@ -185,14 +194,18 @@ tb_found: if (sk->sk_reuse == SK_FORCE_REUSE) goto success; - if (tb->fastreuse > 0 && - sk->sk_reuse && sk->sk_state != TCP_LISTEN && + if (((tb->fastreuse > 0 && + sk->sk_reuse && sk->sk_state != TCP_LISTEN) || + (tb->fastreuseport > 0 && + sk->sk_reuseport && uid_eq(tb->fastuid, uid))) && smallest_size == -1) { goto success; } else { ret = 1; if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) { - if (sk->sk_reuse && sk->sk_state != TCP_LISTEN && + if (((sk->sk_reuse && sk->sk_state != TCP_LISTEN) || + (tb->fastreuseport > 0 && + sk->sk_reuseport && uid_eq(tb->fastuid, uid))) && smallest_size != -1 && --attempts >= 0) { spin_unlock(&head->lock); goto again; @@ -212,9 +225,19 @@ tb_not_found: tb->fastreuse = 1; else tb->fastreuse = 0; - } else if (tb->fastreuse && - (!sk->sk_reuse || sk->sk_state == TCP_LISTEN)) - tb->fastreuse = 0; + if (sk->sk_reuseport) { + tb->fastreuseport = 1; + tb->fastuid = uid; + } else + tb->fastreuseport = 0; + } else { + if (tb->fastreuse && + (!sk->sk_reuse || sk->sk_state == TCP_LISTEN)) + tb->fastreuse = 0; + if (tb->fastreuseport && + (!sk->sk_reuseport || !uid_eq(tb->fastuid, uid))) + tb->fastreuseport = 0; + } success: if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, snum); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 4750d2b74d7..2e453bde699 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -73,8 +73,9 @@ EXPORT_SYMBOL(inet_frags_init); void inet_frags_init_net(struct netns_frags *nf) { nf->nqueues = 0; - atomic_set(&nf->mem, 0); + init_frag_mem_limit(nf); INIT_LIST_HEAD(&nf->lru_list); + spin_lock_init(&nf->lru_lock); } EXPORT_SYMBOL(inet_frags_init_net); @@ -91,6 +92,8 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f) local_bh_disable(); inet_frag_evictor(nf, f, true); local_bh_enable(); + + percpu_counter_destroy(&nf->mem); } EXPORT_SYMBOL(inet_frags_exit_net); @@ -98,9 +101,9 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) { write_lock(&f->lock); hlist_del(&fq->list); - list_del(&fq->lru_list); fq->net->nqueues--; write_unlock(&f->lock); + inet_frag_lru_del(fq); } void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) @@ -117,12 +120,8 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) EXPORT_SYMBOL(inet_frag_kill); static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f, - struct sk_buff *skb, int *work) + struct sk_buff *skb) { - if (work) - *work -= skb->truesize; - - atomic_sub(skb->truesize, &nf->mem); if (f->skb_free) f->skb_free(skb); kfree_skb(skb); @@ -133,6 +132,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, { struct sk_buff *fp; struct netns_frags *nf; + unsigned int sum, sum_truesize = 0; WARN_ON(!(q->last_in & INET_FRAG_COMPLETE)); WARN_ON(del_timer(&q->timer) != 0); @@ -143,13 +143,14 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, while (fp) { struct sk_buff *xp = fp->next; - frag_kfree_skb(nf, f, fp, work); + sum_truesize += fp->truesize; + frag_kfree_skb(nf, f, fp); fp = xp; } - + sum = sum_truesize + f->qsize; if (work) - *work -= f->qsize; - atomic_sub(f->qsize, &nf->mem); + *work -= sum; + sub_frag_mem_limit(q, sum); if (f->destructor) f->destructor(q); @@ -164,22 +165,23 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force) int work, evicted = 0; if (!force) { - if (atomic_read(&nf->mem) <= nf->high_thresh) + if (frag_mem_limit(nf) <= nf->high_thresh) return 0; } - work = atomic_read(&nf->mem) - nf->low_thresh; + work = frag_mem_limit(nf) - nf->low_thresh; while (work > 0) { - read_lock(&f->lock); + spin_lock(&nf->lru_lock); + if (list_empty(&nf->lru_list)) { - read_unlock(&f->lock); + spin_unlock(&nf->lru_lock); break; } q = list_first_entry(&nf->lru_list, struct inet_frag_queue, lru_list); atomic_inc(&q->refcnt); - read_unlock(&f->lock); + spin_unlock(&nf->lru_lock); spin_lock(&q->lock); if (!(q->last_in & INET_FRAG_COMPLETE)) @@ -233,9 +235,9 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, atomic_inc(&qp->refcnt); hlist_add_head(&qp->list, &f->hash[hash]); - list_add_tail(&qp->lru_list, &nf->lru_list); nf->nqueues++; write_unlock(&f->lock); + inet_frag_lru_add(nf, qp); return qp; } @@ -250,7 +252,8 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, q->net = nf; f->constructor(q, arg); - atomic_add(f->qsize, &nf->mem); + add_frag_mem_limit(q, f->qsize); + setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); atomic_set(&q->refcnt, 1); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index fa3ae814871..0ce0595d986 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -39,6 +39,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, write_pnet(&tb->ib_net, hold_net(net)); tb->port = snum; tb->fastreuse = 0; + tb->fastreuseport = 0; tb->num_owners = 0; INIT_HLIST_HEAD(&tb->owners); hlist_add_head(&tb->node, &head->chain); @@ -151,16 +152,16 @@ static inline int compute_score(struct sock *sk, struct net *net, if (net_eq(sock_net(sk), net) && inet->inet_num == hnum && !ipv6_only_sock(sk)) { __be32 rcv_saddr = inet->inet_rcv_saddr; - score = sk->sk_family == PF_INET ? 1 : 0; + score = sk->sk_family == PF_INET ? 2 : 1; if (rcv_saddr) { if (rcv_saddr != daddr) return -1; - score += 2; + score += 4; } if (sk->sk_bound_dev_if) { if (sk->sk_bound_dev_if != dif) return -1; - score += 2; + score += 4; } } return score; @@ -176,6 +177,7 @@ static inline int compute_score(struct sock *sk, struct net *net, struct sock *__inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, + const __be32 saddr, __be16 sport, const __be32 daddr, const unsigned short hnum, const int dif) { @@ -183,17 +185,29 @@ struct sock *__inet_lookup_listener(struct net *net, struct hlist_nulls_node *node; unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; - int score, hiscore; + int score, hiscore, matches = 0, reuseport = 0; + u32 phash = 0; rcu_read_lock(); begin: result = NULL; - hiscore = -1; + hiscore = 0; sk_nulls_for_each_rcu(sk, node, &ilb->head) { score = compute_score(sk, net, hnum, daddr, dif); if (score > hiscore) { result = sk; hiscore = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + phash = inet_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; + } + } else if (score == hiscore && reuseport) { + matches++; + if (((u64)phash * matches) >> 32 == 0) + result = sk; + phash = next_pseudo_random32(phash); } } /* @@ -501,7 +515,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, inet_bind_bucket_for_each(tb, node, &head->chain) { if (net_eq(ib_net(tb), net) && tb->port == port) { - if (tb->fastreuse >= 0) + if (tb->fastreuse >= 0 || + tb->fastreuseport >= 0) goto next_port; WARN_ON(hlist_empty(&tb->owners)); if (!check_established(death_row, sk, @@ -518,6 +533,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, break; } tb->fastreuse = -1; + tb->fastreuseport = -1; goto ok; next_port: diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index eb9d63a570c..1211613c6c3 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -122,7 +122,7 @@ int ip_frag_nqueues(struct net *net) int ip_frag_mem(struct net *net) { - return atomic_read(&net->ipv4.frags.mem); + return sum_frag_mem_limit(&net->ipv4.frags); } static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, @@ -161,13 +161,6 @@ static bool ip4_frag_match(struct inet_frag_queue *q, void *a) qp->user == arg->user; } -/* Memory Tracking Functions. */ -static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb) -{ - atomic_sub(skb->truesize, &nf->mem); - kfree_skb(skb); -} - static void ip4_frag_init(struct inet_frag_queue *q, void *a) { struct ipq *qp = container_of(q, struct ipq, q); @@ -340,6 +333,7 @@ static inline int ip_frag_too_far(struct ipq *qp) static int ip_frag_reinit(struct ipq *qp) { struct sk_buff *fp; + unsigned int sum_truesize = 0; if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) { atomic_inc(&qp->q.refcnt); @@ -349,9 +343,12 @@ static int ip_frag_reinit(struct ipq *qp) fp = qp->q.fragments; do { struct sk_buff *xp = fp->next; - frag_kfree_skb(qp->q.net, fp); + + sum_truesize += fp->truesize; + kfree_skb(fp); fp = xp; } while (fp); + sub_frag_mem_limit(&qp->q, sum_truesize); qp->q.last_in = 0; qp->q.len = 0; @@ -496,7 +493,8 @@ found: qp->q.fragments = next; qp->q.meat -= free_it->len; - frag_kfree_skb(qp->q.net, free_it); + sub_frag_mem_limit(&qp->q, free_it->truesize); + kfree_skb(free_it); } } @@ -519,7 +517,7 @@ found: qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; qp->ecn |= ecn; - atomic_add(skb->truesize, &qp->q.net->mem); + add_frag_mem_limit(&qp->q, skb->truesize); if (offset == 0) qp->q.last_in |= INET_FRAG_FIRST_IN; @@ -531,9 +529,7 @@ found: qp->q.meat == qp->q.len) return ip_frag_reasm(qp, prev, dev); - write_lock(&ip4_frags.lock); - list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list); - write_unlock(&ip4_frags.lock); + inet_frag_lru_move(&qp->q); return -EINPROGRESS; err: @@ -617,7 +613,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, head->len -= clone->len; clone->csum = 0; clone->ip_summed = head->ip_summed; - atomic_add(clone->truesize, &qp->q.net->mem); + add_frag_mem_limit(&qp->q, clone->truesize); } skb_push(head, head->data - skb_network_header(head)); @@ -645,7 +641,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, } fp = next; } - atomic_sub(sum_truesize, &qp->q.net->mem); + sub_frag_mem_limit(&qp->q, sum_truesize); head->next = NULL; head->dev = dev; @@ -851,14 +847,22 @@ static inline void ip4_frags_ctl_register(void) static int __net_init ipv4_frags_init_net(struct net *net) { - /* - * Fragment cache limits. We will commit 256K at one time. Should we - * cross that limit we will prune down to 192K. This should cope with - * even the most extreme cases without allowing an attacker to - * measurably harm machine performance. + /* Fragment cache limits. + * + * The fragment memory accounting code, (tries to) account for + * the real memory usage, by measuring both the size of frag + * queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue)) + * and the SKB's truesize. + * + * A 64K fragment consumes 129736 bytes (44*2944)+200 + * (1500 truesize == 2944, sizeof(struct ipq) == 200) + * + * We will commit 4MB at one time. Should we cross that limit + * we will prune down to 3MB, making room for approx 8 big 64K + * fragments 8x128k. */ - net->ipv4.frags.high_thresh = 256 * 1024; - net->ipv4.frags.low_thresh = 192 * 1024; + net->ipv4.frags.high_thresh = 4 * 1024 * 1024; + net->ipv4.frags.low_thresh = 3 * 1024 * 1024; /* * Important NOTE! Fragment queue must be destroyed before MSL expires. * RFC791 is wrong proposing to prolongate timer each fragment arrival diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index e81b1caf2ea..00a14b9864e 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -738,7 +738,7 @@ drop: static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - const struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph; const struct iphdr *tiph; struct flowi4 fl4; u8 tos; @@ -756,6 +756,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev skb_checksum_help(skb)) goto tx_error; + old_iph = ip_hdr(skb); + if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -818,8 +820,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev ttl = tiph->ttl; tos = tiph->tos; - if (tos == 1) { - tos = 0; + if (tos & 0x1) { + tos &= ~0x1; if (skb->protocol == htons(ETH_P_IP)) tos = old_iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 191fc24a745..8f024d41eef 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -472,7 +472,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ - const struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph; struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; @@ -486,6 +486,8 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb_checksum_help(skb)) goto tx_error; + old_iph = ip_hdr(skb); + if (tos & 1) tos = old_iph->tos; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a9454cbd953..7085b9b51e7 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -828,6 +828,49 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, return NULL; } +/* Look for a (*,*,oif) entry */ +static struct mfc_cache *ipmr_cache_find_any_parent(struct mr_table *mrt, + int vifi) +{ + int line = MFC_HASH(htonl(INADDR_ANY), htonl(INADDR_ANY)); + struct mfc_cache *c; + + list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) + if (c->mfc_origin == htonl(INADDR_ANY) && + c->mfc_mcastgrp == htonl(INADDR_ANY) && + c->mfc_un.res.ttls[vifi] < 255) + return c; + + return NULL; +} + +/* Look for a (*,G) entry */ +static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt, + __be32 mcastgrp, int vifi) +{ + int line = MFC_HASH(mcastgrp, htonl(INADDR_ANY)); + struct mfc_cache *c, *proxy; + + if (mcastgrp == htonl(INADDR_ANY)) + goto skip; + + list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) + if (c->mfc_origin == htonl(INADDR_ANY) && + c->mfc_mcastgrp == mcastgrp) { + if (c->mfc_un.res.ttls[vifi] < 255) + return c; + + /* It's ok if the vifi is part of the static tree */ + proxy = ipmr_cache_find_any_parent(mrt, + c->mfc_parent); + if (proxy && proxy->mfc_un.res.ttls[vifi] < 255) + return c; + } + +skip: + return ipmr_cache_find_any_parent(mrt, vifi); +} + /* * Allocate a multicast cache entry */ @@ -1053,7 +1096,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) * MFC cache manipulation by user space mroute daemon */ -static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) +static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) { int line; struct mfc_cache *c, *next; @@ -1062,7 +1105,8 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && - c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { + c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr && + (parent == -1 || parent == c->mfc_parent)) { list_del_rcu(&c->list); mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_cache_free(c); @@ -1073,7 +1117,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) } static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, - struct mfcctl *mfc, int mrtsock) + struct mfcctl *mfc, int mrtsock, int parent) { bool found = false; int line; @@ -1086,7 +1130,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, list_for_each_entry(c, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && - c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { + c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr && + (parent == -1 || parent == c->mfc_parent)) { found = true; break; } @@ -1103,7 +1148,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, return 0; } - if (!ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) + if (mfc->mfcc_mcastgrp.s_addr != htonl(INADDR_ANY) && + !ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) return -EINVAL; c = ipmr_cache_alloc(); @@ -1218,7 +1264,7 @@ static void mrtsock_destruct(struct sock *sk) int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { - int ret; + int ret, parent = 0; struct vifctl vif; struct mfcctl mfc; struct net *net = sock_net(sk); @@ -1287,16 +1333,22 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi */ case MRT_ADD_MFC: case MRT_DEL_MFC: + parent = -1; + case MRT_ADD_MFC_PROXY: + case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) return -EINVAL; if (copy_from_user(&mfc, optval, sizeof(mfc))) return -EFAULT; + if (parent == 0) + parent = mfc.mfcc_parent; rtnl_lock(); - if (optname == MRT_DEL_MFC) - ret = ipmr_mfc_delete(mrt, &mfc); + if (optname == MRT_DEL_MFC || optname == MRT_DEL_MFC_PROXY) + ret = ipmr_mfc_delete(mrt, &mfc, parent); else ret = ipmr_mfc_add(net, mrt, &mfc, - sk == rtnl_dereference(mrt->mroute_sk)); + sk == rtnl_dereference(mrt->mroute_sk), + parent); rtnl_unlock(); return ret; /* @@ -1749,17 +1801,28 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, { int psend = -1; int vif, ct; + int true_vifi = ipmr_find_vif(mrt, skb->dev); vif = cache->mfc_parent; cache->mfc_un.res.pkt++; cache->mfc_un.res.bytes += skb->len; + if (cache->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { + struct mfc_cache *cache_proxy; + + /* For an (*,G) entry, we only check that the incomming + * interface is part of the static tree. + */ + cache_proxy = ipmr_cache_find_any_parent(mrt, vif); + if (cache_proxy && + cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + goto forward; + } + /* * Wrong interface: drop packet and (maybe) send PIM assert. */ if (mrt->vif_table[vif].dev != skb->dev) { - int true_vifi; - if (rt_is_output_route(skb_rtable(skb))) { /* It is our own packet, looped back. * Very complicated situation... @@ -1776,7 +1839,6 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, } cache->mfc_un.res.wrong_if++; - true_vifi = ipmr_find_vif(mrt, skb->dev); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -1794,15 +1856,34 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, goto dont_forward; } +forward: mrt->vif_table[vif].pkt_in++; mrt->vif_table[vif].bytes_in += skb->len; /* * Forward the frame */ + if (cache->mfc_origin == htonl(INADDR_ANY) && + cache->mfc_mcastgrp == htonl(INADDR_ANY)) { + if (true_vifi >= 0 && + true_vifi != cache->mfc_parent && + ip_hdr(skb)->ttl > + cache->mfc_un.res.ttls[cache->mfc_parent]) { + /* It's an (*,*) entry and the packet is not coming from + * the upstream: forward the packet to the upstream + * only. + */ + psend = cache->mfc_parent; + goto last_forward; + } + goto dont_forward; + } for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { - if (ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { + /* For (*,G) entry, don't forward to the incoming interface */ + if ((cache->mfc_origin != htonl(INADDR_ANY) || + ct != true_vifi) && + ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); @@ -1813,6 +1894,7 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, psend = ct; } } +last_forward: if (psend != -1) { if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); @@ -1902,6 +1984,13 @@ int ip_mr_input(struct sk_buff *skb) /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); + if (cache == NULL) { + int vif = ipmr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr, + vif); + } /* * No usable cache entry @@ -2107,7 +2196,12 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, rcu_read_lock(); cache = ipmr_cache_find(mrt, saddr, daddr); + if (cache == NULL && skb->dev) { + int vif = ipmr_find_vif(mrt, skb->dev); + if (vif >= 0) + cache = ipmr_cache_find_any(mrt, daddr, vif); + } if (cache == NULL) { struct sk_buff *skb2; struct iphdr *iph; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 3ea4127404d..7dc6a974359 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -901,7 +901,7 @@ static int get_info(struct net *net, void __user *user, #endif t = try_then_request_module(xt_find_table_lock(net, NFPROTO_ARP, name), "arptable_%s", name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { struct arpt_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT @@ -958,7 +958,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, } t = xt_find_table_lock(net, NFPROTO_ARP, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", @@ -1001,7 +1001,7 @@ static int __do_replace(struct net *net, const char *name, t = try_then_request_module(xt_find_table_lock(net, NFPROTO_ARP, name), "arptable_%s", name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free_newinfo_counters_untrans; } @@ -1158,7 +1158,7 @@ static int do_add_counters(struct net *net, const void __user *user, } t = xt_find_table_lock(net, NFPROTO_ARP, name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } @@ -1646,7 +1646,7 @@ static int compat_get_entries(struct net *net, xt_compat_lock(NFPROTO_ARP); t = xt_find_table_lock(net, NFPROTO_ARP, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 17c5e06da66..3efcf87400c 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1090,7 +1090,7 @@ static int get_info(struct net *net, void __user *user, #endif t = try_then_request_module(xt_find_table_lock(net, AF_INET, name), "iptable_%s", name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { struct ipt_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT @@ -1149,7 +1149,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr, } t = xt_find_table_lock(net, AF_INET, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", private->number); if (get.size == private->size) @@ -1189,7 +1189,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, t = try_then_request_module(xt_find_table_lock(net, AF_INET, name), "iptable_%s", name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free_newinfo_counters_untrans; } @@ -1347,7 +1347,7 @@ do_add_counters(struct net *net, const void __user *user, } t = xt_find_table_lock(net, AF_INET, name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } @@ -1931,7 +1931,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr, xt_compat_lock(AF_INET); t = xt_find_table_lock(net, AF_INET, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; duprintf("t->private->number = %u\n", private->number); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index fcdd0c2406e..48990ada0e1 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -420,54 +420,43 @@ static int ipv4_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_tcp4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_tcp4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_tcp4 :protocol register failed\n"); + pr_err("nf_conntrack_tcp4: pernet registration failed\n"); goto out_tcp; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_udp4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udp4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_udp4 :protocol register failed\n"); + pr_err("nf_conntrack_udp4: pernet registration failed\n"); goto out_udp; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_icmp); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_icmp); if (ret < 0) { - pr_err("nf_conntrack_l4proto_icmp4 :protocol register failed\n"); + pr_err("nf_conntrack_icmp4: pernet registration failed\n"); goto out_icmp; } - ret = nf_conntrack_l3proto_register(net, - &nf_conntrack_l3proto_ipv4); + ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv4); if (ret < 0) { - pr_err("nf_conntrack_l3proto_ipv4 :protocol register failed\n"); + pr_err("nf_conntrack_ipv4: pernet registration failed\n"); goto out_ipv4; } return 0; out_ipv4: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_icmp); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmp); out_icmp: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_udp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp4); out_udp: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_tcp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp4); out_tcp: return ret; } static void ipv4_net_exit(struct net *net) { - nf_conntrack_l3proto_unregister(net, - &nf_conntrack_l3proto_ipv4); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_icmp); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_udp4); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_tcp4); + nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmp); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp4); } static struct pernet_operations ipv4_net_ops = { @@ -500,16 +489,49 @@ static int __init nf_conntrack_l3proto_ipv4_init(void) pr_err("nf_conntrack_ipv4: can't register hooks.\n"); goto cleanup_pernet; } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp4); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register tcp4 proto.\n"); + goto cleanup_hooks; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp4); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register udp4 proto.\n"); + goto cleanup_tcp4; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmp); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register icmpv4 proto.\n"); + goto cleanup_udp4; + } + + ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv4); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register ipv4 proto.\n"); + goto cleanup_icmpv4; + } + #if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) ret = nf_conntrack_ipv4_compat_init(); if (ret < 0) - goto cleanup_hooks; + goto cleanup_proto; #endif return ret; #if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) + cleanup_proto: + nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4); +#endif + cleanup_icmpv4: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmp); + cleanup_udp4: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4); + cleanup_tcp4: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4); cleanup_hooks: nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); -#endif cleanup_pernet: unregister_pernet_subsys(&ipv4_net_ops); cleanup_sockopt: @@ -523,6 +545,10 @@ static void __exit nf_conntrack_l3proto_ipv4_fini(void) #if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) nf_conntrack_ipv4_compat_fini(); #endif + nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmp); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4); nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); unregister_pernet_subsys(&ipv4_net_ops); nf_unregister_sockopt(&so_getorigdst); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index b236ef04914..ef54377fb11 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -232,7 +232,8 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, * * return false if we decode an option that should not be. */ -bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, bool *ecn_ok) +bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, + struct net *net, bool *ecn_ok) { /* echoed timestamp, lowest bits contain options */ u32 options = tcp_opt->rcv_tsecr & TSMASK; @@ -247,7 +248,7 @@ bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, bool *ecn_ok) tcp_opt->sack_ok = (options & (1 << 4)) ? TCP_SACK_SEEN : 0; *ecn_ok = (options >> 5) & 1; - if (*ecn_ok && !sysctl_tcp_ecn) + if (*ecn_ok && !net->ipv4.sysctl_tcp_ecn) return false; if (tcp_opt->sack_ok && !sysctl_tcp_sack) @@ -295,7 +296,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, memset(&tcp_opt, 0, sizeof(tcp_opt)); tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL); - if (!cookie_check_timestamp(&tcp_opt, &ecn_ok)) + if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok)) goto out; ret = NULL; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d84400b6504..2622707602d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -27,6 +27,7 @@ #include <net/tcp_memcontrol.h> static int zero; +static int one = 1; static int two = 2; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; @@ -232,8 +233,8 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, return 0; } -int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer, - size_t *lenp, loff_t *ppos) +static int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer, + size_t *lenp, loff_t *ppos) { ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; @@ -538,13 +539,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .procname = "tcp_ecn", - .data = &sysctl_tcp_ecn, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_dsack", .data = &sysctl_tcp_dsack, .maxlen = sizeof(int), @@ -556,14 +550,16 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_wmem, .maxlen = sizeof(sysctl_tcp_wmem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "tcp_rmem", .data = &sysctl_tcp_rmem, .maxlen = sizeof(sysctl_tcp_rmem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "tcp_app_win", @@ -786,7 +782,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_rmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &one }, { .procname = "udp_wmem_min", @@ -794,7 +790,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_wmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &one }, { } }; @@ -850,6 +846,13 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = ipv4_ping_group_range, }, { + .procname = "tcp_ecn", + .data = &init_net.ipv4.sysctl_tcp_ecn, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "tcp_mem", .maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem), .mode = 0644, @@ -882,6 +885,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) &net->ipv4.sysctl_icmp_ratemask; table[6].data = &net->ipv4.sysctl_ping_group_range; + table[7].data = + &net->ipv4.sysctl_tcp_ecn; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2aa69c8ae60..3ec1f69c5ce 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -896,6 +896,8 @@ new_segment: skb_fill_page_desc(skb, i, page, offset, copy); } + skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG; + skb->len += copy; skb->data_len += copy; skb->truesize += copy; @@ -3032,6 +3034,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | + SKB_GSO_SHARED_FRAG | 0) || !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))) goto out; @@ -3243,7 +3246,7 @@ __tcp_alloc_md5sig_pool(struct sock *sk) struct crypto_hash *hash; hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (!hash || IS_ERR(hash)) + if (IS_ERR_OR_NULL(hash)) goto out_free; per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 18f97ca76b0..492c7cfe145 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -81,8 +81,6 @@ int sysctl_tcp_sack __read_mostly = 1; int sysctl_tcp_fack __read_mostly = 1; int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH; EXPORT_SYMBOL(sysctl_tcp_reordering); -int sysctl_tcp_ecn __read_mostly = 2; -EXPORT_SYMBOL(sysctl_tcp_ecn); int sysctl_tcp_dsack __read_mostly = 1; int sysctl_tcp_app_win __read_mostly = 31; int sysctl_tcp_adv_win_scale __read_mostly = 1; @@ -1242,13 +1240,13 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, */ if (!skb_shinfo(prev)->gso_size) { skb_shinfo(prev)->gso_size = mss; - skb_shinfo(prev)->gso_type = sk->sk_gso_type; + skb_shinfo(prev)->gso_type |= sk->sk_gso_type; } /* CHECKME: To clear or not to clear? Mimics normal skb currently */ if (skb_shinfo(skb)->gso_segs <= 1) { skb_shinfo(skb)->gso_size = 0; - skb_shinfo(skb)->gso_type = 0; + skb_shinfo(skb)->gso_type &= SKB_GSO_SHARED_FRAG; } /* Difference in this won't matter, both ACKed by the same cumul. ACK */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 70b09ef2463..5a1cfc692df 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -656,7 +656,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) * no RST generated if md5 hash doesn't match. */ sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev), - &tcp_hashinfo, ip_hdr(skb)->daddr, + &tcp_hashinfo, ip_hdr(skb)->saddr, + th->source, ip_hdr(skb)->daddr, ntohs(th->source), inet_iif(skb)); /* don't send rst if it can't find key */ if (!sk1) @@ -1567,7 +1568,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, skb); + TCP_ECN_create_request(req, skb, sock_net(sk)); if (want_cookie) { isn = cookie_v4_init_sequence(sk, skb, &req->mss); @@ -2073,6 +2074,7 @@ do_time_wait: case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, + iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); if (sk2) { @@ -2887,6 +2889,7 @@ EXPORT_SYMBOL(tcp_prot); static int __net_init tcp_sk_init(struct net *net) { + net->ipv4.sysctl_tcp_ecn = 2; return 0; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5d451593ef1..367e2ec01da 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -314,7 +314,7 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); tp->ecn_flags = 0; - if (sysctl_tcp_ecn == 1) { + if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; } @@ -1133,6 +1133,7 @@ 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) { + skb_shinfo(skb)->gso_type &= SKB_GSO_SHARED_FRAG; if (skb->len <= mss_now || !sk_can_gso(sk) || skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal @@ -1140,11 +1141,10 @@ static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, */ skb_shinfo(skb)->gso_segs = 1; skb_shinfo(skb)->gso_size = 0; - skb_shinfo(skb)->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; + skb_shinfo(skb)->gso_type |= sk->sk_gso_type; } } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1f4d405eafb..6791aac06ea 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -139,6 +139,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, { struct sock *sk2; struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); sk_nulls_for_each(sk2, node, &hslot->head) if (net_eq(sock_net(sk2), net) && @@ -147,6 +148,8 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (!sk2->sk_reuseport || !sk->sk_reuseport || + !uid_eq(uid, sock_i_uid(sk2))) && (*saddr_comp)(sk, sk2)) { if (bitmap) __set_bit(udp_sk(sk2)->udp_port_hash >> log, @@ -169,6 +172,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, { struct sock *sk2; struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); int res = 0; spin_lock(&hslot2->lock); @@ -179,6 +183,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (!sk2->sk_reuseport || !sk->sk_reuseport || + !uid_eq(uid, sock_i_uid(sk2))) && (*saddr_comp)(sk, sk2)) { res = 1; break; @@ -337,26 +343,26 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, !ipv6_only_sock(sk)) { struct inet_sock *inet = inet_sk(sk); - score = (sk->sk_family == PF_INET ? 1 : 0); + score = (sk->sk_family == PF_INET ? 2 : 1); if (inet->inet_rcv_saddr) { if (inet->inet_rcv_saddr != daddr) return -1; - score += 2; + score += 4; } if (inet->inet_daddr) { if (inet->inet_daddr != saddr) return -1; - score += 2; + score += 4; } if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; - score += 2; + score += 4; } if (sk->sk_bound_dev_if) { if (sk->sk_bound_dev_if != dif) return -1; - score += 2; + score += 4; } } return score; @@ -365,7 +371,6 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, /* * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num) */ -#define SCORE2_MAX (1 + 2 + 2 + 2) static inline int compute_score2(struct sock *sk, struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif) @@ -380,21 +385,21 @@ static inline int compute_score2(struct sock *sk, struct net *net, if (inet->inet_num != hnum) return -1; - score = (sk->sk_family == PF_INET ? 1 : 0); + score = (sk->sk_family == PF_INET ? 2 : 1); if (inet->inet_daddr) { if (inet->inet_daddr != saddr) return -1; - score += 2; + score += 4; } if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; - score += 2; + score += 4; } if (sk->sk_bound_dev_if) { if (sk->sk_bound_dev_if != dif) return -1; - score += 2; + score += 4; } } return score; @@ -409,19 +414,29 @@ static struct sock *udp4_lib_lookup2(struct net *net, { struct sock *sk, *result; struct hlist_nulls_node *node; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; begin: result = NULL; - badness = -1; + badness = 0; udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { score = compute_score2(sk, net, saddr, sport, daddr, hnum, dif); if (score > badness) { result = sk; badness = score; - if (score == SCORE2_MAX) - goto exact_match; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet_ehashfn(net, daddr, hnum, + saddr, htons(sport)); + matches = 1; + } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@ -431,9 +446,7 @@ begin: */ if (get_nulls_value(node) != slot2) goto begin; - if (result) { -exact_match: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, @@ -457,7 +470,8 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, unsigned short hnum = ntohs(dport); unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; rcu_read_lock(); if (hslot->count > 10) { @@ -486,13 +500,24 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, } begin: result = NULL; - badness = -1; + badness = 0; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet_ehashfn(net, daddr, hnum, + saddr, htons(sport)); + matches = 1; + } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@ -971,7 +996,7 @@ back_from_confirm: sizeof(struct udphdr), &ipc, &rt, msg->msg_flags); err = PTR_ERR(skb); - if (skb && !IS_ERR(skb)) + if (!IS_ERR_OR_NULL(skb)) err = udp_send_skb(skb, fl4); goto out; } diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 4ea244891b5..309af19a0a0 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -40,7 +40,7 @@ obj-$(CONFIG_IPV6_SIT) += sit.o obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o obj-$(CONFIG_IPV6_GRE) += ip6_gre.o -obj-y += addrconf_core.o exthdrs_core.o +obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload) obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 420e5632638..7f7332b4469 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -110,10 +110,6 @@ static inline u32 cstamp_delta(unsigned long cstamp) return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; } -#define ADDRCONF_TIMER_FUZZ_MINUS (HZ > 50 ? HZ/50 : 1) -#define ADDRCONF_TIMER_FUZZ (HZ / 4) -#define ADDRCONF_TIMER_FUZZ_MAX (HZ) - #ifdef CONFIG_SYSCTL static void addrconf_sysctl_register(struct inet6_dev *idev); static void addrconf_sysctl_unregister(struct inet6_dev *idev); @@ -1051,7 +1047,7 @@ retry: ipv6_add_addr(idev, &addr, tmp_plen, ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK, addr_flags) : NULL; - if (!ift || IS_ERR(ift)) { + if (IS_ERR_OR_NULL(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); pr_info("%s: retry temporary address regeneration\n", __func__); @@ -2079,7 +2075,7 @@ ok: addr_type&IPV6_ADDR_SCOPE_MASK, addr_flags); - if (!ifp || IS_ERR(ifp)) { + if (IS_ERR_OR_NULL(ifp)) { in6_dev_put(in6_dev); return; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b043c60429b..6b793bfc0e1 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -811,11 +811,10 @@ static struct pernet_operations inet6_net_ops = { static int __init inet6_init(void) { - struct sk_buff *dummy_skb; struct list_head *r; int err = 0; - BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb)); /* Register the socket-side information for inet6_create. */ for (r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 8edf2601065..33be36398a7 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -30,6 +30,7 @@ #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/tcp_states.h> +#include <net/dsfield.h> #include <linux/errqueue.h> #include <asm/uaccess.h> @@ -356,12 +357,11 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) sin->sin6_port = serr->port; sin->sin6_scope_id = 0; if (skb->protocol == htons(ETH_P_IPV6)) { - sin->sin6_addr = - *(struct in6_addr *)(nh + serr->addr_offset); + const struct ipv6hdr *ip6h = container_of((struct in6_addr *)(nh + serr->addr_offset), + struct ipv6hdr, daddr); + sin->sin6_addr = ip6h->daddr; if (np->sndflow) - sin->sin6_flowinfo = - (*(__be32 *)(nh + serr->addr_offset - 24) & - IPV6_FLOWINFO_MASK); + sin->sin6_flowinfo = ip6_flowinfo(ip6h); if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = IP6CB(skb)->iif; } else { @@ -488,13 +488,14 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) } if (np->rxopt.bits.rxtclass) { - int tclass = ipv6_tclass(ipv6_hdr(skb)); + int tclass = ipv6_get_dsfield(ipv6_hdr(skb)); put_cmsg(msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); } - if (np->rxopt.bits.rxflow && (*(__be32 *)nh & IPV6_FLOWINFO_MASK)) { - __be32 flowinfo = *(__be32 *)nh & IPV6_FLOWINFO_MASK; - put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); + if (np->rxopt.bits.rxflow) { + __be32 flowinfo = ip6_flowinfo((struct ipv6hdr *)nh); + if (flowinfo) + put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); } /* HbH is allowed only once */ diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 473f628f9f2..07a7d65a7cb 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -553,7 +553,8 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) const unsigned char *nh = skb_network_header(skb); if (nh[optoff + 1] == 2) { - IP6CB(skb)->ra = optoff; + IP6CB(skb)->flags |= IP6SKB_ROUTERALERT; + memcpy(&IP6CB(skb)->ra, nh + optoff + 2, sizeof(IP6CB(skb)->ra)); return true; } LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_ra: wrong RA length %d\n", diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 30647857a37..b386a2ce4c6 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -32,6 +32,9 @@ int inet6_csk_bind_conflict(const struct sock *sk, { const struct sock *sk2; const struct hlist_node *node; + int reuse = sk->sk_reuse; + int reuseport = sk->sk_reuseport; + kuid_t uid = sock_i_uid((struct sock *)sk); /* We must walk the whole port owner list in this case. -DaveM */ /* @@ -42,11 +45,17 @@ int inet6_csk_bind_conflict(const struct sock *sk, if (sk != sk2 && (!sk->sk_bound_dev_if || !sk2->sk_bound_dev_if || - sk->sk_bound_dev_if == sk2->sk_bound_dev_if) && - (!sk->sk_reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) && - ipv6_rcv_saddr_equal(sk, sk2)) - break; + sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { + if ((!reuse || !sk2->sk_reuse || + sk2->sk_state == TCP_LISTEN) && + (!reuseport || !sk2->sk_reuseport || + (sk2->sk_state != TCP_TIME_WAIT && + !uid_eq(uid, + sock_i_uid((struct sock *)sk2))))) { + if (ipv6_rcv_saddr_equal(sk, sk2)) + break; + } + } } return node != NULL; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index dea17fd28e5..32b4a1675d8 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -158,25 +158,38 @@ static inline int compute_score(struct sock *sk, struct net *net, } struct sock *inet6_lookup_listener(struct net *net, - struct inet_hashinfo *hashinfo, const struct in6_addr *daddr, + struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, + const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif) { struct sock *sk; const struct hlist_nulls_node *node; struct sock *result; - int score, hiscore; + int score, hiscore, matches = 0, reuseport = 0; + u32 phash = 0; unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; rcu_read_lock(); begin: result = NULL; - hiscore = -1; + hiscore = 0; sk_nulls_for_each(sk, node, &ilb->head) { score = compute_score(sk, net, hnum, daddr, dif); if (score > hiscore) { hiscore = score; result = sk; + reuseport = sk->sk_reuseport; + if (reuseport) { + phash = inet6_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; + } + } else if (score == hiscore && reuseport) { + matches++; + if (((u64)phash * matches) >> 32 == 0) + result = sk; + phash = next_pseudo_random32(phash); } } /* diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c new file mode 100644 index 00000000000..72d198b8e4d --- /dev/null +++ b/net/ipv6/ip6_checksum.c @@ -0,0 +1,97 @@ +#include <net/ip.h> +#include <net/udp.h> +#include <net/udplite.h> +#include <asm/checksum.h> + +#ifndef _HAVE_ARCH_IPV6_CSUM +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, unsigned short proto, + __wsum csum) +{ + + int carry; + __u32 ulen; + __u32 uproto; + __u32 sum = (__force u32)csum; + + sum += (__force u32)saddr->s6_addr32[0]; + carry = (sum < (__force u32)saddr->s6_addr32[0]); + sum += carry; + + sum += (__force u32)saddr->s6_addr32[1]; + carry = (sum < (__force u32)saddr->s6_addr32[1]); + sum += carry; + + sum += (__force u32)saddr->s6_addr32[2]; + carry = (sum < (__force u32)saddr->s6_addr32[2]); + sum += carry; + + sum += (__force u32)saddr->s6_addr32[3]; + carry = (sum < (__force u32)saddr->s6_addr32[3]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[0]; + carry = (sum < (__force u32)daddr->s6_addr32[0]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[1]; + carry = (sum < (__force u32)daddr->s6_addr32[1]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[2]; + carry = (sum < (__force u32)daddr->s6_addr32[2]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[3]; + carry = (sum < (__force u32)daddr->s6_addr32[3]); + sum += carry; + + ulen = (__force u32)htonl((__u32) len); + sum += ulen; + carry = (sum < ulen); + sum += carry; + + uproto = (__force u32)htonl(proto); + sum += uproto; + carry = (sum < uproto); + sum += carry; + + return csum_fold((__force __wsum)sum); +} +EXPORT_SYMBOL(csum_ipv6_magic); +#endif + +int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) +{ + int err; + + UDP_SKB_CB(skb)->partial_cov = 0; + UDP_SKB_CB(skb)->cscov = skb->len; + + if (proto == IPPROTO_UDPLITE) { + err = udplite_checksum_init(skb, uh); + if (err) + return err; + } + + if (uh->check == 0) { + /* RFC 2460 section 8.1 says that we SHOULD log + this error. Well, it is reasonable. + */ + LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); + return 1; + } + if (skb->ip_summed == CHECKSUM_COMPLETE && + !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, + skb->len, proto, skb->csum)) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (!skb_csum_unnecessary(skb)) + skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len, proto, 0)); + + return 0; +} +EXPORT_SYMBOL(udp6_csum_init); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c727e471275..db91fe3466a 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -772,9 +772,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, * Push down and install the IP header. */ ipv6h = ipv6_hdr(skb); - *(__be32 *)ipv6h = fl6->flowlabel | htonl(0x60000000); - dsfield = INET_ECN_encapsulate(0, dsfield); - ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield); + ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), fl6->flowlabel); ipv6h->hop_limit = tunnel->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; @@ -1240,7 +1238,7 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen); __be16 *p = (__be16 *)(ipv6h+1); - *(__be32 *)ipv6h = t->fl.u.ip6.flowlabel | htonl(0x60000000); + ip6_flow_hdr(ipv6h, 0, t->fl.u.ip6.flowlabel); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = NEXTHDR_GRE; ipv6h->saddr = t->parms.laddr; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index a52d864d562..4ac5bf30e16 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -212,7 +212,7 @@ resubmit: if (ipv6_addr_is_multicast(&hdr->daddr) && !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, &hdr->saddr) && - !ipv6_is_mld(skb, nexthdr)) + !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) goto discard; } if (!(ipprot->flags & INET6_PROTO_NOPOLICY) && @@ -280,10 +280,8 @@ int ip6_mc_input(struct sk_buff *skb) struct inet6_skb_parm *opt = IP6CB(skb); /* Check for MLD */ - if (unlikely(opt->ra)) { + if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) { /* Check if this is a mld message */ - u8 *ptr = skb_network_header(skb) + opt->ra; - struct icmp6hdr *icmp6; u8 nexthdr = hdr->nexthdr; __be16 frag_off; int offset; @@ -291,7 +289,7 @@ int ip6_mc_input(struct sk_buff *skb) /* Check if the value of Router Alert * is for MLD (0x0000). */ - if ((ptr[2] | ptr[3]) == 0) { + if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) { deliver = false; if (!ipv6_ext_hdr(nexthdr)) { @@ -303,24 +301,10 @@ int ip6_mc_input(struct sk_buff *skb) if (offset < 0) goto out; - if (nexthdr != IPPROTO_ICMPV6) + if (!ipv6_is_mld(skb, nexthdr, offset)) goto out; - if (!pskb_may_pull(skb, (skb_network_header(skb) + - offset + 1 - skb->data))) - goto out; - - icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset); - - switch (icmp6->icmp6_type) { - case ICMPV6_MGM_QUERY: - case ICMPV6_MGM_REPORT: - case ICMPV6_MGM_REDUCTION: - case ICMPV6_MLD2_REPORT: - deliver = true; - break; - } - goto out; + deliver = true; } /* unknown RA - process it normally */ } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index f26f0da7f09..d141fc32a2e 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -100,6 +100,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | + SKB_GSO_SHARED_FRAG | 0))) goto out; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 0c7c03d50dc..906b7e6dd7f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -56,8 +56,6 @@ #include <net/checksum.h> #include <linux/mroute6.h> -int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); - int __ip6_local_out(struct sk_buff *skb) { int len; @@ -88,7 +86,8 @@ static int ip6_finish_output2(struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct neighbour *neigh; - struct rt6_info *rt; + struct in6_addr *nexthop; + int ret; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@ -123,10 +122,17 @@ static int ip6_finish_output2(struct sk_buff *skb) skb->len); } - rt = (struct rt6_info *) dst; - neigh = rt->n; - if (neigh) - return dst_neigh_output(dst, neigh, skb); + rcu_read_lock_bh(); + nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); + if (unlikely(!neigh)) + neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); + if (!IS_ERR(neigh)) { + ret = dst_neigh_output(dst, neigh, skb); + rcu_read_unlock_bh(); + return ret; + } + rcu_read_unlock_bh(); IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -216,7 +222,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl6->flowlabel; + ip6_flow_hdr(hdr, tclass, fl6->flowlabel); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -246,39 +252,6 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, EXPORT_SYMBOL(ip6_xmit); -/* - * To avoid extra problems ND packets are send through this - * routine. It's code duplication but I really want to avoid - * extra checks since ipv6_build_header is used by TCP (which - * is for us performance critical) - */ - -int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev, - const struct in6_addr *saddr, const struct in6_addr *daddr, - int proto, int len) -{ - struct ipv6_pinfo *np = inet6_sk(sk); - struct ipv6hdr *hdr; - - skb->protocol = htons(ETH_P_IPV6); - skb->dev = dev; - - skb_reset_network_header(skb); - skb_put(skb, sizeof(struct ipv6hdr)); - hdr = ipv6_hdr(skb); - - *(__be32*)hdr = htonl(0x60000000); - - hdr->payload_len = htons(len); - hdr->nexthdr = proto; - hdr->hop_limit = np->hop_limit; - - hdr->saddr = *saddr; - hdr->daddr = *daddr; - - return 0; -} - static int ip6_call_ra_chain(struct sk_buff *skb, int sel) { struct ip6_ra_chain *ra; @@ -913,8 +886,12 @@ static int ip6_dst_lookup_tail(struct sock *sk, * dst entry of the nexthop router */ rt = (struct rt6_info *) *dst; - n = rt->n; - if (n && !(n->nud_state & NUD_VALID)) { + rcu_read_lock_bh(); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); + err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; + rcu_read_unlock_bh(); + + if (err) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; int redirect; @@ -1548,9 +1525,7 @@ int ip6_push_pending_frames(struct sock *sk) skb_reset_network_header(skb); hdr = ipv6_hdr(skb); - *(__be32*)hdr = fl6->flowlabel | - htonl(0x60000000 | ((int)np->cork.tclass << 20)); - + ip6_flow_hdr(hdr, np->cork.tclass, fl6->flowlabel); hdr->hop_limit = np->cork.hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a14f28b280f..fff83cbc197 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1030,9 +1030,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); - *(__be32*)ipv6h = fl6->flowlabel | htonl(0x60000000); - dsfield = INET_ECN_encapsulate(0, dsfield); - ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield); + ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), fl6->flowlabel); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 8fd154e5f07..351ce98e90d 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1017,6 +1017,50 @@ static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt, return NULL; } +/* Look for a (*,*,oif) entry */ +static struct mfc6_cache *ip6mr_cache_find_any_parent(struct mr6_table *mrt, + mifi_t mifi) +{ + int line = MFC6_HASH(&in6addr_any, &in6addr_any); + struct mfc6_cache *c; + + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) + if (ipv6_addr_any(&c->mf6c_origin) && + ipv6_addr_any(&c->mf6c_mcastgrp) && + (c->mfc_un.res.ttls[mifi] < 255)) + return c; + + return NULL; +} + +/* Look for a (*,G) entry */ +static struct mfc6_cache *ip6mr_cache_find_any(struct mr6_table *mrt, + struct in6_addr *mcastgrp, + mifi_t mifi) +{ + int line = MFC6_HASH(mcastgrp, &in6addr_any); + struct mfc6_cache *c, *proxy; + + if (ipv6_addr_any(mcastgrp)) + goto skip; + + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) + if (ipv6_addr_any(&c->mf6c_origin) && + ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) { + if (c->mfc_un.res.ttls[mifi] < 255) + return c; + + /* It's ok if the mifi is part of the static tree */ + proxy = ip6mr_cache_find_any_parent(mrt, + c->mf6c_parent); + if (proxy && proxy->mfc_un.res.ttls[mifi] < 255) + return c; + } + +skip: + return ip6mr_cache_find_any_parent(mrt, mifi); +} + /* * Allocate a multicast cache entry */ @@ -1247,7 +1291,8 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) * MFC6 cache manipulation by user space */ -static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc) +static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc, + int parent) { int line; struct mfc6_cache *c, *next; @@ -1256,7 +1301,9 @@ static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc) list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { + ipv6_addr_equal(&c->mf6c_mcastgrp, + &mfc->mf6cc_mcastgrp.sin6_addr) && + (parent == -1 || parent == c->mf6c_parent)) { write_lock_bh(&mrt_lock); list_del(&c->list); write_unlock_bh(&mrt_lock); @@ -1391,7 +1438,7 @@ void ip6_mr_cleanup(void) } static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, - struct mf6cctl *mfc, int mrtsock) + struct mf6cctl *mfc, int mrtsock, int parent) { bool found = false; int line; @@ -1413,7 +1460,9 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { + ipv6_addr_equal(&c->mf6c_mcastgrp, + &mfc->mf6cc_mcastgrp.sin6_addr) && + (parent == -1 || parent == mfc->mf6cc_parent)) { found = true; break; } @@ -1430,7 +1479,8 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, return 0; } - if (!ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) + if (!ipv6_addr_any(&mfc->mf6cc_mcastgrp.sin6_addr) && + !ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) return -EINVAL; c = ip6mr_cache_alloc(); @@ -1596,7 +1646,7 @@ struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { - int ret; + int ret, parent = 0; struct mif6ctl vif; struct mf6cctl mfc; mifi_t mifi; @@ -1653,15 +1703,21 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns */ case MRT6_ADD_MFC: case MRT6_DEL_MFC: + parent = -1; + case MRT6_ADD_MFC_PROXY: + case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) return -EINVAL; if (copy_from_user(&mfc, optval, sizeof(mfc))) return -EFAULT; + if (parent == 0) + parent = mfc.mf6cc_parent; rtnl_lock(); - if (optname == MRT6_DEL_MFC) - ret = ip6mr_mfc_delete(mrt, &mfc); + if (optname == MRT6_DEL_MFC || optname == MRT6_DEL_MFC_PROXY) + ret = ip6mr_mfc_delete(mrt, &mfc, parent); else - ret = ip6mr_mfc_add(net, mrt, &mfc, sk == mrt->mroute6_sk); + ret = ip6mr_mfc_add(net, mrt, &mfc, + sk == mrt->mroute6_sk, parent); rtnl_unlock(); return ret; @@ -2018,19 +2074,29 @@ static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, { int psend = -1; int vif, ct; + int true_vifi = ip6mr_find_vif(mrt, skb->dev); vif = cache->mf6c_parent; cache->mfc_un.res.pkt++; cache->mfc_un.res.bytes += skb->len; + if (ipv6_addr_any(&cache->mf6c_origin) && true_vifi >= 0) { + struct mfc6_cache *cache_proxy; + + /* For an (*,G) entry, we only check that the incomming + * interface is part of the static tree. + */ + cache_proxy = ip6mr_cache_find_any_parent(mrt, vif); + if (cache_proxy && + cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + goto forward; + } + /* * Wrong interface: drop packet and (maybe) send PIM assert. */ if (mrt->vif6_table[vif].dev != skb->dev) { - int true_vifi; - cache->mfc_un.res.wrong_if++; - true_vifi = ip6mr_find_vif(mrt, skb->dev); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -2048,14 +2114,32 @@ static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, goto dont_forward; } +forward: mrt->vif6_table[vif].pkt_in++; mrt->vif6_table[vif].bytes_in += skb->len; /* * Forward the frame */ + if (ipv6_addr_any(&cache->mf6c_origin) && + ipv6_addr_any(&cache->mf6c_mcastgrp)) { + if (true_vifi >= 0 && + true_vifi != cache->mf6c_parent && + ipv6_hdr(skb)->hop_limit > + cache->mfc_un.res.ttls[cache->mf6c_parent]) { + /* It's an (*,*) entry and the packet is not coming from + * the upstream: forward the packet to the upstream + * only. + */ + psend = cache->mf6c_parent; + goto last_forward; + } + goto dont_forward; + } for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { - if (ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) { + /* For (*,G) entry, don't forward to the incoming interface */ + if ((!ipv6_addr_any(&cache->mf6c_origin) || ct != true_vifi) && + ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) @@ -2064,6 +2148,7 @@ static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, psend = ct; } } +last_forward: if (psend != -1) { ip6mr_forward2(net, mrt, skb, cache, psend); return 0; @@ -2099,6 +2184,14 @@ int ip6_mr_input(struct sk_buff *skb) read_lock(&mrt_lock); cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); + if (cache == NULL) { + int vif = ip6mr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ip6mr_cache_find_any(mrt, + &ipv6_hdr(skb)->daddr, + vif); + } /* * No usable cache entry @@ -2186,6 +2279,13 @@ int ip6mr_get_route(struct net *net, read_lock(&mrt_lock); cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); + if (!cache && skb->dev) { + int vif = ip6mr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ip6mr_cache_find_any(mrt, &rt->rt6i_dst.addr, + vif); + } if (!cache) { struct sk_buff *skb2; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 28dfa5f3801..f25002aaf62 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -935,33 +935,6 @@ int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) } /* - * identify MLD packets for MLD filter exceptions - */ -bool ipv6_is_mld(struct sk_buff *skb, int nexthdr) -{ - struct icmp6hdr *pic; - - if (nexthdr != IPPROTO_ICMPV6) - return false; - - if (!pskb_may_pull(skb, sizeof(struct icmp6hdr))) - return false; - - pic = icmp6_hdr(skb); - - switch (pic->icmp6_type) { - case ICMPV6_MGM_QUERY: - case ICMPV6_MGM_REPORT: - case ICMPV6_MGM_REDUCTION: - case ICMPV6_MLD2_REPORT: - return true; - default: - break; - } - return false; -} - -/* * check if the interface/address pair is valid */ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, @@ -1340,6 +1313,31 @@ mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) return scount; } +static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb, + struct net_device *dev, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + int proto, int len) +{ + struct ipv6hdr *hdr; + + skb->protocol = htons(ETH_P_IPV6); + skb->dev = dev; + + skb_reset_network_header(skb); + skb_put(skb, sizeof(struct ipv6hdr)); + hdr = ipv6_hdr(skb); + + ip6_flow_hdr(hdr, 0, 0); + + hdr->payload_len = htons(len); + hdr->nexthdr = proto; + hdr->hop_limit = inet6_sk(sk)->hop_limit; + + hdr->saddr = *saddr; + hdr->daddr = *daddr; +} + static struct sk_buff *mld_newpack(struct net_device *dev, int size) { struct net *net = dev_net(dev); @@ -1375,7 +1373,7 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size) } else saddr = &addr_buf; - ip6_nd_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); + ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); @@ -1418,7 +1416,7 @@ static void mld_sendpack(struct sk_buff *skb) icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - dst = icmp6_dst_alloc(skb->dev, NULL, &fl6); + dst = icmp6_dst_alloc(skb->dev, &fl6); err = 0; if (IS_ERR(dst)) { @@ -1767,7 +1765,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) } else saddr = &addr_buf; - ip6_nd_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); + ip6_mc_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); @@ -1786,7 +1784,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) icmpv6_flow_init(sk, &fl6, type, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - dst = icmp6_dst_alloc(skb->dev, NULL, &fl6); + dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err_out; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 6574175795d..76ef4353d51 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -143,16 +143,12 @@ struct neigh_table nd_tbl = { .gc_thresh3 = 1024, }; -static inline int ndisc_opt_addr_space(struct net_device *dev) +static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data) { - return NDISC_OPT_SPACE(dev->addr_len + ndisc_addr_option_pad(dev->type)); -} - -static u8 *ndisc_fill_addr_option(u8 *opt, int type, void *data, int data_len, - unsigned short addr_type) -{ - int pad = ndisc_addr_option_pad(addr_type); - int space = NDISC_OPT_SPACE(data_len + pad); + int pad = ndisc_addr_option_pad(skb->dev->type); + int data_len = skb->dev->addr_len; + int space = ndisc_opt_addr_space(skb->dev); + u8 *opt = skb_put(skb, space); opt[0] = type; opt[1] = space>>3; @@ -166,7 +162,6 @@ static u8 *ndisc_fill_addr_option(u8 *opt, int type, void *data, int data_len, opt += data_len; if ((space -= data_len) > 0) memset(opt, 0, space); - return opt + space; } static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, @@ -370,91 +365,88 @@ static void pndisc_destructor(struct pneigh_entry *n) ipv6_dev_mc_dec(dev, &maddr); } -static struct sk_buff *ndisc_build_skb(struct net_device *dev, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h, - const struct in6_addr *target, - int llinfo) +static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, + int len) { - struct net *net = dev_net(dev); - struct sock *sk = net->ipv6.ndisc_sk; - struct sk_buff *skb; - struct icmp6hdr *hdr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; - int len; + struct sock *sk = dev_net(dev)->ipv6.ndisc_sk; + struct sk_buff *skb; int err; - u8 *opt; - - if (!dev->addr_len) - llinfo = 0; - - len = sizeof(struct icmp6hdr) + (target ? sizeof(*target) : 0); - if (llinfo) - len += ndisc_opt_addr_space(dev); skb = sock_alloc_send_skb(sk, - (MAX_HEADER + sizeof(struct ipv6hdr) + - len + hlen + tlen), + hlen + sizeof(struct ipv6hdr) + len + tlen, 1, &err); if (!skb) { - ND_PRINTK(0, err, "ND: %s failed to allocate an skb, err=%d\n", + ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb, err=%d\n", __func__, err); return NULL; } - skb_reserve(skb, hlen); - ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len); + skb->protocol = htons(ETH_P_IPV6); + skb->dev = dev; - skb->transport_header = skb->tail; - skb_put(skb, len); + skb_reserve(skb, hlen + sizeof(struct ipv6hdr)); + skb_reset_transport_header(skb); - hdr = (struct icmp6hdr *)skb_transport_header(skb); - memcpy(hdr, icmp6h, sizeof(*hdr)); + return skb; +} - opt = skb_transport_header(skb) + sizeof(struct icmp6hdr); - if (target) { - *(struct in6_addr *)opt = *target; - opt += sizeof(*target); - } +static void ip6_nd_hdr(struct sk_buff *skb, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + int hop_limit, int len) +{ + struct ipv6hdr *hdr; - if (llinfo) - ndisc_fill_addr_option(opt, llinfo, dev->dev_addr, - dev->addr_len, dev->type); + skb_push(skb, sizeof(*hdr)); + skb_reset_network_header(skb); + hdr = ipv6_hdr(skb); - hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len, - IPPROTO_ICMPV6, - csum_partial(hdr, - len, 0)); + ip6_flow_hdr(hdr, 0, 0); - return skb; + hdr->payload_len = htons(len); + hdr->nexthdr = IPPROTO_ICMPV6; + hdr->hop_limit = hop_limit; + + hdr->saddr = *saddr; + hdr->daddr = *daddr; } -static void ndisc_send_skb(struct sk_buff *skb, struct net_device *dev, - struct neighbour *neigh, +static void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h) + const struct in6_addr *saddr) { - struct flowi6 fl6; - struct dst_entry *dst; - struct net *net = dev_net(dev); + struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(skb->dev); struct sock *sk = net->ipv6.ndisc_sk; struct inet6_dev *idev; int err; + struct icmp6hdr *icmp6h = icmp6_hdr(skb); u8 type; type = icmp6h->icmp6_type; - icmpv6_flow_init(sk, &fl6, type, saddr, daddr, dev->ifindex); - dst = icmp6_dst_alloc(dev, neigh, &fl6); - if (IS_ERR(dst)) { - kfree_skb(skb); - return; + if (!dst) { + struct sock *sk = net->ipv6.ndisc_sk; + struct flowi6 fl6; + + icmpv6_flow_init(sk, &fl6, type, saddr, daddr, skb->dev->ifindex); + dst = icmp6_dst_alloc(skb->dev, &fl6); + if (IS_ERR(dst)) { + kfree_skb(skb); + return; + } + + skb_dst_set(skb, dst); } - skb_dst_set(skb, dst); + icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, skb->len, + IPPROTO_ICMPV6, + csum_partial(icmp6h, + skb->len, 0)); + + ip6_nd_hdr(skb, saddr, daddr, inet6_sk(sk)->hop_limit, skb->len); rcu_read_lock(); idev = __in6_dev_get(dst->dev); @@ -470,36 +462,17 @@ static void ndisc_send_skb(struct sk_buff *skb, struct net_device *dev, rcu_read_unlock(); } -/* - * Send a Neighbour Discover packet - */ -static void __ndisc_send(struct net_device *dev, - struct neighbour *neigh, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h, const struct in6_addr *target, - int llinfo) -{ - struct sk_buff *skb; - - skb = ndisc_build_skb(dev, daddr, saddr, icmp6h, target, llinfo); - if (!skb) - return; - - ndisc_send_skb(skb, dev, neigh, daddr, saddr, icmp6h); -} - static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, - int router, int solicited, int override, int inc_opt) + bool router, bool solicited, bool override, bool inc_opt) { + struct sk_buff *skb; struct in6_addr tmpaddr; struct inet6_ifaddr *ifp; const struct in6_addr *src_addr; - struct icmp6hdr icmp6h = { - .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, - }; + struct nd_msg *msg; + int optlen = 0; /* for anycast or proxy, solicited_addr != src_addr */ ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1); @@ -517,13 +490,32 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, src_addr = &tmpaddr; } - icmp6h.icmp6_router = router; - icmp6h.icmp6_solicited = solicited; - icmp6h.icmp6_override = override; + if (!dev->addr_len) + inc_opt = 0; + if (inc_opt) + optlen += ndisc_opt_addr_space(dev); + + skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!skb) + return; - __ndisc_send(dev, neigh, daddr, src_addr, - &icmp6h, solicited_addr, - inc_opt ? ND_OPT_TARGET_LL_ADDR : 0); + msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + *msg = (struct nd_msg) { + .icmph = { + .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, + .icmp6_router = router, + .icmp6_solicited = solicited, + .icmp6_override = override, + }, + .target = *solicited_addr, + }; + + if (inc_opt) + ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, + dev->dev_addr); + + + ndisc_send_skb(skb, daddr, src_addr); } static void ndisc_send_unsol_na(struct net_device *dev) @@ -551,10 +543,11 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr) { + struct sk_buff *skb; struct in6_addr addr_buf; - struct icmp6hdr icmp6h = { - .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, - }; + int inc_opt = dev->addr_len; + int optlen = 0; + struct nd_msg *msg; if (saddr == NULL) { if (ipv6_get_lladdr(dev, &addr_buf, @@ -563,18 +556,37 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, saddr = &addr_buf; } - __ndisc_send(dev, neigh, daddr, saddr, - &icmp6h, solicit, - !ipv6_addr_any(saddr) ? ND_OPT_SOURCE_LL_ADDR : 0); + if (ipv6_addr_any(saddr)) + inc_opt = 0; + if (inc_opt) + optlen += ndisc_opt_addr_space(dev); + + skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!skb) + return; + + msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + *msg = (struct nd_msg) { + .icmph = { + .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, + }, + .target = *solicit, + }; + + if (inc_opt) + ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, + dev->dev_addr); + + ndisc_send_skb(skb, daddr, saddr); } void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr) { - struct icmp6hdr icmp6h = { - .icmp6_type = NDISC_ROUTER_SOLICITATION, - }; + struct sk_buff *skb; + struct rs_msg *msg; int send_sllao = dev->addr_len; + int optlen = 0; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* @@ -598,9 +610,27 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, } } #endif - __ndisc_send(dev, NULL, daddr, saddr, - &icmp6h, NULL, - send_sllao ? ND_OPT_SOURCE_LL_ADDR : 0); + if (!dev->addr_len) + send_sllao = 0; + if (send_sllao) + optlen += ndisc_opt_addr_space(dev); + + skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!skb) + return; + + msg = (struct rs_msg *)skb_put(skb, sizeof(*msg)); + *msg = (struct rs_msg) { + .icmph = { + .icmp6_type = NDISC_ROUTER_SOLICITATION, + }, + }; + + if (send_sllao) + ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, + dev->dev_addr); + + ndisc_send_skb(skb, daddr, saddr); } @@ -676,6 +706,11 @@ static void ndisc_recv_ns(struct sk_buff *skb) bool inc; int is_router = -1; + if (skb->len < sizeof(struct nd_msg)) { + ND_PRINTK(2, warn, "NS: packet too short\n"); + return; + } + if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK(2, warn, "NS: multicast target address\n"); return; @@ -685,11 +720,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) * RFC2461 7.1.1: * DAD has to be destined for solicited node multicast address. */ - if (dad && - !(daddr->s6_addr32[0] == htonl(0xff020000) && - daddr->s6_addr32[1] == htonl(0x00000000) && - daddr->s6_addr32[2] == htonl(0x00000001) && - daddr->s6_addr [12] == 0xff )) { + if (dad && !ipv6_addr_is_solict_mult(daddr)) { ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n"); return; } @@ -780,11 +811,11 @@ static void ndisc_recv_ns(struct sk_buff *skb) } if (is_router < 0) - is_router = !!idev->cnf.forwarding; + is_router = idev->cnf.forwarding; if (dad) { ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &msg->target, - is_router, 0, (ifp != NULL), 1); + !!is_router, false, (ifp != NULL), true); goto out; } @@ -805,8 +836,8 @@ static void ndisc_recv_ns(struct sk_buff *skb) NEIGH_UPDATE_F_OVERRIDE); if (neigh || !dev->header_ops) { ndisc_send_na(dev, neigh, saddr, &msg->target, - is_router, - 1, (ifp != NULL && inc), inc); + !!is_router, + true, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); } @@ -1350,25 +1381,34 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } +static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, + struct sk_buff *orig_skb, + int rd_len) +{ + u8 *opt = skb_put(skb, rd_len); + + memset(opt, 0, 8); + *(opt++) = ND_OPT_REDIRECT_HDR; + *(opt++) = (rd_len >> 3); + opt += 6; + + memcpy(opt, ipv6_hdr(orig_skb), rd_len - 8); +} + void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; - int len = sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); + int optlen = 0; struct inet_peer *peer; struct sk_buff *buff; - struct icmp6hdr *icmph; + struct rd_msg *msg; struct in6_addr saddr_buf; - struct in6_addr *addrp; struct rt6_info *rt; struct dst_entry *dst; - struct inet6_dev *idev; struct flowi6 fl6; - u8 *opt; - int hlen, tlen; int rd_len; - int err; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; bool ret; @@ -1424,7 +1464,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) memcpy(ha_buf, neigh->ha, dev->addr_len); read_unlock_bh(&neigh->lock); ha = ha_buf; - len += ndisc_opt_addr_space(dev); + optlen += ndisc_opt_addr_space(dev); } else read_unlock_bh(&neigh->lock); @@ -1432,80 +1472,40 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) } rd_len = min_t(unsigned int, - IPV6_MIN_MTU-sizeof(struct ipv6hdr)-len, skb->len + 8); + IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(*msg) - optlen, + skb->len + 8); rd_len &= ~0x7; - len += rd_len; - - hlen = LL_RESERVED_SPACE(dev); - tlen = dev->needed_tailroom; - buff = sock_alloc_send_skb(sk, - (MAX_HEADER + sizeof(struct ipv6hdr) + - len + hlen + tlen), - 1, &err); - if (buff == NULL) { - ND_PRINTK(0, err, - "Redirect: %s failed to allocate an skb, err=%d\n", - __func__, err); - goto release; - } - - skb_reserve(buff, hlen); - ip6_nd_hdr(sk, buff, dev, &saddr_buf, &ipv6_hdr(skb)->saddr, - IPPROTO_ICMPV6, len); - - skb_set_transport_header(buff, skb_tail_pointer(buff) - buff->data); - skb_put(buff, len); - icmph = icmp6_hdr(buff); - - memset(icmph, 0, sizeof(struct icmp6hdr)); - icmph->icmp6_type = NDISC_REDIRECT; + optlen += rd_len; - /* - * copy target and destination addresses - */ - - addrp = (struct in6_addr *)(icmph + 1); - *addrp = *target; - addrp++; - *addrp = ipv6_hdr(skb)->daddr; + buff = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!buff) + goto release; - opt = (u8*) (addrp + 1); + msg = (struct rd_msg *)skb_put(buff, sizeof(*msg)); + *msg = (struct rd_msg) { + .icmph = { + .icmp6_type = NDISC_REDIRECT, + }, + .target = *target, + .dest = ipv6_hdr(skb)->daddr, + }; /* * include target_address option */ if (ha) - opt = ndisc_fill_addr_option(opt, ND_OPT_TARGET_LL_ADDR, ha, - dev->addr_len, dev->type); + ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha); /* * build redirect option and copy skb over to the new packet. */ - memset(opt, 0, 8); - *(opt++) = ND_OPT_REDIRECT_HDR; - *(opt++) = (rd_len >> 3); - opt += 6; - - memcpy(opt, ipv6_hdr(skb), rd_len - 8); - - icmph->icmp6_cksum = csum_ipv6_magic(&saddr_buf, &ipv6_hdr(skb)->saddr, - len, IPPROTO_ICMPV6, - csum_partial(icmph, len, 0)); + if (rd_len) + ndisc_fill_redirect_hdr_option(buff, skb, rd_len); skb_dst_set(buff, dst); - rcu_read_lock(); - idev = __in6_dev_get(dst->dev); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); - err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, buff, NULL, dst->dev, - dst_output); - if (!err) { - ICMP6MSGOUT_INC_STATS(net, idev, NDISC_REDIRECT); - ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); - } - - rcu_read_unlock(); + ndisc_send_skb(buff, &ipv6_hdr(skb)->saddr, &saddr_buf); return; release: @@ -1522,7 +1522,7 @@ int ndisc_rcv(struct sk_buff *skb) { struct nd_msg *msg; - if (!pskb_may_pull(skb, skb->len)) + if (skb_linearize(skb)) return 0; msg = (struct nd_msg *)skb_transport_header(skb); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 125a90d6a79..341b54ade72 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1098,7 +1098,7 @@ static int get_info(struct net *net, void __user *user, #endif t = try_then_request_module(xt_find_table_lock(net, AF_INET6, name), "ip6table_%s", name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { struct ip6t_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT @@ -1157,7 +1157,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr, } t = xt_find_table_lock(net, AF_INET6, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", private->number); if (get.size == private->size) @@ -1197,7 +1197,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, t = try_then_request_module(xt_find_table_lock(net, AF_INET6, name), "ip6table_%s", name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free_newinfo_counters_untrans; } @@ -1355,7 +1355,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len, } t = xt_find_table_lock(net, AF_INET6, name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } @@ -1939,7 +1939,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; duprintf("t->private->number = %u\n", private->number); diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 029623dbd41..ed3b427b284 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -126,7 +126,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) skb_put(nskb, sizeof(struct ipv6hdr)); skb_reset_network_header(nskb); ip6h = ipv6_hdr(nskb); - *(__be32 *)ip6h = htonl(0x60000000 | (tclass << 20)); + ip6_flow_hdr(ip6h, tclass, 0); ip6h->hop_limit = ip6_dst_hoplimit(dst); ip6h->nexthdr = IPPROTO_TCP; ip6h->saddr = oip6h->daddr; diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 137e245860a..8a45bb20bed 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -421,54 +421,43 @@ static int ipv6_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_tcp6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_tcp6); if (ret < 0) { - printk(KERN_ERR "nf_conntrack_l4proto_tcp6: protocol register failed\n"); + pr_err("nf_conntrack_tcp6: pernet registration failed\n"); goto out; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_udp6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udp6); if (ret < 0) { - printk(KERN_ERR "nf_conntrack_l4proto_udp6: protocol register failed\n"); + pr_err("nf_conntrack_udp6: pernet registration failed\n"); goto cleanup_tcp6; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_icmpv6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_icmpv6); if (ret < 0) { - printk(KERN_ERR "nf_conntrack_l4proto_icmp6: protocol register failed\n"); + pr_err("nf_conntrack_icmp6: pernet registration failed\n"); goto cleanup_udp6; } - ret = nf_conntrack_l3proto_register(net, - &nf_conntrack_l3proto_ipv6); + ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv6); if (ret < 0) { - printk(KERN_ERR "nf_conntrack_l3proto_ipv6: protocol register failed\n"); + pr_err("nf_conntrack_ipv6: pernet registration failed.\n"); goto cleanup_icmpv6; } return 0; cleanup_icmpv6: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_icmpv6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6); cleanup_udp6: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_udp6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6); cleanup_tcp6: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_tcp6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6); out: return ret; } static void ipv6_net_exit(struct net *net) { - nf_conntrack_l3proto_unregister(net, - &nf_conntrack_l3proto_ipv6); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_icmpv6); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_udp6); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_tcp6); + nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6); } static struct pernet_operations ipv6_net_ops = { @@ -491,19 +480,52 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) ret = register_pernet_subsys(&ipv6_net_ops); if (ret < 0) - goto cleanup_pernet; + goto cleanup_sockopt; + ret = nf_register_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); if (ret < 0) { pr_err("nf_conntrack_ipv6: can't register pre-routing defrag " "hook.\n"); - goto cleanup_ipv6; + goto cleanup_pernet; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register tcp6 proto.\n"); + goto cleanup_hooks; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register udp6 proto.\n"); + goto cleanup_tcp6; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmpv6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register icmpv6 proto.\n"); + goto cleanup_udp6; + } + + ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register ipv6 proto.\n"); + goto cleanup_icmpv6; } return ret; - cleanup_ipv6: - unregister_pernet_subsys(&ipv6_net_ops); + cleanup_icmpv6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); + cleanup_udp6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6); + cleanup_tcp6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6); + cleanup_hooks: + nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); cleanup_pernet: + unregister_pernet_subsys(&ipv6_net_ops); + cleanup_sockopt: nf_unregister_sockopt(&so_getorigdst6); return ret; } @@ -511,6 +533,10 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) static void __exit nf_conntrack_l3proto_ipv6_fini(void) { synchronize_net(); + nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); unregister_pernet_subsys(&ipv6_net_ops); nf_unregister_sockopt(&so_getorigdst6); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 3dacecc9906..c674f158efa 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -319,7 +319,7 @@ found: fq->q.meat += skb->len; if (payload_len > fq->q.max_size) fq->q.max_size = payload_len; - atomic_add(skb->truesize, &fq->q.net->mem); + add_frag_mem_limit(&fq->q, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -328,9 +328,8 @@ found: fq->nhoffset = nhoff; fq->q.last_in |= INET_FRAG_FIRST_IN; } - write_lock(&nf_frags.lock); - list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list); - write_unlock(&nf_frags.lock); + + inet_frag_lru_move(&fq->q); return 0; discard_fq: @@ -398,7 +397,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) clone->ip_summed = head->ip_summed; NFCT_FRAG6_CB(clone)->orig = NULL; - atomic_add(clone->truesize, &fq->q.net->mem); + add_frag_mem_limit(&fq->q, clone->truesize); } /* We have to remove fragment header from datagram and to relocate @@ -422,7 +421,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; } - atomic_sub(head->truesize, &fq->q.net->mem); + sub_frag_mem_limit(&fq->q, head->truesize); head->local_df = 1; head->next = NULL; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index e5253ec9e0f..bab2c270f29 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -327,7 +327,7 @@ found: } fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; - atomic_add(skb->truesize, &fq->q.net->mem); + add_frag_mem_limit(&fq->q, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -341,9 +341,7 @@ found: fq->q.meat == fq->q.len) return ip6_frag_reasm(fq, prev, dev); - write_lock(&ip6_frags.lock); - list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list); - write_unlock(&ip6_frags.lock); + inet_frag_lru_move(&fq->q); return -1; discard_fq: @@ -429,7 +427,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, head->len -= clone->len; clone->csum = 0; clone->ip_summed = head->ip_summed; - atomic_add(clone->truesize, &fq->q.net->mem); + add_frag_mem_limit(&fq->q, clone->truesize); } /* We have to remove fragment header from datagram and to relocate @@ -467,7 +465,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, } fp = next; } - atomic_sub(sum_truesize, &fq->q.net->mem); + sub_frag_mem_limit(&fq->q, sum_truesize); head->next = NULL; head->dev = dev; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e229a3bc345..f3328bc1174 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -145,25 +145,12 @@ static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, struct neighbour *n; daddr = choose_neigh_daddr(rt, skb, daddr); - n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr); + n = __ipv6_neigh_lookup(dst->dev, daddr); if (n) return n; return neigh_create(&nd_tbl, daddr, dst->dev); } -static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev) -{ - struct neighbour *n = __ipv6_neigh_lookup(&nd_tbl, dev, &rt->rt6i_gateway); - if (!n) { - n = neigh_create(&nd_tbl, &rt->rt6i_gateway, dev); - if (IS_ERR(n)) - return PTR_ERR(n); - } - rt->n = n; - - return 0; -} - static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .protocol = cpu_to_be16(ETH_P_IPV6), @@ -301,9 +288,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; - if (rt->n) - neigh_release(rt->n); - if (!(rt->dst.flags & DST_HOST)) dst_destroy_metrics_generic(dst); @@ -354,11 +338,6 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, in6_dev_put(idev); } } - if (rt->n && rt->n->dev == dev) { - rt->n->dev = loopback_dev; - dev_hold(loopback_dev); - dev_put(dev); - } } } @@ -388,15 +367,8 @@ static int rt6_info_hash_nhsfn(unsigned int candidate_count, { unsigned int val = fl6->flowi6_proto; - val ^= (__force u32)fl6->daddr.s6_addr32[0]; - val ^= (__force u32)fl6->daddr.s6_addr32[1]; - val ^= (__force u32)fl6->daddr.s6_addr32[2]; - val ^= (__force u32)fl6->daddr.s6_addr32[3]; - - val ^= (__force u32)fl6->saddr.s6_addr32[0]; - val ^= (__force u32)fl6->saddr.s6_addr32[1]; - val ^= (__force u32)fl6->saddr.s6_addr32[2]; - val ^= (__force u32)fl6->saddr.s6_addr32[3]; + val ^= ipv6_addr_hash(&fl6->daddr); + val ^= ipv6_addr_hash(&fl6->saddr); /* Work only if this not encapsulated */ switch (fl6->flowi6_proto) { @@ -505,24 +477,34 @@ static void rt6_probe(struct rt6_info *rt) * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ - neigh = rt ? rt->n : NULL; - if (!neigh || (neigh->nud_state & NUD_VALID)) + if (!rt || !(rt->rt6i_flags & RTF_GATEWAY)) return; - read_lock_bh(&neigh->lock); - if (!(neigh->nud_state & NUD_VALID) && + rcu_read_lock_bh(); + neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + if (neigh) { + write_lock(&neigh->lock); + if (neigh->nud_state & NUD_VALID) + goto out; + } + + if (!neigh || time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { struct in6_addr mcaddr; struct in6_addr *target; - neigh->updated = jiffies; - read_unlock_bh(&neigh->lock); + if (neigh) { + neigh->updated = jiffies; + write_unlock(&neigh->lock); + } - target = (struct in6_addr *)&neigh->primary_key; + target = (struct in6_addr *)&rt->rt6i_gateway; addrconf_addr_solict_mult(target, &mcaddr); ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); } else { - read_unlock_bh(&neigh->lock); +out: + write_unlock(&neigh->lock); } + rcu_read_unlock_bh(); } #else static inline void rt6_probe(struct rt6_info *rt) @@ -549,20 +531,24 @@ static inline bool rt6_check_neigh(struct rt6_info *rt) struct neighbour *neigh; bool ret = false; - neigh = rt->n; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) - ret = true; - else if (neigh) { - read_lock_bh(&neigh->lock); + return true; + + rcu_read_lock_bh(); + neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + if (neigh) { + read_lock(&neigh->lock); if (neigh->nud_state & NUD_VALID) ret = true; #ifdef CONFIG_IPV6_ROUTER_PREF else if (!(neigh->nud_state & NUD_FAILED)) ret = true; #endif - read_unlock_bh(&neigh->lock); + read_unlock(&neigh->lock); } + rcu_read_unlock_bh(); + return ret; } @@ -838,8 +824,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, rt = ip6_rt_copy(ort, daddr); if (rt) { - int attempts = !in_softirq(); - if (!(rt->rt6i_flags & RTF_GATEWAY)) { if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) @@ -855,32 +839,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, rt->rt6i_src.plen = 128; } #endif - - retry: - if (rt6_bind_neighbour(rt, rt->dst.dev)) { - struct net *net = dev_net(rt->dst.dev); - int saved_rt_min_interval = - net->ipv6.sysctl.ip6_rt_gc_min_interval; - int saved_rt_elasticity = - net->ipv6.sysctl.ip6_rt_gc_elasticity; - - if (attempts-- > 0) { - net->ipv6.sysctl.ip6_rt_gc_elasticity = 1; - net->ipv6.sysctl.ip6_rt_gc_min_interval = 0; - - ip6_dst_gc(&net->ipv6.ip6_dst_ops); - - net->ipv6.sysctl.ip6_rt_gc_elasticity = - saved_rt_elasticity; - net->ipv6.sysctl.ip6_rt_gc_min_interval = - saved_rt_min_interval; - goto retry; - } - - net_warn_ratelimited("Neighbour table overflow\n"); - dst_free(&rt->dst); - return NULL; - } } return rt; @@ -891,10 +849,8 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, { struct rt6_info *rt = ip6_rt_copy(ort, daddr); - if (rt) { + if (rt) rt->rt6i_flags |= RTF_CACHE; - rt->n = neigh_clone(ort->n); - } return rt; } @@ -928,7 +884,7 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY))) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl6->daddr); @@ -994,7 +950,7 @@ void ip6_route_input(struct sk_buff *skb) .flowi6_iif = skb->dev->ifindex, .daddr = iph->daddr, .saddr = iph->saddr, - .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, + .flowlabel = ip6_flowinfo(iph), .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, }; @@ -1159,7 +1115,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, fl6.flowi6_flags = 0; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; - fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK; + fl6.flowlabel = ip6_flowinfo(iph); dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) @@ -1187,7 +1143,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) fl6.flowi6_flags = 0; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; - fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK; + fl6.flowlabel = ip6_flowinfo(iph); dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) @@ -1247,7 +1203,6 @@ static struct dst_entry *icmp6_dst_gc_list; static DEFINE_SPINLOCK(icmp6_dst_lock); struct dst_entry *icmp6_dst_alloc(struct net_device *dev, - struct neighbour *neigh, struct flowi6 *fl6) { struct dst_entry *dst; @@ -1265,20 +1220,8 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, goto out; } - if (neigh) - neigh_hold(neigh); - else { - neigh = ip6_neigh_lookup(&rt->dst, NULL, &fl6->daddr); - if (IS_ERR(neigh)) { - in6_dev_put(idev); - dst_free(&rt->dst); - return ERR_CAST(neigh); - } - } - rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; - rt->n = neigh; atomic_set(&rt->dst.__refcnt, 1); rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; @@ -1587,12 +1530,6 @@ int ip6_route_add(struct fib6_config *cfg) } else rt->rt6i_prefsrc.plen = 0; - if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) { - err = rt6_bind_neighbour(rt, dev); - if (err) - goto out; - } - rt->rt6i_flags = cfg->fc_flags; install_route: @@ -1705,37 +1642,32 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu struct net *net = dev_net(skb->dev); struct netevent_redirect netevent; struct rt6_info *rt, *nrt = NULL; - const struct in6_addr *target; struct ndisc_options ndopts; - const struct in6_addr *dest; - struct neighbour *old_neigh; struct inet6_dev *in6_dev; struct neighbour *neigh; - struct icmp6hdr *icmph; + struct rd_msg *msg; int optlen, on_link; u8 *lladdr; optlen = skb->tail - skb->transport_header; - optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); + optlen -= sizeof(*msg); if (optlen < 0) { net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); return; } - icmph = icmp6_hdr(skb); - target = (const struct in6_addr *) (icmph + 1); - dest = target + 1; + msg = (struct rd_msg *)icmp6_hdr(skb); - if (ipv6_addr_is_multicast(dest)) { + if (ipv6_addr_is_multicast(&msg->dest)) { net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); return; } on_link = 0; - if (ipv6_addr_equal(dest, target)) { + if (ipv6_addr_equal(&msg->dest, &msg->target)) { on_link = 1; - } else if (ipv6_addr_type(target) != + } else if (ipv6_addr_type(&msg->target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); return; @@ -1752,7 +1684,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu * first-hop router for the specified ICMP Destination Address. */ - if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { + if (!ndisc_parse_options(msg->opt, optlen, &ndopts)) { net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); return; } @@ -1779,15 +1711,10 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu */ dst_confirm(&rt->dst); - neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); + neigh = __neigh_lookup(&nd_tbl, &msg->target, skb->dev, 1); if (!neigh) return; - /* Duplicate redirect: silently ignore. */ - old_neigh = rt->n; - if (neigh == old_neigh) - goto out; - /* * We have finally decided to accept it. */ @@ -1799,7 +1726,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu NEIGH_UPDATE_F_ISROUTER)) ); - nrt = ip6_rt_copy(rt, dest); + nrt = ip6_rt_copy(rt, &msg->dest); if (!nrt) goto out; @@ -1808,16 +1735,14 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu nrt->rt6i_flags &= ~RTF_GATEWAY; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - nrt->n = neigh_clone(neigh); if (ip6_ins_rt(nrt)) goto out; netevent.old = &rt->dst; - netevent.old_neigh = old_neigh; netevent.new = &nrt->dst; - netevent.new_neigh = neigh; - netevent.daddr = dest; + netevent.daddr = &msg->dest; + netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); if (rt->rt6i_flags & RTF_CACHE) { @@ -2123,7 +2048,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, { struct net *net = dev_net(idev->dev); struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL); - int err; if (!rt) { net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n"); @@ -2142,11 +2066,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_flags |= RTF_ANYCAST; else rt->rt6i_flags |= RTF_LOCAL; - err = rt6_bind_neighbour(rt, rt->dst.dev); - if (err) { - dst_free(&rt->dst); - return ERR_PTR(err); - } rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; @@ -2492,7 +2411,6 @@ static int rt6_fill_node(struct net *net, struct nlmsghdr *nlh; long expires; u32 table; - struct neighbour *n; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -2605,9 +2523,8 @@ static int rt6_fill_node(struct net *net, if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; - n = rt->n; - if (n) { - if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) + if (rt->rt6i_flags & RTF_GATEWAY) { + if (nla_put(skb, RTA_GATEWAY, 16, &rt->rt6i_gateway) < 0) goto nla_put_failure; } @@ -2802,7 +2719,6 @@ struct rt6_proc_arg static int rt6_info_route(struct rt6_info *rt, void *p_arg) { struct seq_file *m = p_arg; - struct neighbour *n; seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); @@ -2811,9 +2727,8 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) #else seq_puts(m, "00000000000000000000000000000000 00 "); #endif - n = rt->n; - if (n) { - seq_printf(m, "%pi6", n->primary_key); + if (rt->rt6i_flags & RTF_GATEWAY) { + seq_printf(m, "%pi6", &rt->rt6i_gateway); } else { seq_puts(m, "00000000000000000000000000000000"); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index cfba99b2c2a..02f96dcbcf0 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -72,6 +72,8 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static int ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); static void ipip6_dev_free(struct net_device *dev); +static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, + __be32 *v4dst); static struct rtnl_link_ops sit_link_ops __read_mostly; static int sit_net_id __read_mostly; @@ -590,17 +592,21 @@ out: return err; } +static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, + const struct in6_addr *v6addr) +{ + __be32 v4embed = 0; + if (check_6rd(tunnel, v6addr, &v4embed) && v4addr != v4embed) + return true; + return false; +} + static int ipip6_rcv(struct sk_buff *skb) { - const struct iphdr *iph; + const struct iphdr *iph = ip_hdr(skb); struct ip_tunnel *tunnel; int err; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - goto out; - - iph = ip_hdr(skb); - tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { @@ -613,10 +619,19 @@ static int ipip6_rcv(struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); skb->pkt_type = PACKET_HOST; - if ((tunnel->dev->priv_flags & IFF_ISATAP) && - !isatap_chksrc(skb, iph, tunnel)) { - tunnel->dev->stats.rx_errors++; - goto out; + if (tunnel->dev->priv_flags & IFF_ISATAP) { + if (!isatap_chksrc(skb, iph, tunnel)) { + tunnel->dev->stats.rx_errors++; + goto out; + } + } else { + if (is_spoofed_6rd(tunnel, iph->saddr, + &ipv6_hdr(skb)->saddr) || + is_spoofed_6rd(tunnel, iph->daddr, + &ipv6_hdr(skb)->daddr)) { + tunnel->dev->stats.rx_errors++; + goto out; + } } __skb_tunnel_rx(skb, tunnel->dev); @@ -650,14 +665,12 @@ out: } /* - * Returns the embedded IPv4 address if the IPv6 address - * comes from 6rd / 6to4 (RFC 3056) addr space. + * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function + * stores the embedded IPv4 address in v4dst and returns true. */ -static inline -__be32 try_6rd(const struct in6_addr *v6dst, struct ip_tunnel *tunnel) +static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, + __be32 *v4dst) { - __be32 dst = 0; - #ifdef CONFIG_IPV6_SIT_6RD if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, tunnel->ip6rd.prefixlen)) { @@ -676,14 +689,24 @@ __be32 try_6rd(const struct in6_addr *v6dst, struct ip_tunnel *tunnel) d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >> (32 - pbi1); - dst = tunnel->ip6rd.relay_prefix | htonl(d); + *v4dst = tunnel->ip6rd.relay_prefix | htonl(d); + return true; } #else if (v6dst->s6_addr16[0] == htons(0x2002)) { /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ - memcpy(&dst, &v6dst->s6_addr16[1], 4); + memcpy(v4dst, &v6dst->s6_addr16[1], 4); + return true; } #endif + return false; +} + +static inline __be32 try_6rd(struct ip_tunnel *tunnel, + const struct in6_addr *v6dst) +{ + __be32 dst = 0; + check_6rd(tunnel, v6dst, &dst); return dst; } @@ -744,7 +767,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (!dst) - dst = try_6rd(&iph6->daddr, tunnel); + dst = try_6rd(tunnel, &iph6->daddr); if (!dst) { struct neighbour *neigh = NULL; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 40161977f7c..8a0848b60b3 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -179,7 +179,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) memset(&tcp_opt, 0, sizeof(tcp_opt)); tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL); - if (!cookie_check_timestamp(&tcp_opt, &ecn_ok)) + if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok)) goto out; ret = NULL; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 93825dd3a7c..06087e58738 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -834,7 +834,8 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) * no RST generated if md5 hash doesn't match. */ sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev), - &tcp_hashinfo, &ipv6h->daddr, + &tcp_hashinfo, &ipv6h->saddr, + th->source, &ipv6h->daddr, ntohs(th->source), inet6_iif(skb)); if (!sk1) return; @@ -1027,7 +1028,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) treq->rmt_addr = ipv6_hdr(skb)->saddr; treq->loc_addr = ipv6_hdr(skb)->daddr; if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, skb); + TCP_ECN_create_request(req, skb, sock_net(sk)); treq->iif = sk->sk_bound_dev_if; @@ -1163,7 +1164,7 @@ 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_tclass(ipv6_hdr(skb)); + newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count @@ -1243,7 +1244,7 @@ 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_tclass(ipv6_hdr(skb)); + newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); /* Clone native IPv6 options from listening socket (if any) @@ -1456,7 +1457,7 @@ ipv6_pktoptions: if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; if (np->rxopt.bits.rxtclass) - np->rcv_tclass = ipv6_tclass(ipv6_hdr(skb)); + np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); if (ipv6_opt_accepted(sk, opt_skb)) { skb_set_owner_r(opt_skb, sk); opt_skb = xchg(&np->pktoptions, opt_skb); @@ -1598,6 +1599,7 @@ do_time_wait: struct sock *sk2; sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, + &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_iif(skb)); if (sk2 != NULL) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index dfaa29b8b29..cb5bf497c09 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -45,6 +45,7 @@ #include <net/tcp_states.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> +#include <net/inet6_hashtables.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -203,7 +204,8 @@ static struct sock *udp6_lib_lookup2(struct net *net, { struct sock *sk, *result; struct hlist_nulls_node *node; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; begin: result = NULL; @@ -214,8 +216,18 @@ begin: if (score > badness) { result = sk; badness = score; - if (score == SCORE2_MAX) + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet6_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; + } else if (score == SCORE2_MAX) goto exact_match; + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@ -249,7 +261,8 @@ struct sock *__udp6_lib_lookup(struct net *net, unsigned short hnum = ntohs(dport); unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; rcu_read_lock(); if (hslot->count > 10) { @@ -284,6 +297,17 @@ begin: if (score > badness) { result = sk; badness = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet6_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; + } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@ -752,40 +776,6 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, return 0; } -static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, - int proto) -{ - int err; - - UDP_SKB_CB(skb)->partial_cov = 0; - UDP_SKB_CB(skb)->cscov = skb->len; - - if (proto == IPPROTO_UDPLITE) { - err = udplite_checksum_init(skb, uh); - if (err) - return err; - } - - if (uh->check == 0) { - /* RFC 2460 section 8.1 says that we SHOULD log - this error. Well, it is reasonable. - */ - LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); - return 1; - } - if (skb->ip_summed == CHECKSUM_COMPLETE && - !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, - skb->len, proto, skb->csum)) - skb->ip_summed = CHECKSUM_UNNECESSARY; - - if (!skb_csum_unnecessary(skb)) - skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len, proto, 0)); - - return 0; -} - int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index c9844135c9c..12827374433 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -110,7 +110,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ - xdst->u.rt6.n = neigh_clone(rt->n); xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | RTF_LOCAL); xdst->u.rt6.rt6i_metric = rt->rt6i_metric; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index ee5a7065aac..babd1674388 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -72,7 +72,7 @@ static inline unsigned int xfrm6_tunnel_spi_hash_byaddr(const xfrm_address_t *ad { unsigned int h; - h = (__force u32)(addr->a6[0] ^ addr->a6[1] ^ addr->a6[2] ^ addr->a6[3]); + h = ipv6_addr_hash((const struct in6_addr *)addr); h ^= h >> 16; h ^= h >> 8; h &= XFRM6_TUNNEL_SPI_BYADDR_HSIZE - 1; diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index 2bb2beb6a37..3c83a1e5ab0 100644 --- a/net/irda/irnet/irnet_ppp.c +++ b/net/irda/irnet/irnet_ppp.c @@ -214,8 +214,7 @@ irnet_get_discovery_log(irnet_socket * ap) * After reading : discoveries = NULL ; disco_index = Y ; disco_number = -1 */ static inline int -irnet_read_discovery_log(irnet_socket * ap, - char * event) +irnet_read_discovery_log(irnet_socket *ap, char *event, int buf_size) { int done_event = 0; @@ -237,12 +236,13 @@ irnet_read_discovery_log(irnet_socket * ap, if(ap->disco_index < ap->disco_number) { /* Write an event */ - sprintf(event, "Found %08x (%s) behind %08x {hints %02X-%02X}\n", - ap->discoveries[ap->disco_index].daddr, - ap->discoveries[ap->disco_index].info, - ap->discoveries[ap->disco_index].saddr, - ap->discoveries[ap->disco_index].hints[0], - ap->discoveries[ap->disco_index].hints[1]); + snprintf(event, buf_size, + "Found %08x (%s) behind %08x {hints %02X-%02X}\n", + ap->discoveries[ap->disco_index].daddr, + ap->discoveries[ap->disco_index].info, + ap->discoveries[ap->disco_index].saddr, + ap->discoveries[ap->disco_index].hints[0], + ap->discoveries[ap->disco_index].hints[1]); DEBUG(CTRL_INFO, "Writing discovery %d : %s\n", ap->disco_index, ap->discoveries[ap->disco_index].info); @@ -282,27 +282,24 @@ irnet_ctrl_read(irnet_socket * ap, size_t count) { DECLARE_WAITQUEUE(wait, current); - char event[64]; /* Max event is 61 char */ + char event[75]; ssize_t ret = 0; DENTER(CTRL_TRACE, "(ap=0x%p, count=%Zd)\n", ap, count); - /* Check if we can write an event out in one go */ - DABORT(count < sizeof(event), -EOVERFLOW, CTRL_ERROR, "Buffer to small.\n"); - #ifdef INITIAL_DISCOVERY /* Check if we have read the log */ - if(irnet_read_discovery_log(ap, event)) + if (irnet_read_discovery_log(ap, event, sizeof(event))) { - /* We have an event !!! Copy it to the user */ - if(copy_to_user(buf, event, strlen(event))) + count = min(strlen(event), count); + if (copy_to_user(buf, event, count)) { DERROR(CTRL_ERROR, "Invalid user space pointer.\n"); return -EFAULT; } DEXIT(CTRL_TRACE, "\n"); - return strlen(event); + return count; } #endif /* INITIAL_DISCOVERY */ @@ -339,79 +336,81 @@ irnet_ctrl_read(irnet_socket * ap, switch(irnet_events.log[ap->event_index].event) { case IRNET_DISCOVER: - sprintf(event, "Discovered %08x (%s) behind %08x {hints %02X-%02X}\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].saddr, - irnet_events.log[ap->event_index].hints.byte[0], - irnet_events.log[ap->event_index].hints.byte[1]); + snprintf(event, sizeof(event), + "Discovered %08x (%s) behind %08x {hints %02X-%02X}\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].saddr, + irnet_events.log[ap->event_index].hints.byte[0], + irnet_events.log[ap->event_index].hints.byte[1]); break; case IRNET_EXPIRE: - sprintf(event, "Expired %08x (%s) behind %08x {hints %02X-%02X}\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].saddr, - irnet_events.log[ap->event_index].hints.byte[0], - irnet_events.log[ap->event_index].hints.byte[1]); + snprintf(event, sizeof(event), + "Expired %08x (%s) behind %08x {hints %02X-%02X}\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].saddr, + irnet_events.log[ap->event_index].hints.byte[0], + irnet_events.log[ap->event_index].hints.byte[1]); break; case IRNET_CONNECT_TO: - sprintf(event, "Connected to %08x (%s) on ppp%d\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].unit); + snprintf(event, sizeof(event), "Connected to %08x (%s) on ppp%d\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].unit); break; case IRNET_CONNECT_FROM: - sprintf(event, "Connection from %08x (%s) on ppp%d\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].unit); + snprintf(event, sizeof(event), "Connection from %08x (%s) on ppp%d\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].unit); break; case IRNET_REQUEST_FROM: - sprintf(event, "Request from %08x (%s) behind %08x\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].saddr); + snprintf(event, sizeof(event), "Request from %08x (%s) behind %08x\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].saddr); break; case IRNET_NOANSWER_FROM: - sprintf(event, "No-answer from %08x (%s) on ppp%d\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].unit); + snprintf(event, sizeof(event), "No-answer from %08x (%s) on ppp%d\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].unit); break; case IRNET_BLOCKED_LINK: - sprintf(event, "Blocked link with %08x (%s) on ppp%d\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].unit); + snprintf(event, sizeof(event), "Blocked link with %08x (%s) on ppp%d\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].unit); break; case IRNET_DISCONNECT_FROM: - sprintf(event, "Disconnection from %08x (%s) on ppp%d\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].unit); + snprintf(event, sizeof(event), "Disconnection from %08x (%s) on ppp%d\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].unit); break; case IRNET_DISCONNECT_TO: - sprintf(event, "Disconnected to %08x (%s)\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name); + snprintf(event, sizeof(event), "Disconnected to %08x (%s)\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name); break; default: - sprintf(event, "Bug\n"); + snprintf(event, sizeof(event), "Bug\n"); } /* Increment our event index */ ap->event_index = (ap->event_index + 1) % IRNET_MAX_EVENTS; DEBUG(CTRL_INFO, "Event is :%s", event); - /* Copy it to the user */ - if(copy_to_user(buf, event, strlen(event))) + count = min(strlen(event), count); + if (copy_to_user(buf, event, count)) { DERROR(CTRL_ERROR, "Invalid user space pointer.\n"); return -EFAULT; } DEXIT(CTRL_TRACE, "\n"); - return strlen(event); + return count; } /*------------------------------------------------------------------*/ diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index eb9df22418f..2f0ccbc5f13 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -149,16 +149,133 @@ void ieee80211_assign_tid_tx(struct sta_info *sta, int tid, rcu_assign_pointer(sta->ampdu_mlme.tid_tx[tid], tid_tx); } +static inline int ieee80211_ac_from_tid(int tid) +{ + return ieee802_1d_to_ac[tid & 7]; +} + +/* + * When multiple aggregation sessions on multiple stations + * are being created/destroyed simultaneously, we need to + * refcount the global queue stop caused by that in order + * to not get into a situation where one of the aggregation + * setup or teardown re-enables queues before the other is + * ready to handle that. + * + * These two functions take care of this issue by keeping + * a global "agg_queue_stop" refcount. + */ +static void __acquires(agg_queue) +ieee80211_stop_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) +{ + int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; + + if (atomic_inc_return(&sdata->local->agg_queue_stop[queue]) == 1) + ieee80211_stop_queue_by_reason( + &sdata->local->hw, queue, + IEEE80211_QUEUE_STOP_REASON_AGGREGATION); + __acquire(agg_queue); +} + +static void __releases(agg_queue) +ieee80211_wake_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) +{ + int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; + + if (atomic_dec_return(&sdata->local->agg_queue_stop[queue]) == 0) + ieee80211_wake_queue_by_reason( + &sdata->local->hw, queue, + IEEE80211_QUEUE_STOP_REASON_AGGREGATION); + __release(agg_queue); +} + +/* + * splice packets from the STA's pending to the local pending, + * requires a call to ieee80211_agg_splice_finish later + */ +static void __acquires(agg_queue) +ieee80211_agg_splice_packets(struct ieee80211_sub_if_data *sdata, + struct tid_ampdu_tx *tid_tx, u16 tid) +{ + struct ieee80211_local *local = sdata->local; + int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; + unsigned long flags; + + ieee80211_stop_queue_agg(sdata, tid); + + if (WARN(!tid_tx, + "TID %d gone but expected when splicing aggregates from the pending queue\n", + tid)) + return; + + if (!skb_queue_empty(&tid_tx->pending)) { + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + /* copy over remaining packets */ + skb_queue_splice_tail_init(&tid_tx->pending, + &local->pending[queue]); + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + } +} + +static void __releases(agg_queue) +ieee80211_agg_splice_finish(struct ieee80211_sub_if_data *sdata, u16 tid) +{ + ieee80211_wake_queue_agg(sdata, tid); +} + +static void ieee80211_remove_tid_tx(struct sta_info *sta, int tid) +{ + struct tid_ampdu_tx *tid_tx; + + lockdep_assert_held(&sta->ampdu_mlme.mtx); + lockdep_assert_held(&sta->lock); + + tid_tx = rcu_dereference_protected_tid_tx(sta, tid); + + /* + * When we get here, the TX path will not be lockless any more wrt. + * aggregation, since the OPERATIONAL bit has long been cleared. + * Thus it will block on getting the lock, if it occurs. So if we + * stop the queue now, we will not get any more packets, and any + * that might be being processed will wait for us here, thereby + * guaranteeing that no packets go to the tid_tx pending queue any + * more. + */ + + ieee80211_agg_splice_packets(sta->sdata, tid_tx, tid); + + /* future packets must not find the tid_tx struct any more */ + ieee80211_assign_tid_tx(sta, tid, NULL); + + ieee80211_agg_splice_finish(sta->sdata, tid); + + kfree_rcu(tid_tx, rcu_head); +} + int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, - enum ieee80211_back_parties initiator, - bool tx) + enum ieee80211_agg_stop_reason reason) { struct ieee80211_local *local = sta->local; struct tid_ampdu_tx *tid_tx; + enum ieee80211_ampdu_mlme_action action; int ret; lockdep_assert_held(&sta->ampdu_mlme.mtx); + switch (reason) { + case AGG_STOP_DECLINED: + case AGG_STOP_LOCAL_REQUEST: + case AGG_STOP_PEER_REQUEST: + action = IEEE80211_AMPDU_TX_STOP_CONT; + break; + case AGG_STOP_DESTROY_STA: + action = IEEE80211_AMPDU_TX_STOP_FLUSH; + break; + default: + WARN_ON_ONCE(1); + return -EINVAL; + } + spin_lock_bh(&sta->lock); tid_tx = rcu_dereference_protected_tid_tx(sta, tid); @@ -167,10 +284,19 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, return -ENOENT; } - /* if we're already stopping ignore any new requests to stop */ + /* + * if we're already stopping ignore any new requests to stop + * unless we're destroying it in which case notify the driver + */ if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { spin_unlock_bh(&sta->lock); - return -EALREADY; + if (reason != AGG_STOP_DESTROY_STA) + return -EALREADY; + ret = drv_ampdu_action(local, sta->sdata, + IEEE80211_AMPDU_TX_STOP_FLUSH_CONT, + &sta->sta, tid, NULL, 0); + WARN_ON_ONCE(ret); + goto remove_tid_tx; } if (test_bit(HT_AGG_STATE_WANT_START, &tid_tx->state)) { @@ -212,11 +338,12 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, */ synchronize_net(); - tid_tx->stop_initiator = initiator; - tid_tx->tx_stop = tx; + tid_tx->stop_initiator = reason == AGG_STOP_PEER_REQUEST ? + WLAN_BACK_RECIPIENT : + WLAN_BACK_INITIATOR; + tid_tx->tx_stop = reason == AGG_STOP_LOCAL_REQUEST; - ret = drv_ampdu_action(local, sta->sdata, - IEEE80211_AMPDU_TX_STOP, + ret = drv_ampdu_action(local, sta->sdata, action, &sta->sta, tid, NULL, 0); /* HW shall not deny going back to legacy */ @@ -227,7 +354,14 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, */ } - return ret; + if (reason == AGG_STOP_DESTROY_STA) { + remove_tid_tx: + spin_lock_bh(&sta->lock); + ieee80211_remove_tid_tx(sta, tid); + spin_unlock_bh(&sta->lock); + } + + return 0; } /* @@ -264,80 +398,6 @@ static void sta_addba_resp_timer_expired(unsigned long data) rcu_read_unlock(); } -static inline int ieee80211_ac_from_tid(int tid) -{ - return ieee802_1d_to_ac[tid & 7]; -} - -/* - * When multiple aggregation sessions on multiple stations - * are being created/destroyed simultaneously, we need to - * refcount the global queue stop caused by that in order - * to not get into a situation where one of the aggregation - * setup or teardown re-enables queues before the other is - * ready to handle that. - * - * These two functions take care of this issue by keeping - * a global "agg_queue_stop" refcount. - */ -static void __acquires(agg_queue) -ieee80211_stop_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) -{ - int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; - - if (atomic_inc_return(&sdata->local->agg_queue_stop[queue]) == 1) - ieee80211_stop_queue_by_reason( - &sdata->local->hw, queue, - IEEE80211_QUEUE_STOP_REASON_AGGREGATION); - __acquire(agg_queue); -} - -static void __releases(agg_queue) -ieee80211_wake_queue_agg(struct ieee80211_sub_if_data *sdata, int tid) -{ - int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; - - if (atomic_dec_return(&sdata->local->agg_queue_stop[queue]) == 0) - ieee80211_wake_queue_by_reason( - &sdata->local->hw, queue, - IEEE80211_QUEUE_STOP_REASON_AGGREGATION); - __release(agg_queue); -} - -/* - * splice packets from the STA's pending to the local pending, - * requires a call to ieee80211_agg_splice_finish later - */ -static void __acquires(agg_queue) -ieee80211_agg_splice_packets(struct ieee80211_sub_if_data *sdata, - struct tid_ampdu_tx *tid_tx, u16 tid) -{ - struct ieee80211_local *local = sdata->local; - int queue = sdata->vif.hw_queue[ieee80211_ac_from_tid(tid)]; - unsigned long flags; - - ieee80211_stop_queue_agg(sdata, tid); - - if (WARN(!tid_tx, - "TID %d gone but expected when splicing aggregates from the pending queue\n", - tid)) - return; - - if (!skb_queue_empty(&tid_tx->pending)) { - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - /* copy over remaining packets */ - skb_queue_splice_tail_init(&tid_tx->pending, - &local->pending[queue]); - spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - } -} - -static void __releases(agg_queue) -ieee80211_agg_splice_finish(struct ieee80211_sub_if_data *sdata, u16 tid) -{ - ieee80211_wake_queue_agg(sdata, tid); -} - void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) { struct tid_ampdu_tx *tid_tx; @@ -660,14 +720,13 @@ void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, EXPORT_SYMBOL(ieee80211_start_tx_ba_cb_irqsafe); int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, - enum ieee80211_back_parties initiator, - bool tx) + enum ieee80211_agg_stop_reason reason) { int ret; mutex_lock(&sta->ampdu_mlme.mtx); - ret = ___ieee80211_stop_tx_ba_session(sta, tid, initiator, tx); + ret = ___ieee80211_stop_tx_ba_session(sta, tid, reason); mutex_unlock(&sta->ampdu_mlme.mtx); @@ -751,24 +810,7 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) ieee80211_send_delba(sta->sdata, ra, tid, WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE); - /* - * When we get here, the TX path will not be lockless any more wrt. - * aggregation, since the OPERATIONAL bit has long been cleared. - * Thus it will block on getting the lock, if it occurs. So if we - * stop the queue now, we will not get any more packets, and any - * that might be being processed will wait for us here, thereby - * guaranteeing that no packets go to the tid_tx pending queue any - * more. - */ - - ieee80211_agg_splice_packets(sta->sdata, tid_tx, tid); - - /* future packets must not find the tid_tx struct any more */ - ieee80211_assign_tid_tx(sta, tid, NULL); - - ieee80211_agg_splice_finish(sta->sdata, tid); - - kfree_rcu(tid_tx, rcu_head); + ieee80211_remove_tid_tx(sta, tid); unlock_sta: spin_unlock_bh(&sta->lock); @@ -868,8 +910,7 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, } } else { - ___ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_INITIATOR, - false); + ___ieee80211_stop_tx_ba_session(sta, tid, AGG_STOP_DECLINED); } out: diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 516fbc96fef..661b878bd19 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -520,6 +520,7 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) BIT(NL80211_STA_FLAG_WME) | BIT(NL80211_STA_FLAG_MFP) | BIT(NL80211_STA_FLAG_AUTHENTICATED) | + BIT(NL80211_STA_FLAG_ASSOCIATED) | BIT(NL80211_STA_FLAG_TDLS_PEER); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_AUTHORIZED); @@ -531,6 +532,8 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_MFP); if (test_sta_flag(sta, WLAN_STA_AUTH)) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_AUTHENTICATED); + if (test_sta_flag(sta, WLAN_STA_ASSOC)) + sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_ASSOCIATED); if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_TDLS_PEER); } @@ -940,6 +943,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->vif.bss_conf.beacon_int = params->beacon_interval; sdata->vif.bss_conf.dtim_period = params->dtim_period; + sdata->vif.bss_conf.enable_beacon = true; sdata->vif.bss_conf.ssid_len = params->ssid_len; if (params->ssid_len) @@ -1020,8 +1024,15 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) kfree_rcu(old_probe_resp, rcu_head); list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) - sta_info_flush(local, vlan); - sta_info_flush(local, sdata); + sta_info_flush_defer(vlan); + sta_info_flush_defer(sdata); + rcu_barrier(); + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) + sta_info_flush_cleanup(vlan); + sta_info_flush_cleanup(sdata); + + sdata->vif.bss_conf.enable_beacon = false; + clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); drv_stop_ap(sdata->local, sdata); @@ -1079,6 +1090,58 @@ static void ieee80211_send_layer2_update(struct sta_info *sta) netif_rx_ni(skb); } +static int sta_apply_auth_flags(struct ieee80211_local *local, + struct sta_info *sta, + u32 mask, u32 set) +{ + int ret; + + if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED) && + set & BIT(NL80211_STA_FLAG_AUTHENTICATED) && + !test_sta_flag(sta, WLAN_STA_AUTH)) { + ret = sta_info_move_state(sta, IEEE80211_STA_AUTH); + if (ret) + return ret; + } + + if (mask & BIT(NL80211_STA_FLAG_ASSOCIATED) && + set & BIT(NL80211_STA_FLAG_ASSOCIATED) && + !test_sta_flag(sta, WLAN_STA_ASSOC)) { + ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); + if (ret) + return ret; + } + + if (mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { + if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) + ret = sta_info_move_state(sta, IEEE80211_STA_AUTHORIZED); + else if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); + else + ret = 0; + if (ret) + return ret; + } + + if (mask & BIT(NL80211_STA_FLAG_ASSOCIATED) && + !(set & BIT(NL80211_STA_FLAG_ASSOCIATED)) && + test_sta_flag(sta, WLAN_STA_ASSOC)) { + ret = sta_info_move_state(sta, IEEE80211_STA_AUTH); + if (ret) + return ret; + } + + if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED) && + !(set & BIT(NL80211_STA_FLAG_AUTHENTICATED)) && + test_sta_flag(sta, WLAN_STA_AUTH)) { + ret = sta_info_move_state(sta, IEEE80211_STA_NONE); + if (ret) + return ret; + } + + return 0; +} + static int sta_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) @@ -1096,52 +1159,20 @@ static int sta_apply_parameters(struct ieee80211_local *local, mask = params->sta_flags_mask; set = params->sta_flags_set; - /* - * In mesh mode, we can clear AUTHENTICATED flag but must - * also make ASSOCIATED follow appropriately for the driver - * API. See also below, after AUTHORIZED changes. - */ - if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED)) { - /* cfg80211 should not allow this in non-mesh modes */ - if (WARN_ON(!ieee80211_vif_is_mesh(&sdata->vif))) - return -EINVAL; - - if (set & BIT(NL80211_STA_FLAG_AUTHENTICATED) && - !test_sta_flag(sta, WLAN_STA_AUTH)) { - ret = sta_info_move_state(sta, IEEE80211_STA_AUTH); - if (ret) - return ret; - ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); - if (ret) - return ret; - } - } - - if (mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { - if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) - ret = sta_info_move_state(sta, IEEE80211_STA_AUTHORIZED); - else if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) - ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); - if (ret) - return ret; - } - - if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED)) { - /* cfg80211 should not allow this in non-mesh modes */ - if (WARN_ON(!ieee80211_vif_is_mesh(&sdata->vif))) - return -EINVAL; - - if (!(set & BIT(NL80211_STA_FLAG_AUTHENTICATED)) && - test_sta_flag(sta, WLAN_STA_AUTH)) { - ret = sta_info_move_state(sta, IEEE80211_STA_AUTH); - if (ret) - return ret; - ret = sta_info_move_state(sta, IEEE80211_STA_NONE); - if (ret) - return ret; - } + if (ieee80211_vif_is_mesh(&sdata->vif)) { + /* + * In mesh mode, ASSOCIATED isn't part of the nl80211 + * API but must follow AUTHENTICATED for driver state. + */ + if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED)) + mask |= BIT(NL80211_STA_FLAG_ASSOCIATED); + if (set & BIT(NL80211_STA_FLAG_AUTHENTICATED)) + set |= BIT(NL80211_STA_FLAG_ASSOCIATED); } + ret = sta_apply_auth_flags(local, sta, mask, set); + if (ret) + return ret; if (mask & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) { if (set & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) @@ -1187,10 +1218,11 @@ static int sta_apply_parameters(struct ieee80211_local *local, sta->sta.aid = params->aid; /* - * FIXME: updating the following information is racy when this - * function is called from ieee80211_change_station(). - * However, all this information should be static so - * maybe we should just reject attemps to change it. + * Some of the following updates would be racy if called on an + * existing station, via ieee80211_change_station(). However, + * all such changes are rejected by cfg80211 except for updates + * changing the supported rates on an existing but not yet used + * TDLS peer. */ if (params->listen_interval >= 0) @@ -1221,18 +1253,33 @@ static int sta_apply_parameters(struct ieee80211_local *local, if (ieee80211_vif_is_mesh(&sdata->vif)) { #ifdef CONFIG_MAC80211_MESH - if (sdata->u.mesh.security & IEEE80211_MESH_SEC_SECURED) + if (sdata->u.mesh.security & IEEE80211_MESH_SEC_SECURED) { + u32 changed = 0; + switch (params->plink_state) { - case NL80211_PLINK_LISTEN: case NL80211_PLINK_ESTAB: + if (sta->plink_state != NL80211_PLINK_ESTAB) + changed = mesh_plink_inc_estab_count( + sdata); + sta->plink_state = params->plink_state; + break; + case NL80211_PLINK_LISTEN: case NL80211_PLINK_BLOCKED: + case NL80211_PLINK_OPN_SNT: + case NL80211_PLINK_OPN_RCVD: + case NL80211_PLINK_CNF_RCVD: + case NL80211_PLINK_HOLDING: + if (sta->plink_state == NL80211_PLINK_ESTAB) + changed = mesh_plink_dec_estab_count( + sdata); sta->plink_state = params->plink_state; break; default: /* nothing */ break; } - else + ieee80211_bss_info_change_notify(sdata, changed); + } else { switch (params->plink_action) { case PLINK_ACTION_OPEN: mesh_plink_open(sta); @@ -1241,6 +1288,7 @@ static int sta_apply_parameters(struct ieee80211_local *local, mesh_plink_block(sta); break; } + } #endif } @@ -1275,6 +1323,10 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (!sta) return -ENOMEM; + /* + * defaults -- if userspace wants something else we'll + * change it accordingly in sta_apply_parameters() + */ sta_info_pre_move_state(sta, IEEE80211_STA_AUTH); sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC); @@ -1311,7 +1363,6 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev, u8 *mac) { - struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -1319,7 +1370,7 @@ static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev, if (mac) return sta_info_destroy_addr_bss(sdata, mac); - sta_info_flush(local, sdata); + sta_info_flush(sdata); return 0; } @@ -1625,6 +1676,9 @@ static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh, memcpy(sdata->vif.bss_conf.mcast_rate, setup->mcast_rate, sizeof(setup->mcast_rate)); + sdata->vif.bss_conf.beacon_int = setup->beacon_interval; + sdata->vif.bss_conf.dtim_period = setup->dtim_period; + return 0; } @@ -2207,7 +2261,8 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - if (sdata->vif.type != NL80211_IFTYPE_STATION) + if (sdata->vif.type != NL80211_IFTYPE_STATION && + sdata->vif.type != NL80211_IFTYPE_MESH_POINT) return -EOPNOTSUPP; if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS)) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 80e55527504..1bfe0a8b19d 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -381,7 +381,8 @@ void ieee80211_iter_chan_contexts_atomic( rcu_read_lock(); list_for_each_entry_rcu(ctx, &local->chanctx_list, list) - iter(hw, &ctx->conf, iter_data); + if (ctx->driver_present) + iter(hw, &ctx->conf, iter_data); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_iter_chan_contexts_atomic); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 698dc7e6f30..0c07f94c537 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -207,6 +207,14 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local, { might_sleep(); + WARN_ON_ONCE(changed & (BSS_CHANGED_BEACON | + BSS_CHANGED_BEACON_ENABLED) && + sdata->vif.type != NL80211_IFTYPE_AP && + sdata->vif.type != NL80211_IFTYPE_ADHOC && + sdata->vif.type != NL80211_IFTYPE_MESH_POINT); + WARN_ON_ONCE(sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE && + changed & ~BSS_CHANGED_IDLE); + check_sdata_in_driver(sdata); trace_drv_bss_info_changed(local, sdata, info, changed); @@ -913,6 +921,8 @@ static inline int drv_add_chanctx(struct ieee80211_local *local, if (local->ops->add_chanctx) ret = local->ops->add_chanctx(&local->hw, &ctx->conf); trace_drv_return_int(local, ret); + if (!ret) + ctx->driver_present = true; return ret; } @@ -924,6 +934,7 @@ static inline void drv_remove_chanctx(struct ieee80211_local *local, if (local->ops->remove_chanctx) local->ops->remove_chanctx(&local->hw, &ctx->conf); trace_drv_return_void(local); + ctx->driver_present = false; } static inline void drv_change_chanctx(struct ieee80211_local *local, @@ -931,8 +942,10 @@ static inline void drv_change_chanctx(struct ieee80211_local *local, u32 changed) { trace_drv_change_chanctx(local, ctx, changed); - if (local->ops->change_chanctx) + if (local->ops->change_chanctx) { + WARN_ON_ONCE(!ctx->driver_present); local->ops->change_chanctx(&local->hw, &ctx->conf, changed); + } trace_drv_return_void(local); } @@ -945,10 +958,12 @@ static inline int drv_assign_vif_chanctx(struct ieee80211_local *local, check_sdata_in_driver(sdata); trace_drv_assign_vif_chanctx(local, sdata, ctx); - if (local->ops->assign_vif_chanctx) + if (local->ops->assign_vif_chanctx) { + WARN_ON_ONCE(!ctx->driver_present); ret = local->ops->assign_vif_chanctx(&local->hw, &sdata->vif, &ctx->conf); + } trace_drv_return_int(local, ret); return ret; @@ -961,10 +976,12 @@ static inline void drv_unassign_vif_chanctx(struct ieee80211_local *local, check_sdata_in_driver(sdata); trace_drv_unassign_vif_chanctx(local, sdata, ctx); - if (local->ops->unassign_vif_chanctx) + if (local->ops->unassign_vif_chanctx) { + WARN_ON_ONCE(!ctx->driver_present); local->ops->unassign_vif_chanctx(&local->hw, &sdata->vif, &ctx->conf); + } trace_drv_return_void(local); } diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index a71d891794a..61ac7c48ac0 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -62,6 +62,9 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata, __check_htcap_disable(sdata, ht_cap, IEEE80211_HT_CAP_SUP_WIDTH_20_40); __check_htcap_disable(sdata, ht_cap, IEEE80211_HT_CAP_SGI_40); + /* Allow user to disable SGI-20 (SGI-40 is handled above) */ + __check_htcap_disable(sdata, ht_cap, IEEE80211_HT_CAP_SGI_20); + /* Allow user to disable the max-AMSDU bit. */ __check_htcap_disable(sdata, ht_cap, IEEE80211_HT_CAP_MAX_AMSDU); @@ -117,6 +120,21 @@ void ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, IEEE80211_HT_CAP_SGI_20 | IEEE80211_HT_CAP_SGI_40 | IEEE80211_HT_CAP_DSSSCCK40)); + + /* Unset 40 MHz if we're not using a 40 MHz channel */ + switch (sdata->vif.bss_conf.chandef.width) { + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + ht_cap->cap &= ~IEEE80211_HT_CAP_SGI_40; + ht_cap->cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; + break; + case NL80211_CHAN_WIDTH_40: + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + break; + } + /* * The STBC bits are asymmetric -- if we don't have * TX then mask out the peer's RX and vice versa. @@ -179,16 +197,19 @@ void ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, ieee80211_apply_htcap_overrides(sdata, ht_cap); } -void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, bool tx) +void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, + enum ieee80211_agg_stop_reason reason) { int i; cancel_work_sync(&sta->ampdu_mlme.work); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { - __ieee80211_stop_tx_ba_session(sta, i, WLAN_BACK_INITIATOR, tx); + __ieee80211_stop_tx_ba_session(sta, i, reason); __ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, - WLAN_REASON_QSTA_LEAVE_QBSS, tx); + WLAN_REASON_QSTA_LEAVE_QBSS, + reason != AGG_STOP_DESTROY_STA && + reason != AGG_STOP_PEER_REQUEST); } } @@ -245,8 +266,7 @@ void ieee80211_ba_session_work(struct work_struct *work) if (tid_tx && test_and_clear_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state)) ___ieee80211_stop_tx_ba_session(sta, tid, - WLAN_BACK_INITIATOR, - true); + AGG_STOP_LOCAL_REQUEST); } mutex_unlock(&sta->ampdu_mlme.mtx); } @@ -314,8 +334,7 @@ void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, __ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_INITIATOR, 0, true); else - __ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_RECIPIENT, - true); + __ieee80211_stop_tx_ba_session(sta, tid, AGG_STOP_PEER_REQUEST); } int ieee80211_send_smps_action(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 6b7644e818d..b4b866f4191 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -67,7 +67,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, skb_reserve(skb, sdata->local->hw.extra_tx_headroom); if (!ether_addr_equal(ifibss->bssid, bssid)) - sta_info_flush(sdata->local, sdata); + sta_info_flush(sdata); /* if merging, indicate to driver that we leave the old IBSS */ if (sdata->vif.bss_conf.ibss_joined) { @@ -191,6 +191,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, rcu_assign_pointer(ifibss->presp, skb); + sdata->vif.bss_conf.enable_beacon = true; sdata->vif.bss_conf.beacon_int = beacon_int; sdata->vif.bss_conf.basic_rates = basic_rates; bss_change = BSS_CHANGED_BEACON_INT; @@ -425,11 +426,9 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata, } static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, - size_t len, + struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status, - struct ieee802_11_elems *elems, - bool beacon) + struct ieee802_11_elems *elems) { struct ieee80211_local *local = sdata->local; int freq; @@ -530,7 +529,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, } bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems, - channel, beacon); + channel); if (!bss) return; @@ -877,14 +876,21 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, ieee80211_tx_skb(sdata, skb); } -static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, - size_t len, - struct ieee80211_rx_status *rx_status) +static +void ieee80211_rx_mgmt_probe_beacon(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len, + struct ieee80211_rx_status *rx_status) { size_t baselen; struct ieee802_11_elems elems; + BUILD_BUG_ON(offsetof(typeof(mgmt->u.probe_resp), variable) != + offsetof(typeof(mgmt->u.beacon), variable)); + + /* + * either beacon or probe_resp but the variable field is at the + * same offset + */ baselen = (u8 *) mgmt->u.probe_resp.variable - (u8 *) mgmt; if (baselen > len) return; @@ -892,25 +898,7 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, ieee802_11_parse_elems(mgmt->u.probe_resp.variable, len - baselen, &elems); - ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, false); -} - -static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, - size_t len, - struct ieee80211_rx_status *rx_status) -{ - size_t baselen; - struct ieee802_11_elems elems; - - /* Process beacon from the current BSS */ - baselen = (u8 *) mgmt->u.beacon.variable - (u8 *) mgmt; - if (baselen > len) - return; - - ieee802_11_parse_elems(mgmt->u.beacon.variable, len - baselen, &elems); - - ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, true); + ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems); } void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, @@ -934,12 +922,9 @@ void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, ieee80211_rx_mgmt_probe_req(sdata, skb); break; case IEEE80211_STYPE_PROBE_RESP: - ieee80211_rx_mgmt_probe_resp(sdata, mgmt, skb->len, - rx_status); - break; case IEEE80211_STYPE_BEACON: - ieee80211_rx_mgmt_beacon(sdata, mgmt, skb->len, - rx_status); + ieee80211_rx_mgmt_probe_beacon(sdata, mgmt, skb->len, + rx_status); break; case IEEE80211_STYPE_AUTH: ieee80211_rx_mgmt_auth_ibss(sdata, mgmt, skb->len); @@ -1182,7 +1167,7 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) memset(ifibss->bssid, 0, ETH_ALEN); ifibss->ssid_len = 0; - sta_info_flush(sdata->local, sdata); + sta_info_flush(sdata); spin_lock_bh(&ifibss->incomplete_lock); while (!list_empty(&ifibss->incomplete_stations)) { @@ -1205,6 +1190,8 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) RCU_INIT_POINTER(sdata->u.ibss.presp, NULL); sdata->vif.bss_conf.ibss_joined = false; sdata->vif.bss_conf.ibss_creator = false; + sdata->vif.bss_conf.enable_beacon = false; + clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED | BSS_CHANGED_IBSS); synchronize_rcu(); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 2ed065c0956..63f0430c131 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -405,6 +405,8 @@ struct ieee80211_mgd_assoc_data { u8 ap_ht_param; + struct ieee80211_vht_cap ap_vht_cap; + size_t ie_len; u8 ie[]; }; @@ -659,10 +661,13 @@ enum ieee80211_sub_if_data_flags { * change handling while the interface is up * @SDATA_STATE_OFFCHANNEL: This interface is currently in offchannel * mode, so queues are stopped + * @SDATA_STATE_OFFCHANNEL_BEACON_STOPPED: Beaconing was stopped due + * to offchannel, reset when offchannel returns */ enum ieee80211_sdata_state_bits { SDATA_STATE_RUNNING, SDATA_STATE_OFFCHANNEL, + SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, }; /** @@ -685,6 +690,7 @@ struct ieee80211_chanctx { enum ieee80211_chanctx_mode mode; int refcount; + bool driver_present; struct ieee80211_chanctx_conf conf; }; @@ -783,6 +789,11 @@ struct ieee80211_sub_if_data { struct dentry *default_mgmt_key; } debugfs; #endif + +#ifdef CONFIG_PM + struct ieee80211_bss_conf suspend_bss_conf; +#endif + /* must be last, dynamically sized area in this! */ struct ieee80211_vif vif; }; @@ -1346,8 +1357,7 @@ ieee80211_bss_info_update(struct ieee80211_local *local, struct ieee80211_mgmt *mgmt, size_t len, struct ieee802_11_elems *elems, - struct ieee80211_channel *channel, - bool beacon); + struct ieee80211_channel *channel); void ieee80211_rx_bss_put(struct ieee80211_local *local, struct ieee80211_bss *bss); @@ -1420,7 +1430,8 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, u16 initiator, u16 reason, bool stop); void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, u16 initiator, u16 reason, bool stop); -void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, bool tx); +void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, + enum ieee80211_agg_stop_reason reason); void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_mgmt *mgmt, size_t len); @@ -1434,11 +1445,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, size_t len); int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, - enum ieee80211_back_parties initiator, - bool tx); + enum ieee80211_agg_stop_reason reason); int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, - enum ieee80211_back_parties initiator, - bool tx); + enum ieee80211_agg_stop_reason reason); void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid); void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid); void ieee80211_ba_session_work(struct work_struct *work); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 8be854e86cd..06fac2991d4 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -747,7 +747,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, unsigned long flags; struct sk_buff *skb, *tmp; u32 hw_reconf_flags = 0; - int i; + int i, flushed; clear_bit(SDATA_STATE_RUNNING, &sdata->state); @@ -772,11 +772,15 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, * (because if we remove a STA after ops->remove_interface() * the driver will have removed the vif info already!) * - * This is relevant only in AP, WDS and mesh modes, since in - * all other modes we've already removed all stations when - * disconnecting etc. + * 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. */ - sta_info_flush(local, sdata); + flushed = sta_info_flush_defer(sdata); + WARN_ON_ONCE((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) || + (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1)); /* * Don't count this interface for promisc/allmulti while it @@ -859,11 +863,17 @@ 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. - * Call synchronize_rcu() to wait for the RX path - * should it be using the interface and enqueuing - * frames at this very time on another CPU. + * + * sta_info_flush_cleanup() requires rcu_barrier() + * first to wait for the station call_rcu() calls + * to complete, here we need at least sychronize_rcu() + * it to wait for the RX path in case it is using the + * interface and enqueuing frames at this very time on + * another CPU. */ - synchronize_rcu(); + rcu_barrier(); + sta_info_flush_cleanup(sdata); + skb_queue_purge(&sdata->skb_queue); /* @@ -961,7 +971,6 @@ static void ieee80211_set_multicast_list(struct net_device *dev) */ static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata) { - struct ieee80211_local *local = sdata->local; int flushed; int i; @@ -977,7 +986,7 @@ 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(local, sdata); + flushed = sta_info_flush(sdata); WARN_ON(flushed); } @@ -1218,6 +1227,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_AP: skb_queue_head_init(&sdata->u.ap.ps.bc_buf); INIT_LIST_HEAD(&sdata->u.ap.vlans); + sdata->vif.bss_conf.bssid = sdata->vif.addr; break; case NL80211_IFTYPE_P2P_CLIENT: type = NL80211_IFTYPE_STATION; @@ -1225,9 +1235,11 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, sdata->vif.p2p = true; /* fall through */ case NL80211_IFTYPE_STATION: + sdata->vif.bss_conf.bssid = sdata->u.mgd.bssid; ieee80211_sta_setup_sdata(sdata); break; case NL80211_IFTYPE_ADHOC: + sdata->vif.bss_conf.bssid = sdata->u.ibss.bssid; ieee80211_ibss_setup_sdata(sdata); break; case NL80211_IFTYPE_MESH_POINT: @@ -1241,8 +1253,12 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, MONITOR_FLAG_OTHER_BSS; break; case NL80211_IFTYPE_WDS: + sdata->vif.bss_conf.bssid = NULL; + break; case NL80211_IFTYPE_AP_VLAN: + break; case NL80211_IFTYPE_P2P_DEVICE: + sdata->vif.bss_conf.bssid = sdata->vif.addr; break; case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 1b087fff93e..39cfe8f10ad 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -207,76 +207,10 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, u32 changed) { struct ieee80211_local *local = sdata->local; - static const u8 zero[ETH_ALEN] = { 0 }; if (!changed) return; - if (sdata->vif.type == NL80211_IFTYPE_STATION) { - sdata->vif.bss_conf.bssid = sdata->u.mgd.bssid; - } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - sdata->vif.bss_conf.bssid = sdata->u.ibss.bssid; - else if (sdata->vif.type == NL80211_IFTYPE_AP) - sdata->vif.bss_conf.bssid = sdata->vif.addr; - else if (sdata->vif.type == NL80211_IFTYPE_WDS) - sdata->vif.bss_conf.bssid = NULL; - else if (ieee80211_vif_is_mesh(&sdata->vif)) { - sdata->vif.bss_conf.bssid = zero; - } else if (sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE) { - sdata->vif.bss_conf.bssid = sdata->vif.addr; - WARN_ONCE(changed & ~(BSS_CHANGED_IDLE), - "P2P Device BSS changed %#x", changed); - } else { - WARN_ON(1); - return; - } - - switch (sdata->vif.type) { - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_WDS: - case NL80211_IFTYPE_MESH_POINT: - break; - default: - /* do not warn to simplify caller in scan.c */ - changed &= ~BSS_CHANGED_BEACON_ENABLED; - if (WARN_ON(changed & BSS_CHANGED_BEACON)) - return; - break; - } - - if (changed & BSS_CHANGED_BEACON_ENABLED) { - if (local->quiescing || !ieee80211_sdata_running(sdata) || - test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) { - sdata->vif.bss_conf.enable_beacon = false; - } else { - /* - * Beacon should be enabled, but AP mode must - * check whether there is a beacon configured. - */ - switch (sdata->vif.type) { - case NL80211_IFTYPE_AP: - sdata->vif.bss_conf.enable_beacon = - !!sdata->u.ap.beacon; - break; - case NL80211_IFTYPE_ADHOC: - sdata->vif.bss_conf.enable_beacon = - !!sdata->u.ibss.presp; - break; -#ifdef CONFIG_MAC80211_MESH - case NL80211_IFTYPE_MESH_POINT: - sdata->vif.bss_conf.enable_beacon = - !!sdata->u.mesh.mesh_id_len; - break; -#endif - default: - /* not reached */ - WARN_ON(1); - break; - } - } - } - drv_bss_info_changed(local, sdata, &sdata->vif.bss_conf, changed); } @@ -537,6 +471,7 @@ static const struct ieee80211_ht_cap mac80211_ht_capa_mod_mask = { .cap_info = cpu_to_le16(IEEE80211_HT_CAP_SUP_WIDTH_20_40 | IEEE80211_HT_CAP_MAX_AMSDU | + IEEE80211_HT_CAP_SGI_20 | IEEE80211_HT_CAP_SGI_40), .mcs = { .rx_mask = { 0xff, 0xff, 0xff, 0xff, 0xff, @@ -606,7 +541,8 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, wiphy->features |= NL80211_FEATURE_SK_TX_STATUS | NL80211_FEATURE_SAE | NL80211_FEATURE_HT_IBSS | - NL80211_FEATURE_VIF_TXPOWER; + NL80211_FEATURE_VIF_TXPOWER | + NL80211_FEATURE_FULL_AP_CLIENT_STATE; if (!ops->hw_scan) wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN | diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 649ad513547..694e27376af 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -20,16 +20,11 @@ int mesh_allocated; static struct kmem_cache *rm_cache; -#ifdef CONFIG_MAC80211_MESH bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt) { return (mgmt->u.action.u.mesh_action.action_code == WLAN_MESH_ACTION_HWMP_PATH_SELECTION); } -#else -bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt) -{ return false; } -#endif void ieee80211s_init(void) { @@ -607,6 +602,12 @@ void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_local *local = sdata->local; + u32 changed = BSS_CHANGED_BEACON | + BSS_CHANGED_BEACON_ENABLED | + BSS_CHANGED_HT | + BSS_CHANGED_BASIC_RATES | + BSS_CHANGED_BEACON_INT; + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); local->fif_other_bss++; /* mesh ifaces must set allmulti to forward mcast traffic */ @@ -624,15 +625,16 @@ void ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata) ieee80211_queue_work(&local->hw, &sdata->work); sdata->vif.bss_conf.ht_operation_mode = ifmsh->mshcfg.ht_opmode; - sdata->vif.bss_conf.beacon_int = MESH_DEFAULT_BEACON_INTERVAL; + sdata->vif.bss_conf.enable_beacon = true; sdata->vif.bss_conf.basic_rates = - ieee80211_mandatory_rates(sdata->local, - ieee80211_get_sdata_band(sdata)); - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON | - BSS_CHANGED_BEACON_ENABLED | - BSS_CHANGED_HT | - BSS_CHANGED_BASIC_RATES | - BSS_CHANGED_BEACON_INT); + ieee80211_mandatory_rates(local, band); + + if (band == IEEE80211_BAND_5GHZ) { + sdata->vif.bss_conf.use_short_slot = true; + changed |= BSS_CHANGED_ERP_SLOT; + } + + ieee80211_bss_info_change_notify(sdata, changed); netif_carrier_on(sdata->dev); } @@ -646,10 +648,12 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) /* stop the beacon */ ifmsh->mesh_id_len = 0; + sdata->vif.bss_conf.enable_beacon = false; + clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); /* flush STAs and mpaths on this iface */ - sta_info_flush(sdata->local, sdata); + sta_info_flush(sdata); mesh_path_flush_by_iface(sdata); del_timer_sync(&sdata->u.mesh.housekeeping_timer); @@ -805,6 +809,7 @@ void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + static u8 zero_addr[ETH_ALEN] = {}; setup_timer(&ifmsh->housekeeping_timer, ieee80211_mesh_housekeeping_timer, @@ -830,4 +835,6 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) INIT_LIST_HEAD(&ifmsh->preq_queue.list); spin_lock_init(&ifmsh->mesh_preq_queue_lock); spin_lock_init(&ifmsh->sync_offset_lock); + + sdata->vif.bss_conf.bssid = zero_addr; } diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 84c28c6101c..aff301544c7 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -191,8 +191,6 @@ struct mesh_rmc { #define IEEE80211_MESH_PEER_INACTIVITY_LIMIT (1800 * HZ) #define IEEE80211_MESH_HOUSEKEEPING_INTERVAL (60 * HZ) -#define MESH_DEFAULT_BEACON_INTERVAL 1000 /* in 1024 us units */ - #define MESH_PATH_EXPIRE (600 * HZ) /* Default maximum number of plinks per interface */ @@ -307,6 +305,20 @@ extern int mesh_paths_generation; #ifdef CONFIG_MAC80211_MESH extern int mesh_allocated; +static inline +u32 mesh_plink_inc_estab_count(struct ieee80211_sub_if_data *sdata) +{ + atomic_inc(&sdata->u.mesh.estab_plinks); + return mesh_accept_plinks_update(sdata); +} + +static inline +u32 mesh_plink_dec_estab_count(struct ieee80211_sub_if_data *sdata) +{ + atomic_dec(&sdata->u.mesh.estab_plinks); + return mesh_accept_plinks_update(sdata); +} + static inline int mesh_plink_free_count(struct ieee80211_sub_if_data *sdata) { return sdata->u.mesh.mshcfg.dot11MeshMaxPeerLinks - diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 2659e428b80..6b4603a9003 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -220,12 +220,14 @@ static void prepare_frame_for_deferred_tx(struct ieee80211_sub_if_data *sdata, } /** - * mesh_send_path error - Sends a PERR mesh management frame + * mesh_path_error_tx - Sends a PERR mesh management frame * + * @ttl: allowed remaining hops * @target: broken destination * @target_sn: SN of the broken destination * @target_rcode: reason code for this PERR * @ra: node this frame is addressed to + * @sdata: local mesh subif * * Note: This function may be called with driver locks taken that the driver * also acquires in the TX path. To avoid a deadlock we don't transmit the @@ -353,6 +355,7 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local, * @sdata: local mesh subif * @mgmt: mesh management frame * @hwmp_ie: hwmp information element (PREP or PREQ) + * @action: type of hwmp ie * * This function updates the path routing information to the originator and the * transmitter of a HWMP PREQ or PREP frame. diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 4b274e9c91a..9e0416696a8 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -41,20 +41,6 @@ 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); -static inline -u32 mesh_plink_inc_estab_count(struct ieee80211_sub_if_data *sdata) -{ - atomic_inc(&sdata->u.mesh.estab_plinks); - return mesh_accept_plinks_update(sdata); -} - -static inline -u32 mesh_plink_dec_estab_count(struct ieee80211_sub_if_data *sdata) -{ - atomic_dec(&sdata->u.mesh.estab_plinks); - return mesh_accept_plinks_update(sdata); -} - /** * mesh_plink_fsm_restart - restart a mesh peer link finite state machine * diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a3552929a21..e930175771f 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -199,11 +199,11 @@ static u32 ieee80211_config_ht_tx(struct ieee80211_sub_if_data *sdata, case NL80211_CHAN_WIDTH_40: if (sdata->vif.bss_conf.chandef.chan->center_freq > sdata->vif.bss_conf.chandef.center_freq1 && - chan->flags & IEEE80211_CHAN_NO_HT40PLUS) + chan->flags & IEEE80211_CHAN_NO_HT40MINUS) disable_40 = true; if (sdata->vif.bss_conf.chandef.chan->center_freq < sdata->vif.bss_conf.chandef.center_freq1 && - chan->flags & IEEE80211_CHAN_NO_HT40MINUS) + chan->flags & IEEE80211_CHAN_NO_HT40PLUS) disable_40 = true; break; default: @@ -341,11 +341,13 @@ static void ieee80211_add_ht_ie(struct ieee80211_sub_if_data *sdata, static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - struct ieee80211_supported_band *sband) + struct ieee80211_supported_band *sband, + struct ieee80211_vht_cap *ap_vht_cap) { u8 *pos; u32 cap; struct ieee80211_sta_vht_cap vht_cap; + int i; BUILD_BUG_ON(sizeof(vht_cap) != sizeof(sband->vht_cap)); @@ -364,6 +366,42 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, cap &= ~IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ; } + /* + * Some APs apparently get confused if our capabilities are better + * than theirs, so restrict what we advertise in the assoc request. + */ + if (!(ap_vht_cap->vht_cap_info & + cpu_to_le32(IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE))) + cap &= ~IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE; + + if (!(ap_vht_cap->vht_cap_info & + cpu_to_le32(IEEE80211_VHT_CAP_TXSTBC))) + cap &= ~(IEEE80211_VHT_CAP_RXSTBC_1 | + IEEE80211_VHT_CAP_RXSTBC_3 | + IEEE80211_VHT_CAP_RXSTBC_4); + + for (i = 0; i < 8; i++) { + int shift = i * 2; + u16 mask = IEEE80211_VHT_MCS_NOT_SUPPORTED << shift; + u16 ap_mcs, our_mcs; + + ap_mcs = (le16_to_cpu(ap_vht_cap->supp_mcs.tx_mcs_map) & + mask) >> shift; + our_mcs = (le16_to_cpu(vht_cap.vht_mcs.rx_mcs_map) & + mask) >> shift; + + switch (ap_mcs) { + default: + if (our_mcs <= ap_mcs) + break; + /* fall through */ + case IEEE80211_VHT_MCS_NOT_SUPPORTED: + vht_cap.vht_mcs.rx_mcs_map &= cpu_to_le16(~mask); + vht_cap.vht_mcs.rx_mcs_map |= + cpu_to_le16(ap_mcs << shift); + } + } + /* reserve and fill IE */ pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2); ieee80211_ie_build_vht_cap(pos, &vht_cap, cap); @@ -562,7 +600,8 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) sband, chan, sdata->smps_mode); if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) - ieee80211_add_vht_ie(sdata, skb, sband); + ieee80211_add_vht_ie(sdata, skb, sband, + &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) { @@ -1486,7 +1525,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sta = sta_info_get(sdata, ifmgd->bssid); if (sta) { set_sta_flag(sta, WLAN_STA_BLOCK_BA); - ieee80211_sta_tear_down_BA_sessions(sta, false); + ieee80211_sta_tear_down_BA_sessions(sta, AGG_STOP_DESTROY_STA); } mutex_unlock(&local->sta_mtx); @@ -1521,7 +1560,7 @@ 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(local, sdata); + sta_info_flush_defer(sdata); /* finally reset all BSS / config parameters */ changed |= ieee80211_reset_erp_info(sdata); @@ -2369,8 +2408,7 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status, - struct ieee802_11_elems *elems, - bool beacon) + struct ieee802_11_elems *elems) { struct ieee80211_local *local = sdata->local; int freq; @@ -2404,7 +2442,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, return; bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems, - channel, beacon); + channel); if (bss) ieee80211_rx_bss_put(local, bss); @@ -2447,7 +2485,7 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, ieee802_11_parse_elems(mgmt->u.probe_resp.variable, len - baselen, &elems); - ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, false); + ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems); if (ifmgd->associated && ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid)) @@ -2528,8 +2566,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ieee802_11_parse_elems(mgmt->u.beacon.variable, len - baselen, &elems); - ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, - false); + ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems); ifmgd->assoc_data->have_beacon = true; ifmgd->assoc_data->sent_assoc = false; /* continue assoc process */ @@ -2682,8 +2719,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ifmgd->beacon_crc = ncrc; ifmgd->beacon_crc_valid = true; - ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems, - true); + ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, &elems); if (ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, elems.wmm_param_len)) @@ -3756,7 +3792,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_bss *bss = (void *)req->bss->priv; struct ieee80211_mgd_assoc_data *assoc_data; struct ieee80211_supported_band *sband; - const u8 *ssidie, *ht_ie; + const u8 *ssidie, *ht_ie, *vht_ie; int i, err; assoc_data = kzalloc(sizeof(*assoc_data) + req->ie_len, GFP_KERNEL); @@ -3875,6 +3911,12 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, ((struct ieee80211_ht_operation *)(ht_ie + 2))->ht_param; else ifmgd->flags |= IEEE80211_STA_DISABLE_HT; + vht_ie = ieee80211_bss_get_ie(req->bss, WLAN_EID_VHT_CAPABILITY); + if (vht_ie && vht_ie[1] >= sizeof(struct ieee80211_vht_cap)) + memcpy(&assoc_data->ap_vht_cap, vht_ie + 2, + sizeof(struct ieee80211_vht_cap)); + else + ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; rcu_read_unlock(); if (bss->wmm_used && bss->uapsd_supported && diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index a3ad4c3c80a..82baf5b6ecf 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -125,11 +125,13 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local) set_bit(SDATA_STATE_OFFCHANNEL, &sdata->state); /* Check to see if we should disable beaconing. */ - if (sdata->vif.type == NL80211_IFTYPE_AP || - sdata->vif.type == NL80211_IFTYPE_ADHOC || - sdata->vif.type == NL80211_IFTYPE_MESH_POINT) + if (sdata->vif.bss_conf.enable_beacon) { + set_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, + &sdata->state); + sdata->vif.bss_conf.enable_beacon = false; ieee80211_bss_info_change_notify( sdata, BSS_CHANGED_BEACON_ENABLED); + } if (sdata->vif.type != NL80211_IFTYPE_MONITOR) { netif_tx_stop_all_queues(sdata->dev); @@ -178,11 +180,12 @@ void ieee80211_offchannel_return(struct ieee80211_local *local) netif_tx_wake_all_queues(sdata->dev); } - if (sdata->vif.type == NL80211_IFTYPE_AP || - sdata->vif.type == NL80211_IFTYPE_ADHOC || - sdata->vif.type == NL80211_IFTYPE_MESH_POINT) + if (test_and_clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, + &sdata->state)) { + sdata->vif.bss_conf.enable_beacon = true; ieee80211_bss_info_change_notify( sdata, BSS_CHANGED_BEACON_ENABLED); + } } mutex_unlock(&local->iflist_mtx); } diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 79a48f37d40..e45b83610e8 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -7,25 +7,23 @@ #include "led.h" /* return value indicates whether the driver should be further notified */ -static bool ieee80211_quiesce(struct ieee80211_sub_if_data *sdata) +static void ieee80211_quiesce(struct ieee80211_sub_if_data *sdata) { switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: ieee80211_sta_quiesce(sdata); - return true; + break; case NL80211_IFTYPE_ADHOC: ieee80211_ibss_quiesce(sdata); - return true; + break; case NL80211_IFTYPE_MESH_POINT: ieee80211_mesh_quiesce(sdata); - return true; - case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_MONITOR: - /* don't tell driver about this */ - return false; + break; default: - return true; + break; } + + cancel_work_sync(&sdata->work); } int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) @@ -44,7 +42,8 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) mutex_lock(&local->sta_mtx); list_for_each_entry(sta, &local->sta_list, list) { set_sta_flag(sta, WLAN_STA_BLOCK_BA); - ieee80211_sta_tear_down_BA_sessions(sta, true); + ieee80211_sta_tear_down_BA_sessions( + sta, AGG_STOP_LOCAL_REQUEST); } mutex_unlock(&local->sta_mtx); } @@ -94,10 +93,9 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) WARN_ON(err != 1); local->wowlan = false; } else { - list_for_each_entry(sdata, &local->interfaces, list) { - cancel_work_sync(&sdata->work); - ieee80211_quiesce(sdata); - } + list_for_each_entry(sdata, &local->interfaces, list) + if (ieee80211_sdata_running(sdata)) + ieee80211_quiesce(sdata); goto suspend; } } @@ -124,17 +122,43 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) /* remove all interfaces */ list_for_each_entry(sdata, &local->interfaces, list) { - cancel_work_sync(&sdata->work); + static u8 zero_addr[ETH_ALEN] = {}; + u32 changed = 0; - if (!ieee80211_quiesce(sdata)) + if (!ieee80211_sdata_running(sdata)) continue; - if (!ieee80211_sdata_running(sdata)) + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_MONITOR: + /* skip these */ continue; + case NL80211_IFTYPE_STATION: + if (sdata->vif.bss_conf.assoc) + changed = BSS_CHANGED_ASSOC | + BSS_CHANGED_BSSID | + BSS_CHANGED_IDLE; + break; + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_MESH_POINT: + if (sdata->vif.bss_conf.enable_beacon) + changed = BSS_CHANGED_BEACON_ENABLED; + break; + default: + break; + } + + ieee80211_quiesce(sdata); + + sdata->suspend_bss_conf = sdata->vif.bss_conf; + memset(&sdata->vif.bss_conf, 0, sizeof(sdata->vif.bss_conf)); + sdata->vif.bss_conf.idle = true; + if (sdata->suspend_bss_conf.bssid) + sdata->vif.bss_conf.bssid = zero_addr; - /* disable beaconing */ - ieee80211_bss_info_change_notify(sdata, - BSS_CHANGED_BEACON_ENABLED); + /* disable beaconing or remove association */ + ieee80211_bss_info_change_notify(sdata, changed); if (sdata->vif.type == NL80211_IFTYPE_AP && rcu_access_pointer(sdata->u.ap.beacon)) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 580704eba8b..a19089565c4 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2353,7 +2353,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) sdata->vif.type != NL80211_IFTYPE_ADHOC) break; - /* verify action & smps_control are present */ + /* verify action & smps_control/chanwidth are present */ if (len < IEEE80211_MIN_ACTION_SIZE + 2) goto invalid; @@ -2392,6 +2392,35 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) IEEE80211_RC_SMPS_CHANGED); goto handled; } + case WLAN_HT_ACTION_NOTIFY_CHANWIDTH: { + struct ieee80211_supported_band *sband; + u8 chanwidth = mgmt->u.action.u.ht_notify_cw.chanwidth; + bool old_40mhz, new_40mhz; + + /* If it doesn't support 40 MHz it can't change ... */ + if (!rx->sta->supports_40mhz) + goto handled; + + old_40mhz = rx->sta->sta.ht_cap.cap & + IEEE80211_HT_CAP_SUP_WIDTH_20_40; + new_40mhz = chanwidth == IEEE80211_HT_CHANWIDTH_ANY; + + if (old_40mhz == new_40mhz) + goto handled; + + if (new_40mhz) + rx->sta->sta.ht_cap.cap |= + IEEE80211_HT_CAP_SUP_WIDTH_20_40; + else + rx->sta->sta.ht_cap.cap &= + ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; + + sband = rx->local->hw.wiphy->bands[status->band]; + + rate_control_rate_update(local, sband, rx->sta, + IEEE80211_RC_BW_CHANGED); + goto handled; + } default: goto invalid; } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index bf82e69d060..607684c47d5 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -65,12 +65,11 @@ static bool is_uapsd_supported(struct ieee802_11_elems *elems) struct ieee80211_bss * ieee80211_bss_info_update(struct ieee80211_local *local, struct ieee80211_rx_status *rx_status, - struct ieee80211_mgmt *mgmt, - size_t len, + struct ieee80211_mgmt *mgmt, size_t len, struct ieee802_11_elems *elems, - struct ieee80211_channel *channel, - bool beacon) + struct ieee80211_channel *channel) { + bool beacon = ieee80211_is_beacon(mgmt->frame_control); struct cfg80211_bss *cbss; struct ieee80211_bss *bss; int clen, srlen; @@ -203,7 +202,7 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) bss = ieee80211_bss_info_update(local, rx_status, mgmt, skb->len, &elems, - channel, beacon); + channel); if (bss) ieee80211_rx_bss_put(local, bss); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index ca9fde19818..9d864ed5f3d 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -104,6 +104,16 @@ static void cleanup_single_sta(struct sta_info *sta) * 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)) { @@ -774,7 +784,7 @@ int __must_check __sta_info_destroy(struct sta_info *sta) * will be sufficient. */ set_sta_flag(sta, WLAN_STA_BLOCK_BA); - ieee80211_sta_tear_down_BA_sessions(sta, false); + ieee80211_sta_tear_down_BA_sessions(sta, AGG_STOP_DESTROY_STA); ret = sta_info_hash_del(local, sta); if (ret) @@ -885,20 +895,12 @@ void sta_info_init(struct ieee80211_local *local) void sta_info_stop(struct ieee80211_local *local) { del_timer_sync(&local->sta_cleanup); - sta_info_flush(local, NULL); } -/** - * sta_info_flush - flush matching STA entries from the STA table - * - * Returns the number of removed STA entries. - * - * @local: local interface data - * @sdata: matching rule for the net device (sta->dev) or %NULL to match all STAs - */ -int sta_info_flush(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) + +int sta_info_flush_defer(struct ieee80211_sub_if_data *sdata) { + struct ieee80211_local *local = sdata->local; struct sta_info *sta, *tmp; int ret = 0; @@ -906,30 +908,22 @@ int sta_info_flush(struct ieee80211_local *local, mutex_lock(&local->sta_mtx); list_for_each_entry_safe(sta, tmp, &local->sta_list, list) { - if (!sdata || sdata == sta->sdata) { + if (sdata == sta->sdata) { WARN_ON(__sta_info_destroy(sta)); ret++; } } mutex_unlock(&local->sta_mtx); - rcu_barrier(); - - if (sdata) { - ieee80211_cleanup_sdata_stas(sdata); - cancel_work_sync(&sdata->cleanup_stations_wk); - } else { - mutex_lock(&local->iflist_mtx); - list_for_each_entry(sdata, &local->interfaces, list) { - ieee80211_cleanup_sdata_stas(sdata); - cancel_work_sync(&sdata->cleanup_stations_wk); - } - mutex_unlock(&local->iflist_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) { diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 37c1889afd3..af7d78aa552 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -92,6 +92,13 @@ enum ieee80211_sta_info_flags { #define HT_AGG_STATE_WANT_START 4 #define HT_AGG_STATE_WANT_STOP 5 +enum ieee80211_agg_stop_reason { + AGG_STOP_DECLINED, + AGG_STOP_LOCAL_REQUEST, + AGG_STOP_PEER_REQUEST, + AGG_STOP_DESTROY_STA, +}; + /** * struct tid_ampdu_tx - TID aggregation information (Tx). * @@ -548,8 +555,39 @@ 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(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata); +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 + * + * Returns the number of removed STA entries. + * + * @sdata: sdata to remove all stations from + */ +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; +} + void sta_set_rate_info_tx(struct sta_info *sta, const struct ieee80211_tx_rate *rate, struct rate_info *rinfo); diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index a8270b441a6..41861b91daa 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -28,21 +28,27 @@ #define VIF_PR_FMT " vif:%s(%d%s)" #define VIF_PR_ARG __get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : "" -#define CHANCTX_ENTRY __field(u32, control_freq) \ +#define CHANDEF_ENTRY __field(u32, control_freq) \ __field(u32, chan_width) \ __field(u32, center_freq1) \ - __field(u32, center_freq2) \ + __field(u32, center_freq2) +#define CHANDEF_ASSIGN(c) \ + __entry->control_freq = (c)->chan->center_freq; \ + __entry->chan_width = (c)->width; \ + __entry->center_freq1 = (c)->center_freq1; \ + __entry->center_freq1 = (c)->center_freq2; +#define CHANDEF_PR_FMT " control:%d MHz width:%d center: %d/%d MHz" +#define CHANDEF_PR_ARG __entry->control_freq, __entry->chan_width, \ + __entry->center_freq1, __entry->center_freq2 + +#define CHANCTX_ENTRY CHANDEF_ENTRY \ __field(u8, rx_chains_static) \ __field(u8, rx_chains_dynamic) -#define CHANCTX_ASSIGN __entry->control_freq = ctx->conf.def.chan->center_freq;\ - __entry->chan_width = ctx->conf.def.width; \ - __entry->center_freq1 = ctx->conf.def.center_freq1; \ - __entry->center_freq2 = ctx->conf.def.center_freq2; \ +#define CHANCTX_ASSIGN CHANDEF_ASSIGN(&ctx->conf.def) \ __entry->rx_chains_static = ctx->conf.rx_chains_static; \ __entry->rx_chains_dynamic = ctx->conf.rx_chains_dynamic -#define CHANCTX_PR_FMT " control:%d MHz width:%d center: %d/%d MHz chains:%d/%d" -#define CHANCTX_PR_ARG __entry->control_freq, __entry->chan_width, \ - __entry->center_freq1, __entry->center_freq2, \ +#define CHANCTX_PR_FMT CHANDEF_PR_FMT " chains:%d/%d" +#define CHANCTX_PR_ARG CHANDEF_PR_ARG, \ __entry->rx_chains_static, __entry->rx_chains_dynamic diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 467c1d1b66f..f32d68186db 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2264,9 +2264,8 @@ void ieee80211_tx_pending(unsigned long data) /* functions for drivers to get certain frames */ -static void ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, - struct ps_data *ps, - struct sk_buff *skb) +static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, + struct ps_data *ps, struct sk_buff *skb) { u8 *pos, *tim; int aid0 = 0; @@ -2328,6 +2327,31 @@ static void ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, } } +static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, + struct ps_data *ps, struct sk_buff *skb) +{ + struct ieee80211_local *local = sdata->local; + + /* + * Not very nice, but we want to allow the driver to call + * ieee80211_beacon_get() as a response to the set_tim() + * callback. That, however, is already invoked under the + * sta_lock to guarantee consistent and race-free update + * of the tim bitmap in mac80211 and the driver. + */ + if (local->tim_in_locked_section) { + __ieee80211_beacon_add_tim(sdata, ps, skb); + } else { + unsigned long flags; + + spin_lock_irqsave(&local->tim_lock, flags); + __ieee80211_beacon_add_tim(sdata, ps, skb); + spin_unlock_irqrestore(&local->tim_lock, flags); + } + + return 0; +} + struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 *tim_offset, u16 *tim_length) @@ -2372,22 +2396,7 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, memcpy(skb_put(skb, beacon->head_len), beacon->head, beacon->head_len); - /* - * Not very nice, but we want to allow the driver to call - * ieee80211_beacon_get() as a response to the set_tim() - * callback. That, however, is already invoked under the - * sta_lock to guarantee consistent and race-free update - * of the tim bitmap in mac80211 and the driver. - */ - if (local->tim_in_locked_section) { - ieee80211_beacon_add_tim(sdata, &ap->ps, skb); - } else { - unsigned long flags; - - spin_lock_irqsave(&local->tim_lock, flags); - ieee80211_beacon_add_tim(sdata, &ap->ps, skb); - spin_unlock_irqrestore(&local->tim_lock, flags); - } + ieee80211_beacon_add_tim(sdata, &ap->ps, skb); if (tim_offset) *tim_offset = beacon->head_len; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index f11e8c540db..7519018ff71 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1358,6 +1358,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) struct ieee80211_chanctx *ctx; struct sta_info *sta; int res, i; + bool reconfig_due_to_wowlan = false; #ifdef CONFIG_PM if (local->suspended) @@ -1377,6 +1378,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) * res is 1, which means the driver requested * to go through a regular reset on wakeup. */ + reconfig_due_to_wowlan = true; } #endif /* everything else happens only if HW was up & running */ @@ -1526,6 +1528,11 @@ int ieee80211_reconfig(struct ieee80211_local *local) BSS_CHANGED_IDLE | BSS_CHANGED_TXPOWER; +#ifdef CONFIG_PM + if (local->resuming && !reconfig_due_to_wowlan) + sdata->vif.bss_conf = sdata->suspend_bss_conf; +#endif + switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: changed |= BSS_CHANGED_ASSOC | @@ -1550,9 +1557,11 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* fall through */ case NL80211_IFTYPE_MESH_POINT: - changed |= BSS_CHANGED_BEACON | - BSS_CHANGED_BEACON_ENABLED; - ieee80211_bss_info_change_notify(sdata, changed); + if (sdata->vif.bss_conf.enable_beacon) { + changed |= BSS_CHANGED_BEACON | + BSS_CHANGED_BEACON_ENABLED; + ieee80211_bss_info_change_notify(sdata, changed); + } break; case NL80211_IFTYPE_WDS: break; @@ -1632,7 +1641,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) mutex_lock(&local->sta_mtx); list_for_each_entry(sta, &local->sta_list, list) { - ieee80211_sta_tear_down_BA_sessions(sta, true); + ieee80211_sta_tear_down_BA_sessions( + sta, AGG_STOP_LOCAL_REQUEST); clear_sta_flag(sta, WLAN_STA_BLOCK_BA); } @@ -1646,10 +1656,11 @@ int ieee80211_reconfig(struct ieee80211_local *local) * If this is for hw restart things are still running. * We may want to change that later, however. */ - if (!local->suspended) { + if (!local->suspended || reconfig_due_to_wowlan) drv_restart_complete(local); + + if (!local->suspended) return 0; - } #ifdef CONFIG_PM /* first set suspended false, then resuming */ @@ -1864,7 +1875,7 @@ u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, } u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, - u32 cap) + u32 cap) { __le32 tmp; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 49e96df5fbc..eb2c8ebf6d9 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -124,6 +124,12 @@ config NF_CONNTRACK_TIMESTAMP If unsure, say `N'. +config NF_CONNTRACK_LABELS + bool + help + This option enables support for assigning user-defined flag bits + to connection tracking entries. It selected by the connlabel match. + config NF_CT_PROTO_DCCP tristate 'DCCP protocol connection tracking support (EXPERIMENTAL)' depends on EXPERIMENTAL @@ -805,6 +811,15 @@ config NETFILTER_XT_MATCH_ADDRTYPE If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. +config NETFILTER_XT_MATCH_BPF + tristate '"bpf" match support' + depends on NETFILTER_ADVANCED + help + BPF matching applies a linux socket filter to each packet and + accepts those for which the filter returns non-zero. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_MATCH_CLUSTER tristate '"cluster" match support' depends on NF_CONNTRACK @@ -842,6 +857,18 @@ config NETFILTER_XT_MATCH_CONNBYTES If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. +config NETFILTER_XT_MATCH_CONNLABEL + tristate '"connlabel" match support' + select NF_CONNTRACK_LABELS + depends on NETFILTER_ADVANCED + ---help--- + This match allows you to test and assign userspace-defined labels names + to a connection. The kernel only stores bit values - mapping + names to bits is done by userspace. + + Unlike connmark, more than 32 flag bits may be assigned to a + connection simultaneously. + config NETFILTER_XT_MATCH_CONNLIMIT tristate '"connlimit" match support"' depends on NF_CONNTRACK diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 32596978df1..a1abf87d43b 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -4,6 +4,7 @@ nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_exp nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o +nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o obj-$(CONFIG_NETFILTER) = netfilter.o @@ -98,9 +99,11 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_IDLETIMER) += xt_IDLETIMER.o # matches obj-$(CONFIG_NETFILTER_XT_MATCH_ADDRTYPE) += xt_addrtype.o +obj-$(CONFIG_NETFILTER_XT_MATCH_BPF) += xt_bpf.o obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o +obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLABEL) += xt_connlabel.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o obj-$(CONFIG_NETFILTER_XT_MATCH_CPU) += xt_cpu.o diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c index 7df424e2d10..2d3030ab5b6 100644 --- a/net/netfilter/nf_conntrack_acct.c +++ b/net/netfilter/nf_conntrack_acct.c @@ -106,36 +106,26 @@ static void nf_conntrack_acct_fini_sysctl(struct net *net) } #endif -int nf_conntrack_acct_init(struct net *net) +int nf_conntrack_acct_pernet_init(struct net *net) { - int ret; - net->ct.sysctl_acct = nf_ct_acct; + return nf_conntrack_acct_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&acct_extend); - if (ret < 0) { - printk(KERN_ERR "nf_conntrack_acct: Unable to register extension\n"); - goto out_extend_register; - } - } +void nf_conntrack_acct_pernet_fini(struct net *net) +{ + nf_conntrack_acct_fini_sysctl(net); +} - ret = nf_conntrack_acct_init_sysctl(net); +int nf_conntrack_acct_init(void) +{ + int ret = nf_ct_extend_register(&acct_extend); if (ret < 0) - goto out_sysctl; - - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&acct_extend); -out_extend_register: + pr_err("nf_conntrack_acct: Unable to register extension\n"); return ret; } -void nf_conntrack_acct_fini(struct net *net) +void nf_conntrack_acct_fini(void) { - nf_conntrack_acct_fini_sysctl(net); - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&acct_extend); + nf_ct_extend_unregister(&acct_extend); } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e4a0c4fb3a7..c8e001a9c45 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -45,6 +45,7 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_conntrack_timeout.h> +#include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_core.h> @@ -763,6 +764,7 @@ void nf_conntrack_free(struct nf_conn *ct) } EXPORT_SYMBOL_GPL(nf_conntrack_free); + /* Allocate a new conntrack: we return -ENOMEM if classification failed due to stress. Otherwise it really is unclassifiable. */ static struct nf_conntrack_tuple_hash * @@ -809,6 +811,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); + nf_ct_labels_ext_add(ct); ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL; nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0, @@ -1331,18 +1334,42 @@ static int untrack_refs(void) return cnt; } -static void nf_conntrack_cleanup_init_net(void) +void nf_conntrack_cleanup_start(void) +{ + RCU_INIT_POINTER(ip_ct_attach, NULL); +} + +void nf_conntrack_cleanup_end(void) { + RCU_INIT_POINTER(nf_ct_destroy, NULL); while (untrack_refs() > 0) schedule(); #ifdef CONFIG_NF_CONNTRACK_ZONES nf_ct_extend_unregister(&nf_ct_zone_extend); #endif + nf_conntrack_proto_fini(); + nf_conntrack_labels_fini(); + nf_conntrack_helper_fini(); + nf_conntrack_timeout_fini(); + nf_conntrack_ecache_fini(); + nf_conntrack_tstamp_fini(); + nf_conntrack_acct_fini(); + nf_conntrack_expect_fini(); } -static void nf_conntrack_cleanup_net(struct net *net) +/* + * Mishearing the voices in his head, our hero wonders how he's + * supposed to kill the mall. + */ +void nf_conntrack_cleanup_net(struct net *net) { + /* + * This makes sure all current packets have passed through + * netfilter framework. Roll on, two-stage module + * delete... + */ + synchronize_net(); i_see_dead_people: nf_ct_iterate_cleanup(net, kill_all, NULL); nf_ct_release_dying_list(net); @@ -1352,38 +1379,17 @@ static void nf_conntrack_cleanup_net(struct net *net) } nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); - nf_conntrack_helper_fini(net); - nf_conntrack_timeout_fini(net); - nf_conntrack_ecache_fini(net); - nf_conntrack_tstamp_fini(net); - nf_conntrack_acct_fini(net); - nf_conntrack_expect_fini(net); + nf_conntrack_proto_pernet_fini(net); + nf_conntrack_helper_pernet_fini(net); + nf_conntrack_ecache_pernet_fini(net); + nf_conntrack_tstamp_pernet_fini(net); + nf_conntrack_acct_pernet_fini(net); + nf_conntrack_expect_pernet_fini(net); kmem_cache_destroy(net->ct.nf_conntrack_cachep); kfree(net->ct.slabname); free_percpu(net->ct.stat); } -/* Mishearing the voices in his head, our hero wonders how he's - supposed to kill the mall. */ -void nf_conntrack_cleanup(struct net *net) -{ - if (net_eq(net, &init_net)) - RCU_INIT_POINTER(ip_ct_attach, NULL); - - /* This makes sure all current packets have passed through - netfilter framework. Roll on, two-stage module - delete... */ - synchronize_net(); - nf_conntrack_proto_fini(net); - nf_conntrack_cleanup_net(net); -} - -void nf_conntrack_cleanup_end(void) -{ - RCU_INIT_POINTER(nf_ct_destroy, NULL); - nf_conntrack_cleanup_init_net(); -} - void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) { struct hlist_nulls_head *hash; @@ -1474,7 +1480,7 @@ void nf_ct_untracked_status_or(unsigned long bits) } EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or); -static int nf_conntrack_init_init_net(void) +int nf_conntrack_init_start(void) { int max_factor = 8; int ret, cpu; @@ -1501,11 +1507,44 @@ static int nf_conntrack_init_init_net(void) printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n", NF_CONNTRACK_VERSION, nf_conntrack_htable_size, nf_conntrack_max); + + ret = nf_conntrack_expect_init(); + if (ret < 0) + goto err_expect; + + ret = nf_conntrack_acct_init(); + if (ret < 0) + goto err_acct; + + ret = nf_conntrack_tstamp_init(); + if (ret < 0) + goto err_tstamp; + + ret = nf_conntrack_ecache_init(); + if (ret < 0) + goto err_ecache; + + ret = nf_conntrack_timeout_init(); + if (ret < 0) + goto err_timeout; + + ret = nf_conntrack_helper_init(); + if (ret < 0) + goto err_helper; + + ret = nf_conntrack_labels_init(); + if (ret < 0) + goto err_labels; + #ifdef CONFIG_NF_CONNTRACK_ZONES ret = nf_ct_extend_register(&nf_ct_zone_extend); if (ret < 0) goto err_extend; #endif + ret = nf_conntrack_proto_init(); + if (ret < 0) + goto err_proto; + /* Set up fake conntrack: to never be deleted, not in any hashes */ for_each_possible_cpu(cpu) { struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu); @@ -1516,12 +1555,38 @@ static int nf_conntrack_init_init_net(void) nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED); return 0; +err_proto: #ifdef CONFIG_NF_CONNTRACK_ZONES + nf_ct_extend_unregister(&nf_ct_zone_extend); err_extend: #endif + nf_conntrack_labels_fini(); +err_labels: + nf_conntrack_helper_fini(); +err_helper: + nf_conntrack_timeout_fini(); +err_timeout: + nf_conntrack_ecache_fini(); +err_ecache: + nf_conntrack_tstamp_fini(); +err_tstamp: + nf_conntrack_acct_fini(); +err_acct: + nf_conntrack_expect_fini(); +err_expect: return ret; } +void nf_conntrack_init_end(void) +{ + /* For use by REJECT target */ + RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach); + RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack); + + /* Howto get NAT offsets */ + RCU_INIT_POINTER(nf_ct_nat_offset, NULL); +} + /* * We need to use special "null" values, not used in hash table */ @@ -1529,7 +1594,7 @@ err_extend: #define DYING_NULLS_VAL ((1<<30)+1) #define TEMPLATE_NULLS_VAL ((1<<30)+2) -static int nf_conntrack_init_net(struct net *net) +int nf_conntrack_init_net(struct net *net) { int ret; @@ -1565,35 +1630,36 @@ static int nf_conntrack_init_net(struct net *net) printk(KERN_ERR "Unable to create nf_conntrack_hash\n"); goto err_hash; } - ret = nf_conntrack_expect_init(net); + ret = nf_conntrack_expect_pernet_init(net); if (ret < 0) goto err_expect; - ret = nf_conntrack_acct_init(net); + ret = nf_conntrack_acct_pernet_init(net); if (ret < 0) goto err_acct; - ret = nf_conntrack_tstamp_init(net); + ret = nf_conntrack_tstamp_pernet_init(net); if (ret < 0) goto err_tstamp; - ret = nf_conntrack_ecache_init(net); + ret = nf_conntrack_ecache_pernet_init(net); if (ret < 0) goto err_ecache; - ret = nf_conntrack_timeout_init(net); - if (ret < 0) - goto err_timeout; - ret = nf_conntrack_helper_init(net); + ret = nf_conntrack_helper_pernet_init(net); if (ret < 0) goto err_helper; + ret = nf_conntrack_proto_pernet_init(net); + if (ret < 0) + goto err_proto; return 0; + +err_proto: + nf_conntrack_helper_pernet_fini(net); err_helper: - nf_conntrack_timeout_fini(net); -err_timeout: - nf_conntrack_ecache_fini(net); + nf_conntrack_ecache_pernet_fini(net); err_ecache: - nf_conntrack_tstamp_fini(net); + nf_conntrack_tstamp_pernet_fini(net); err_tstamp: - nf_conntrack_acct_fini(net); + nf_conntrack_acct_pernet_fini(net); err_acct: - nf_conntrack_expect_fini(net); + nf_conntrack_expect_pernet_fini(net); err_expect: nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); err_hash: @@ -1610,38 +1676,3 @@ s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq); EXPORT_SYMBOL_GPL(nf_ct_nat_offset); - -int nf_conntrack_init(struct net *net) -{ - int ret; - - if (net_eq(net, &init_net)) { - ret = nf_conntrack_init_init_net(); - if (ret < 0) - goto out_init_net; - } - ret = nf_conntrack_proto_init(net); - if (ret < 0) - goto out_proto; - ret = nf_conntrack_init_net(net); - if (ret < 0) - goto out_net; - - if (net_eq(net, &init_net)) { - /* For use by REJECT target */ - RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach); - RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack); - - /* Howto get NAT offsets */ - RCU_INIT_POINTER(nf_ct_nat_offset, NULL); - } - return 0; - -out_net: - nf_conntrack_proto_fini(net); -out_proto: - if (net_eq(net, &init_net)) - nf_conntrack_cleanup_init_net(); -out_init_net: - return ret; -} diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index faa978f1714..b5d2eb8bf0d 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -233,38 +233,27 @@ static void nf_conntrack_event_fini_sysctl(struct net *net) } #endif /* CONFIG_SYSCTL */ -int nf_conntrack_ecache_init(struct net *net) +int nf_conntrack_ecache_pernet_init(struct net *net) { - int ret; - net->ct.sysctl_events = nf_ct_events; net->ct.sysctl_events_retry_timeout = nf_ct_events_retry_timeout; + return nf_conntrack_event_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&event_extend); - if (ret < 0) { - printk(KERN_ERR "nf_ct_event: Unable to register " - "event extension.\n"); - goto out_extend_register; - } - } +void nf_conntrack_ecache_pernet_fini(struct net *net) +{ + nf_conntrack_event_fini_sysctl(net); +} - ret = nf_conntrack_event_init_sysctl(net); +int nf_conntrack_ecache_init(void) +{ + int ret = nf_ct_extend_register(&event_extend); if (ret < 0) - goto out_sysctl; - - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&event_extend); -out_extend_register: + pr_err("nf_ct_event: Unable to register event extension.\n"); return ret; } -void nf_conntrack_ecache_fini(struct net *net) +void nf_conntrack_ecache_fini(void) { - nf_conntrack_event_fini_sysctl(net); - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&event_extend); + nf_ct_extend_unregister(&event_extend); } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 527651a53a4..bdd341899ed 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -587,53 +587,50 @@ static void exp_proc_remove(struct net *net) module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400); -int nf_conntrack_expect_init(struct net *net) +int nf_conntrack_expect_pernet_init(struct net *net) { int err = -ENOMEM; - if (net_eq(net, &init_net)) { - if (!nf_ct_expect_hsize) { - nf_ct_expect_hsize = net->ct.htable_size / 256; - if (!nf_ct_expect_hsize) - nf_ct_expect_hsize = 1; - } - nf_ct_expect_max = nf_ct_expect_hsize * 4; - } - net->ct.expect_count = 0; net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0); if (net->ct.expect_hash == NULL) goto err1; - if (net_eq(net, &init_net)) { - nf_ct_expect_cachep = kmem_cache_create("nf_conntrack_expect", - sizeof(struct nf_conntrack_expect), - 0, 0, NULL); - if (!nf_ct_expect_cachep) - goto err2; - } - err = exp_proc_init(net); if (err < 0) - goto err3; + goto err2; return 0; - -err3: - if (net_eq(net, &init_net)) - kmem_cache_destroy(nf_ct_expect_cachep); err2: nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize); err1: return err; } -void nf_conntrack_expect_fini(struct net *net) +void nf_conntrack_expect_pernet_fini(struct net *net) { exp_proc_remove(net); - if (net_eq(net, &init_net)) { - rcu_barrier(); /* Wait for call_rcu() before destroy */ - kmem_cache_destroy(nf_ct_expect_cachep); - } nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize); } + +int nf_conntrack_expect_init(void) +{ + if (!nf_ct_expect_hsize) { + nf_ct_expect_hsize = nf_conntrack_htable_size / 256; + if (!nf_ct_expect_hsize) + nf_ct_expect_hsize = 1; + } + nf_ct_expect_max = nf_ct_expect_hsize * 4; + nf_ct_expect_cachep = kmem_cache_create("nf_conntrack_expect", + sizeof(struct nf_conntrack_expect), + 0, 0, NULL); + if (!nf_ct_expect_cachep) + return -ENOMEM; + return 0; +} + +void nf_conntrack_expect_fini(void) +{ + rcu_barrier(); /* Wait for call_rcu() before destroy */ + kmem_cache_destroy(nf_ct_expect_cachep); +} diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 884f2b39319..2f380f73c4c 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -423,44 +423,41 @@ static struct nf_ct_ext_type helper_extend __read_mostly = { .id = NF_CT_EXT_HELPER, }; -int nf_conntrack_helper_init(struct net *net) +int nf_conntrack_helper_pernet_init(struct net *net) { - int err; - net->ct.auto_assign_helper_warned = false; net->ct.sysctl_auto_assign_helper = nf_ct_auto_assign_helper; + return nf_conntrack_helper_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ - nf_ct_helper_hash = - nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); - if (!nf_ct_helper_hash) - return -ENOMEM; +void nf_conntrack_helper_pernet_fini(struct net *net) +{ + nf_conntrack_helper_fini_sysctl(net); +} - err = nf_ct_extend_register(&helper_extend); - if (err < 0) - goto err1; +int nf_conntrack_helper_init(void) +{ + int ret; + nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ + nf_ct_helper_hash = + nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); + if (!nf_ct_helper_hash) + return -ENOMEM; + + ret = nf_ct_extend_register(&helper_extend); + if (ret < 0) { + pr_err("nf_ct_helper: Unable to register helper extension.\n"); + goto out_extend; } - err = nf_conntrack_helper_init_sysctl(net); - if (err < 0) - goto out_sysctl; - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&helper_extend); -err1: +out_extend: nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); - return err; + return ret; } -void nf_conntrack_helper_fini(struct net *net) +void nf_conntrack_helper_fini(void) { - nf_conntrack_helper_fini_sysctl(net); - if (net_eq(net, &init_net)) { - nf_ct_extend_unregister(&helper_extend); - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); - } + nf_ct_extend_unregister(&helper_extend); + nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); } diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c new file mode 100644 index 00000000000..8fe2e99428b --- /dev/null +++ b/net/netfilter/nf_conntrack_labels.c @@ -0,0 +1,112 @@ +/* + * test/set flag bits stored in conntrack extension area. + * + * (C) 2013 Astaro GmbH & Co KG + * + * 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/ctype.h> +#include <linux/export.h> +#include <linux/jhash.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/slab.h> + +#include <net/netfilter/nf_conntrack_ecache.h> +#include <net/netfilter/nf_conntrack_labels.h> + +static unsigned int label_bits(const struct nf_conn_labels *l) +{ + unsigned int longs = l->words; + return longs * BITS_PER_LONG; +} + +bool nf_connlabel_match(const struct nf_conn *ct, u16 bit) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + + if (!labels) + return false; + + return bit < label_bits(labels) && test_bit(bit, labels->bits); +} +EXPORT_SYMBOL_GPL(nf_connlabel_match); + +int nf_connlabel_set(struct nf_conn *ct, u16 bit) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + + if (!labels || bit >= label_bits(labels)) + return -ENOSPC; + + if (test_bit(bit, labels->bits)) + return 0; + + if (test_and_set_bit(bit, labels->bits)) + nf_conntrack_event_cache(IPCT_LABEL, ct); + + return 0; +} +EXPORT_SYMBOL_GPL(nf_connlabel_set); + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) +static void replace_u32(u32 *address, u32 mask, u32 new) +{ + u32 old, tmp; + + do { + old = *address; + tmp = (old & mask) ^ new; + } while (cmpxchg(address, old, tmp) != old); +} + +int nf_connlabels_replace(struct nf_conn *ct, + const u32 *data, + const u32 *mask, unsigned int words32) +{ + struct nf_conn_labels *labels; + unsigned int size, i; + u32 *dst; + + labels = nf_ct_labels_find(ct); + if (!labels) + return -ENOSPC; + + size = labels->words * sizeof(long); + if (size < (words32 * sizeof(u32))) + words32 = size / sizeof(u32); + + dst = (u32 *) labels->bits; + if (words32) { + for (i = 0; i < words32; i++) + replace_u32(&dst[i], mask ? ~mask[i] : 0, data[i]); + } + + size /= sizeof(u32); + for (i = words32; i < size; i++) /* pad */ + replace_u32(&dst[i], 0, 0); + + nf_conntrack_event_cache(IPCT_LABEL, ct); + return 0; +} +EXPORT_SYMBOL_GPL(nf_connlabels_replace); +#endif + +static struct nf_ct_ext_type labels_extend __read_mostly = { + .len = sizeof(struct nf_conn_labels), + .align = __alignof__(struct nf_conn_labels), + .id = NF_CT_EXT_LABELS, +}; + +int nf_conntrack_labels_init(void) +{ + return nf_ct_extend_register(&labels_extend); +} + +void nf_conntrack_labels_fini(void) +{ + nf_ct_extend_unregister(&labels_extend); +} diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 627b0e50b23..2334cc5d2b1 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -43,6 +43,7 @@ #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> +#include <net/netfilter/nf_conntrack_labels.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_l4proto.h> @@ -323,6 +324,40 @@ nla_put_failure: #define ctnetlink_dump_secctx(a, b) (0) #endif +#ifdef CONFIG_NF_CONNTRACK_LABELS +static int ctnetlink_label_size(const struct nf_conn *ct) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + + if (!labels) + return 0; + return nla_total_size(labels->words * sizeof(long)); +} + +static int +ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + unsigned int len, i; + + if (!labels) + return 0; + + len = labels->words * sizeof(long); + i = 0; + do { + if (labels->bits[i] != 0) + return nla_put(skb, CTA_LABELS, len, labels->bits); + i++; + } while (i < labels->words); + + return 0; +} +#else +#define ctnetlink_dump_labels(a, b) (0) +#define ctnetlink_label_size(a) (0) +#endif + #define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple) static inline int @@ -463,6 +498,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, ctnetlink_dump_helpinfo(skb, ct) < 0 || ctnetlink_dump_mark(skb, ct) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || + ctnetlink_dump_labels(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || ctnetlink_dump_master(skb, ct) < 0 || @@ -561,6 +597,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif + ctnetlink_proto_size(ct) + + ctnetlink_label_size(ct) ; } @@ -662,6 +699,9 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) && ctnetlink_dump_secctx(skb, ct) < 0) goto nla_put_failure; #endif + if (events & (1 << IPCT_LABEL) && + ctnetlink_dump_labels(skb, ct) < 0) + goto nla_put_failure; if (events & (1 << IPCT_RELATED) && ctnetlink_dump_master(skb, ct) < 0) @@ -921,6 +961,7 @@ ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, return 0; } +#define __CTA_LABELS_MAX_LENGTH ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE) static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_TUPLE_ORIG] = { .type = NLA_NESTED }, [CTA_TUPLE_REPLY] = { .type = NLA_NESTED }, @@ -937,6 +978,10 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_NAT_SEQ_ADJ_REPLY] = { .type = NLA_NESTED }, [CTA_ZONE] = { .type = NLA_U16 }, [CTA_MARK_MASK] = { .type = NLA_U32 }, + [CTA_LABELS] = { .type = NLA_BINARY, + .len = __CTA_LABELS_MAX_LENGTH }, + [CTA_LABELS_MASK] = { .type = NLA_BINARY, + .len = __CTA_LABELS_MAX_LENGTH }, }; static int @@ -1465,6 +1510,31 @@ ctnetlink_change_nat_seq_adj(struct nf_conn *ct, #endif static int +ctnetlink_attach_labels(struct nf_conn *ct, const struct nlattr * const cda[]) +{ +#ifdef CONFIG_NF_CONNTRACK_LABELS + size_t len = nla_len(cda[CTA_LABELS]); + const void *mask = cda[CTA_LABELS_MASK]; + + if (len & (sizeof(u32)-1)) /* must be multiple of u32 */ + return -EINVAL; + + if (mask) { + if (nla_len(cda[CTA_LABELS_MASK]) == 0 || + nla_len(cda[CTA_LABELS_MASK]) != len) + return -EINVAL; + mask = nla_data(cda[CTA_LABELS_MASK]); + } + + len /= sizeof(u32); + + return nf_connlabels_replace(ct, nla_data(cda[CTA_LABELS]), mask, len); +#else + return -EOPNOTSUPP; +#endif +} + +static int ctnetlink_change_conntrack(struct nf_conn *ct, const struct nlattr * const cda[]) { @@ -1510,6 +1580,11 @@ ctnetlink_change_conntrack(struct nf_conn *ct, return err; } #endif + if (cda[CTA_LABELS]) { + err = ctnetlink_attach_labels(ct, cda); + if (err < 0) + return err; + } return 0; } @@ -1598,6 +1673,8 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); + nf_ct_labels_ext_add(ct); + /* we must add conntrack extensions before confirmation. */ ct->status |= IPS_CONFIRMED; @@ -1716,6 +1793,10 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, else events = IPCT_NEW; + if (cda[CTA_LABELS] && + ctnetlink_attach_labels(ct, cda) == 0) + events |= (1 << IPCT_LABEL); + nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | @@ -1983,6 +2064,8 @@ ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct) if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) goto nla_put_failure; #endif + if (ctnetlink_dump_labels(skb, ct) < 0) + goto nla_put_failure; rcu_read_unlock(); return 0; @@ -2011,6 +2094,11 @@ ctnetlink_nfqueue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) if (err < 0) return err; } + if (cda[CTA_LABELS]) { + err = ctnetlink_attach_labels(ct, cda); + if (err < 0) + return err; + } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ct->mark = ntohl(nla_get_be32(cda[CTA_MARK])); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 51e928db48c..58ab4050830 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -212,8 +212,7 @@ static void nf_ct_l3proto_unregister_sysctl(struct net *net, #endif } -static int -nf_conntrack_l3proto_register_net(struct nf_conntrack_l3proto *proto) +int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto) { int ret = 0; struct nf_conntrack_l3proto *old; @@ -242,8 +241,9 @@ out_unlock: return ret; } +EXPORT_SYMBOL_GPL(nf_ct_l3proto_register); -int nf_conntrack_l3proto_register(struct net *net, +int nf_ct_l3proto_pernet_register(struct net *net, struct nf_conntrack_l3proto *proto) { int ret = 0; @@ -254,22 +254,11 @@ int nf_conntrack_l3proto_register(struct net *net, return ret; } - ret = nf_ct_l3proto_register_sysctl(net, proto); - if (ret < 0) - return ret; - - if (net == &init_net) { - ret = nf_conntrack_l3proto_register_net(proto); - if (ret < 0) - nf_ct_l3proto_unregister_sysctl(net, proto); - } - - return ret; + return nf_ct_l3proto_register_sysctl(net, proto); } -EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_register); +EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_register); -static void -nf_conntrack_l3proto_unregister_net(struct nf_conntrack_l3proto *proto) +void nf_ct_l3proto_unregister(struct nf_conntrack_l3proto *proto) { BUG_ON(proto->l3proto >= AF_MAX); @@ -283,19 +272,17 @@ nf_conntrack_l3proto_unregister_net(struct nf_conntrack_l3proto *proto) synchronize_rcu(); } +EXPORT_SYMBOL_GPL(nf_ct_l3proto_unregister); -void nf_conntrack_l3proto_unregister(struct net *net, +void nf_ct_l3proto_pernet_unregister(struct net *net, struct nf_conntrack_l3proto *proto) { - if (net == &init_net) - nf_conntrack_l3proto_unregister_net(proto); - nf_ct_l3proto_unregister_sysctl(net, proto); /* Remove all contrack entries for this protocol */ nf_ct_iterate_cleanup(net, kill_l3proto, proto); } -EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_unregister); +EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_unregister); static struct nf_proto_net *nf_ct_l4proto_net(struct net *net, struct nf_conntrack_l4proto *l4proto) @@ -376,8 +363,7 @@ void nf_ct_l4proto_unregister_sysctl(struct net *net, /* FIXME: Allow NULL functions and sub in pointers to generic for them. --RR */ -static int -nf_conntrack_l4proto_register_net(struct nf_conntrack_l4proto *l4proto) +int nf_ct_l4proto_register(struct nf_conntrack_l4proto *l4proto) { int ret = 0; @@ -431,8 +417,9 @@ out_unlock: mutex_unlock(&nf_ct_proto_mutex); return ret; } +EXPORT_SYMBOL_GPL(nf_ct_l4proto_register); -int nf_conntrack_l4proto_register(struct net *net, +int nf_ct_l4proto_pernet_register(struct net *net, struct nf_conntrack_l4proto *l4proto) { int ret = 0; @@ -452,22 +439,13 @@ int nf_conntrack_l4proto_register(struct net *net, if (ret < 0) goto out; - if (net == &init_net) { - ret = nf_conntrack_l4proto_register_net(l4proto); - if (ret < 0) { - nf_ct_l4proto_unregister_sysctl(net, pn, l4proto); - goto out; - } - } - pn->users++; out: return ret; } -EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_register); +EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register); -static void -nf_conntrack_l4proto_unregister_net(struct nf_conntrack_l4proto *l4proto) +void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *l4proto) { BUG_ON(l4proto->l3proto >= PF_MAX); @@ -482,15 +460,13 @@ nf_conntrack_l4proto_unregister_net(struct nf_conntrack_l4proto *l4proto) synchronize_rcu(); } +EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister); -void nf_conntrack_l4proto_unregister(struct net *net, +void nf_ct_l4proto_pernet_unregister(struct net *net, struct nf_conntrack_l4proto *l4proto) { struct nf_proto_net *pn = NULL; - if (net == &init_net) - nf_conntrack_l4proto_unregister_net(l4proto); - pn = nf_ct_l4proto_net(net, l4proto); if (pn == NULL) return; @@ -501,11 +477,10 @@ void nf_conntrack_l4proto_unregister(struct net *net, /* Remove all contrack entries for this protocol */ nf_ct_iterate_cleanup(net, kill_l4proto, l4proto); } -EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_unregister); +EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister); -int nf_conntrack_proto_init(struct net *net) +int nf_conntrack_proto_pernet_init(struct net *net) { - unsigned int i; int err; struct nf_proto_net *pn = nf_ct_l4proto_net(net, &nf_conntrack_l4proto_generic); @@ -520,19 +495,12 @@ int nf_conntrack_proto_init(struct net *net) if (err < 0) return err; - if (net == &init_net) { - for (i = 0; i < AF_MAX; i++) - rcu_assign_pointer(nf_ct_l3protos[i], - &nf_conntrack_l3proto_generic); - } - pn->users++; return 0; } -void nf_conntrack_proto_fini(struct net *net) +void nf_conntrack_proto_pernet_fini(struct net *net) { - unsigned int i; struct nf_proto_net *pn = nf_ct_l4proto_net(net, &nf_conntrack_l4proto_generic); @@ -540,9 +508,21 @@ void nf_conntrack_proto_fini(struct net *net) nf_ct_l4proto_unregister_sysctl(net, pn, &nf_conntrack_l4proto_generic); - if (net == &init_net) { - /* free l3proto protocol tables */ - for (i = 0; i < PF_MAX; i++) - kfree(nf_ct_protos[i]); - } +} + +int nf_conntrack_proto_init(void) +{ + unsigned int i; + for (i = 0; i < AF_MAX; i++) + rcu_assign_pointer(nf_ct_l3protos[i], + &nf_conntrack_l3proto_generic); + return 0; +} + +void nf_conntrack_proto_fini(void) +{ + unsigned int i; + /* free l3proto protocol tables */ + for (i = 0; i < PF_MAX; i++) + kfree(nf_ct_protos[i]); } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index a8ae287bc7a..432f9578000 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -935,32 +935,27 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { static __net_init int dccp_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &dccp_proto4); + ret = nf_ct_l4proto_pernet_register(net, &dccp_proto4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_dccp4 :protocol register failed.\n"); + pr_err("nf_conntrack_dccp4: pernet registration failed.\n"); goto out; } - ret = nf_conntrack_l4proto_register(net, - &dccp_proto6); + ret = nf_ct_l4proto_pernet_register(net, &dccp_proto6); if (ret < 0) { - pr_err("nf_conntrack_l4proto_dccp6 :protocol register failed.\n"); + pr_err("nf_conntrack_dccp6: pernet registration failed.\n"); goto cleanup_dccp4; } return 0; cleanup_dccp4: - nf_conntrack_l4proto_unregister(net, - &dccp_proto4); + nf_ct_l4proto_pernet_unregister(net, &dccp_proto4); out: return ret; } static __net_exit void dccp_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, - &dccp_proto6); - nf_conntrack_l4proto_unregister(net, - &dccp_proto4); + nf_ct_l4proto_pernet_unregister(net, &dccp_proto6); + nf_ct_l4proto_pernet_unregister(net, &dccp_proto4); } static struct pernet_operations dccp_net_ops = { @@ -972,11 +967,33 @@ static struct pernet_operations dccp_net_ops = { static int __init nf_conntrack_proto_dccp_init(void) { - return register_pernet_subsys(&dccp_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&dccp_proto4); + if (ret < 0) + goto out_dccp4; + + ret = nf_ct_l4proto_register(&dccp_proto6); + if (ret < 0) + goto out_dccp6; + + ret = register_pernet_subsys(&dccp_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&dccp_proto6); +out_dccp6: + nf_ct_l4proto_unregister(&dccp_proto4); +out_dccp4: + return ret; } static void __exit nf_conntrack_proto_dccp_fini(void) { + nf_ct_l4proto_unregister(&dccp_proto6); + nf_ct_l4proto_unregister(&dccp_proto4); unregister_pernet_subsys(&dccp_net_ops); } diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index b09b7af7f6f..bd7d01d9c7e 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -397,15 +397,15 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { static int proto_gre_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, &nf_conntrack_l4proto_gre4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_gre4); if (ret < 0) - pr_err("nf_conntrack_l4proto_gre4 :protocol register failed.\n"); + pr_err("nf_conntrack_gre4: pernet registration failed.\n"); return ret; } static void proto_gre_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_gre4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_gre4); nf_ct_gre_keymap_flush(net); } @@ -418,11 +418,26 @@ static struct pernet_operations proto_gre_net_ops = { static int __init nf_ct_proto_gre_init(void) { - return register_pernet_subsys(&proto_gre_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_gre4); + if (ret < 0) + goto out_gre4; + + ret = register_pernet_subsys(&proto_gre_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_gre4); +out_gre4: + return ret; } static void __exit nf_ct_proto_gre_fini(void) { + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_gre4); unregister_pernet_subsys(&proto_gre_net_ops); } diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c746d61f83e..480f616d593 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -853,33 +853,28 @@ static int sctp_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_sctp4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_sctp4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_sctp4 :protocol register failed.\n"); + pr_err("nf_conntrack_sctp4: pernet registration failed.\n"); goto out; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_sctp6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_sctp6); if (ret < 0) { - pr_err("nf_conntrack_l4proto_sctp6 :protocol register failed.\n"); + pr_err("nf_conntrack_sctp6: pernet registration failed.\n"); goto cleanup_sctp4; } return 0; cleanup_sctp4: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_sctp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp4); out: return ret; } static void sctp_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_sctp6); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_sctp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp4); } static struct pernet_operations sctp_net_ops = { @@ -891,11 +886,33 @@ static struct pernet_operations sctp_net_ops = { static int __init nf_conntrack_proto_sctp_init(void) { - return register_pernet_subsys(&sctp_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_sctp4); + if (ret < 0) + goto out_sctp4; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_sctp6); + if (ret < 0) + goto out_sctp6; + + ret = register_pernet_subsys(&sctp_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp6); +out_sctp6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp4); +out_sctp4: + return ret; } static void __exit nf_conntrack_proto_sctp_fini(void) { + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp4); unregister_pernet_subsys(&sctp_net_ops); } diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 4b66df20928..157489581c3 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -336,30 +336,28 @@ static int udplite_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_udplite4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udplite4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_udplite4 :protocol register failed.\n"); + pr_err("nf_conntrack_udplite4: pernet registration failed.\n"); goto out; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_udplite6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udplite6); if (ret < 0) { - pr_err("nf_conntrack_l4proto_udplite4 :protocol register failed.\n"); + pr_err("nf_conntrack_udplite6: pernet registration failed.\n"); goto cleanup_udplite4; } return 0; cleanup_udplite4: - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite4); out: return ret; } static void udplite_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite6); - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite4); } static struct pernet_operations udplite_net_ops = { @@ -371,11 +369,33 @@ static struct pernet_operations udplite_net_ops = { static int __init nf_conntrack_proto_udplite_init(void) { - return register_pernet_subsys(&udplite_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udplite4); + if (ret < 0) + goto out_udplite4; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udplite6); + if (ret < 0) + goto out_udplite6; + + ret = register_pernet_subsys(&udplite_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite6); +out_udplite6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite4); +out_udplite4: + return ret; } static void __exit nf_conntrack_proto_udplite_exit(void) { + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite4); unregister_pernet_subsys(&udplite_net_ops); } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index df8f4f28448..72a67bbe351 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1440,8 +1440,25 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); unsigned int matchoff, matchlen; unsigned int cseq, i; + union nf_inet_addr addr; + __be16 port; + + /* Many Cisco IP phones use a high source port for SIP requests, but + * listen for the response on port 5060. If we are the local + * router for one of these phones, save the port number from the + * Via: header so that nf_nat_sip can redirect the responses to + * the correct port. + */ + if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, + SIP_HDR_VIA_UDP, NULL, &matchoff, + &matchlen, &addr, &port) > 0 && + port != ct->tuplehash[dir].tuple.src.u.udp.port && + nf_inet_addr_cmp(&addr, &ct->tuplehash[dir].tuple.src.u3)) + ct_sip_info->forced_dport = port; for (i = 0; i < ARRAY_SIZE(sip_handlers); i++) { const struct sip_handler *handler; diff --git a/net/netfilter/nf_conntrack_snmp.c b/net/netfilter/nf_conntrack_snmp.c index 6e545e26289..87b95a2c270 100644 --- a/net/netfilter/nf_conntrack_snmp.c +++ b/net/netfilter/nf_conntrack_snmp.c @@ -16,6 +16,7 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_expect.h> +#include <linux/netfilter/nf_conntrack_snmp.h> #define SNMP_PORT 161 diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index e7185c68481..7936bf7f90b 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -472,13 +472,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) { struct ctl_table *table; - if (net_eq(net, &init_net)) { - nf_ct_netfilter_header = - register_net_sysctl(&init_net, "net", nf_ct_netfilter_table); - if (!nf_ct_netfilter_header) - goto out; - } - table = kmemdup(nf_ct_sysctl_table, sizeof(nf_ct_sysctl_table), GFP_KERNEL); if (!table) @@ -502,10 +495,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) out_unregister_netfilter: kfree(table); out_kmemdup: - if (net_eq(net, &init_net)) - unregister_net_sysctl_table(nf_ct_netfilter_header); -out: - printk(KERN_ERR "nf_conntrack: can't register to sysctl.\n"); return -ENOMEM; } @@ -513,8 +502,6 @@ static void nf_conntrack_standalone_fini_sysctl(struct net *net) { struct ctl_table *table; - if (net_eq(net, &init_net)) - unregister_net_sysctl_table(nf_ct_netfilter_header); table = net->ct.sysctl_header->ctl_table_arg; unregister_net_sysctl_table(net->ct.sysctl_header); kfree(table); @@ -530,51 +517,85 @@ static void nf_conntrack_standalone_fini_sysctl(struct net *net) } #endif /* CONFIG_SYSCTL */ -static int nf_conntrack_net_init(struct net *net) +static int nf_conntrack_pernet_init(struct net *net) { int ret; - ret = nf_conntrack_init(net); + ret = nf_conntrack_init_net(net); if (ret < 0) goto out_init; + ret = nf_conntrack_standalone_init_proc(net); if (ret < 0) goto out_proc; + net->ct.sysctl_checksum = 1; net->ct.sysctl_log_invalid = 0; ret = nf_conntrack_standalone_init_sysctl(net); if (ret < 0) goto out_sysctl; + return 0; out_sysctl: nf_conntrack_standalone_fini_proc(net); out_proc: - nf_conntrack_cleanup(net); + nf_conntrack_cleanup_net(net); out_init: return ret; } -static void nf_conntrack_net_exit(struct net *net) +static void nf_conntrack_pernet_exit(struct net *net) { nf_conntrack_standalone_fini_sysctl(net); nf_conntrack_standalone_fini_proc(net); - nf_conntrack_cleanup(net); + nf_conntrack_cleanup_net(net); } static struct pernet_operations nf_conntrack_net_ops = { - .init = nf_conntrack_net_init, - .exit = nf_conntrack_net_exit, + .init = nf_conntrack_pernet_init, + .exit = nf_conntrack_pernet_exit, }; static int __init nf_conntrack_standalone_init(void) { - return register_pernet_subsys(&nf_conntrack_net_ops); + int ret = nf_conntrack_init_start(); + if (ret < 0) + goto out_start; + +#ifdef CONFIG_SYSCTL + nf_ct_netfilter_header = + register_net_sysctl(&init_net, "net", nf_ct_netfilter_table); + if (!nf_ct_netfilter_header) { + pr_err("nf_conntrack: can't register to sysctl.\n"); + goto out_sysctl; + } +#endif + + ret = register_pernet_subsys(&nf_conntrack_net_ops); + if (ret < 0) + goto out_pernet; + + nf_conntrack_init_end(); + return 0; + +out_pernet: +#ifdef CONFIG_SYSCTL + unregister_net_sysctl_table(nf_ct_netfilter_header); +out_sysctl: +#endif + nf_conntrack_cleanup_end(); +out_start: + return ret; } static void __exit nf_conntrack_standalone_fini(void) { + nf_conntrack_cleanup_start(); unregister_pernet_subsys(&nf_conntrack_net_ops); +#ifdef CONFIG_SYSCTL + unregister_net_sysctl_table(nf_ct_netfilter_header); +#endif nf_conntrack_cleanup_end(); } diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c index a878ce5b252..93da609d9d2 100644 --- a/net/netfilter/nf_conntrack_timeout.c +++ b/net/netfilter/nf_conntrack_timeout.c @@ -37,24 +37,15 @@ static struct nf_ct_ext_type timeout_extend __read_mostly = { .id = NF_CT_EXT_TIMEOUT, }; -int nf_conntrack_timeout_init(struct net *net) +int nf_conntrack_timeout_init(void) { - int ret = 0; - - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&timeout_extend); - if (ret < 0) { - printk(KERN_ERR "nf_ct_timeout: Unable to register " - "timeout extension.\n"); - return ret; - } - } - - return 0; + int ret = nf_ct_extend_register(&timeout_extend); + if (ret < 0) + pr_err("nf_ct_timeout: Unable to register timeout extension.\n"); + return ret; } -void nf_conntrack_timeout_fini(struct net *net) +void nf_conntrack_timeout_fini(void) { - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&timeout_extend); + nf_ct_extend_unregister(&timeout_extend); } diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c index 7ea8026f07c..902fb0a6b38 100644 --- a/net/netfilter/nf_conntrack_timestamp.c +++ b/net/netfilter/nf_conntrack_timestamp.c @@ -88,37 +88,28 @@ static void nf_conntrack_tstamp_fini_sysctl(struct net *net) } #endif -int nf_conntrack_tstamp_init(struct net *net) +int nf_conntrack_tstamp_pernet_init(struct net *net) { - int ret; - net->ct.sysctl_tstamp = nf_ct_tstamp; + return nf_conntrack_tstamp_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&tstamp_extend); - if (ret < 0) { - printk(KERN_ERR "nf_ct_tstamp: Unable to register " - "extension\n"); - goto out_extend_register; - } - } +void nf_conntrack_tstamp_pernet_fini(struct net *net) +{ + nf_conntrack_tstamp_fini_sysctl(net); + nf_ct_extend_unregister(&tstamp_extend); +} - ret = nf_conntrack_tstamp_init_sysctl(net); +int nf_conntrack_tstamp_init(void) +{ + int ret; + ret = nf_ct_extend_register(&tstamp_extend); if (ret < 0) - goto out_sysctl; - - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&tstamp_extend); -out_extend_register: + pr_err("nf_ct_tstamp: Unable to register extension\n"); return ret; } -void nf_conntrack_tstamp_fini(struct net *net) +void nf_conntrack_tstamp_fini(void) { - nf_conntrack_tstamp_fini_sysctl(net); - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&tstamp_extend); + nf_ct_extend_unregister(&tstamp_extend); } diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index 16303c75221..5951146e768 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -95,6 +95,7 @@ static int map_addr(struct sk_buff *skb, unsigned int protoff, enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; unsigned int buflen; union nf_inet_addr newaddr; @@ -107,7 +108,8 @@ static int map_addr(struct sk_buff *skb, unsigned int protoff, } else if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, addr) && ct->tuplehash[dir].tuple.dst.u.udp.port == port) { newaddr = ct->tuplehash[!dir].tuple.src.u3; - newport = ct->tuplehash[!dir].tuple.src.u.udp.port; + newport = ct_sip_info->forced_dport ? : + ct->tuplehash[!dir].tuple.src.u.udp.port; } else return 1; @@ -144,6 +146,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); unsigned int coff, matchoff, matchlen; enum sip_header_types hdr; union nf_inet_addr addr; @@ -258,6 +261,21 @@ next: !map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_TO)) return NF_DROP; + /* Mangle destination port for Cisco phones, then fix up checksums */ + if (dir == IP_CT_DIR_REPLY && ct_sip_info->forced_dport) { + struct udphdr *uh; + + if (!skb_make_writable(skb, skb->len)) + return NF_DROP; + + uh = (void *)skb->data + protoff; + uh->dest = ct_sip_info->forced_dport; + + if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, protoff, + 0, 0, NULL, 0)) + return NF_DROP; + } + return NF_ACCEPT; } @@ -311,8 +329,10 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); union nf_inet_addr newaddr; u_int16_t port; + __be16 srcport; char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; unsigned int buflen; @@ -326,8 +346,9 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, /* If the signalling port matches the connection's source port in the * original direction, try to use the destination port in the opposite * direction. */ - if (exp->tuple.dst.u.udp.port == - ct->tuplehash[dir].tuple.src.u.udp.port) + srcport = ct_sip_info->forced_dport ? : + ct->tuplehash[dir].tuple.src.u.udp.port; + if (exp->tuple.dst.u.udp.port == srcport) port = ntohs(ct->tuplehash[!dir].tuple.dst.u.udp.port); else port = ntohs(exp->tuple.dst.u.udp.port); diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c new file mode 100644 index 00000000000..12d4da8e6c7 --- /dev/null +++ b/net/netfilter/xt_bpf.c @@ -0,0 +1,73 @@ +/* Xtables module to match packets using a BPF filter. + * Copyright 2013 Google Inc. + * Written by Willem de Bruijn <willemb@google.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/module.h> +#include <linux/skbuff.h> +#include <linux/filter.h> + +#include <linux/netfilter/xt_bpf.h> +#include <linux/netfilter/x_tables.h> + +MODULE_AUTHOR("Willem de Bruijn <willemb@google.com>"); +MODULE_DESCRIPTION("Xtables: BPF filter match"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_bpf"); +MODULE_ALIAS("ip6t_bpf"); + +static int bpf_mt_check(const struct xt_mtchk_param *par) +{ + struct xt_bpf_info *info = par->matchinfo; + struct sock_fprog program; + + program.len = info->bpf_program_num_elem; + program.filter = (struct sock_filter __user *) info->bpf_program; + if (sk_unattached_filter_create(&info->filter, &program)) { + pr_info("bpf: check failed: parse error\n"); + return -EINVAL; + } + + return 0; +} + +static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_bpf_info *info = par->matchinfo; + + return SK_RUN_FILTER(info->filter, skb); +} + +static void bpf_mt_destroy(const struct xt_mtdtor_param *par) +{ + const struct xt_bpf_info *info = par->matchinfo; + sk_unattached_filter_destroy(info->filter); +} + +static struct xt_match bpf_mt_reg __read_mostly = { + .name = "bpf", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = bpf_mt_check, + .match = bpf_mt, + .destroy = bpf_mt_destroy, + .matchsize = sizeof(struct xt_bpf_info), + .me = THIS_MODULE, +}; + +static int __init bpf_mt_init(void) +{ + return xt_register_match(&bpf_mt_reg); +} + +static void __exit bpf_mt_exit(void) +{ + xt_unregister_match(&bpf_mt_reg); +} + +module_init(bpf_mt_init); +module_exit(bpf_mt_exit); diff --git a/net/netfilter/xt_connlabel.c b/net/netfilter/xt_connlabel.c new file mode 100644 index 00000000000..9f8719df200 --- /dev/null +++ b/net/netfilter/xt_connlabel.c @@ -0,0 +1,99 @@ +/* + * (C) 2013 Astaro GmbH & Co KG + * + * 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/module.h> +#include <linux/skbuff.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_labels.h> +#include <linux/netfilter/x_tables.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); +MODULE_DESCRIPTION("Xtables: add/match connection trackling labels"); +MODULE_ALIAS("ipt_connlabel"); +MODULE_ALIAS("ip6t_connlabel"); + +static bool +connlabel_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_connlabel_mtinfo *info = par->matchinfo; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + bool invert = info->options & XT_CONNLABEL_OP_INVERT; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL || nf_ct_is_untracked(ct)) + return invert; + + if (info->options & XT_CONNLABEL_OP_SET) + return (nf_connlabel_set(ct, info->bit) == 0) ^ invert; + + return nf_connlabel_match(ct, info->bit) ^ invert; +} + +static int connlabel_mt_check(const struct xt_mtchk_param *par) +{ + const int options = XT_CONNLABEL_OP_INVERT | + XT_CONNLABEL_OP_SET; + struct xt_connlabel_mtinfo *info = par->matchinfo; + int ret; + size_t words; + + if (info->bit > XT_CONNLABEL_MAXBIT) + return -ERANGE; + + if (info->options & ~options) { + pr_err("Unknown options in mask %x\n", info->options); + return -EINVAL; + } + + ret = nf_ct_l3proto_try_module_get(par->family); + if (ret < 0) { + pr_info("cannot load conntrack support for proto=%u\n", + par->family); + return ret; + } + + par->net->ct.labels_used++; + words = BITS_TO_LONGS(info->bit+1); + if (words > par->net->ct.label_words) + par->net->ct.label_words = words; + + return ret; +} + +static void connlabel_mt_destroy(const struct xt_mtdtor_param *par) +{ + par->net->ct.labels_used--; + if (par->net->ct.labels_used == 0) + par->net->ct.label_words = 0; + nf_ct_l3proto_module_put(par->family); +} + +static struct xt_match connlabels_mt_reg __read_mostly = { + .name = "connlabel", + .family = NFPROTO_UNSPEC, + .checkentry = connlabel_mt_check, + .match = connlabel_mt, + .matchsize = sizeof(struct xt_connlabel_mtinfo), + .destroy = connlabel_mt_destroy, + .me = THIS_MODULE, +}; + +static int __init connlabel_mt_init(void) +{ + return xt_register_match(&connlabels_mt_reg); +} + +static void __exit connlabel_mt_exit(void) +{ + xt_unregister_match(&connlabels_mt_reg); +} + +module_init(connlabel_mt_init); +module_exit(connlabel_mt_exit); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c0353d55d56..74827e3b26a 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2185,7 +2185,6 @@ static struct pernet_operations __net_initdata netlink_net_ops = { static int __init netlink_proto_init(void) { - struct sk_buff *dummy_skb; int i; unsigned long limit; unsigned int order; @@ -2194,7 +2193,7 @@ static int __init netlink_proto_init(void) if (err != 0) goto out; - BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); if (!nl_table) diff --git a/net/nfc/core.c b/net/nfc/core.c index aa64ea44167..25522e56d35 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -338,7 +338,7 @@ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol) dev->active_target = target; dev->rf_mode = NFC_RF_INITIATOR; - if (dev->ops->check_presence) + if (dev->ops->check_presence && !dev->shutting_down) mod_timer(&dev->check_pres_timer, jiffies + msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); } @@ -429,7 +429,7 @@ int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, struct sk_buff *skb, rc = dev->ops->im_transceive(dev, dev->active_target, skb, cb, cb_context); - if (!rc && dev->ops->check_presence) + if (!rc && dev->ops->check_presence && !dev->shutting_down) mod_timer(&dev->check_pres_timer, jiffies + msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); } else if (dev->rf_mode == NFC_RF_TARGET && dev->ops->tm_send != NULL) { @@ -684,11 +684,6 @@ static void nfc_release(struct device *d) pr_debug("dev_name=%s\n", dev_name(&dev->dev)); - if (dev->ops->check_presence) { - del_timer_sync(&dev->check_pres_timer); - cancel_work_sync(&dev->check_pres_work); - } - nfc_genl_data_exit(&dev->genl_data); kfree(dev->targets); kfree(dev); @@ -706,15 +701,16 @@ static void nfc_check_pres_work(struct work_struct *work) rc = dev->ops->check_presence(dev, dev->active_target); if (rc == -EOPNOTSUPP) goto exit; - if (!rc) { - mod_timer(&dev->check_pres_timer, jiffies + - msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); - } else { + if (rc) { u32 active_target_idx = dev->active_target->idx; device_unlock(&dev->dev); nfc_target_lost(dev, active_target_idx); return; } + + if (!dev->shutting_down) + mod_timer(&dev->check_pres_timer, jiffies + + msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); } exit: @@ -761,6 +757,7 @@ struct nfc_dev *nfc_get_device(unsigned int idx) */ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, u32 supported_protocols, + u32 supported_se, int tx_headroom, int tx_tailroom) { struct nfc_dev *dev; @@ -778,6 +775,8 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, dev->ops = ops; dev->supported_protocols = supported_protocols; + dev->supported_se = supported_se; + dev->active_se = NFC_SE_NONE; dev->tx_headroom = tx_headroom; dev->tx_tailroom = tx_tailroom; @@ -853,26 +852,27 @@ void nfc_unregister_device(struct nfc_dev *dev) id = dev->idx; - mutex_lock(&nfc_devlist_mutex); - nfc_devlist_generation++; - - /* lock to avoid unregistering a device while an operation - is in progress */ - device_lock(&dev->dev); - device_del(&dev->dev); - device_unlock(&dev->dev); + if (dev->ops->check_presence) { + device_lock(&dev->dev); + dev->shutting_down = true; + device_unlock(&dev->dev); + del_timer_sync(&dev->check_pres_timer); + cancel_work_sync(&dev->check_pres_work); + } - mutex_unlock(&nfc_devlist_mutex); + rc = nfc_genl_device_removed(dev); + if (rc) + pr_debug("The userspace won't be notified that the device %s " + "was removed\n", dev_name(&dev->dev)); nfc_llcp_unregister_device(dev); - rc = nfc_genl_device_removed(dev); - if (rc) - pr_debug("The userspace won't be notified that the device %s was removed\n", - dev_name(&dev->dev)); + mutex_lock(&nfc_devlist_mutex); + nfc_devlist_generation++; + device_del(&dev->dev); + mutex_unlock(&nfc_devlist_mutex); ida_simple_remove(&nfc_index_ida, id); - } EXPORT_SYMBOL(nfc_unregister_device); diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c index 7d99410e6c1..64f922be928 100644 --- a/net/nfc/hci/command.c +++ b/net/nfc/hci/command.c @@ -280,14 +280,19 @@ static int nfc_hci_delete_pipe(struct nfc_hci_dev *hdev, u8 pipe) static int nfc_hci_clear_all_pipes(struct nfc_hci_dev *hdev) { u8 param[2]; + size_t param_len = 2; /* TODO: Find out what the identity reference data is * and fill param with it. HCI spec 6.1.3.5 */ pr_debug("\n"); + if (test_bit(NFC_HCI_QUIRK_SHORT_CLEAR, &hdev->quirks)) + param_len = 0; + return nfc_hci_execute_cmd(hdev, NFC_HCI_ADMIN_PIPE, - NFC_HCI_ADM_CLEAR_ALL_PIPE, param, 2, NULL); + NFC_HCI_ADM_CLEAR_ALL_PIPE, param, param_len, + NULL); } int nfc_hci_disconnect_gate(struct nfc_hci_dev *hdev, u8 gate) diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 7bea574d593..91020b210d8 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -57,6 +57,8 @@ static void nfc_hci_msg_tx_work(struct work_struct *work) int r = 0; mutex_lock(&hdev->msg_tx_mutex); + if (hdev->shutting_down) + goto exit; if (hdev->cmd_pending_msg) { if (timer_pending(&hdev->cmd_timer) == 0) { @@ -295,6 +297,12 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event, goto exit; } + if (hdev->ops->event_received) { + r = hdev->ops->event_received(hdev, gate, event, skb); + if (r <= 0) + goto exit_noskb; + } + switch (event) { case NFC_HCI_EVT_TARGET_DISCOVERED: if (skb->len < 1) { /* no status data? */ @@ -320,17 +328,15 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event, r = nfc_hci_target_discovered(hdev, gate); break; default: - if (hdev->ops->event_received) { - hdev->ops->event_received(hdev, gate, event, skb); - return; - } - + pr_info("Discarded unknown event %x to gate %x\n", event, gate); + r = -EINVAL; break; } exit: kfree_skb(skb); +exit_noskb: if (r) { /* TODO: There was an error dispatching the event, * how to propagate up to nfc core? @@ -669,8 +675,10 @@ static int hci_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb) if (hdev->ops->tm_send) return hdev->ops->tm_send(hdev, skb); - else - return -ENOTSUPP; + + kfree_skb(skb); + + return -ENOTSUPP; } static int hci_check_presence(struct nfc_dev *nfc_dev, @@ -787,7 +795,9 @@ static struct nfc_ops hci_nfc_ops = { struct nfc_hci_dev *nfc_hci_allocate_device(struct nfc_hci_ops *ops, struct nfc_hci_init_data *init_data, + unsigned long quirks, u32 protocols, + u32 supported_se, const char *llc_name, int tx_headroom, int tx_tailroom, @@ -813,7 +823,7 @@ struct nfc_hci_dev *nfc_hci_allocate_device(struct nfc_hci_ops *ops, return NULL; } - hdev->ndev = nfc_allocate_device(&hci_nfc_ops, protocols, + hdev->ndev = nfc_allocate_device(&hci_nfc_ops, protocols, supported_se, tx_headroom + HCI_CMDS_HEADROOM, tx_tailroom); if (!hdev->ndev) { @@ -830,6 +840,8 @@ struct nfc_hci_dev *nfc_hci_allocate_device(struct nfc_hci_ops *ops, memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe)); + hdev->quirks = quirks; + return hdev; } EXPORT_SYMBOL(nfc_hci_allocate_device); @@ -868,6 +880,28 @@ void nfc_hci_unregister_device(struct nfc_hci_dev *hdev) { struct hci_msg *msg, *n; + mutex_lock(&hdev->msg_tx_mutex); + + if (hdev->cmd_pending_msg) { + if (hdev->cmd_pending_msg->cb) + hdev->cmd_pending_msg->cb( + hdev->cmd_pending_msg->cb_context, + NULL, -ESHUTDOWN); + kfree(hdev->cmd_pending_msg); + hdev->cmd_pending_msg = NULL; + } + + hdev->shutting_down = true; + + mutex_unlock(&hdev->msg_tx_mutex); + + del_timer_sync(&hdev->cmd_timer); + cancel_work_sync(&hdev->msg_tx_work); + + cancel_work_sync(&hdev->msg_rx_work); + + nfc_unregister_device(hdev->ndev); + skb_queue_purge(&hdev->rx_hcp_frags); skb_queue_purge(&hdev->msg_rx_queue); @@ -876,13 +910,6 @@ void nfc_hci_unregister_device(struct nfc_hci_dev *hdev) skb_queue_purge(&msg->msg_frags); kfree(msg); } - - del_timer_sync(&hdev->cmd_timer); - - nfc_unregister_device(hdev->ndev); - - cancel_work_sync(&hdev->msg_tx_work); - cancel_work_sync(&hdev->msg_rx_work); } EXPORT_SYMBOL(nfc_hci_unregister_device); diff --git a/net/nfc/hci/hcp.c b/net/nfc/hci/hcp.c index bc308a7ca60..b6b4109f234 100644 --- a/net/nfc/hci/hcp.c +++ b/net/nfc/hci/hcp.c @@ -105,6 +105,13 @@ int nfc_hci_hcp_message_tx(struct nfc_hci_dev *hdev, u8 pipe, } mutex_lock(&hdev->msg_tx_mutex); + + if (hdev->shutting_down) { + err = -ESHUTDOWN; + mutex_unlock(&hdev->msg_tx_mutex); + goto out_skb_err; + } + list_add_tail(&cmd->msg_l, &hdev->msg_tx_queue); mutex_unlock(&hdev->msg_tx_mutex); diff --git a/net/nfc/llcp/commands.c b/net/nfc/llcp/commands.c index df24be48d4d..c6bc3bd9505 100644 --- a/net/nfc/llcp/commands.c +++ b/net/nfc/llcp/commands.c @@ -304,6 +304,8 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) skb = llcp_add_header(skb, 0, 0, LLCP_PDU_SYMM); + __net_timestamp(skb); + nfc_llcp_send_to_raw_sock(local, skb, NFC_LLCP_DIRECTION_TX); return nfc_data_exchange(dev, local->target_idx, skb, diff --git a/net/nfc/llcp/llcp.c b/net/nfc/llcp/llcp.c index ec43914c92a..85bc75c38de 100644 --- a/net/nfc/llcp/llcp.c +++ b/net/nfc/llcp/llcp.c @@ -54,7 +54,6 @@ static void nfc_llcp_socket_purge(struct nfc_llcp_sock *sock) skb_queue_purge(&sock->tx_queue); skb_queue_purge(&sock->tx_pending_queue); - skb_queue_purge(&sock->tx_backlog_queue); if (local == NULL) return; @@ -668,6 +667,8 @@ static void nfc_llcp_tx_work(struct work_struct *work) if (ptype == LLCP_PDU_I) copy_skb = skb_copy(skb, GFP_ATOMIC); + __net_timestamp(skb); + nfc_llcp_send_to_raw_sock(local, skb, NFC_LLCP_DIRECTION_TX); @@ -781,9 +782,15 @@ static void nfc_llcp_recv_ui(struct nfc_llcp_local *local, /* There is no sequence with UI frames */ skb_pull(skb, LLCP_HEADER_SIZE); - if (sock_queue_rcv_skb(&llcp_sock->sk, skb)) { - pr_err("receive queue is full\n"); - skb_queue_head(&llcp_sock->tx_backlog_queue, skb); + if (!sock_queue_rcv_skb(&llcp_sock->sk, skb)) { + /* + * UI frames will be freed from the socket layer, so we + * need to keep them alive until someone receives them. + */ + skb_get(skb); + } else { + pr_err("Receive queue is full\n"); + kfree_skb(skb); } nfc_llcp_sock_put(llcp_sock); @@ -976,9 +983,15 @@ static void nfc_llcp_recv_hdlc(struct nfc_llcp_local *local, pr_err("Received out of sequence I PDU\n"); skb_pull(skb, LLCP_HEADER_SIZE + LLCP_SEQUENCE_SIZE); - if (sock_queue_rcv_skb(&llcp_sock->sk, skb)) { - pr_err("receive queue is full\n"); - skb_queue_head(&llcp_sock->tx_backlog_queue, skb); + if (!sock_queue_rcv_skb(&llcp_sock->sk, skb)) { + /* + * I frames will be freed from the socket layer, so we + * need to keep them alive until someone receives them. + */ + skb_get(skb); + } else { + pr_err("Receive queue is full\n"); + kfree_skb(skb); } } @@ -1245,6 +1258,8 @@ static void nfc_llcp_rx_work(struct work_struct *work) print_hex_dump(KERN_DEBUG, "LLCP Rx: ", DUMP_PREFIX_OFFSET, 16, 1, skb->data, skb->len, true); + __net_timestamp(skb); + nfc_llcp_send_to_raw_sock(local, skb, NFC_LLCP_DIRECTION_RX); switch (ptype) { @@ -1296,6 +1311,13 @@ static void nfc_llcp_rx_work(struct work_struct *work) local->rx_pending = NULL; } +static void __nfc_llcp_recv(struct nfc_llcp_local *local, struct sk_buff *skb) +{ + local->rx_pending = skb; + del_timer(&local->link_timer); + schedule_work(&local->rx_work); +} + void nfc_llcp_recv(void *data, struct sk_buff *skb, int err) { struct nfc_llcp_local *local = (struct nfc_llcp_local *) data; @@ -1306,9 +1328,7 @@ void nfc_llcp_recv(void *data, struct sk_buff *skb, int err) return; } - local->rx_pending = skb_get(skb); - del_timer(&local->link_timer); - schedule_work(&local->rx_work); + __nfc_llcp_recv(local, skb); } int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb) @@ -1319,9 +1339,7 @@ int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb) if (local == NULL) return -ENODEV; - local->rx_pending = skb_get(skb); - del_timer(&local->link_timer); - schedule_work(&local->rx_work); + __nfc_llcp_recv(local, skb); return 0; } diff --git a/net/nfc/llcp/llcp.h b/net/nfc/llcp/llcp.h index 0d62366f8cc..0eae5c50950 100644 --- a/net/nfc/llcp/llcp.h +++ b/net/nfc/llcp/llcp.h @@ -121,7 +121,6 @@ struct nfc_llcp_sock { struct sk_buff_head tx_queue; struct sk_buff_head tx_pending_queue; - struct sk_buff_head tx_backlog_queue; struct list_head accept_queue; struct sock *parent; diff --git a/net/nfc/llcp/sock.c b/net/nfc/llcp/sock.c index fea22eb41b8..5332751943a 100644 --- a/net/nfc/llcp/sock.c +++ b/net/nfc/llcp/sock.c @@ -672,25 +672,27 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock, copied = min_t(unsigned int, rlen, len); cskb = skb; - if (memcpy_toiovec(msg->msg_iov, cskb->data, copied)) { + if (skb_copy_datagram_iovec(cskb, 0, msg->msg_iov, copied)) { if (!(flags & MSG_PEEK)) skb_queue_head(&sk->sk_receive_queue, skb); return -EFAULT; } + sock_recv_timestamp(msg, sk, skb); + 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 *sockaddr = + (struct sockaddr_nfc_llcp *) msg->msg_name; - pr_debug("Datagram socket %d %d\n", ui_cb->dsap, ui_cb->ssap); + msg->msg_namelen = sizeof(struct sockaddr_nfc_llcp); - sockaddr.sa_family = AF_NFC; - sockaddr.nfc_protocol = NFC_PROTO_NFC_DEP; - sockaddr.dsap = ui_cb->dsap; - sockaddr.ssap = ui_cb->ssap; + pr_debug("Datagram socket %d %d\n", ui_cb->dsap, ui_cb->ssap); - memcpy(msg->msg_name, &sockaddr, sizeof(sockaddr)); - msg->msg_namelen = sizeof(sockaddr); + sockaddr->sa_family = AF_NFC; + sockaddr->nfc_protocol = NFC_PROTO_NFC_DEP; + sockaddr->dsap = ui_cb->dsap; + sockaddr->ssap = ui_cb->ssap; } /* Mark read part of skb as used */ @@ -806,7 +808,6 @@ struct sock *nfc_llcp_sock_alloc(struct socket *sock, int type, gfp_t gfp) llcp_sock->reserved_ssap = LLCP_SAP_MAX; skb_queue_head_init(&llcp_sock->tx_queue); skb_queue_head_init(&llcp_sock->tx_pending_queue); - skb_queue_head_init(&llcp_sock->tx_backlog_queue); INIT_LIST_HEAD(&llcp_sock->accept_queue); if (sock != NULL) @@ -821,7 +822,6 @@ void nfc_llcp_sock_free(struct nfc_llcp_sock *sock) skb_queue_purge(&sock->tx_queue); skb_queue_purge(&sock->tx_pending_queue); - skb_queue_purge(&sock->tx_backlog_queue); list_del_init(&sock->accept_queue); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 5f98dc1bf03..48ada0ec749 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -658,6 +658,7 @@ static struct nfc_ops nci_nfc_ops = { */ struct nci_dev *nci_allocate_device(struct nci_ops *ops, __u32 supported_protocols, + __u32 supported_se, int tx_headroom, int tx_tailroom) { struct nci_dev *ndev; @@ -680,6 +681,7 @@ struct nci_dev *nci_allocate_device(struct nci_ops *ops, ndev->nfc_dev = nfc_allocate_device(&nci_nfc_ops, supported_protocols, + supported_se, tx_headroom + NCI_DATA_HDR_SIZE, tx_tailroom); if (!ndev->nfc_dev) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 3568ae16786..504b883439f 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -366,6 +366,7 @@ static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev, if (nla_put_string(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)) || nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols) || + nla_put_u32(msg, NFC_ATTR_SE, dev->supported_se) || nla_put_u8(msg, NFC_ATTR_DEVICE_POWERED, dev->dev_up) || nla_put_u8(msg, NFC_ATTR_RF_MODE, dev->rf_mode)) goto nla_put_failure; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index f996db34324..d8c13a96545 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1989,10 +1989,9 @@ static struct pernet_operations ovs_net_ops = { static int __init dp_init(void) { - struct sk_buff *dummy_skb; int err; - BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); pr_info("Open vSwitch switching datapath\n"); diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 5d460c37df0..0531de6c7a4 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -69,7 +69,6 @@ static int internal_dev_mac_addr(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - dev->addr_assign_type &= ~NET_ADDR_RANDOM; memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); return 0; } @@ -98,7 +97,7 @@ static int internal_dev_stop(struct net_device *netdev) static void internal_dev_getinfo(struct net_device *netdev, struct ethtool_drvinfo *info) { - strcpy(info->driver, "openvswitch"); + strlcpy(info->driver, "openvswitch", sizeof(info->driver)); } static const struct ethtool_ops internal_dev_ethtool_ops = { diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 05996d0dd82..5b0fd291bab 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -10,6 +10,7 @@ */ #include <linux/module.h> +#include <linux/kernel.h> #include <linux/net.h> #include <linux/slab.h> #include <linux/skbuff.h> @@ -792,10 +793,9 @@ static const struct net_proto_family rxrpc_family_ops = { */ static int __init af_rxrpc_init(void) { - struct sk_buff *dummy_skb; int ret = -1; - BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > FIELD_SIZEOF(struct sk_buff, cb)); rxrpc_epoch = htonl(get_seconds()); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 65d240cbf74..8579c4bb20c 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -485,8 +485,9 @@ errout: return err; } -struct tc_action *tcf_action_init_1(struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind) +struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, + struct nlattr *est, char *name, int ovr, + int bind) { struct tc_action *a; struct tc_action_ops *a_o; @@ -542,9 +543,9 @@ struct tc_action *tcf_action_init_1(struct nlattr *nla, struct nlattr *est, /* backward compatibility for policer */ if (name == NULL) - err = a_o->init(tb[TCA_ACT_OPTIONS], est, a, ovr, bind); + err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, a, ovr, bind); else - err = a_o->init(nla, est, a, ovr, bind); + err = a_o->init(net, nla, est, a, ovr, bind); if (err < 0) goto err_free; @@ -566,8 +567,9 @@ err_out: return ERR_PTR(err); } -struct tc_action *tcf_action_init(struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind) +struct tc_action *tcf_action_init(struct net *net, struct nlattr *nla, + struct nlattr *est, char *name, int ovr, + int bind) { struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *head = NULL, *act, *act_prev = NULL; @@ -579,7 +581,7 @@ struct tc_action *tcf_action_init(struct nlattr *nla, struct nlattr *est, return ERR_PTR(err); for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_init_1(tb[i], est, name, ovr, bind); + act = tcf_action_init_1(net, tb[i], est, name, ovr, bind); if (IS_ERR(act)) goto err; act->order = i; @@ -960,7 +962,7 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, struct tc_action *a; u32 seq = n->nlmsg_seq; - act = tcf_action_init(nla, NULL, NULL, ovr, 0); + act = tcf_action_init(net, nla, NULL, NULL, ovr, 0); if (act == NULL) goto done; if (IS_ERR(act)) { diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 2c8ad7c86e4..08fa1e8a4ca 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -51,7 +51,7 @@ static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { [TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), }, }; -static int tcf_csum_init(struct nlattr *nla, struct nlattr *est, +static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { struct nlattr *tb[TCA_CSUM_MAX + 1]; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 05d60859d8e..fd2b3cff5fa 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -58,8 +58,9 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { [TCA_GACT_PROB] = { .len = sizeof(struct tc_gact_p) }, }; -static int tcf_gact_init(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_gact_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) { struct nlattr *tb[TCA_GACT_MAX + 1]; struct tc_gact *parm; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 58fb3c7aab9..0fb9e3f567e 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -102,7 +102,7 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, }; -static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, +static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { struct nlattr *tb[TCA_IPT_MAX + 1]; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 9c0fd0c7881..5d676edc22a 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -62,8 +62,9 @@ static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { [TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) }, }; -static int tcf_mirred_init(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_mirred_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, int ovr, + int bind) { struct nlattr *tb[TCA_MIRRED_MAX + 1]; struct tc_mirred *parm; @@ -88,7 +89,7 @@ static int tcf_mirred_init(struct nlattr *nla, struct nlattr *est, return -EINVAL; } if (parm->ifindex) { - dev = __dev_get_by_index(&init_net, parm->ifindex); + dev = __dev_get_by_index(net, parm->ifindex); if (dev == NULL) return -ENODEV; switch (dev->type) { diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index b5d029eb44f..876f0ef2969 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -44,7 +44,7 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { [TCA_NAT_PARMS] = { .len = sizeof(struct tc_nat) }, }; -static int tcf_nat_init(struct nlattr *nla, struct nlattr *est, +static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { struct nlattr *tb[TCA_NAT_MAX + 1]; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 45c53ab067a..0c3faddf3f2 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -38,8 +38,9 @@ static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, }; -static int tcf_pedit_init(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_pedit_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) { struct nlattr *tb[TCA_PEDIT_MAX + 1]; struct tc_pedit *parm; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index a9de23297d4..8dbd695c160 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -130,8 +130,9 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { [TCA_POLICE_RESULT] = { .type = NLA_U32 }, }; -static int tcf_act_police_locate(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_act_police_locate(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) { unsigned int h; int ret = 0, err; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 3714f60f0b3..7725eb4ab75 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -95,8 +95,9 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { [TCA_DEF_DATA] = { .type = NLA_STRING, .len = SIMP_MAX_DATA }, }; -static int tcf_simp_init(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_simp_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) { struct nlattr *tb[TCA_DEF_MAX + 1]; struct tc_defact *parm; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 476e0fac671..cb4221171f9 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -67,8 +67,9 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { [TCA_SKBEDIT_MARK] = { .len = sizeof(u32) }, }; -static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_skbedit_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) { struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tc_skbedit *parm; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ff55ed6c49b..964f5e4f4b8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -321,7 +321,7 @@ replay: } } - err = tp->ops->change(skb, tp, cl, t->tcm_handle, tca, &fh); + err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh); if (err == 0) { if (tp_created) { spin_lock_bh(root_lock); @@ -508,7 +508,7 @@ void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_destroy); -int tcf_exts_validate(struct tcf_proto *tp, struct nlattr **tb, +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) { @@ -519,7 +519,7 @@ int tcf_exts_validate(struct tcf_proto *tp, struct nlattr **tb, struct tc_action *act; if (map->police && tb[map->police]) { - act = tcf_action_init_1(tb[map->police], rate_tlv, + act = tcf_action_init_1(net, tb[map->police], rate_tlv, "police", TCA_ACT_NOREPLACE, TCA_ACT_BIND); if (IS_ERR(act)) @@ -528,8 +528,9 @@ int tcf_exts_validate(struct tcf_proto *tp, struct nlattr **tb, act->type = TCA_OLD_COMPAT; exts->action = act; } else if (map->action && tb[map->action]) { - act = tcf_action_init(tb[map->action], rate_tlv, NULL, - TCA_ACT_NOREPLACE, TCA_ACT_BIND); + act = tcf_action_init(net, tb[map->action], rate_tlv, + NULL, TCA_ACT_NOREPLACE, + TCA_ACT_BIND); if (IS_ERR(act)) return PTR_ERR(act); diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 344a11b342e..d76a35d0dc8 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -132,15 +132,16 @@ static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = { [TCA_BASIC_EMATCHES] = { .type = NLA_NESTED }, }; -static int basic_set_parms(struct tcf_proto *tp, struct basic_filter *f, - unsigned long base, struct nlattr **tb, +static int basic_set_parms(struct net *net, struct tcf_proto *tp, + struct basic_filter *f, unsigned long base, + struct nlattr **tb, struct nlattr *est) { int err = -EINVAL; struct tcf_exts e; struct tcf_ematch_tree t; - err = tcf_exts_validate(tp, tb, est, &e, &basic_ext_map); + err = tcf_exts_validate(net, tp, tb, est, &e, &basic_ext_map); if (err < 0) return err; @@ -162,7 +163,7 @@ errout: return err; } -static int basic_change(struct sk_buff *in_skb, +static int basic_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) { @@ -182,7 +183,7 @@ static int basic_change(struct sk_buff *in_skb, if (f != NULL) { if (handle && f->handle != handle) return -EINVAL; - return basic_set_parms(tp, f, base, tb, tca[TCA_RATE]); + return basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE]); } err = -ENOBUFS; @@ -208,7 +209,7 @@ static int basic_change(struct sk_buff *in_skb, f->handle = head->hgenerator; } - err = basic_set_parms(tp, f, base, tb, tca[TCA_RATE]); + err = basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE]); if (err < 0) goto errout; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 6db7855b902..3a294eb98d6 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -178,7 +178,7 @@ static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = { [TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED }, }; -static int cls_cgroup_change(struct sk_buff *in_skb, +static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) @@ -215,7 +215,8 @@ static int cls_cgroup_change(struct sk_buff *in_skb, if (err < 0) return err; - err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &cgroup_ext_map); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, + &cgroup_ext_map); if (err < 0) return err; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index ce82d0cb1b4..aa36a8c8b33 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -351,7 +351,7 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = { [TCA_FLOW_PERTURB] = { .type = NLA_U32 }, }; -static int flow_change(struct sk_buff *in_skb, +static int flow_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) @@ -397,7 +397,7 @@ static int flow_change(struct sk_buff *in_skb, return -EOPNOTSUPP; } - err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &flow_ext_map); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &flow_ext_map); if (err < 0) return err; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 4075a0aef2a..1135d8227f9 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -192,7 +192,7 @@ static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = { }; static int -fw_change_attrs(struct tcf_proto *tp, struct fw_filter *f, +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; @@ -200,7 +200,7 @@ fw_change_attrs(struct tcf_proto *tp, struct fw_filter *f, u32 mask; int err; - err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &fw_ext_map); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &fw_ext_map); if (err < 0) return err; @@ -233,7 +233,7 @@ errout: return err; } -static int fw_change(struct sk_buff *in_skb, +static int fw_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -255,7 +255,7 @@ static int fw_change(struct sk_buff *in_skb, if (f != NULL) { if (f->id != handle && handle) return -EINVAL; - return fw_change_attrs(tp, f, tb, tca, base); + return fw_change_attrs(net, tp, f, tb, tca, base); } if (!handle) @@ -282,7 +282,7 @@ static int fw_change(struct sk_buff *in_skb, f->id = handle; - err = fw_change_attrs(tp, f, tb, tca, base); + err = fw_change_attrs(net, tp, f, tb, tca, base); if (err < 0) goto errout; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index c10d57bf98f..37da567d833 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -335,9 +335,10 @@ static const struct nla_policy route4_policy[TCA_ROUTE4_MAX + 1] = { [TCA_ROUTE4_IIF] = { .type = NLA_U32 }, }; -static int route4_set_parms(struct tcf_proto *tp, unsigned long base, - struct route4_filter *f, u32 handle, struct route4_head *head, - struct nlattr **tb, struct nlattr *est, int new) +static int route4_set_parms(struct net *net, struct tcf_proto *tp, + unsigned long base, struct route4_filter *f, + u32 handle, struct route4_head *head, + struct nlattr **tb, struct nlattr *est, int new) { int err; u32 id = 0, to = 0, nhandle = 0x8000; @@ -346,7 +347,7 @@ static int route4_set_parms(struct tcf_proto *tp, unsigned long base, struct route4_bucket *b; struct tcf_exts e; - err = tcf_exts_validate(tp, tb, est, &e, &route_ext_map); + err = tcf_exts_validate(net, tp, tb, est, &e, &route_ext_map); if (err < 0) return err; @@ -427,7 +428,7 @@ errout: return err; } -static int route4_change(struct sk_buff *in_skb, +static int route4_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -457,7 +458,7 @@ static int route4_change(struct sk_buff *in_skb, if (f->bkt) old_handle = f->handle; - err = route4_set_parms(tp, base, f, handle, head, tb, + err = route4_set_parms(net, tp, base, f, handle, head, tb, tca[TCA_RATE], 0); if (err < 0) return err; @@ -480,7 +481,7 @@ static int route4_change(struct sk_buff *in_skb, if (f == NULL) goto errout; - err = route4_set_parms(tp, base, f, handle, head, tb, + err = route4_set_parms(net, tp, base, f, handle, head, tb, tca[TCA_RATE], 1); if (err < 0) goto errout; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 494bbb90924..252d8b05872 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -416,7 +416,7 @@ static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = { [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) }, }; -static int rsvp_change(struct sk_buff *in_skb, +static int rsvp_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -440,7 +440,7 @@ static int rsvp_change(struct sk_buff *in_skb, if (err < 0) return err; - err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &rsvp_ext_map); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &rsvp_ext_map); if (err < 0) return err; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index a1293b4ab7a..b86535a4016 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -197,9 +197,10 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = { }; static int -tcindex_set_parms(struct tcf_proto *tp, unsigned long base, u32 handle, - struct tcindex_data *p, struct tcindex_filter_result *r, - struct nlattr **tb, struct nlattr *est) +tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, + u32 handle, struct tcindex_data *p, + struct tcindex_filter_result *r, struct nlattr **tb, + struct nlattr *est) { int err, balloc = 0; struct tcindex_filter_result new_filter_result, *old_r = r; @@ -208,7 +209,7 @@ tcindex_set_parms(struct tcf_proto *tp, unsigned long base, u32 handle, struct tcindex_filter *f = NULL; /* make gcc behave */ struct tcf_exts e; - err = tcf_exts_validate(tp, tb, est, &e, &tcindex_ext_map); + err = tcf_exts_validate(net, tp, tb, est, &e, &tcindex_ext_map); if (err < 0) return err; @@ -332,7 +333,7 @@ errout: } static int -tcindex_change(struct sk_buff *in_skb, +tcindex_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) { @@ -353,7 +354,8 @@ tcindex_change(struct sk_buff *in_skb, if (err < 0) return err; - return tcindex_set_parms(tp, base, handle, p, r, tb, tca[TCA_RATE]); + return tcindex_set_parms(net, tp, base, handle, p, r, tb, + tca[TCA_RATE]); } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index c7c27bc91b5..eb07a1e536e 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -488,15 +488,15 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_MARK] = { .len = sizeof(struct tc_u32_mark) }, }; -static int u32_set_parms(struct tcf_proto *tp, unsigned long base, - struct tc_u_hnode *ht, +static int u32_set_parms(struct net *net, struct tcf_proto *tp, + unsigned long base, struct tc_u_hnode *ht, struct tc_u_knode *n, struct nlattr **tb, struct nlattr *est) { int err; struct tcf_exts e; - err = tcf_exts_validate(tp, tb, est, &e, &u32_ext_map); + err = tcf_exts_validate(net, tp, tb, est, &e, &u32_ext_map); if (err < 0) return err; @@ -544,7 +544,7 @@ errout: return err; } -static int u32_change(struct sk_buff *in_skb, +static int u32_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) @@ -570,7 +570,8 @@ static int u32_change(struct sk_buff *in_skb, if (TC_U32_KEY(n->handle) == 0) return -EINVAL; - return u32_set_parms(tp, base, n->ht_up, n, tb, tca[TCA_RATE]); + return u32_set_parms(net, tp, base, n->ht_up, n, tb, + tca[TCA_RATE]); } if (tb[TCA_U32_DIVISOR]) { @@ -656,7 +657,7 @@ static int u32_change(struct sk_buff *in_skb, } #endif - err = u32_set_parms(tp, base, ht, n, tb, tca[TCA_RATE]); + err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE]); if (err == 0) { struct tc_u_knode **ins; for (ins = &ht->ht[TC_U32_HASH(handle)]; *ins; ins = &(*ins)->next) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index f898b1c58bd..1c2e46cb919 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -595,7 +595,7 @@ static void sctp_v4_ecn_capable(struct sock *sk) INET_ECN_xmit(sk); } -void sctp_addr_wq_timeout_handler(unsigned long arg) +static void sctp_addr_wq_timeout_handler(unsigned long arg) { struct net *net = (struct net *)arg; struct sctp_sockaddr_entry *addrw, *temp; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5b5c876c80e..0c612361c15 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2426,9 +2426,8 @@ static struct pernet_operations unix_net_ops = { static int __init af_unix_init(void) { int rc = -1; - struct sk_buff *dummy_skb; - BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct unix_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); rc = proto_register(&unix_proto, 1); if (rc != 0) { diff --git a/net/wireless/ap.c b/net/wireless/ap.c index 324e8d851dc..a4a14e8f55c 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -46,3 +46,65 @@ int cfg80211_stop_ap(struct cfg80211_registered_device *rdev, return err; } + +void cfg80211_ch_switch_notify(struct net_device *dev, + struct cfg80211_chan_def *chandef) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + trace_cfg80211_ch_switch_notify(dev, chandef); + + wdev_lock(wdev); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP && + wdev->iftype != NL80211_IFTYPE_P2P_GO)) + goto out; + + wdev->channel = chandef->chan; + nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL); +out: + wdev_unlock(wdev); + return; +} +EXPORT_SYMBOL(cfg80211_ch_switch_notify); + +bool cfg80211_rx_spurious_frame(struct net_device *dev, + const u8 *addr, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + bool ret; + + trace_cfg80211_rx_spurious_frame(dev, addr); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP && + wdev->iftype != NL80211_IFTYPE_P2P_GO)) { + trace_cfg80211_return_bool(false); + return false; + } + ret = nl80211_unexpected_frame(dev, addr, gfp); + trace_cfg80211_return_bool(ret); + return ret; +} +EXPORT_SYMBOL(cfg80211_rx_spurious_frame); + +bool cfg80211_rx_unexpected_4addr_frame(struct net_device *dev, + const u8 *addr, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + bool ret; + + trace_cfg80211_rx_unexpected_4addr_frame(dev, addr); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP && + wdev->iftype != NL80211_IFTYPE_P2P_GO && + wdev->iftype != NL80211_IFTYPE_AP_VLAN)) { + trace_cfg80211_return_bool(false); + return false; + } + ret = nl80211_unexpected_4addr_frame(dev, addr, gfp); + trace_cfg80211_return_bool(ret); + return ret; +} +EXPORT_SYMBOL(cfg80211_rx_unexpected_4addr_frame); diff --git a/net/wireless/chan.c b/net/wireless/chan.c index a7990bb1652..396373f3ec2 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -76,6 +76,10 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) return false; if (!chandef->center_freq2) return false; + /* adjacent is not allowed -- that's a 160 MHz channel */ + if (chandef->center_freq1 - chandef->center_freq2 == 80 || + chandef->center_freq2 - chandef->center_freq1 == 80) + return false; break; case NL80211_CHAN_WIDTH_80: if (chandef->center_freq1 != control_freq + 30 && diff --git a/net/wireless/core.c b/net/wireless/core.c index b677eab55b6..9245729694d 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -57,9 +57,6 @@ struct cfg80211_registered_device *cfg80211_rdev_by_wiphy_idx(int wiphy_idx) { struct cfg80211_registered_device *result = NULL, *rdev; - if (!wiphy_idx_valid(wiphy_idx)) - return NULL; - assert_cfg80211_lock(); list_for_each_entry(rdev, &cfg80211_rdev_list, list) { @@ -74,10 +71,8 @@ struct cfg80211_registered_device *cfg80211_rdev_by_wiphy_idx(int wiphy_idx) int get_wiphy_idx(struct wiphy *wiphy) { - struct cfg80211_registered_device *rdev; - if (!wiphy) - return WIPHY_IDX_STALE; - rdev = wiphy_to_dev(wiphy); + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + return rdev->wiphy_idx; } @@ -86,9 +81,6 @@ struct wiphy *wiphy_idx_to_wiphy(int wiphy_idx) { struct cfg80211_registered_device *rdev; - if (!wiphy_idx_valid(wiphy_idx)) - return NULL; - assert_cfg80211_lock(); rdev = cfg80211_rdev_by_wiphy_idx(wiphy_idx); @@ -309,7 +301,7 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) rdev->wiphy_idx = wiphy_counter++; - if (unlikely(!wiphy_idx_valid(rdev->wiphy_idx))) { + if (unlikely(rdev->wiphy_idx < 0)) { wiphy_counter--; mutex_unlock(&cfg80211_mutex); /* ugh, wrapped! */ @@ -390,8 +382,11 @@ static int wiphy_verify_combinations(struct wiphy *wiphy) c = &wiphy->iface_combinations[i]; - /* Combinations with just one interface aren't real */ - if (WARN_ON(c->max_interfaces < 2)) + /* + * Combinations with just one interface aren't real, + * however we make an exception for DFS. + */ + if (WARN_ON((c->max_interfaces < 2) && !c->radar_detect_widths)) return -EINVAL; /* Need at least one channel */ @@ -406,6 +401,11 @@ static int wiphy_verify_combinations(struct wiphy *wiphy) CFG80211_MAX_NUM_DIFFERENT_CHANNELS)) return -EINVAL; + /* DFS only works on one channel. */ + if (WARN_ON(c->radar_detect_widths && + (c->num_different_channels > 1))) + return -EINVAL; + if (WARN_ON(!c->n_limits)) return -EINVAL; diff --git a/net/wireless/core.h b/net/wireless/core.h index 3563097169c..8396f7671c8 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -18,6 +18,9 @@ #include <net/cfg80211.h> #include "reg.h" + +#define WIPHY_IDX_INVALID -1 + struct cfg80211_registered_device { const struct cfg80211_ops *ops; struct list_head list; @@ -86,7 +89,7 @@ struct cfg80211_registered_device { /* must be last because of the way we do wiphy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ - struct wiphy wiphy __attribute__((__aligned__(NETDEV_ALIGN))); + struct wiphy wiphy __aligned(NETDEV_ALIGN); }; static inline @@ -96,13 +99,6 @@ struct cfg80211_registered_device *wiphy_to_dev(struct wiphy *wiphy) return container_of(wiphy, struct cfg80211_registered_device, wiphy); } -/* Note 0 is valid, hence phy0 */ -static inline -bool wiphy_idx_valid(int wiphy_idx) -{ - return wiphy_idx >= 0; -} - static inline void cfg80211_rdev_free_wowlan(struct cfg80211_registered_device *rdev) { @@ -126,12 +122,6 @@ static inline void assert_cfg80211_lock(void) lockdep_assert_held(&cfg80211_mutex); } -/* - * You can use this to mark a wiphy_idx as not having an associated wiphy. - * It guarantees cfg80211_rdev_by_wiphy_idx(wiphy_idx) will return NULL - */ -#define WIPHY_IDX_STALE -1 - struct cfg80211_internal_bss { struct list_head list; struct rb_node rbn; @@ -435,7 +425,8 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, enum nl80211_iftype iftype, struct ieee80211_channel *chan, - enum cfg80211_chan_mode chanmode); + enum cfg80211_chan_mode chanmode, + u8 radar_detect); static inline int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, @@ -443,7 +434,7 @@ cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype) { return cfg80211_can_use_iftype_chan(rdev, wdev, iftype, NULL, - CHAN_MODE_UNDEFINED); + CHAN_MODE_UNDEFINED, 0); } static inline int @@ -460,7 +451,7 @@ cfg80211_can_use_chan(struct cfg80211_registered_device *rdev, enum cfg80211_chan_mode chanmode) { return cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype, - chan, chanmode); + chan, chanmode, 0); } void diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c index 48c48ffafa1..e37862f1b12 100644 --- a/net/wireless/ethtool.c +++ b/net/wireless/ethtool.c @@ -15,10 +15,10 @@ static void cfg80211_get_drvinfo(struct net_device *dev, strlcpy(info->version, init_utsname()->release, sizeof(info->version)); if (wdev->wiphy->fw_version[0]) - strncpy(info->fw_version, wdev->wiphy->fw_version, + strlcpy(info->fw_version, wdev->wiphy->fw_version, sizeof(info->fw_version)); else - strncpy(info->fw_version, "N/A", sizeof(info->fw_version)); + strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); strlcpy(info->bus_info, dev_name(wiphy_dev(wdev->wiphy)), sizeof(info->bus_info)); diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index f9d6ce5cfab..55957a284f6 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -44,6 +44,10 @@ #define MESH_SYNC_NEIGHBOR_OFFSET_MAX 50 +#define MESH_DEFAULT_BEACON_INTERVAL 1000 /* in 1024 us units (=TUs) */ +#define MESH_DEFAULT_DTIM_PERIOD 2 +#define MESH_DEFAULT_AWAKE_WINDOW 10 /* in 1024 us units (=TUs) */ + const struct mesh_config default_mesh_config = { .dot11MeshRetryTimeout = MESH_RET_T, .dot11MeshConfirmTimeout = MESH_CONF_T, @@ -69,6 +73,8 @@ const struct mesh_config default_mesh_config = { .dot11MeshHWMPactivePathToRootTimeout = MESH_PATH_TO_ROOT_TIMEOUT, .dot11MeshHWMProotInterval = MESH_ROOT_INTERVAL, .dot11MeshHWMPconfirmationInterval = MESH_ROOT_CONFIRMATION_INTERVAL, + .power_mode = NL80211_MESH_POWER_ACTIVE, + .dot11MeshAwakeWindowDuration = MESH_DEFAULT_AWAKE_WINDOW, }; const struct mesh_setup default_mesh_setup = { @@ -79,6 +85,8 @@ const struct mesh_setup default_mesh_setup = { .ie = NULL, .ie_len = 0, .is_secure = false, + .beacon_interval = MESH_DEFAULT_BEACON_INTERVAL, + .dtim_period = MESH_DEFAULT_DTIM_PERIOD, }; int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 5e8123ee63f..461e692cdfe 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -987,65 +987,3 @@ void cfg80211_pmksa_candidate_notify(struct net_device *dev, int index, nl80211_pmksa_candidate_notify(rdev, dev, index, bssid, preauth, gfp); } EXPORT_SYMBOL(cfg80211_pmksa_candidate_notify); - -void cfg80211_ch_switch_notify(struct net_device *dev, - struct cfg80211_chan_def *chandef) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - struct wiphy *wiphy = wdev->wiphy; - struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - - trace_cfg80211_ch_switch_notify(dev, chandef); - - wdev_lock(wdev); - - if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP && - wdev->iftype != NL80211_IFTYPE_P2P_GO)) - goto out; - - wdev->channel = chandef->chan; - nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL); -out: - wdev_unlock(wdev); - return; -} -EXPORT_SYMBOL(cfg80211_ch_switch_notify); - -bool cfg80211_rx_spurious_frame(struct net_device *dev, - const u8 *addr, gfp_t gfp) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - bool ret; - - trace_cfg80211_rx_spurious_frame(dev, addr); - - if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP && - wdev->iftype != NL80211_IFTYPE_P2P_GO)) { - trace_cfg80211_return_bool(false); - return false; - } - ret = nl80211_unexpected_frame(dev, addr, gfp); - trace_cfg80211_return_bool(ret); - return ret; -} -EXPORT_SYMBOL(cfg80211_rx_spurious_frame); - -bool cfg80211_rx_unexpected_4addr_frame(struct net_device *dev, - const u8 *addr, gfp_t gfp) -{ - struct wireless_dev *wdev = dev->ieee80211_ptr; - bool ret; - - trace_cfg80211_rx_unexpected_4addr_frame(dev, addr); - - if (WARN_ON(wdev->iftype != NL80211_IFTYPE_AP && - wdev->iftype != NL80211_IFTYPE_P2P_GO && - wdev->iftype != NL80211_IFTYPE_AP_VLAN)) { - trace_cfg80211_return_bool(false); - return false; - } - ret = nl80211_unexpected_4addr_frame(dev, addr, gfp); - trace_cfg80211_return_bool(ret); - return ret; -} -EXPORT_SYMBOL(cfg80211_rx_unexpected_4addr_frame); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f45706adaf3..33de80364c5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -856,6 +856,9 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy, nla_put_u32(msg, NL80211_IFACE_COMB_MAXNUM, c->max_interfaces)) goto nla_put_failure; + if (nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS, + c->radar_detect_widths)) + goto nla_put_failure; nla_nest_end(msg, nl_combi); } @@ -2079,6 +2082,13 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) !(rdev->wiphy.interface_modes & (1 << type))) return -EOPNOTSUPP; + if (type == NL80211_IFTYPE_P2P_DEVICE && info->attrs[NL80211_ATTR_MAC]) { + nla_memcpy(params.macaddr, info->attrs[NL80211_ATTR_MAC], + ETH_ALEN); + if (!is_valid_ether_addr(params.macaddr)) + return -EADDRNOTAVAIL; + } + if (info->attrs[NL80211_ATTR_4ADDR]) { params.use_4addr = !!nla_get_u8(info->attrs[NL80211_ATTR_4ADDR]); err = nl80211_valid_4addr(rdev, NULL, params.use_4addr, type); @@ -3001,6 +3011,18 @@ static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq, nla_put_u32(msg, NL80211_STA_INFO_BEACON_LOSS, sinfo->beacon_loss_count)) goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_LOCAL_PM) && + nla_put_u32(msg, NL80211_STA_INFO_LOCAL_PM, + sinfo->local_pm)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_PEER_PM) && + nla_put_u32(msg, NL80211_STA_INFO_PEER_PM, + sinfo->peer_pm)) + goto nla_put_failure; + if ((sinfo->filled & STATION_INFO_NONPEER_PM) && + nla_put_u32(msg, NL80211_STA_INFO_NONPEER_PM, + sinfo->nonpeer_pm)) + goto nla_put_failure; if (sinfo->filled & STATION_INFO_BSS_PARAM) { bss_param = nla_nest_start(msg, NL80211_STA_INFO_BSS_PARAM); if (!bss_param) @@ -3188,13 +3210,9 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_RATES]); } - if (info->attrs[NL80211_ATTR_STA_LISTEN_INTERVAL]) - params.listen_interval = - nla_get_u16(info->attrs[NL80211_ATTR_STA_LISTEN_INTERVAL]); - - if (info->attrs[NL80211_ATTR_HT_CAPABILITY]) - params.ht_capa = - nla_data(info->attrs[NL80211_ATTR_HT_CAPABILITY]); + if (info->attrs[NL80211_ATTR_STA_LISTEN_INTERVAL] || + info->attrs[NL80211_ATTR_HT_CAPABILITY]) + return -EINVAL; if (!rdev->ops->change_station) return -EOPNOTSUPP; @@ -3210,6 +3228,17 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) params.plink_state = nla_get_u8(info->attrs[NL80211_ATTR_STA_PLINK_STATE]); + if (info->attrs[NL80211_ATTR_LOCAL_MESH_POWER_MODE]) { + enum nl80211_mesh_power_mode pm = nla_get_u32( + info->attrs[NL80211_ATTR_LOCAL_MESH_POWER_MODE]); + + if (pm <= NL80211_MESH_POWER_UNKNOWN || + pm > NL80211_MESH_POWER_MAX) + return -EINVAL; + + params.local_pm = pm; + } + switch (dev->ieee80211_ptr->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: @@ -3217,6 +3246,8 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) /* disallow mesh-specific things */ if (params.plink_action) return -EINVAL; + if (params.local_pm) + return -EINVAL; /* TDLS can't be set, ... */ if (params.sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) @@ -3231,11 +3262,25 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) /* accept only the listed bits */ if (params.sta_flags_mask & ~(BIT(NL80211_STA_FLAG_AUTHORIZED) | + BIT(NL80211_STA_FLAG_AUTHENTICATED) | + BIT(NL80211_STA_FLAG_ASSOCIATED) | BIT(NL80211_STA_FLAG_SHORT_PREAMBLE) | BIT(NL80211_STA_FLAG_WME) | BIT(NL80211_STA_FLAG_MFP))) return -EINVAL; + /* but authenticated/associated only if driver handles it */ + if (!(rdev->wiphy.features & + NL80211_FEATURE_FULL_AP_CLIENT_STATE) && + params.sta_flags_mask & + (BIT(NL80211_STA_FLAG_AUTHENTICATED) | + BIT(NL80211_STA_FLAG_ASSOCIATED))) + return -EINVAL; + + /* reject other things that can't change */ + if (params.supported_rates) + return -EINVAL; + /* must be last in here for error handling */ params.vlan = get_vlan(info, rdev); if (IS_ERR(params.vlan)) @@ -3255,9 +3300,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) /* disallow things sta doesn't support */ if (params.plink_action) return -EINVAL; - if (params.ht_capa) - return -EINVAL; - if (params.listen_interval >= 0) + if (params.local_pm) return -EINVAL; /* reject any changes other than AUTHORIZED */ if (params.sta_flags_mask & ~BIT(NL80211_STA_FLAG_AUTHORIZED)) @@ -3267,9 +3310,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) /* disallow things mesh doesn't support */ if (params.vlan) return -EINVAL; - if (params.ht_capa) - return -EINVAL; - if (params.listen_interval >= 0) + if (params.supported_rates) return -EINVAL; /* * No special handling for TDLS here -- the userspace @@ -3393,17 +3434,31 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) /* but don't bother the driver with it */ params.sta_flags_mask &= ~BIT(NL80211_STA_FLAG_TDLS_PEER); + /* allow authenticated/associated only if driver handles it */ + if (!(rdev->wiphy.features & + NL80211_FEATURE_FULL_AP_CLIENT_STATE) && + params.sta_flags_mask & + (BIT(NL80211_STA_FLAG_AUTHENTICATED) | + BIT(NL80211_STA_FLAG_ASSOCIATED))) + return -EINVAL; + /* must be last in here for error handling */ params.vlan = get_vlan(info, rdev); if (IS_ERR(params.vlan)) return PTR_ERR(params.vlan); break; case NL80211_IFTYPE_MESH_POINT: + /* associated is disallowed */ + if (params.sta_flags_mask & BIT(NL80211_STA_FLAG_ASSOCIATED)) + return -EINVAL; /* TDLS peers cannot be added */ if (params.sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) return -EINVAL; break; case NL80211_IFTYPE_STATION: + /* associated is disallowed */ + if (params.sta_flags_mask & BIT(NL80211_STA_FLAG_ASSOCIATED)) + return -EINVAL; /* Only TDLS peers can be added */ if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))) return -EINVAL; @@ -3787,12 +3842,8 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) * window between nl80211_init() and regulatory_init(), if that is * even possible. */ - mutex_lock(&cfg80211_mutex); - if (unlikely(!cfg80211_regdomain)) { - mutex_unlock(&cfg80211_mutex); + if (unlikely(!rcu_access_pointer(cfg80211_regdomain))) return -EINPROGRESS; - } - mutex_unlock(&cfg80211_mutex); if (!info->attrs[NL80211_ATTR_REG_ALPHA2]) return -EINVAL; @@ -3908,7 +3959,11 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, nla_put_u16(msg, NL80211_MESHCONF_HWMP_ROOT_INTERVAL, cur_params.dot11MeshHWMProotInterval) || nla_put_u16(msg, NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, - cur_params.dot11MeshHWMPconfirmationInterval)) + cur_params.dot11MeshHWMPconfirmationInterval) || + nla_put_u32(msg, NL80211_MESHCONF_POWER_MODE, + cur_params.power_mode) || + nla_put_u16(msg, NL80211_MESHCONF_AWAKE_WINDOW, + cur_params.dot11MeshAwakeWindowDuration)) goto nla_put_failure; nla_nest_end(msg, pinfoattr); genlmsg_end(msg, hdr); @@ -3947,6 +4002,8 @@ static const struct nla_policy nl80211_meshconf_params_policy[NL80211_MESHCONF_A [NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT] = { .type = NLA_U32 }, [NL80211_MESHCONF_HWMP_ROOT_INTERVAL] = { .type = NLA_U16 }, [NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL] = { .type = NLA_U16 }, + [NL80211_MESHCONF_POWER_MODE] = { .type = NLA_U32 }, + [NL80211_MESHCONF_AWAKE_WINDOW] = { .type = NLA_U16 }, }; static const struct nla_policy @@ -3967,13 +4024,15 @@ static int nl80211_parse_mesh_config(struct genl_info *info, struct nlattr *tb[NL80211_MESHCONF_ATTR_MAX + 1]; u32 mask = 0; -#define FILL_IN_MESH_PARAM_IF_SET(table, cfg, param, mask, attr_num, nla_fn) \ -do {\ - if (table[attr_num]) {\ - cfg->param = nla_fn(table[attr_num]); \ - mask |= (1 << (attr_num - 1)); \ - } \ -} while (0);\ +#define FILL_IN_MESH_PARAM_IF_SET(tb, cfg, param, min, max, mask, attr, fn) \ +do { \ + if (tb[attr]) { \ + if (fn(tb[attr]) < min || fn(tb[attr]) > max) \ + return -EINVAL; \ + cfg->param = fn(tb[attr]); \ + mask |= (1 << (attr - 1)); \ + } \ +} while (0) if (!info->attrs[NL80211_ATTR_MESH_CONFIG]) @@ -3988,83 +4047,98 @@ do {\ BUILD_BUG_ON(NL80211_MESHCONF_ATTR_MAX > 32); /* Fill in the params struct */ - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshRetryTimeout, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshRetryTimeout, 1, 255, mask, NL80211_MESHCONF_RETRY_TIMEOUT, nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshConfirmTimeout, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshConfirmTimeout, 1, 255, mask, NL80211_MESHCONF_CONFIRM_TIMEOUT, nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHoldingTimeout, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHoldingTimeout, 1, 255, mask, NL80211_MESHCONF_HOLDING_TIMEOUT, nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshMaxPeerLinks, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshMaxPeerLinks, 0, 255, mask, NL80211_MESHCONF_MAX_PEER_LINKS, nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshMaxRetries, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshMaxRetries, 0, 16, mask, NL80211_MESHCONF_MAX_RETRIES, nla_get_u8); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshTTL, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshTTL, 1, 255, mask, NL80211_MESHCONF_TTL, nla_get_u8); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, element_ttl, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, element_ttl, 1, 255, mask, NL80211_MESHCONF_ELEMENT_TTL, nla_get_u8); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, auto_open_plinks, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, auto_open_plinks, 0, 1, mask, NL80211_MESHCONF_AUTO_OPEN_PLINKS, nla_get_u8); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshNbrOffsetMaxNeighbor, mask, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshNbrOffsetMaxNeighbor, + 1, 255, mask, NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, nla_get_u32); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPmaxPREQretries, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPmaxPREQretries, 0, 255, mask, NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, nla_get_u8); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, path_refresh_time, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, path_refresh_time, 1, 65535, mask, NL80211_MESHCONF_PATH_REFRESH_TIME, nla_get_u32); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, min_discovery_timeout, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, min_discovery_timeout, 1, 65535, mask, NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT, nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathTimeout, mask, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathTimeout, + 1, 65535, mask, NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT, nla_get_u32); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPpreqMinInterval, - mask, NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, + 1, 65535, mask, + NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPperrMinInterval, - mask, NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL, + 1, 65535, mask, + NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL, nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, - dot11MeshHWMPnetDiameterTraversalTime, mask, + dot11MeshHWMPnetDiameterTraversalTime, + 1, 65535, mask, NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, nla_get_u16); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPRootMode, mask, - NL80211_MESHCONF_HWMP_ROOTMODE, nla_get_u8); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPRannInterval, mask, - NL80211_MESHCONF_HWMP_RANN_INTERVAL, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPRootMode, 0, 4, + mask, NL80211_MESHCONF_HWMP_ROOTMODE, + nla_get_u8); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPRannInterval, 1, 65535, + mask, NL80211_MESHCONF_HWMP_RANN_INTERVAL, nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, - dot11MeshGateAnnouncementProtocol, mask, - NL80211_MESHCONF_GATE_ANNOUNCEMENTS, + dot11MeshGateAnnouncementProtocol, 0, 1, + mask, NL80211_MESHCONF_GATE_ANNOUNCEMENTS, nla_get_u8); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshForwarding, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshForwarding, 0, 1, mask, NL80211_MESHCONF_FORWARDING, nla_get_u8); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, rssi_threshold, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, rssi_threshold, 1, 255, mask, NL80211_MESHCONF_RSSI_THRESHOLD, nla_get_u32); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, ht_opmode, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, ht_opmode, 0, 16, mask, NL80211_MESHCONF_HT_OPMODE, nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathToRootTimeout, - mask, + 1, 65535, mask, NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, nla_get_u32); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMProotInterval, + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMProotInterval, 1, 65535, mask, NL80211_MESHCONF_HWMP_ROOT_INTERVAL, nla_get_u16); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, - dot11MeshHWMPconfirmationInterval, mask, + dot11MeshHWMPconfirmationInterval, + 1, 65535, mask, NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, nla_get_u16); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, power_mode, + NL80211_MESH_POWER_ACTIVE, + NL80211_MESH_POWER_MAX, + mask, NL80211_MESHCONF_POWER_MODE, + nla_get_u32); + FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshAwakeWindowDuration, + 0, 65535, mask, + NL80211_MESHCONF_AWAKE_WINDOW, nla_get_u16); if (mask_out) *mask_out = mask; @@ -4152,6 +4226,7 @@ static int nl80211_update_mesh_config(struct sk_buff *skb, static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) { + const struct ieee80211_regdomain *regdom; struct sk_buff *msg; void *hdr = NULL; struct nlattr *nl_reg_rules; @@ -4174,35 +4249,36 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) if (!hdr) goto put_failure; - if (nla_put_string(msg, NL80211_ATTR_REG_ALPHA2, - cfg80211_regdomain->alpha2) || - (cfg80211_regdomain->dfs_region && - nla_put_u8(msg, NL80211_ATTR_DFS_REGION, - cfg80211_regdomain->dfs_region))) - goto nla_put_failure; - if (reg_last_request_cell_base() && nla_put_u32(msg, NL80211_ATTR_USER_REG_HINT_TYPE, NL80211_USER_REG_HINT_CELL_BASE)) goto nla_put_failure; + rcu_read_lock(); + regdom = rcu_dereference(cfg80211_regdomain); + + if (nla_put_string(msg, NL80211_ATTR_REG_ALPHA2, regdom->alpha2) || + (regdom->dfs_region && + nla_put_u8(msg, NL80211_ATTR_DFS_REGION, regdom->dfs_region))) + goto nla_put_failure_rcu; + nl_reg_rules = nla_nest_start(msg, NL80211_ATTR_REG_RULES); if (!nl_reg_rules) - goto nla_put_failure; + goto nla_put_failure_rcu; - for (i = 0; i < cfg80211_regdomain->n_reg_rules; i++) { + for (i = 0; i < regdom->n_reg_rules; i++) { struct nlattr *nl_reg_rule; const struct ieee80211_reg_rule *reg_rule; const struct ieee80211_freq_range *freq_range; const struct ieee80211_power_rule *power_rule; - reg_rule = &cfg80211_regdomain->reg_rules[i]; + reg_rule = ®dom->reg_rules[i]; freq_range = ®_rule->freq_range; power_rule = ®_rule->power_rule; nl_reg_rule = nla_nest_start(msg, i); if (!nl_reg_rule) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u32(msg, NL80211_ATTR_REG_RULE_FLAGS, reg_rule->flags) || @@ -4216,10 +4292,11 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) power_rule->max_antenna_gain) || nla_put_u32(msg, NL80211_ATTR_POWER_RULE_MAX_EIRP, power_rule->max_eirp)) - goto nla_put_failure; + goto nla_put_failure_rcu; nla_nest_end(msg, nl_reg_rule); } + rcu_read_unlock(); nla_nest_end(msg, nl_reg_rules); @@ -4227,6 +4304,8 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) err = genlmsg_reply(msg, info); goto out; +nla_put_failure_rcu: + rcu_read_unlock(); nla_put_failure: genlmsg_cancel(msg, hdr); put_failure: @@ -4259,27 +4338,18 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) dfs_region = nla_get_u8(info->attrs[NL80211_ATTR_DFS_REGION]); nla_for_each_nested(nl_reg_rule, info->attrs[NL80211_ATTR_REG_RULES], - rem_reg_rules) { + rem_reg_rules) { num_rules++; if (num_rules > NL80211_MAX_SUPP_REG_RULES) return -EINVAL; } - mutex_lock(&cfg80211_mutex); - - if (!reg_is_valid_request(alpha2)) { - r = -EINVAL; - goto bad_reg; - } - size_of_regd = sizeof(struct ieee80211_regdomain) + - (num_rules * sizeof(struct ieee80211_reg_rule)); + num_rules * sizeof(struct ieee80211_reg_rule); rd = kzalloc(size_of_regd, GFP_KERNEL); - if (!rd) { - r = -ENOMEM; - goto bad_reg; - } + if (!rd) + return -ENOMEM; rd->n_reg_rules = num_rules; rd->alpha2[0] = alpha2[0]; @@ -4293,10 +4363,10 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) rd->dfs_region = dfs_region; nla_for_each_nested(nl_reg_rule, info->attrs[NL80211_ATTR_REG_RULES], - rem_reg_rules) { + rem_reg_rules) { nla_parse(tb, NL80211_REG_RULE_ATTR_MAX, - nla_data(nl_reg_rule), nla_len(nl_reg_rule), - reg_rule_policy); + nla_data(nl_reg_rule), nla_len(nl_reg_rule), + reg_rule_policy); r = parse_reg_rule(tb, &rd->reg_rules[rule_idx]); if (r) goto bad_reg; @@ -4309,16 +4379,14 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) } } - BUG_ON(rule_idx != num_rules); + mutex_lock(&cfg80211_mutex); r = set_regdom(rd); - + /* set_regdom took ownership */ + rd = NULL; mutex_unlock(&cfg80211_mutex); - return r; - bad_reg: - mutex_unlock(&cfg80211_mutex); kfree(rd); return r; } @@ -5867,6 +5935,15 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) connect.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); } + if (info->attrs[NL80211_ATTR_USE_MFP]) { + connect.mfp = nla_get_u32(info->attrs[NL80211_ATTR_USE_MFP]); + if (connect.mfp != NL80211_MFP_REQUIRED && + connect.mfp != NL80211_MFP_NO) + return -EINVAL; + } else { + connect.mfp = NL80211_MFP_NO; + } + if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { connect.channel = ieee80211_get_channel(wiphy, @@ -6652,6 +6729,21 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) nla_get_u32(info->attrs[NL80211_ATTR_MCAST_RATE]))) return -EINVAL; + if (info->attrs[NL80211_ATTR_BEACON_INTERVAL]) { + setup.beacon_interval = + nla_get_u32(info->attrs[NL80211_ATTR_BEACON_INTERVAL]); + if (setup.beacon_interval < 10 || + setup.beacon_interval > 10000) + return -EINVAL; + } + + if (info->attrs[NL80211_ATTR_DTIM_PERIOD]) { + setup.dtim_period = + nla_get_u32(info->attrs[NL80211_ATTR_DTIM_PERIOD]); + if (setup.dtim_period < 1 || setup.dtim_period > 100) + return -EINVAL; + } + if (info->attrs[NL80211_ATTR_MESH_SETUP]) { /* parse additional setup parameters if given */ err = nl80211_parse_mesh_setup(info, &setup); @@ -8051,7 +8143,7 @@ void nl80211_send_reg_change_event(struct regulatory_request *request) goto nla_put_failure; } - if (wiphy_idx_valid(request->wiphy_idx) && + if (request->wiphy_idx != WIPHY_IDX_INVALID && nla_put_u32(msg, NL80211_ATTR_WIPHY, request->wiphy_idx)) goto nla_put_failure; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 82c4fc7c994..de02d633c21 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -48,7 +48,6 @@ #include <linux/export.h> #include <linux/slab.h> #include <linux/list.h> -#include <linux/random.h> #include <linux/ctype.h> #include <linux/nl80211.h> #include <linux/platform_device.h> @@ -66,6 +65,13 @@ #define REG_DBG_PRINT(args...) #endif +enum reg_request_treatment { + REG_REQ_OK, + REG_REQ_IGNORE, + REG_REQ_INTERSECT, + REG_REQ_ALREADY_SET, +}; + static struct regulatory_request core_request_world = { .initiator = NL80211_REGDOM_SET_BY_CORE, .alpha2[0] = '0', @@ -76,7 +82,8 @@ static struct regulatory_request core_request_world = { }; /* Receipt of information from last regulatory request */ -static struct regulatory_request *last_request = &core_request_world; +static struct regulatory_request __rcu *last_request = + (void __rcu *)&core_request_world; /* To trigger userspace events */ static struct platform_device *reg_pdev; @@ -88,16 +95,16 @@ static struct device_type reg_device_type = { /* * Central wireless core regulatory domains, we only need two, * the current one and a world regulatory domain in case we have no - * information to give us an alpha2 + * information to give us an alpha2. */ -const struct ieee80211_regdomain *cfg80211_regdomain; +const struct ieee80211_regdomain __rcu *cfg80211_regdomain; /* * Protects static reg.c components: - * - cfg80211_world_regdom - * - cfg80211_regdom - * - last_request - * - reg_num_devs_support_basehint + * - cfg80211_regdomain (if not used with RCU) + * - cfg80211_world_regdom + * - last_request (if not used with RCU) + * - reg_num_devs_support_basehint */ static DEFINE_MUTEX(reg_mutex); @@ -112,6 +119,31 @@ static inline void assert_reg_lock(void) lockdep_assert_held(®_mutex); } +static const struct ieee80211_regdomain *get_cfg80211_regdom(void) +{ + return rcu_dereference_protected(cfg80211_regdomain, + lockdep_is_held(®_mutex)); +} + +static const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy) +{ + return rcu_dereference_protected(wiphy->regd, + lockdep_is_held(®_mutex)); +} + +static void rcu_free_regdom(const struct ieee80211_regdomain *r) +{ + if (!r) + return; + kfree_rcu((struct ieee80211_regdomain *)r, rcu_head); +} + +static struct regulatory_request *get_last_request(void) +{ + return rcu_dereference_check(last_request, + lockdep_is_held(®_mutex)); +} + /* Used to queue up regulatory hints */ static LIST_HEAD(reg_requests_list); static spinlock_t reg_requests_lock; @@ -177,28 +209,37 @@ static char user_alpha2[2]; module_param(ieee80211_regdom, charp, 0444); MODULE_PARM_DESC(ieee80211_regdom, "IEEE 802.11 regulatory domain code"); -static void reset_regdomains(bool full_reset) +static void reset_regdomains(bool full_reset, + const struct ieee80211_regdomain *new_regdom) { + const struct ieee80211_regdomain *r; + struct regulatory_request *lr; + + assert_reg_lock(); + + r = get_cfg80211_regdom(); + /* avoid freeing static information or freeing something twice */ - if (cfg80211_regdomain == cfg80211_world_regdom) - cfg80211_regdomain = NULL; + if (r == cfg80211_world_regdom) + r = NULL; if (cfg80211_world_regdom == &world_regdom) cfg80211_world_regdom = NULL; - if (cfg80211_regdomain == &world_regdom) - cfg80211_regdomain = NULL; + if (r == &world_regdom) + r = NULL; - kfree(cfg80211_regdomain); - kfree(cfg80211_world_regdom); + rcu_free_regdom(r); + rcu_free_regdom(cfg80211_world_regdom); cfg80211_world_regdom = &world_regdom; - cfg80211_regdomain = NULL; + rcu_assign_pointer(cfg80211_regdomain, new_regdom); if (!full_reset) return; - if (last_request != &core_request_world) - kfree(last_request); - last_request = &core_request_world; + lr = get_last_request(); + if (lr != &core_request_world && lr) + kfree_rcu(lr, rcu_head); + rcu_assign_pointer(last_request, &core_request_world); } /* @@ -207,30 +248,29 @@ static void reset_regdomains(bool full_reset) */ static void update_world_regdomain(const struct ieee80211_regdomain *rd) { - BUG_ON(!last_request); + struct regulatory_request *lr; + + lr = get_last_request(); + + WARN_ON(!lr); - reset_regdomains(false); + reset_regdomains(false, rd); cfg80211_world_regdom = rd; - cfg80211_regdomain = rd; } bool is_world_regdom(const char *alpha2) { if (!alpha2) return false; - if (alpha2[0] == '0' && alpha2[1] == '0') - return true; - return false; + return alpha2[0] == '0' && alpha2[1] == '0'; } static bool is_alpha2_set(const char *alpha2) { if (!alpha2) return false; - if (alpha2[0] != 0 && alpha2[1] != 0) - return true; - return false; + return alpha2[0] && alpha2[1]; } static bool is_unknown_alpha2(const char *alpha2) @@ -241,9 +281,7 @@ static bool is_unknown_alpha2(const char *alpha2) * Special case where regulatory domain was built by driver * but a specific alpha2 cannot be determined */ - if (alpha2[0] == '9' && alpha2[1] == '9') - return true; - return false; + return alpha2[0] == '9' && alpha2[1] == '9'; } static bool is_intersected_alpha2(const char *alpha2) @@ -255,39 +293,30 @@ static bool is_intersected_alpha2(const char *alpha2) * result of an intersection between two regulatory domain * structures */ - if (alpha2[0] == '9' && alpha2[1] == '8') - return true; - return false; + return alpha2[0] == '9' && alpha2[1] == '8'; } static bool is_an_alpha2(const char *alpha2) { if (!alpha2) return false; - if (isalpha(alpha2[0]) && isalpha(alpha2[1])) - return true; - return false; + return isalpha(alpha2[0]) && isalpha(alpha2[1]); } static bool alpha2_equal(const char *alpha2_x, const char *alpha2_y) { if (!alpha2_x || !alpha2_y) return false; - if (alpha2_x[0] == alpha2_y[0] && - alpha2_x[1] == alpha2_y[1]) - return true; - return false; + return alpha2_x[0] == alpha2_y[0] && alpha2_x[1] == alpha2_y[1]; } static bool regdom_changes(const char *alpha2) { - assert_cfg80211_lock(); + const struct ieee80211_regdomain *r = get_cfg80211_regdom(); - if (!cfg80211_regdomain) + if (!r) return true; - if (alpha2_equal(cfg80211_regdomain->alpha2, alpha2)) - return false; - return true; + return !alpha2_equal(r->alpha2, alpha2); } /* @@ -301,38 +330,36 @@ static bool is_user_regdom_saved(void) return false; /* This would indicate a mistake on the design */ - if (WARN((!is_world_regdom(user_alpha2) && - !is_an_alpha2(user_alpha2)), + if (WARN(!is_world_regdom(user_alpha2) && !is_an_alpha2(user_alpha2), "Unexpected user alpha2: %c%c\n", - user_alpha2[0], - user_alpha2[1])) + user_alpha2[0], user_alpha2[1])) return false; return true; } -static int reg_copy_regd(const struct ieee80211_regdomain **dst_regd, - const struct ieee80211_regdomain *src_regd) +static const struct ieee80211_regdomain * +reg_copy_regd(const struct ieee80211_regdomain *src_regd) { struct ieee80211_regdomain *regd; - int size_of_regd = 0; + int size_of_regd; unsigned int i; - size_of_regd = sizeof(struct ieee80211_regdomain) + - ((src_regd->n_reg_rules + 1) * sizeof(struct ieee80211_reg_rule)); + size_of_regd = + sizeof(struct ieee80211_regdomain) + + src_regd->n_reg_rules * sizeof(struct ieee80211_reg_rule); regd = kzalloc(size_of_regd, GFP_KERNEL); if (!regd) - return -ENOMEM; + return ERR_PTR(-ENOMEM); memcpy(regd, src_regd, sizeof(struct ieee80211_regdomain)); for (i = 0; i < src_regd->n_reg_rules; i++) memcpy(®d->reg_rules[i], &src_regd->reg_rules[i], - sizeof(struct ieee80211_reg_rule)); + sizeof(struct ieee80211_reg_rule)); - *dst_regd = regd; - return 0; + return regd; } #ifdef CONFIG_CFG80211_INTERNAL_REGDB @@ -347,9 +374,8 @@ static DEFINE_MUTEX(reg_regdb_search_mutex); static void reg_regdb_search(struct work_struct *work) { struct reg_regdb_search_request *request; - const struct ieee80211_regdomain *curdom, *regdom; - int i, r; - bool set_reg = false; + const struct ieee80211_regdomain *curdom, *regdom = NULL; + int i; mutex_lock(&cfg80211_mutex); @@ -360,14 +386,11 @@ static void reg_regdb_search(struct work_struct *work) list); list_del(&request->list); - for (i=0; i<reg_regdb_size; i++) { + for (i = 0; i < reg_regdb_size; i++) { curdom = reg_regdb[i]; - if (!memcmp(request->alpha2, curdom->alpha2, 2)) { - r = reg_copy_regd(®dom, curdom); - if (r) - break; - set_reg = true; + if (alpha2_equal(request->alpha2, curdom->alpha2)) { + regdom = reg_copy_regd(curdom); break; } } @@ -376,7 +399,7 @@ static void reg_regdb_search(struct work_struct *work) } mutex_unlock(®_regdb_search_mutex); - if (set_reg) + if (!IS_ERR_OR_NULL(regdom)) set_regdom(regdom); mutex_unlock(&cfg80211_mutex); @@ -434,15 +457,14 @@ static int call_crda(const char *alpha2) return kobject_uevent(®_pdev->dev.kobj, KOBJ_CHANGE); } -/* Used by nl80211 before kmalloc'ing our regulatory domain */ -bool reg_is_valid_request(const char *alpha2) +static bool reg_is_valid_request(const char *alpha2) { - assert_cfg80211_lock(); + struct regulatory_request *lr = get_last_request(); - if (!last_request) + if (!lr || lr->processed) return false; - return alpha2_equal(last_request->alpha2, alpha2); + return alpha2_equal(lr->alpha2, alpha2); } /* Sanity check on a regulatory rule */ @@ -460,7 +482,7 @@ static bool is_valid_reg_rule(const struct ieee80211_reg_rule *rule) freq_diff = freq_range->end_freq_khz - freq_range->start_freq_khz; if (freq_range->end_freq_khz <= freq_range->start_freq_khz || - freq_range->max_bandwidth_khz > freq_diff) + freq_range->max_bandwidth_khz > freq_diff) return false; return true; @@ -487,8 +509,7 @@ static bool is_valid_rd(const struct ieee80211_regdomain *rd) } static bool reg_does_bw_fit(const struct ieee80211_freq_range *freq_range, - u32 center_freq_khz, - u32 bw_khz) + u32 center_freq_khz, u32 bw_khz) { u32 start_freq_khz, end_freq_khz; @@ -518,7 +539,7 @@ static bool reg_does_bw_fit(const struct ieee80211_freq_range *freq_range, * regulatory rule support for other "bands". **/ static bool freq_in_rule_band(const struct ieee80211_freq_range *freq_range, - u32 freq_khz) + u32 freq_khz) { #define ONE_GHZ_IN_KHZ 1000000 /* @@ -540,10 +561,9 @@ static bool freq_in_rule_band(const struct ieee80211_freq_range *freq_range, * Helper for regdom_intersect(), this does the real * mathematical intersection fun */ -static int reg_rules_intersect( - const struct ieee80211_reg_rule *rule1, - const struct ieee80211_reg_rule *rule2, - struct ieee80211_reg_rule *intersected_rule) +static int reg_rules_intersect(const struct ieee80211_reg_rule *rule1, + const struct ieee80211_reg_rule *rule2, + struct ieee80211_reg_rule *intersected_rule) { const struct ieee80211_freq_range *freq_range1, *freq_range2; struct ieee80211_freq_range *freq_range; @@ -560,11 +580,11 @@ static int reg_rules_intersect( power_rule = &intersected_rule->power_rule; freq_range->start_freq_khz = max(freq_range1->start_freq_khz, - freq_range2->start_freq_khz); + freq_range2->start_freq_khz); freq_range->end_freq_khz = min(freq_range1->end_freq_khz, - freq_range2->end_freq_khz); + freq_range2->end_freq_khz); freq_range->max_bandwidth_khz = min(freq_range1->max_bandwidth_khz, - freq_range2->max_bandwidth_khz); + freq_range2->max_bandwidth_khz); freq_diff = freq_range->end_freq_khz - freq_range->start_freq_khz; if (freq_range->max_bandwidth_khz > freq_diff) @@ -575,7 +595,7 @@ static int reg_rules_intersect( power_rule->max_antenna_gain = min(power_rule1->max_antenna_gain, power_rule2->max_antenna_gain); - intersected_rule->flags = (rule1->flags | rule2->flags); + intersected_rule->flags = rule1->flags | rule2->flags; if (!is_valid_reg_rule(intersected_rule)) return -EINVAL; @@ -596,9 +616,9 @@ static int reg_rules_intersect( * resulting intersection of rules between rd1 and rd2. We will * kzalloc() this structure for you. */ -static struct ieee80211_regdomain *regdom_intersect( - const struct ieee80211_regdomain *rd1, - const struct ieee80211_regdomain *rd2) +static struct ieee80211_regdomain * +regdom_intersect(const struct ieee80211_regdomain *rd1, + const struct ieee80211_regdomain *rd2) { int r, size_of_regd; unsigned int x, y; @@ -607,12 +627,7 @@ static struct ieee80211_regdomain *regdom_intersect( struct ieee80211_reg_rule *intersected_rule; struct ieee80211_regdomain *rd; /* This is just a dummy holder to help us count */ - struct ieee80211_reg_rule irule; - - /* Uses the stack temporarily for counter arithmetic */ - intersected_rule = &irule; - - memset(intersected_rule, 0, sizeof(struct ieee80211_reg_rule)); + struct ieee80211_reg_rule dummy_rule; if (!rd1 || !rd2) return NULL; @@ -629,11 +644,8 @@ static struct ieee80211_regdomain *regdom_intersect( rule1 = &rd1->reg_rules[x]; for (y = 0; y < rd2->n_reg_rules; y++) { rule2 = &rd2->reg_rules[y]; - if (!reg_rules_intersect(rule1, rule2, - intersected_rule)) + if (!reg_rules_intersect(rule1, rule2, &dummy_rule)) num_rules++; - memset(intersected_rule, 0, - sizeof(struct ieee80211_reg_rule)); } } @@ -641,15 +653,15 @@ static struct ieee80211_regdomain *regdom_intersect( return NULL; size_of_regd = sizeof(struct ieee80211_regdomain) + - ((num_rules + 1) * sizeof(struct ieee80211_reg_rule)); + num_rules * sizeof(struct ieee80211_reg_rule); rd = kzalloc(size_of_regd, GFP_KERNEL); if (!rd) return NULL; - for (x = 0; x < rd1->n_reg_rules; x++) { + for (x = 0; x < rd1->n_reg_rules && rule_idx < num_rules; x++) { rule1 = &rd1->reg_rules[x]; - for (y = 0; y < rd2->n_reg_rules; y++) { + for (y = 0; y < rd2->n_reg_rules && rule_idx < num_rules; y++) { rule2 = &rd2->reg_rules[y]; /* * This time around instead of using the stack lets @@ -657,8 +669,7 @@ static struct ieee80211_regdomain *regdom_intersect( * a memcpy() */ intersected_rule = &rd->reg_rules[rule_idx]; - r = reg_rules_intersect(rule1, rule2, - intersected_rule); + r = reg_rules_intersect(rule1, rule2, intersected_rule); /* * No need to memset here the intersected rule here as * we're not using the stack anymore @@ -699,34 +710,16 @@ static u32 map_regdom_flags(u32 rd_flags) return channel_flags; } -static int freq_reg_info_regd(struct wiphy *wiphy, - u32 center_freq, - u32 desired_bw_khz, - const struct ieee80211_reg_rule **reg_rule, - const struct ieee80211_regdomain *custom_regd) +static const struct ieee80211_reg_rule * +freq_reg_info_regd(struct wiphy *wiphy, u32 center_freq, + const struct ieee80211_regdomain *regd) { int i; bool band_rule_found = false; - const struct ieee80211_regdomain *regd; bool bw_fits = false; - if (!desired_bw_khz) - desired_bw_khz = MHZ_TO_KHZ(20); - - regd = custom_regd ? custom_regd : cfg80211_regdomain; - - /* - * Follow the driver's regulatory domain, if present, unless a country - * IE has been processed or a user wants to help complaince further - */ - if (!custom_regd && - last_request->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && - last_request->initiator != NL80211_REGDOM_SET_BY_USER && - wiphy->regd) - regd = wiphy->regd; - if (!regd) - return -EINVAL; + return ERR_PTR(-EINVAL); for (i = 0; i < regd->n_reg_rules; i++) { const struct ieee80211_reg_rule *rr; @@ -743,33 +736,36 @@ static int freq_reg_info_regd(struct wiphy *wiphy, if (!band_rule_found) band_rule_found = freq_in_rule_band(fr, center_freq); - bw_fits = reg_does_bw_fit(fr, - center_freq, - desired_bw_khz); + bw_fits = reg_does_bw_fit(fr, center_freq, MHZ_TO_KHZ(20)); - if (band_rule_found && bw_fits) { - *reg_rule = rr; - return 0; - } + if (band_rule_found && bw_fits) + return rr; } if (!band_rule_found) - return -ERANGE; + return ERR_PTR(-ERANGE); - return -EINVAL; + return ERR_PTR(-EINVAL); } -int freq_reg_info(struct wiphy *wiphy, - u32 center_freq, - u32 desired_bw_khz, - const struct ieee80211_reg_rule **reg_rule) +const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy, + u32 center_freq) { - assert_cfg80211_lock(); - return freq_reg_info_regd(wiphy, - center_freq, - desired_bw_khz, - reg_rule, - NULL); + const struct ieee80211_regdomain *regd; + struct regulatory_request *lr = get_last_request(); + + /* + * Follow the driver's regulatory domain, if present, unless a country + * IE has been processed or a user wants to help complaince further + */ + if (lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && + lr->initiator != NL80211_REGDOM_SET_BY_USER && + wiphy->regd) + regd = get_wiphy_regdom(wiphy); + else + regd = get_cfg80211_regdom(); + + return freq_reg_info_regd(wiphy, center_freq, regd); } EXPORT_SYMBOL(freq_reg_info); @@ -792,7 +788,6 @@ static const char *reg_initiator_name(enum nl80211_reg_initiator initiator) } static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan, - u32 desired_bw_khz, const struct ieee80211_reg_rule *reg_rule) { const struct ieee80211_power_rule *power_rule; @@ -807,21 +802,16 @@ static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan, else snprintf(max_antenna_gain, 32, "%d", power_rule->max_antenna_gain); - REG_DBG_PRINT("Updating information on frequency %d MHz " - "for a %d MHz width channel with regulatory rule:\n", - chan->center_freq, - KHZ_TO_MHZ(desired_bw_khz)); + REG_DBG_PRINT("Updating information on frequency %d MHz with regulatory rule:\n", + chan->center_freq); REG_DBG_PRINT("%d KHz - %d KHz @ %d KHz), (%s mBi, %d mBm)\n", - freq_range->start_freq_khz, - freq_range->end_freq_khz, - freq_range->max_bandwidth_khz, - max_antenna_gain, + freq_range->start_freq_khz, freq_range->end_freq_khz, + freq_range->max_bandwidth_khz, max_antenna_gain, power_rule->max_eirp); } #else static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan, - u32 desired_bw_khz, const struct ieee80211_reg_rule *reg_rule) { return; @@ -831,43 +821,25 @@ static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan, /* * Note that right now we assume the desired channel bandwidth * is always 20 MHz for each individual channel (HT40 uses 20 MHz - * per channel, the primary and the extension channel). To support - * smaller custom bandwidths such as 5 MHz or 10 MHz we'll need a - * new ieee80211_channel.target_bw and re run the regulatory check - * on the wiphy with the target_bw specified. Then we can simply use - * that below for the desired_bw_khz below. + * per channel, the primary and the extension channel). */ static void handle_channel(struct wiphy *wiphy, enum nl80211_reg_initiator initiator, - enum ieee80211_band band, - unsigned int chan_idx) + struct ieee80211_channel *chan) { - int r; u32 flags, bw_flags = 0; - u32 desired_bw_khz = MHZ_TO_KHZ(20); const struct ieee80211_reg_rule *reg_rule = NULL; const struct ieee80211_power_rule *power_rule = NULL; const struct ieee80211_freq_range *freq_range = NULL; - struct ieee80211_supported_band *sband; - struct ieee80211_channel *chan; struct wiphy *request_wiphy = NULL; + struct regulatory_request *lr = get_last_request(); - assert_cfg80211_lock(); - - request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); - - sband = wiphy->bands[band]; - BUG_ON(chan_idx >= sband->n_channels); - chan = &sband->channels[chan_idx]; + request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); flags = chan->orig_flags; - r = freq_reg_info(wiphy, - MHZ_TO_KHZ(chan->center_freq), - desired_bw_khz, - ®_rule); - - if (r) { + reg_rule = freq_reg_info(wiphy, MHZ_TO_KHZ(chan->center_freq)); + if (IS_ERR(reg_rule)) { /* * We will disable all channels that do not match our * received regulatory rule unless the hint is coming @@ -879,7 +851,7 @@ static void handle_channel(struct wiphy *wiphy, * while 5 GHz is still supported. */ if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && - r == -ERANGE) + PTR_ERR(reg_rule) == -ERANGE) return; REG_DBG_PRINT("Disabling freq %d MHz\n", chan->center_freq); @@ -887,7 +859,7 @@ static void handle_channel(struct wiphy *wiphy, return; } - chan_reg_rule_print_dbg(chan, desired_bw_khz, reg_rule); + chan_reg_rule_print_dbg(chan, reg_rule); power_rule = ®_rule->power_rule; freq_range = ®_rule->freq_range; @@ -895,7 +867,7 @@ static void handle_channel(struct wiphy *wiphy, if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(40)) bw_flags = IEEE80211_CHAN_NO_HT40; - if (last_request->initiator == NL80211_REGDOM_SET_BY_DRIVER && + if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && request_wiphy && request_wiphy == wiphy && request_wiphy->flags & WIPHY_FLAG_STRICT_REGULATORY) { /* @@ -914,8 +886,9 @@ static void handle_channel(struct wiphy *wiphy, chan->beacon_found = false; chan->flags = flags | bw_flags | map_regdom_flags(reg_rule->flags); - chan->max_antenna_gain = min(chan->orig_mag, - (int) MBI_TO_DBI(power_rule->max_antenna_gain)); + chan->max_antenna_gain = + min_t(int, chan->orig_mag, + MBI_TO_DBI(power_rule->max_antenna_gain)); chan->max_reg_power = (int) MBM_TO_DBM(power_rule->max_eirp); if (chan->orig_mpwr) { /* @@ -935,68 +908,65 @@ static void handle_channel(struct wiphy *wiphy, } static void handle_band(struct wiphy *wiphy, - enum ieee80211_band band, - enum nl80211_reg_initiator initiator) + enum nl80211_reg_initiator initiator, + struct ieee80211_supported_band *sband) { unsigned int i; - struct ieee80211_supported_band *sband; - BUG_ON(!wiphy->bands[band]); - sband = wiphy->bands[band]; + if (!sband) + return; for (i = 0; i < sband->n_channels; i++) - handle_channel(wiphy, initiator, band, i); + handle_channel(wiphy, initiator, &sband->channels[i]); } static bool reg_request_cell_base(struct regulatory_request *request) { if (request->initiator != NL80211_REGDOM_SET_BY_USER) return false; - if (request->user_reg_hint_type != NL80211_USER_REG_HINT_CELL_BASE) - return false; - return true; + return request->user_reg_hint_type == NL80211_USER_REG_HINT_CELL_BASE; } bool reg_last_request_cell_base(void) { bool val; - assert_cfg80211_lock(); mutex_lock(®_mutex); - val = reg_request_cell_base(last_request); + val = reg_request_cell_base(get_last_request()); mutex_unlock(®_mutex); + return val; } #ifdef CONFIG_CFG80211_CERTIFICATION_ONUS - /* Core specific check */ -static int reg_ignore_cell_hint(struct regulatory_request *pending_request) +static enum reg_request_treatment +reg_ignore_cell_hint(struct regulatory_request *pending_request) { + struct regulatory_request *lr = get_last_request(); + if (!reg_num_devs_support_basehint) - return -EOPNOTSUPP; + return REG_REQ_IGNORE; - if (reg_request_cell_base(last_request)) { - if (!regdom_changes(pending_request->alpha2)) - return -EALREADY; - return 0; - } - return 0; + if (reg_request_cell_base(lr) && + !regdom_changes(pending_request->alpha2)) + return REG_REQ_ALREADY_SET; + + return REG_REQ_OK; } /* Device specific check */ static bool reg_dev_ignore_cell_hint(struct wiphy *wiphy) { - if (!(wiphy->features & NL80211_FEATURE_CELL_BASE_REG_HINTS)) - return true; - return false; + return !(wiphy->features & NL80211_FEATURE_CELL_BASE_REG_HINTS); } #else static int reg_ignore_cell_hint(struct regulatory_request *pending_request) { - return -EOPNOTSUPP; + return REG_REQ_IGNORE; } -static int reg_dev_ignore_cell_hint(struct wiphy *wiphy) + +static bool reg_dev_ignore_cell_hint(struct wiphy *wiphy) { return true; } @@ -1006,18 +976,17 @@ static int reg_dev_ignore_cell_hint(struct wiphy *wiphy) static bool ignore_reg_update(struct wiphy *wiphy, enum nl80211_reg_initiator initiator) { - if (!last_request) { - REG_DBG_PRINT("Ignoring regulatory request %s since " - "last_request is not set\n", + struct regulatory_request *lr = get_last_request(); + + if (!lr) { + REG_DBG_PRINT("Ignoring regulatory request %s since last_request is not set\n", reg_initiator_name(initiator)); return true; } if (initiator == NL80211_REGDOM_SET_BY_CORE && wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY) { - REG_DBG_PRINT("Ignoring regulatory request %s " - "since the driver uses its own custom " - "regulatory domain\n", + REG_DBG_PRINT("Ignoring regulatory request %s since the driver uses its own custom regulatory domain\n", reg_initiator_name(initiator)); return true; } @@ -1028,22 +997,35 @@ static bool ignore_reg_update(struct wiphy *wiphy, */ if (wiphy->flags & WIPHY_FLAG_STRICT_REGULATORY && !wiphy->regd && initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && - !is_world_regdom(last_request->alpha2)) { - REG_DBG_PRINT("Ignoring regulatory request %s " - "since the driver requires its own regulatory " - "domain to be set first\n", + !is_world_regdom(lr->alpha2)) { + REG_DBG_PRINT("Ignoring regulatory request %s since the driver requires its own regulatory domain to be set first\n", reg_initiator_name(initiator)); return true; } - if (reg_request_cell_base(last_request)) + if (reg_request_cell_base(lr)) return reg_dev_ignore_cell_hint(wiphy); return false; } -static void handle_reg_beacon(struct wiphy *wiphy, - unsigned int chan_idx, +static bool reg_is_world_roaming(struct wiphy *wiphy) +{ + const struct ieee80211_regdomain *cr = get_cfg80211_regdom(); + const struct ieee80211_regdomain *wr = get_wiphy_regdom(wiphy); + struct regulatory_request *lr = get_last_request(); + + if (is_world_regdom(cr->alpha2) || (wr && is_world_regdom(wr->alpha2))) + return true; + + if (lr && lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && + wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY) + return true; + + return false; +} + +static void handle_reg_beacon(struct wiphy *wiphy, unsigned int chan_idx, struct reg_beacon *reg_beacon) { struct ieee80211_supported_band *sband; @@ -1051,8 +1033,6 @@ static void handle_reg_beacon(struct wiphy *wiphy, bool channel_changed = false; struct ieee80211_channel chan_before; - assert_cfg80211_lock(); - sband = wiphy->bands[reg_beacon->chan.band]; chan = &sband->channels[chan_idx]; @@ -1064,6 +1044,9 @@ static void handle_reg_beacon(struct wiphy *wiphy, chan->beacon_found = true; + if (!reg_is_world_roaming(wiphy)) + return; + if (wiphy->flags & WIPHY_FLAG_DISABLE_BEACON_HINTS) return; @@ -1094,8 +1077,6 @@ static void wiphy_update_new_beacon(struct wiphy *wiphy, unsigned int i; struct ieee80211_supported_band *sband; - assert_cfg80211_lock(); - if (!wiphy->bands[reg_beacon->chan.band]) return; @@ -1114,11 +1095,6 @@ static void wiphy_update_beacon_reg(struct wiphy *wiphy) struct ieee80211_supported_band *sband; struct reg_beacon *reg_beacon; - assert_cfg80211_lock(); - - if (list_empty(®_beacon_list)) - return; - list_for_each_entry(reg_beacon, ®_beacon_list, list) { if (!wiphy->bands[reg_beacon->chan.band]) continue; @@ -1128,18 +1104,6 @@ static void wiphy_update_beacon_reg(struct wiphy *wiphy) } } -static bool reg_is_world_roaming(struct wiphy *wiphy) -{ - if (is_world_regdom(cfg80211_regdomain->alpha2) || - (wiphy->regd && is_world_regdom(wiphy->regd->alpha2))) - return true; - if (last_request && - last_request->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && - wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY) - return true; - return false; -} - /* Reap the advantages of previously found beacons */ static void reg_process_beacons(struct wiphy *wiphy) { @@ -1149,39 +1113,29 @@ static void reg_process_beacons(struct wiphy *wiphy) */ if (!last_request) return; - if (!reg_is_world_roaming(wiphy)) - return; wiphy_update_beacon_reg(wiphy); } -static bool is_ht40_not_allowed(struct ieee80211_channel *chan) +static bool is_ht40_allowed(struct ieee80211_channel *chan) { if (!chan) - return true; + return false; if (chan->flags & IEEE80211_CHAN_DISABLED) - return true; + return false; /* This would happen when regulatory rules disallow HT40 completely */ - if (IEEE80211_CHAN_NO_HT40 == (chan->flags & (IEEE80211_CHAN_NO_HT40))) - return true; - return false; + if ((chan->flags & IEEE80211_CHAN_NO_HT40) == IEEE80211_CHAN_NO_HT40) + return false; + return true; } static void reg_process_ht_flags_channel(struct wiphy *wiphy, - enum ieee80211_band band, - unsigned int chan_idx) + struct ieee80211_channel *channel) { - struct ieee80211_supported_band *sband; - struct ieee80211_channel *channel; + struct ieee80211_supported_band *sband = wiphy->bands[channel->band]; struct ieee80211_channel *channel_before = NULL, *channel_after = NULL; unsigned int i; - assert_cfg80211_lock(); - - sband = wiphy->bands[band]; - BUG_ON(chan_idx >= sband->n_channels); - channel = &sband->channels[chan_idx]; - - if (is_ht40_not_allowed(channel)) { + if (!is_ht40_allowed(channel)) { channel->flags |= IEEE80211_CHAN_NO_HT40; return; } @@ -1192,6 +1146,7 @@ static void reg_process_ht_flags_channel(struct wiphy *wiphy, */ for (i = 0; i < sband->n_channels; i++) { struct ieee80211_channel *c = &sband->channels[i]; + if (c->center_freq == (channel->center_freq - 20)) channel_before = c; if (c->center_freq == (channel->center_freq + 20)) @@ -1203,28 +1158,27 @@ static void reg_process_ht_flags_channel(struct wiphy *wiphy, * if that ever changes we also need to change the below logic * to include that as well. */ - if (is_ht40_not_allowed(channel_before)) + if (!is_ht40_allowed(channel_before)) channel->flags |= IEEE80211_CHAN_NO_HT40MINUS; else channel->flags &= ~IEEE80211_CHAN_NO_HT40MINUS; - if (is_ht40_not_allowed(channel_after)) + if (!is_ht40_allowed(channel_after)) channel->flags |= IEEE80211_CHAN_NO_HT40PLUS; else channel->flags &= ~IEEE80211_CHAN_NO_HT40PLUS; } static void reg_process_ht_flags_band(struct wiphy *wiphy, - enum ieee80211_band band) + struct ieee80211_supported_band *sband) { unsigned int i; - struct ieee80211_supported_band *sband; - BUG_ON(!wiphy->bands[band]); - sband = wiphy->bands[band]; + if (!sband) + return; for (i = 0; i < sband->n_channels; i++) - reg_process_ht_flags_channel(wiphy, band, i); + reg_process_ht_flags_channel(wiphy, &sband->channels[i]); } static void reg_process_ht_flags(struct wiphy *wiphy) @@ -1234,34 +1188,29 @@ static void reg_process_ht_flags(struct wiphy *wiphy) if (!wiphy) return; - for (band = 0; band < IEEE80211_NUM_BANDS; band++) { - if (wiphy->bands[band]) - reg_process_ht_flags_band(wiphy, band); - } - + for (band = 0; band < IEEE80211_NUM_BANDS; band++) + reg_process_ht_flags_band(wiphy, wiphy->bands[band]); } static void wiphy_update_regulatory(struct wiphy *wiphy, enum nl80211_reg_initiator initiator) { enum ieee80211_band band; - - assert_reg_lock(); + struct regulatory_request *lr = get_last_request(); if (ignore_reg_update(wiphy, initiator)) return; - last_request->dfs_region = cfg80211_regdomain->dfs_region; + lr->dfs_region = get_cfg80211_regdom()->dfs_region; - for (band = 0; band < IEEE80211_NUM_BANDS; band++) { - if (wiphy->bands[band]) - handle_band(wiphy, band, initiator); - } + for (band = 0; band < IEEE80211_NUM_BANDS; band++) + handle_band(wiphy, initiator, wiphy->bands[band]); reg_process_beacons(wiphy); reg_process_ht_flags(wiphy); + if (wiphy->reg_notifier) - wiphy->reg_notifier(wiphy, last_request); + wiphy->reg_notifier(wiphy, lr); } static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator) @@ -1269,6 +1218,8 @@ static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator) struct cfg80211_registered_device *rdev; struct wiphy *wiphy; + assert_cfg80211_lock(); + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { wiphy = &rdev->wiphy; wiphy_update_regulatory(wiphy, initiator); @@ -1280,47 +1231,30 @@ static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator) if (initiator == NL80211_REGDOM_SET_BY_CORE && wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY && wiphy->reg_notifier) - wiphy->reg_notifier(wiphy, last_request); + wiphy->reg_notifier(wiphy, get_last_request()); } } static void handle_channel_custom(struct wiphy *wiphy, - enum ieee80211_band band, - unsigned int chan_idx, + struct ieee80211_channel *chan, const struct ieee80211_regdomain *regd) { - int r; - u32 desired_bw_khz = MHZ_TO_KHZ(20); u32 bw_flags = 0; const struct ieee80211_reg_rule *reg_rule = NULL; const struct ieee80211_power_rule *power_rule = NULL; const struct ieee80211_freq_range *freq_range = NULL; - struct ieee80211_supported_band *sband; - struct ieee80211_channel *chan; - - assert_reg_lock(); - sband = wiphy->bands[band]; - BUG_ON(chan_idx >= sband->n_channels); - chan = &sband->channels[chan_idx]; - - r = freq_reg_info_regd(wiphy, - MHZ_TO_KHZ(chan->center_freq), - desired_bw_khz, - ®_rule, - regd); + reg_rule = freq_reg_info_regd(wiphy, MHZ_TO_KHZ(chan->center_freq), + regd); - if (r) { - REG_DBG_PRINT("Disabling freq %d MHz as custom " - "regd has no rule that fits a %d MHz " - "wide channel\n", - chan->center_freq, - KHZ_TO_MHZ(desired_bw_khz)); + 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; return; } - chan_reg_rule_print_dbg(chan, desired_bw_khz, reg_rule); + chan_reg_rule_print_dbg(chan, reg_rule); power_rule = ®_rule->power_rule; freq_range = ®_rule->freq_range; @@ -1334,17 +1268,17 @@ static void handle_channel_custom(struct wiphy *wiphy, (int) MBM_TO_DBM(power_rule->max_eirp); } -static void handle_band_custom(struct wiphy *wiphy, enum ieee80211_band band, +static void handle_band_custom(struct wiphy *wiphy, + struct ieee80211_supported_band *sband, const struct ieee80211_regdomain *regd) { unsigned int i; - struct ieee80211_supported_band *sband; - BUG_ON(!wiphy->bands[band]); - sband = wiphy->bands[band]; + if (!sband) + return; for (i = 0; i < sband->n_channels; i++) - handle_channel_custom(wiphy, band, i, regd); + handle_channel_custom(wiphy, &sband->channels[i], regd); } /* Used by drivers prior to wiphy registration */ @@ -1354,60 +1288,50 @@ void wiphy_apply_custom_regulatory(struct wiphy *wiphy, enum ieee80211_band band; unsigned int bands_set = 0; - mutex_lock(®_mutex); for (band = 0; band < IEEE80211_NUM_BANDS; band++) { if (!wiphy->bands[band]) continue; - handle_band_custom(wiphy, band, regd); + handle_band_custom(wiphy, wiphy->bands[band], regd); bands_set++; } - mutex_unlock(®_mutex); /* * no point in calling this if it won't have any effect - * on your device's supportd bands. + * on your device's supported bands. */ WARN_ON(!bands_set); } EXPORT_SYMBOL(wiphy_apply_custom_regulatory); -/* - * Return value which can be used by ignore_request() to indicate - * it has been determined we should intersect two regulatory domains - */ -#define REG_INTERSECT 1 - /* This has the logic which determines when a new request * should be ignored. */ -static int ignore_request(struct wiphy *wiphy, +static enum reg_request_treatment +get_reg_request_treatment(struct wiphy *wiphy, struct regulatory_request *pending_request) { struct wiphy *last_wiphy = NULL; - - assert_cfg80211_lock(); + struct regulatory_request *lr = get_last_request(); /* All initial requests are respected */ - if (!last_request) - return 0; + if (!lr) + return REG_REQ_OK; switch (pending_request->initiator) { case NL80211_REGDOM_SET_BY_CORE: - return 0; + return REG_REQ_OK; case NL80211_REGDOM_SET_BY_COUNTRY_IE: - - if (reg_request_cell_base(last_request)) { + if (reg_request_cell_base(lr)) { /* Trust a Cell base station over the AP's country IE */ if (regdom_changes(pending_request->alpha2)) - return -EOPNOTSUPP; - return -EALREADY; + return REG_REQ_IGNORE; + return REG_REQ_ALREADY_SET; } - last_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); + last_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); if (unlikely(!is_an_alpha2(pending_request->alpha2))) return -EINVAL; - if (last_request->initiator == - NL80211_REGDOM_SET_BY_COUNTRY_IE) { + if (lr->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE) { if (last_wiphy != wiphy) { /* * Two cards with two APs claiming different @@ -1416,23 +1340,23 @@ static int ignore_request(struct wiphy *wiphy, * to be correct. Reject second one for now. */ if (regdom_changes(pending_request->alpha2)) - return -EOPNOTSUPP; - return -EALREADY; + 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 0; - return -EALREADY; + return REG_REQ_OK; + return REG_REQ_ALREADY_SET; } return 0; case NL80211_REGDOM_SET_BY_DRIVER: - if (last_request->initiator == NL80211_REGDOM_SET_BY_CORE) { + if (lr->initiator == NL80211_REGDOM_SET_BY_CORE) { if (regdom_changes(pending_request->alpha2)) - return 0; - return -EALREADY; + return REG_REQ_OK; + return REG_REQ_ALREADY_SET; } /* @@ -1440,59 +1364,59 @@ static int ignore_request(struct wiphy *wiphy, * back in or if you add a new device for which the previously * loaded card also agrees on the regulatory domain. */ - if (last_request->initiator == NL80211_REGDOM_SET_BY_DRIVER && + if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && !regdom_changes(pending_request->alpha2)) - return -EALREADY; + return REG_REQ_ALREADY_SET; - return REG_INTERSECT; + 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 (reg_request_cell_base(last_request)) - return -EOPNOTSUPP; + if (reg_request_cell_base(lr)) + return REG_REQ_IGNORE; - if (last_request->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE) - return REG_INTERSECT; + 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 (last_request->initiator == NL80211_REGDOM_SET_BY_USER && - last_request->intersect) - return -EOPNOTSUPP; + 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 (last_request->initiator == NL80211_REGDOM_SET_BY_CORE || - last_request->initiator == NL80211_REGDOM_SET_BY_DRIVER || - last_request->initiator == NL80211_REGDOM_SET_BY_USER) { - if (regdom_changes(last_request->alpha2)) - return -EAGAIN; - } + 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 (!regdom_changes(pending_request->alpha2)) - return -EALREADY; + return REG_REQ_ALREADY_SET; - return 0; + return REG_REQ_OK; } - return -EINVAL; + return REG_REQ_IGNORE; } static void reg_set_request_processed(void) { bool need_more_processing = false; + struct regulatory_request *lr = get_last_request(); - last_request->processed = true; + lr->processed = true; spin_lock(®_requests_lock); if (!list_empty(®_requests_list)) need_more_processing = true; spin_unlock(®_requests_lock); - if (last_request->initiator == NL80211_REGDOM_SET_BY_USER) + if (lr->initiator == NL80211_REGDOM_SET_BY_USER) cancel_delayed_work(®_timeout); if (need_more_processing) @@ -1508,116 +1432,122 @@ static void reg_set_request_processed(void) * The Wireless subsystem can use this function to hint to the wireless core * what it believes should be the current regulatory domain. * - * Returns zero if all went fine, %-EALREADY if a regulatory domain had - * already been set or other standard error codes. + * Returns one of the different reg request treatment values. * - * Caller must hold &cfg80211_mutex and ®_mutex + * Caller must hold ®_mutex */ -static int __regulatory_hint(struct wiphy *wiphy, - struct regulatory_request *pending_request) +static enum reg_request_treatment +__regulatory_hint(struct wiphy *wiphy, + struct regulatory_request *pending_request) { + const struct ieee80211_regdomain *regd; bool intersect = false; - int r = 0; - - assert_cfg80211_lock(); + enum reg_request_treatment treatment; + struct regulatory_request *lr; - r = ignore_request(wiphy, pending_request); + treatment = get_reg_request_treatment(wiphy, pending_request); - if (r == REG_INTERSECT) { + switch (treatment) { + case REG_REQ_INTERSECT: if (pending_request->initiator == NL80211_REGDOM_SET_BY_DRIVER) { - r = reg_copy_regd(&wiphy->regd, cfg80211_regdomain); - if (r) { + regd = reg_copy_regd(get_cfg80211_regdom()); + if (IS_ERR(regd)) { kfree(pending_request); - return r; + return PTR_ERR(regd); } + rcu_assign_pointer(wiphy->regd, regd); } intersect = true; - } else if (r) { + 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 (r == -EALREADY && - pending_request->initiator == - NL80211_REGDOM_SET_BY_DRIVER) { - r = reg_copy_regd(&wiphy->regd, cfg80211_regdomain); - if (r) { + 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 r; + return REG_REQ_IGNORE; } - r = -EALREADY; + treatment = REG_REQ_ALREADY_SET; + rcu_assign_pointer(wiphy->regd, regd); goto new_request; } kfree(pending_request); - return r; + return treatment; } new_request: - if (last_request != &core_request_world) - kfree(last_request); + lr = get_last_request(); + if (lr != &core_request_world && lr) + kfree_rcu(lr, rcu_head); - last_request = pending_request; - last_request->intersect = intersect; + pending_request->intersect = intersect; + pending_request->processed = false; + rcu_assign_pointer(last_request, pending_request); + lr = pending_request; pending_request = NULL; - if (last_request->initiator == NL80211_REGDOM_SET_BY_USER) { - user_alpha2[0] = last_request->alpha2[0]; - user_alpha2[1] = last_request->alpha2[1]; + if (lr->initiator == NL80211_REGDOM_SET_BY_USER) { + user_alpha2[0] = lr->alpha2[0]; + user_alpha2[1] = lr->alpha2[1]; } - /* When r == REG_INTERSECT we do need to call CRDA */ - if (r < 0) { + /* When r == REG_REQ_INTERSECT we do need to call CRDA */ + if (treatment != REG_REQ_OK && treatment != REG_REQ_INTERSECT) { /* * 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 (r == -EALREADY) { - nl80211_send_reg_change_event(last_request); + if (treatment == REG_REQ_ALREADY_SET) { + nl80211_send_reg_change_event(lr); reg_set_request_processed(); } - return r; + return treatment; } - return call_crda(last_request->alpha2); + if (call_crda(lr->alpha2)) + return REG_REQ_IGNORE; + return REG_REQ_OK; } /* This processes *all* regulatory hints */ static void reg_process_hint(struct regulatory_request *reg_request, enum nl80211_reg_initiator reg_initiator) { - int r = 0; struct wiphy *wiphy = NULL; - BUG_ON(!reg_request->alpha2); + if (WARN_ON(!reg_request->alpha2)) + return; - if (wiphy_idx_valid(reg_request->wiphy_idx)) + 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_initiator == NL80211_REGDOM_SET_BY_DRIVER && !wiphy) { kfree(reg_request); return; } - r = __regulatory_hint(wiphy, reg_request); - /* This is required so that the orig_* parameters are saved */ - if (r == -EALREADY && wiphy && - wiphy->flags & WIPHY_FLAG_STRICT_REGULATORY) { - wiphy_update_regulatory(wiphy, reg_initiator); - 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); + break; + default: + if (reg_initiator == NL80211_REGDOM_SET_BY_USER) + schedule_delayed_work(®_timeout, + msecs_to_jiffies(3142)); + break; } - - /* - * We only time out user hints, given that they should be the only - * source of bogus requests. - */ - if (r != -EALREADY && - reg_initiator == NL80211_REGDOM_SET_BY_USER) - schedule_delayed_work(®_timeout, msecs_to_jiffies(3142)); } /* @@ -1627,15 +1557,15 @@ static void reg_process_hint(struct regulatory_request *reg_request, */ static void reg_process_pending_hints(void) { - struct regulatory_request *reg_request; + struct regulatory_request *reg_request, *lr; mutex_lock(&cfg80211_mutex); mutex_lock(®_mutex); + lr = get_last_request(); /* When last_request->processed becomes true this will be rescheduled */ - if (last_request && !last_request->processed) { - REG_DBG_PRINT("Pending regulatory request, waiting " - "for it to be processed...\n"); + if (lr && !lr->processed) { + REG_DBG_PRINT("Pending regulatory request, waiting for it to be processed...\n"); goto out; } @@ -1666,23 +1596,14 @@ static void reg_process_pending_beacon_hints(void) struct cfg80211_registered_device *rdev; struct reg_beacon *pending_beacon, *tmp; - /* - * No need to hold the reg_mutex here as we just touch wiphys - * and do not read or access regulatory variables. - */ mutex_lock(&cfg80211_mutex); + mutex_lock(®_mutex); /* This goes through the _pending_ beacon list */ spin_lock_bh(®_pending_beacons_lock); - if (list_empty(®_pending_beacons)) { - spin_unlock_bh(®_pending_beacons_lock); - goto out; - } - list_for_each_entry_safe(pending_beacon, tmp, ®_pending_beacons, list) { - list_del_init(&pending_beacon->list); /* Applies the beacon hint to current wiphys */ @@ -1694,7 +1615,7 @@ static void reg_process_pending_beacon_hints(void) } spin_unlock_bh(®_pending_beacons_lock); -out: + mutex_unlock(®_mutex); mutex_unlock(&cfg80211_mutex); } @@ -1706,10 +1627,8 @@ static void reg_todo(struct work_struct *work) static void queue_regulatory_request(struct regulatory_request *request) { - if (isalpha(request->alpha2[0])) - request->alpha2[0] = toupper(request->alpha2[0]); - if (isalpha(request->alpha2[1])) - request->alpha2[1] = toupper(request->alpha2[1]); + request->alpha2[0] = toupper(request->alpha2[0]); + request->alpha2[1] = toupper(request->alpha2[1]); spin_lock(®_requests_lock); list_add_tail(&request->list, ®_requests_list); @@ -1726,8 +1645,7 @@ static int regulatory_hint_core(const char *alpha2) { struct regulatory_request *request; - request = kzalloc(sizeof(struct regulatory_request), - GFP_KERNEL); + request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) return -ENOMEM; @@ -1746,13 +1664,14 @@ int regulatory_hint_user(const char *alpha2, { struct regulatory_request *request; - BUG_ON(!alpha2); + if (WARN_ON(!alpha2)) + return -EINVAL; request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) return -ENOMEM; - request->wiphy_idx = WIPHY_IDX_STALE; + request->wiphy_idx = WIPHY_IDX_INVALID; request->alpha2[0] = alpha2[0]; request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_USER; @@ -1768,8 +1687,8 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2) { struct regulatory_request *request; - BUG_ON(!alpha2); - BUG_ON(!wiphy); + if (WARN_ON(!alpha2 || !wiphy)) + return -EINVAL; request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) @@ -1777,9 +1696,6 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2) request->wiphy_idx = get_wiphy_idx(wiphy); - /* Must have registered wiphy first */ - BUG_ON(!wiphy_idx_valid(request->wiphy_idx)); - request->alpha2[0] = alpha2[0]; request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_DRIVER; @@ -1794,18 +1710,17 @@ EXPORT_SYMBOL(regulatory_hint); * We hold wdev_lock() here so we cannot hold cfg80211_mutex() and * therefore cannot iterate over the rdev list here. */ -void regulatory_hint_11d(struct wiphy *wiphy, - enum ieee80211_band band, - const u8 *country_ie, - u8 country_ie_len) +void regulatory_hint_11d(struct wiphy *wiphy, enum ieee80211_band band, + const u8 *country_ie, u8 country_ie_len) { char alpha2[2]; enum environment_cap env = ENVIRON_ANY; - struct regulatory_request *request; + struct regulatory_request *request, *lr; mutex_lock(®_mutex); + lr = get_last_request(); - if (unlikely(!last_request)) + if (unlikely(!lr)) goto out; /* IE len must be evenly divisible by 2 */ @@ -1828,9 +1743,8 @@ void regulatory_hint_11d(struct wiphy *wiphy, * We leave conflict resolution to the workqueue, where can hold * cfg80211_mutex. */ - if (likely(last_request->initiator == - NL80211_REGDOM_SET_BY_COUNTRY_IE && - wiphy_idx_valid(last_request->wiphy_idx))) + if (lr->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && + lr->wiphy_idx != WIPHY_IDX_INVALID) goto out; request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); @@ -1843,12 +1757,7 @@ void regulatory_hint_11d(struct wiphy *wiphy, request->initiator = NL80211_REGDOM_SET_BY_COUNTRY_IE; request->country_ie_env = env; - mutex_unlock(®_mutex); - queue_regulatory_request(request); - - return; - out: mutex_unlock(®_mutex); } @@ -1863,8 +1772,7 @@ static void restore_alpha2(char *alpha2, bool reset_user) if (is_user_regdom_saved()) { /* Unless we're asked to ignore it and reset it */ if (reset_user) { - REG_DBG_PRINT("Restoring regulatory settings " - "including user preference\n"); + REG_DBG_PRINT("Restoring regulatory settings including user preference\n"); user_alpha2[0] = '9'; user_alpha2[1] = '7'; @@ -1874,26 +1782,20 @@ static void restore_alpha2(char *alpha2, bool reset_user) * back as they were for a full restore. */ if (!is_world_regdom(ieee80211_regdom)) { - REG_DBG_PRINT("Keeping preference on " - "module parameter ieee80211_regdom: %c%c\n", - ieee80211_regdom[0], - ieee80211_regdom[1]); + REG_DBG_PRINT("Keeping preference on module parameter ieee80211_regdom: %c%c\n", + ieee80211_regdom[0], ieee80211_regdom[1]); alpha2[0] = ieee80211_regdom[0]; alpha2[1] = ieee80211_regdom[1]; } } else { - REG_DBG_PRINT("Restoring regulatory settings " - "while preserving user preference for: %c%c\n", - user_alpha2[0], - user_alpha2[1]); + REG_DBG_PRINT("Restoring regulatory settings while preserving user preference for: %c%c\n", + user_alpha2[0], user_alpha2[1]); alpha2[0] = user_alpha2[0]; alpha2[1] = user_alpha2[1]; } } else if (!is_world_regdom(ieee80211_regdom)) { - REG_DBG_PRINT("Keeping preference on " - "module parameter ieee80211_regdom: %c%c\n", - ieee80211_regdom[0], - ieee80211_regdom[1]); + REG_DBG_PRINT("Keeping preference on module parameter ieee80211_regdom: %c%c\n", + ieee80211_regdom[0], ieee80211_regdom[1]); alpha2[0] = ieee80211_regdom[0]; alpha2[1] = ieee80211_regdom[1]; } else @@ -1948,7 +1850,7 @@ static void restore_regulatory_settings(bool reset_user) mutex_lock(&cfg80211_mutex); mutex_lock(®_mutex); - reset_regdomains(true); + reset_regdomains(true, &world_regdom); restore_alpha2(alpha2, reset_user); /* @@ -1958,49 +1860,35 @@ static void restore_regulatory_settings(bool reset_user) * settings. */ spin_lock(®_requests_lock); - if (!list_empty(®_requests_list)) { - list_for_each_entry_safe(reg_request, tmp, - ®_requests_list, list) { - if (reg_request->initiator != - NL80211_REGDOM_SET_BY_USER) - continue; - list_move_tail(®_request->list, &tmp_reg_req_list); - } + list_for_each_entry_safe(reg_request, tmp, ®_requests_list, list) { + if (reg_request->initiator != NL80211_REGDOM_SET_BY_USER) + continue; + list_move_tail(®_request->list, &tmp_reg_req_list); } spin_unlock(®_requests_lock); /* Clear beacon hints */ spin_lock_bh(®_pending_beacons_lock); - if (!list_empty(®_pending_beacons)) { - list_for_each_entry_safe(reg_beacon, btmp, - ®_pending_beacons, list) { - list_del(®_beacon->list); - kfree(reg_beacon); - } + list_for_each_entry_safe(reg_beacon, btmp, ®_pending_beacons, list) { + list_del(®_beacon->list); + kfree(reg_beacon); } spin_unlock_bh(®_pending_beacons_lock); - if (!list_empty(®_beacon_list)) { - list_for_each_entry_safe(reg_beacon, btmp, - ®_beacon_list, list) { - list_del(®_beacon->list); - kfree(reg_beacon); - } + list_for_each_entry_safe(reg_beacon, btmp, ®_beacon_list, list) { + list_del(®_beacon->list); + kfree(reg_beacon); } /* First restore to the basic regulatory settings */ - cfg80211_regdomain = cfg80211_world_regdom; - world_alpha2[0] = cfg80211_regdomain->alpha2[0]; - world_alpha2[1] = cfg80211_regdomain->alpha2[1]; + world_alpha2[0] = cfg80211_world_regdom->alpha2[0]; + 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) restore_custom_reg_settings(&rdev->wiphy); } - mutex_unlock(®_mutex); - mutex_unlock(&cfg80211_mutex); - regulatory_hint_core(world_alpha2); /* @@ -2011,20 +1899,8 @@ static void restore_regulatory_settings(bool reset_user) if (is_an_alpha2(alpha2)) regulatory_hint_user(user_alpha2, NL80211_USER_REG_HINT_USER); - if (list_empty(&tmp_reg_req_list)) - return; - - mutex_lock(&cfg80211_mutex); - mutex_lock(®_mutex); - spin_lock(®_requests_lock); - list_for_each_entry_safe(reg_request, tmp, &tmp_reg_req_list, list) { - REG_DBG_PRINT("Adding request for country %c%c back " - "into the queue\n", - reg_request->alpha2[0], - reg_request->alpha2[1]); - list_move_tail(®_request->list, ®_requests_list); - } + list_splice_tail_init(&tmp_reg_req_list, ®_requests_list); spin_unlock(®_requests_lock); mutex_unlock(®_mutex); @@ -2037,8 +1913,7 @@ static void restore_regulatory_settings(bool reset_user) void regulatory_hint_disconnect(void) { - REG_DBG_PRINT("All devices are disconnected, going to " - "restore regulatory settings\n"); + REG_DBG_PRINT("All devices are disconnected, going to restore regulatory settings\n"); restore_regulatory_settings(false); } @@ -2051,31 +1926,48 @@ static bool freq_is_chan_12_13_14(u16 freq) return false; } +static bool pending_reg_beacon(struct ieee80211_channel *beacon_chan) +{ + struct reg_beacon *pending_beacon; + + list_for_each_entry(pending_beacon, ®_pending_beacons, list) + if (beacon_chan->center_freq == + pending_beacon->chan.center_freq) + return true; + return false; +} + int regulatory_hint_found_beacon(struct wiphy *wiphy, struct ieee80211_channel *beacon_chan, gfp_t gfp) { struct reg_beacon *reg_beacon; + bool processing; - if (likely((beacon_chan->beacon_found || - (beacon_chan->flags & IEEE80211_CHAN_RADAR) || + if (beacon_chan->beacon_found || + beacon_chan->flags & IEEE80211_CHAN_RADAR || (beacon_chan->band == IEEE80211_BAND_2GHZ && - !freq_is_chan_12_13_14(beacon_chan->center_freq))))) + !freq_is_chan_12_13_14(beacon_chan->center_freq))) + return 0; + + spin_lock_bh(®_pending_beacons_lock); + processing = pending_reg_beacon(beacon_chan); + spin_unlock_bh(®_pending_beacons_lock); + + if (processing) return 0; reg_beacon = kzalloc(sizeof(struct reg_beacon), gfp); if (!reg_beacon) return -ENOMEM; - REG_DBG_PRINT("Found new beacon on " - "frequency: %d MHz (Ch %d) on %s\n", + REG_DBG_PRINT("Found new beacon on frequency: %d MHz (Ch %d) on %s\n", beacon_chan->center_freq, ieee80211_frequency_to_channel(beacon_chan->center_freq), wiphy_name(wiphy)); memcpy(®_beacon->chan, beacon_chan, - sizeof(struct ieee80211_channel)); - + sizeof(struct ieee80211_channel)); /* * Since we can be called from BH or and non-BH context @@ -2155,21 +2047,19 @@ static void print_dfs_region(u8 dfs_region) pr_info(" DFS Master region JP"); break; default: - pr_info(" DFS Master region Uknown"); + pr_info(" DFS Master region Unknown"); break; } } static void print_regdomain(const struct ieee80211_regdomain *rd) { + struct regulatory_request *lr = get_last_request(); if (is_intersected_alpha2(rd->alpha2)) { - - if (last_request->initiator == - NL80211_REGDOM_SET_BY_COUNTRY_IE) { + if (lr->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE) { struct cfg80211_registered_device *rdev; - rdev = cfg80211_rdev_by_wiphy_idx( - last_request->wiphy_idx); + rdev = cfg80211_rdev_by_wiphy_idx(lr->wiphy_idx); if (rdev) { pr_info("Current regulatory domain updated by AP to: %c%c\n", rdev->country_ie_alpha2[0], @@ -2178,22 +2068,21 @@ static void print_regdomain(const struct ieee80211_regdomain *rd) pr_info("Current regulatory domain intersected:\n"); } else pr_info("Current regulatory domain intersected:\n"); - } else if (is_world_regdom(rd->alpha2)) + } else if (is_world_regdom(rd->alpha2)) { pr_info("World regulatory domain updated:\n"); - else { + } else { if (is_unknown_alpha2(rd->alpha2)) pr_info("Regulatory domain changed to driver built-in settings (unknown country)\n"); else { - if (reg_request_cell_base(last_request)) - pr_info("Regulatory domain changed " - "to country: %c%c by Cell Station\n", + if (reg_request_cell_base(lr)) + pr_info("Regulatory domain changed to country: %c%c by Cell Station\n", rd->alpha2[0], rd->alpha2[1]); else - pr_info("Regulatory domain changed " - "to country: %c%c\n", + pr_info("Regulatory domain changed to country: %c%c\n", rd->alpha2[0], rd->alpha2[1]); } } + print_dfs_region(rd->dfs_region); print_rd_rules(rd); } @@ -2207,22 +2096,23 @@ static void print_regdomain_info(const struct ieee80211_regdomain *rd) /* Takes ownership of rd only if it doesn't fail */ static int __set_regdom(const struct ieee80211_regdomain *rd) { + 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 (!reg_is_valid_request(rd->alpha2)) + return -EINVAL; + if (is_world_regdom(rd->alpha2)) { - if (WARN_ON(!reg_is_valid_request(rd->alpha2))) - return -EINVAL; update_world_regdomain(rd); return 0; } if (!is_alpha2_set(rd->alpha2) && !is_an_alpha2(rd->alpha2) && - !is_unknown_alpha2(rd->alpha2)) - return -EINVAL; - - if (!last_request) + !is_unknown_alpha2(rd->alpha2)) return -EINVAL; /* @@ -2230,7 +2120,7 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) * rd is non static (it means CRDA was present and was used last) * and the pending request came in from a country IE */ - if (last_request->initiator != NL80211_REGDOM_SET_BY_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 @@ -2246,29 +2136,23 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) * internal EEPROM data */ - if (WARN_ON(!reg_is_valid_request(rd->alpha2))) - return -EINVAL; - if (!is_valid_rd(rd)) { pr_err("Invalid regulatory domain detected:\n"); print_regdomain_info(rd); return -EINVAL; } - request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); + request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); if (!request_wiphy && - (last_request->initiator == NL80211_REGDOM_SET_BY_DRIVER || - last_request->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE)) { + (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER || + lr->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE)) { schedule_delayed_work(®_timeout, 0); return -ENODEV; } - if (!last_request->intersect) { - int r; - - if (last_request->initiator != NL80211_REGDOM_SET_BY_DRIVER) { - reset_regdomains(false); - cfg80211_regdomain = rd; + if (!lr->intersect) { + if (lr->initiator != NL80211_REGDOM_SET_BY_DRIVER) { + reset_regdomains(false, rd); return 0; } @@ -2284,20 +2168,19 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) if (request_wiphy->regd) return -EALREADY; - r = reg_copy_regd(&request_wiphy->regd, rd); - if (r) - return r; + regd = reg_copy_regd(rd); + if (IS_ERR(regd)) + return PTR_ERR(regd); - reset_regdomains(false); - cfg80211_regdomain = rd; + rcu_assign_pointer(request_wiphy->regd, regd); + reset_regdomains(false, rd); return 0; } /* Intersection requires a bit more work */ - if (last_request->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE) { - - intersected_rd = regdom_intersect(rd, cfg80211_regdomain); + if (lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE) { + intersected_rd = regdom_intersect(rd, get_cfg80211_regdom()); if (!intersected_rd) return -EINVAL; @@ -2306,15 +2189,14 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) * However if a driver requested this specific regulatory * domain we keep it for its private use */ - if (last_request->initiator == NL80211_REGDOM_SET_BY_DRIVER) - request_wiphy->regd = rd; + if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER) + rcu_assign_pointer(request_wiphy->regd, rd); else kfree(rd); rd = NULL; - reset_regdomains(false); - cfg80211_regdomain = intersected_rd; + reset_regdomains(false, intersected_rd); return 0; } @@ -2326,15 +2208,15 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) /* * Use this call to set the current regulatory domain. Conflicts with * multiple drivers can be ironed out later. Caller must've already - * kmalloc'd the rd structure. Caller must hold cfg80211_mutex + * kmalloc'd the rd structure. */ int set_regdom(const struct ieee80211_regdomain *rd) { + struct regulatory_request *lr; int r; - assert_cfg80211_lock(); - mutex_lock(®_mutex); + lr = get_last_request(); /* Note that this doesn't update the wiphys, this is done below */ r = __set_regdom(rd); @@ -2343,23 +2225,25 @@ int set_regdom(const struct ieee80211_regdomain *rd) reg_set_request_processed(); kfree(rd); - mutex_unlock(®_mutex); - return r; + goto out; } /* This would make this whole thing pointless */ - if (!last_request->intersect) - BUG_ON(rd != cfg80211_regdomain); + if (WARN_ON(!lr->intersect && rd != get_cfg80211_regdom())) { + r = -EINVAL; + goto out; + } /* update all wiphys now with the new established regulatory domain */ - update_all_wiphy_regulatory(last_request->initiator); + update_all_wiphy_regulatory(lr->initiator); - print_regdomain(cfg80211_regdomain); + print_regdomain(get_cfg80211_regdom()); - nl80211_send_reg_change_event(last_request); + nl80211_send_reg_change_event(lr); reg_set_request_processed(); + out: mutex_unlock(®_mutex); return r; @@ -2367,20 +2251,26 @@ int set_regdom(const struct ieee80211_regdomain *rd) int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env) { - if (last_request && !last_request->processed) { - if (add_uevent_var(env, "COUNTRY=%c%c", - last_request->alpha2[0], - last_request->alpha2[1])) - return -ENOMEM; + struct regulatory_request *lr; + u8 alpha2[2]; + bool add = false; + + rcu_read_lock(); + lr = get_last_request(); + if (lr && !lr->processed) { + memcpy(alpha2, lr->alpha2, 2); + add = true; } + rcu_read_unlock(); + if (add) + return add_uevent_var(env, "COUNTRY=%c%c", + alpha2[0], alpha2[1]); return 0; } void wiphy_regulatory_register(struct wiphy *wiphy) { - assert_cfg80211_lock(); - mutex_lock(®_mutex); if (!reg_dev_ignore_cell_hint(wiphy)) @@ -2395,32 +2285,32 @@ void wiphy_regulatory_register(struct wiphy *wiphy) void wiphy_regulatory_deregister(struct wiphy *wiphy) { struct wiphy *request_wiphy = NULL; - - assert_cfg80211_lock(); + struct regulatory_request *lr; mutex_lock(®_mutex); + lr = get_last_request(); if (!reg_dev_ignore_cell_hint(wiphy)) reg_num_devs_support_basehint--; - kfree(wiphy->regd); + rcu_free_regdom(get_wiphy_regdom(wiphy)); + rcu_assign_pointer(wiphy->regd, NULL); - if (last_request) - request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); + if (lr) + request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); if (!request_wiphy || request_wiphy != wiphy) goto out; - last_request->wiphy_idx = WIPHY_IDX_STALE; - last_request->country_ie_env = ENVIRON_ANY; + lr->wiphy_idx = WIPHY_IDX_INVALID; + lr->country_ie_env = ENVIRON_ANY; out: mutex_unlock(®_mutex); } static void reg_timeout_work(struct work_struct *work) { - REG_DBG_PRINT("Timeout while waiting for CRDA to reply, " - "restoring regulatory settings\n"); + REG_DBG_PRINT("Timeout while waiting for CRDA to reply, restoring regulatory settings\n"); restore_regulatory_settings(true); } @@ -2439,13 +2329,13 @@ int __init regulatory_init(void) reg_regdb_size_check(); - cfg80211_regdomain = cfg80211_world_regdom; + rcu_assign_pointer(cfg80211_regdomain, cfg80211_world_regdom); user_alpha2[0] = '9'; user_alpha2[1] = '7'; /* We always try to get an update for the static regdomain */ - err = regulatory_hint_core(cfg80211_regdomain->alpha2); + err = regulatory_hint_core(cfg80211_world_regdom->alpha2); if (err) { if (err == -ENOMEM) return err; @@ -2457,10 +2347,6 @@ int __init regulatory_init(void) * errors as non-fatal. */ pr_err("kobject_uevent_env() was unable to call CRDA during init\n"); -#ifdef CONFIG_CFG80211_REG_DEBUG - /* We want to find out exactly why when debugging */ - WARN_ON(err); -#endif } /* @@ -2474,7 +2360,7 @@ int __init regulatory_init(void) return 0; } -void /* __init_or_exit */ regulatory_exit(void) +void regulatory_exit(void) { struct regulatory_request *reg_request, *tmp; struct reg_beacon *reg_beacon, *btmp; @@ -2482,43 +2368,27 @@ void /* __init_or_exit */ regulatory_exit(void) cancel_work_sync(®_work); cancel_delayed_work_sync(®_timeout); - mutex_lock(&cfg80211_mutex); + /* Lock to suppress warnings */ mutex_lock(®_mutex); - - reset_regdomains(true); + reset_regdomains(true, NULL); + mutex_unlock(®_mutex); dev_set_uevent_suppress(®_pdev->dev, true); platform_device_unregister(reg_pdev); - spin_lock_bh(®_pending_beacons_lock); - if (!list_empty(®_pending_beacons)) { - list_for_each_entry_safe(reg_beacon, btmp, - ®_pending_beacons, list) { - list_del(®_beacon->list); - kfree(reg_beacon); - } + list_for_each_entry_safe(reg_beacon, btmp, ®_pending_beacons, list) { + list_del(®_beacon->list); + kfree(reg_beacon); } - spin_unlock_bh(®_pending_beacons_lock); - if (!list_empty(®_beacon_list)) { - list_for_each_entry_safe(reg_beacon, btmp, - ®_beacon_list, list) { - list_del(®_beacon->list); - kfree(reg_beacon); - } + list_for_each_entry_safe(reg_beacon, btmp, ®_beacon_list, list) { + list_del(®_beacon->list); + kfree(reg_beacon); } - spin_lock(®_requests_lock); - if (!list_empty(®_requests_list)) { - list_for_each_entry_safe(reg_request, tmp, - ®_requests_list, list) { - list_del(®_request->list); - kfree(reg_request); - } + list_for_each_entry_safe(reg_request, tmp, ®_requests_list, list) { + list_del(®_request->list); + kfree(reg_request); } - spin_unlock(®_requests_lock); - - mutex_unlock(®_mutex); - mutex_unlock(&cfg80211_mutex); } diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 4c0a32ffd53..af2d5f8a5d8 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -16,10 +16,9 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -extern const struct ieee80211_regdomain *cfg80211_regdomain; +extern const struct ieee80211_regdomain __rcu *cfg80211_regdomain; bool is_world_regdom(const char *alpha2); -bool reg_is_valid_request(const char *alpha2); bool reg_supported_dfs_region(u8 dfs_region); int regulatory_hint_user(const char *alpha2, @@ -55,8 +54,8 @@ bool reg_last_request_cell_base(void); * set the wiphy->disable_beacon_hints to true. */ int regulatory_hint_found_beacon(struct wiphy *wiphy, - struct ieee80211_channel *beacon_chan, - gfp_t gfp); + struct ieee80211_channel *beacon_chan, + gfp_t gfp); /** * regulatory_hint_11d - hints a country IE as a regulatory domain diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f2431e41a37..a825dfe12cf 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -192,7 +192,8 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev) prev_bssid, params->ssid, params->ssid_len, params->ie, params->ie_len, - false, ¶ms->crypto, + params->mfp != NL80211_MFP_NO, + ¶ms->crypto, params->flags, ¶ms->ht_capa, ¶ms->ht_capa_mask); if (err) @@ -519,10 +520,8 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, * - country_ie + 2, the start of the country ie data, and * - and country_ie[1] which is the IE length */ - regulatory_hint_11d(wdev->wiphy, - bss->channel->band, - country_ie + 2, - country_ie[1]); + regulatory_hint_11d(wdev->wiphy, bss->channel->band, + country_ie + 2, country_ie[1]); kfree(country_ie); } diff --git a/net/wireless/util.c b/net/wireless/util.c index 16d76a807c2..1c2795d52db 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1184,7 +1184,8 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, enum nl80211_iftype iftype, struct ieee80211_channel *chan, - enum cfg80211_chan_mode chanmode) + enum cfg80211_chan_mode chanmode, + u8 radar_detect) { struct wireless_dev *wdev_iter; u32 used_iftypes = BIT(iftype); @@ -1195,14 +1196,45 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, enum cfg80211_chan_mode chmode; int num_different_channels = 0; int total = 1; + bool radar_required; int i, j; ASSERT_RTNL(); lockdep_assert_held(&rdev->devlist_mtx); + if (WARN_ON(hweight32(radar_detect) > 1)) + return -EINVAL; + + switch (iftype) { + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_MESH_POINT: + case NL80211_IFTYPE_P2P_GO: + case NL80211_IFTYPE_WDS: + radar_required = !!(chan->flags & IEEE80211_CHAN_RADAR); + break; + case NL80211_IFTYPE_P2P_CLIENT: + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_MONITOR: + radar_required = false; + break; + case NL80211_IFTYPE_P2P_DEVICE: + case NUM_NL80211_IFTYPES: + case NL80211_IFTYPE_UNSPECIFIED: + default: + return -EINVAL; + } + + if (radar_required && !radar_detect) + return -EINVAL; + /* Always allow software iftypes */ - if (rdev->wiphy.software_iftypes & BIT(iftype)) + if (rdev->wiphy.software_iftypes & BIT(iftype)) { + if (radar_detect) + return -EINVAL; return 0; + } memset(num, 0, sizeof(num)); memset(used_channels, 0, sizeof(used_channels)); @@ -1275,7 +1307,7 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, used_iftypes |= BIT(wdev_iter->iftype); } - if (total == 1) + if (total == 1 && !radar_detect) return 0; for (i = 0; i < rdev->wiphy.n_iface_combinations; i++) { @@ -1308,6 +1340,9 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, } } + if (radar_detect && !(c->radar_detect_widths & radar_detect)) + goto cont; + /* * Finally check that all iftypes that we're currently * using are actually part of this combination. If they diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 4ce2d93162c..f9a54955474 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -700,8 +700,7 @@ void xfrm_probe_algs(void) } for (i = 0; i < ealg_entries(); i++) { - status = crypto_has_blkcipher(ealg_list[i].name, 0, - CRYPTO_ALG_ASYNC); + status = crypto_has_ablkcipher(ealg_list[i].name, 0, 0); if (ealg_list[i].available != status) ealg_list[i].available = status; } diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 95a338c89f9..3670526e70b 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -61,6 +61,12 @@ static int xfrm_output_one(struct sk_buff *skb, int err) } spin_lock_bh(&x->lock); + + if (unlikely(x->km.state != XFRM_STATE_VALID)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEINVALID); + goto error_nolock; + } + err = xfrm_state_check_expire(x); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED); diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index d0a1af8ed58..603903853e8 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -43,6 +43,7 @@ static const struct snmp_mib xfrm_mib_list[] = { SNMP_MIB_ITEM("XfrmOutPolDead", LINUX_MIB_XFRMOUTPOLDEAD), SNMP_MIB_ITEM("XfrmOutPolError", LINUX_MIB_XFRMOUTPOLERROR), SNMP_MIB_ITEM("XfrmFwdHdrError", LINUX_MIB_XFRMFWDHDRERROR), + SNMP_MIB_ITEM("XfrmOutStateInvalid", LINUX_MIB_XFRMOUTSTATEINVALID), SNMP_MIB_SENTINEL }; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 3459692092e..0adae918a7a 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -158,8 +158,8 @@ out_unlock: mutex_unlock(&hash_resize_mutex); } -static DEFINE_RWLOCK(xfrm_state_afinfo_lock); -static struct xfrm_state_afinfo *xfrm_state_afinfo[NPROTO]; +static DEFINE_SPINLOCK(xfrm_state_afinfo_lock); +static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO]; static DEFINE_SPINLOCK(xfrm_state_gc_lock); @@ -168,58 +168,45 @@ int __xfrm_state_delete(struct xfrm_state *x); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); -static struct xfrm_state_afinfo *xfrm_state_lock_afinfo(unsigned int family) -{ - struct xfrm_state_afinfo *afinfo; - if (unlikely(family >= NPROTO)) - return NULL; - write_lock_bh(&xfrm_state_afinfo_lock); - afinfo = xfrm_state_afinfo[family]; - if (unlikely(!afinfo)) - write_unlock_bh(&xfrm_state_afinfo_lock); - return afinfo; -} - -static void xfrm_state_unlock_afinfo(struct xfrm_state_afinfo *afinfo) - __releases(xfrm_state_afinfo_lock) -{ - write_unlock_bh(&xfrm_state_afinfo_lock); -} - +static DEFINE_SPINLOCK(xfrm_type_lock); int xfrm_register_type(const struct xfrm_type *type, unsigned short family) { - struct xfrm_state_afinfo *afinfo = xfrm_state_lock_afinfo(family); + struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); const struct xfrm_type **typemap; int err = 0; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; typemap = afinfo->type_map; + spin_lock_bh(&xfrm_type_lock); if (likely(typemap[type->proto] == NULL)) typemap[type->proto] = type; else err = -EEXIST; - xfrm_state_unlock_afinfo(afinfo); + spin_unlock_bh(&xfrm_type_lock); + xfrm_state_put_afinfo(afinfo); return err; } EXPORT_SYMBOL(xfrm_register_type); int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family) { - struct xfrm_state_afinfo *afinfo = xfrm_state_lock_afinfo(family); + struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); const struct xfrm_type **typemap; int err = 0; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; typemap = afinfo->type_map; + spin_lock_bh(&xfrm_type_lock); if (unlikely(typemap[type->proto] != type)) err = -ENOENT; else typemap[type->proto] = NULL; - xfrm_state_unlock_afinfo(afinfo); + spin_unlock_bh(&xfrm_type_lock); + xfrm_state_put_afinfo(afinfo); return err; } EXPORT_SYMBOL(xfrm_unregister_type); @@ -256,6 +243,7 @@ static void xfrm_put_type(const struct xfrm_type *type) module_put(type->owner); } +static DEFINE_SPINLOCK(xfrm_mode_lock); int xfrm_register_mode(struct xfrm_mode *mode, int family) { struct xfrm_state_afinfo *afinfo; @@ -265,12 +253,13 @@ int xfrm_register_mode(struct xfrm_mode *mode, int family) if (unlikely(mode->encap >= XFRM_MODE_MAX)) return -EINVAL; - afinfo = xfrm_state_lock_afinfo(family); + afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; err = -EEXIST; modemap = afinfo->mode_map; + spin_lock_bh(&xfrm_mode_lock); if (modemap[mode->encap]) goto out; @@ -283,7 +272,8 @@ int xfrm_register_mode(struct xfrm_mode *mode, int family) err = 0; out: - xfrm_state_unlock_afinfo(afinfo); + spin_unlock_bh(&xfrm_mode_lock); + xfrm_state_put_afinfo(afinfo); return err; } EXPORT_SYMBOL(xfrm_register_mode); @@ -297,19 +287,21 @@ int xfrm_unregister_mode(struct xfrm_mode *mode, int family) if (unlikely(mode->encap >= XFRM_MODE_MAX)) return -EINVAL; - afinfo = xfrm_state_lock_afinfo(family); + afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; err = -ENOENT; modemap = afinfo->mode_map; + spin_lock_bh(&xfrm_mode_lock); if (likely(modemap[mode->encap] == mode)) { modemap[mode->encap] = NULL; module_put(mode->afinfo->owner); err = 0; } - xfrm_state_unlock_afinfo(afinfo); + spin_unlock_bh(&xfrm_mode_lock); + xfrm_state_put_afinfo(afinfo); return err; } EXPORT_SYMBOL(xfrm_unregister_mode); @@ -1370,9 +1362,6 @@ int xfrm_state_check_expire(struct xfrm_state *x) if (!x->curlft.use_time) x->curlft.use_time = get_seconds(); - if (x->km.state != XFRM_STATE_VALID) - return -EINVAL; - if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { x->km.state = XFRM_STATE_EXPIRED; @@ -1648,27 +1637,26 @@ static void xfrm_replay_timer_handler(unsigned long data) } static LIST_HEAD(xfrm_km_list); -static DEFINE_RWLOCK(xfrm_km_lock); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify_policy) km->notify_policy(xp, dir, c); - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); } void km_state_notify(struct xfrm_state *x, const struct km_event *c) { struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify) km->notify(x, c); - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); } EXPORT_SYMBOL(km_policy_notify); @@ -1698,13 +1686,13 @@ int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) int err = -EINVAL, acqret; struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { acqret = km->acquire(x, t, pol); if (!acqret) err = acqret; } - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_query); @@ -1714,14 +1702,14 @@ int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) int err = -EINVAL; struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->new_mapping) err = km->new_mapping(x, ipaddr, sport); if (!err) break; } - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_new_mapping); @@ -1750,15 +1738,15 @@ int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, int ret; struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->migrate) { ret = km->migrate(sel, dir, type, m, num_migrate, k); if (!ret) err = ret; } } - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_migrate); @@ -1770,15 +1758,15 @@ int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address int ret; struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->report) { ret = km->report(net, proto, sel, addr); if (!ret) err = ret; } } - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_report); @@ -1802,14 +1790,14 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen goto out; err = -EINVAL; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { pol = km->compile_policy(sk, optname, data, optlen, &err); if (err >= 0) break; } - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); if (err >= 0) { xfrm_sk_policy_insert(sk, err, pol); @@ -1823,20 +1811,23 @@ out: } EXPORT_SYMBOL(xfrm_user_policy); +static DEFINE_SPINLOCK(xfrm_km_lock); + int xfrm_register_km(struct xfrm_mgr *km) { - write_lock_bh(&xfrm_km_lock); - list_add_tail(&km->list, &xfrm_km_list); - write_unlock_bh(&xfrm_km_lock); + spin_lock_bh(&xfrm_km_lock); + list_add_tail_rcu(&km->list, &xfrm_km_list); + spin_unlock_bh(&xfrm_km_lock); return 0; } EXPORT_SYMBOL(xfrm_register_km); int xfrm_unregister_km(struct xfrm_mgr *km) { - write_lock_bh(&xfrm_km_lock); - list_del(&km->list); - write_unlock_bh(&xfrm_km_lock); + spin_lock_bh(&xfrm_km_lock); + list_del_rcu(&km->list); + spin_unlock_bh(&xfrm_km_lock); + synchronize_rcu(); return 0; } EXPORT_SYMBOL(xfrm_unregister_km); @@ -1848,12 +1839,12 @@ int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo) return -EINVAL; if (unlikely(afinfo->family >= NPROTO)) return -EAFNOSUPPORT; - write_lock_bh(&xfrm_state_afinfo_lock); + spin_lock_bh(&xfrm_state_afinfo_lock); if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL)) err = -ENOBUFS; else - xfrm_state_afinfo[afinfo->family] = afinfo; - write_unlock_bh(&xfrm_state_afinfo_lock); + rcu_assign_pointer(xfrm_state_afinfo[afinfo->family], afinfo); + spin_unlock_bh(&xfrm_state_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_state_register_afinfo); @@ -1865,14 +1856,15 @@ int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo) return -EINVAL; if (unlikely(afinfo->family >= NPROTO)) return -EAFNOSUPPORT; - write_lock_bh(&xfrm_state_afinfo_lock); + spin_lock_bh(&xfrm_state_afinfo_lock); if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) { if (unlikely(xfrm_state_afinfo[afinfo->family] != afinfo)) err = -EINVAL; else - xfrm_state_afinfo[afinfo->family] = NULL; + RCU_INIT_POINTER(xfrm_state_afinfo[afinfo->family], NULL); } - write_unlock_bh(&xfrm_state_afinfo_lock); + spin_unlock_bh(&xfrm_state_afinfo_lock); + synchronize_rcu(); return err; } EXPORT_SYMBOL(xfrm_state_unregister_afinfo); @@ -1882,17 +1874,16 @@ static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) struct xfrm_state_afinfo *afinfo; if (unlikely(family >= NPROTO)) return NULL; - read_lock(&xfrm_state_afinfo_lock); - afinfo = xfrm_state_afinfo[family]; + rcu_read_lock(); + afinfo = rcu_dereference(xfrm_state_afinfo[family]); if (unlikely(!afinfo)) - read_unlock(&xfrm_state_afinfo_lock); + rcu_read_unlock(); return afinfo; } static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo) - __releases(xfrm_state_afinfo_lock) { - read_unlock(&xfrm_state_afinfo_lock); + rcu_read_unlock(); } /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ |