diff options
Diffstat (limited to 'net')
178 files changed, 4651 insertions, 3008 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 90cc2bdd4064..61bf2a06e85d 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -9,7 +9,7 @@ bool vlan_do_receive(struct sk_buff **skbp) { struct sk_buff *skb = *skbp; __be16 vlan_proto = skb->vlan_proto; - u16 vlan_id = vlan_tx_tag_get_id(skb); + u16 vlan_id = skb_vlan_tag_get_id(skb); struct net_device *vlan_dev; struct vlan_pcpu_stats *rx_stats; diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index 11660a3aab5a..c6fc8f756c9a 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -62,6 +62,7 @@ config BATMAN_ADV_MCAST config BATMAN_ADV_DEBUG bool "B.A.T.M.A.N. debugging" depends on BATMAN_ADV + depends on DEBUG_FS help This is an option for use by developers; most people should say N here. This enables compilation of support for diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 1e8053976e83..00e00e09b000 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -26,9 +26,8 @@ #include "bat_algo.h" #include "network-coding.h" - /** - * batadv_dup_status - duplicate status + * enum batadv_dup_status - duplicate status * @BATADV_NO_DUP: the packet is a duplicate * @BATADV_ORIG_DUP: OGM is a duplicate in the originator (but not for the * neighbor) @@ -517,7 +516,7 @@ out: * @bat_priv: the bat priv with all the soft interface information * @packet_len: (total) length of the OGM * @send_time: timestamp (jiffies) when the packet is to be sent - * @direktlink: true if this is a direct link packet + * @directlink: true if this is a direct link packet * @if_incoming: interface where the packet was received * @if_outgoing: interface for which the retransmission should be considered * @forw_packet: the forwarded packet which should be checked @@ -879,7 +878,7 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) hlist_for_each_entry_rcu(orig_node, head, hash_entry) { spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); word_index = hard_iface->if_num * BATADV_NUM_WORDS; - word = &(orig_node->bat_iv.bcast_own[word_index]); + word = &orig_node->bat_iv.bcast_own[word_index]; batadv_bit_get_packet(bat_priv, word, 1, 0); if_num = hard_iface->if_num; @@ -1362,10 +1361,10 @@ out: return ret; } - /** * batadv_iv_ogm_process_per_outif - process a batman iv OGM for an outgoing if * @skb: the skb containing the OGM + * @ogm_offset: offset from skb->data to start of ogm header * @orig_node: the (cached) orig node for the originator of this OGM * @if_incoming: the interface where this packet was received * @if_outgoing: the interface for which the packet should be considered @@ -1664,7 +1663,7 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset, offset = if_num * BATADV_NUM_WORDS; spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); - word = &(orig_neigh_node->bat_iv.bcast_own[offset]); + word = &orig_neigh_node->bat_iv.bcast_own[offset]; bit_pos = if_incoming_seqno - 2; bit_pos -= ntohl(ogm_packet->seqno); batadv_set_bit(word, bit_pos); @@ -1902,10 +1901,10 @@ out: * batadv_iv_ogm_neigh_is_eob - check if neigh1 is equally good or better than * neigh2 from the metric prospective * @neigh1: the first neighbor object of the comparison - * @if_outgoing: outgoing interface for the first neighbor + * @if_outgoing1: outgoing interface for the first neighbor * @neigh2: the second neighbor object of the comparison * @if_outgoing2: outgoing interface for the second neighbor - + * * Returns true if the metric via neigh1 is equally good or better than * the metric via neigh2, false otherwise. */ diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 9586750022f5..e3da07a64026 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -29,7 +29,6 @@ static void batadv_bitmap_shift_left(unsigned long *seq_bits, int32_t n) bitmap_shift_left(seq_bits, seq_bits, n, BATADV_TQ_LOCAL_WINDOW_SIZE); } - /* receive and process one packet within the sequence number window. * * returns: diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index cc2407351d36..2acaafe60188 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -29,8 +29,7 @@ static inline int batadv_test_bit(const unsigned long *seq_bits, diff = last_seqno - curr_seqno; if (diff < 0 || diff >= BATADV_TQ_LOCAL_WINDOW_SIZE) return 0; - else - return test_bit(diff, seq_bits) != 0; + return test_bit(diff, seq_bits) != 0; } /* turn corresponding bit on, so we can remember that we got the packet */ diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index a957c8140721..ac4b96eccade 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -69,7 +69,6 @@ static inline uint32_t batadv_choose_backbone_gw(const void *data, return hash % size; } - /* compares address and vid of two backbone gws */ static int batadv_compare_backbone_gw(const struct hlist_node *node, const void *data2) @@ -245,14 +244,14 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) spin_unlock_bh(list_lock); } - /* all claims gone, intialize CRC */ + /* all claims gone, initialize CRC */ backbone_gw->crc = BATADV_BLA_CRC_INIT; } /** * batadv_bla_send_claim - sends a claim frame according to the provided info * @bat_priv: the bat priv with all the soft interface information - * @orig: the mac address to be announced within the claim + * @mac: the mac address to be announced within the claim * @vid: the VLAN ID * @claimtype: the type of the claim (CLAIM, UNCLAIM, ANNOUNCE, ...) */ @@ -364,6 +363,7 @@ out: * @bat_priv: the bat priv with all the soft interface information * @orig: the mac address of the originator * @vid: the VLAN ID + * @own_backbone: set if the requested backbone is local * * searches for the backbone gw or creates a new one if it could not * be found. @@ -454,6 +454,7 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv, /** * batadv_bla_answer_request - answer a bla request by sending own claims * @bat_priv: the bat priv with all the soft interface information + * @primary_if: interface where the request came on * @vid: the vid where the request came on * * Repeat all of our own claims, and finally send an ANNOUNCE frame @@ -660,7 +661,6 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, if (unlikely(!backbone_gw)) return 1; - /* handle as ANNOUNCE frame */ backbone_gw->lasttime = jiffies; crc = ntohs(*((__be16 *)(&an_addr[4]))); @@ -775,6 +775,7 @@ static int batadv_handle_claim(struct batadv_priv *bat_priv, /** * batadv_check_claim_group * @bat_priv: the bat priv with all the soft interface information + * @primary_if: the primary interface of this batman interface * @hw_src: the Hardware source in the ARP Header * @hw_dst: the Hardware destination in the ARP Header * @ethhdr: pointer to the Ethernet header of the claim frame @@ -846,10 +847,10 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv, return 2; } - /** * batadv_bla_process_claim * @bat_priv: the bat priv with all the soft interface information + * @primary_if: the primary hard interface of this batman soft interface * @skb: the frame to be checked * * Check if this is a claim frame, and process it accordingly. @@ -1327,7 +1328,7 @@ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, goto out; } /* not found, add a new entry (overwrite the oldest entry) - * and allow it, its the first occurence. + * and allow it, its the first occurrence. */ curr = (bat_priv->bla.bcast_duplist_curr + BATADV_DUPLIST_SIZE - 1); curr %= BATADV_DUPLIST_SIZE; @@ -1343,8 +1344,6 @@ out: return ret; } - - /** * batadv_bla_is_backbone_gw_orig * @bat_priv: the bat priv with all the soft interface information @@ -1386,7 +1385,6 @@ bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig, return false; } - /** * batadv_bla_is_backbone_gw * @skb: the frame to be checked @@ -1476,7 +1474,6 @@ int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, if (!atomic_read(&bat_priv->bridge_loop_avoidance)) goto allow; - if (unlikely(atomic_read(&bat_priv->bla.num_requests))) /* don't allow broadcasts while requests are in flight */ if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index a12e25efaf6f..a4972874c056 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -233,7 +233,6 @@ static int batadv_debug_log_setup(struct batadv_priv *bat_priv) static void batadv_debug_log_cleanup(struct batadv_priv *bat_priv) { - return; } #endif @@ -405,6 +404,7 @@ struct batadv_debuginfo batadv_hardif_debuginfo_##_name = { \ .release = single_release, \ }, \ } + static BATADV_HARDIF_DEBUGINFO(originators, S_IRUGO, batadv_originators_hardif_open); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index b5981113c9a7..aad022dd15df 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1100,6 +1100,7 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, batadv_dat_send_data(bat_priv, skb, ip_src, BATADV_P_DAT_DHT_PUT); batadv_dat_send_data(bat_priv, skb, ip_dst, BATADV_P_DAT_DHT_PUT); } + /** * batadv_dat_snoop_incoming_arp_reply - snoop the ARP reply and fill the local * DAT storage only diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index d76e1d06c5b5..2fe0764c64be 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -25,9 +25,7 @@ #include <linux/if_arp.h> -/** - * BATADV_DAT_ADDR_MAX - maximum address value in the DHT space - */ +/* BATADV_DAT_ADDR_MAX - maximum address value in the DHT space */ #define BATADV_DAT_ADDR_MAX ((batadv_dat_addr_t)~(batadv_dat_addr_t)0) void batadv_dat_status_update(struct net_device *net_dev); diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 00f9e144cc97..3d1dcaa3e8b5 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -23,7 +23,6 @@ #include "hard-interface.h" #include "soft-interface.h" - /** * batadv_frag_clear_chain - delete entries in the fragment buffer chain * @head: head of chain with entries. diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index 5d7a0e66a22b..d848cf6676a2 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -41,8 +41,7 @@ batadv_frag_check_entry(struct batadv_frag_table_entry *frags_entry) if (!hlist_empty(&frags_entry->head) && batadv_has_timed_out(frags_entry->timestamp, BATADV_FRAG_TIMEOUT)) return true; - else - return false; + return false; } #endif /* _NET_BATMAN_ADV_FRAGMENTATION_H_ */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index e0bcf9e84273..27649e85f3f6 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -775,6 +775,7 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, return ret; } + /** * batadv_gw_out_of_range - check if the dhcp request destination is the best gw * @bat_priv: the bat priv with all the soft interface information diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index d1183e882167..12fc77bef23f 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -41,7 +41,6 @@ #include "network-coding.h" #include "fragmentation.h" - /* List manipulations on hardif_list have to be rtnl_lock()'ed, * list traversals just rcu-locked */ @@ -403,6 +402,9 @@ int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev, goto err_free; } + /* reset control block to avoid left overs from previous users */ + memset(skb->cb, 0, sizeof(struct batadv_skb_cb)); + /* all receive handlers return whether they received or reused * the supplied skb. if not, we have to free the skb. */ @@ -651,7 +653,7 @@ static struct batadv_tvlv_handler /** * batadv_tvlv_container_free_ref - decrement the tvlv container refcounter and * possibly free it - * @tvlv_handler: the tvlv container to free + * @tvlv: the tvlv container to free */ static void batadv_tvlv_container_free_ref(struct batadv_tvlv_container *tvlv) { @@ -796,11 +798,11 @@ void batadv_tvlv_container_register(struct batadv_priv *bat_priv, } /** - * batadv_tvlv_realloc_packet_buff - reallocate packet buffer to accomodate + * batadv_tvlv_realloc_packet_buff - reallocate packet buffer to accommodate * requested packet size * @packet_buff: packet buffer * @packet_buff_len: packet buffer size - * @packet_min_len: requested packet minimum size + * @min_packet_len: requested packet minimum size * @additional_packet_len: requested additional packet size on top of minimum * size * diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index a1fcd884f0b1..4d2318829a34 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2014.4.0" +#define BATADV_SOURCE_VERSION "2015.0" #endif /* B.A.T.M.A.N. parameters */ @@ -92,9 +92,8 @@ /* numbers of originator to contact for any PUT/GET DHT operation */ #define BATADV_DAT_CANDIDATES_NUM 3 -/** - * BATADV_TQ_SIMILARITY_THRESHOLD - TQ points that a secondary metric can differ - * at most from the primary one in order to be still considered acceptable +/* BATADV_TQ_SIMILARITY_THRESHOLD - TQ points that a secondary metric can differ + * at most from the primary one in order to be still considered acceptable */ #define BATADV_TQ_SIMILARITY_THRESHOLD 50 @@ -313,10 +312,10 @@ static inline bool batadv_has_timed_out(unsigned long timestamp, * - when adding 128 - it is neither a predecessor nor a successor, * - after adding more than 127 to the starting value - it is a successor */ -#define batadv_seq_before(x, y) ({typeof(x) _d1 = (x); \ - typeof(y) _d2 = (y); \ - typeof(x) _dummy = (_d1 - _d2); \ - (void) (&_d1 == &_d2); \ +#define batadv_seq_before(x, y) ({typeof(x)_d1 = (x); \ + typeof(y)_d2 = (y); \ + typeof(x)_dummy = (_d1 - _d2); \ + (void)(&_d1 == &_d2); \ _dummy > batadv_smallest_signed_int(_dummy); }) #define batadv_seq_after(x, y) batadv_seq_before(y, x) diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index ab6bb2af1d45..b24e4bb64fb5 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -685,11 +685,13 @@ static void batadv_mcast_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, if (orig_initialized) atomic_dec(&bat_priv->mcast.num_disabled); orig->capabilities |= BATADV_ORIG_CAPA_HAS_MCAST; - /* If mcast support is being switched off increase the disabled - * mcast node counter. + /* If mcast support is being switched off or if this is an initial + * OGM without mcast support then increase the disabled mcast + * node counter. */ } else if (!orig_mcast_enabled && - orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST) { + (orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST || + !orig_initialized)) { atomic_inc(&bat_priv->mcast.num_disabled); orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_MCAST; } @@ -738,7 +740,8 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig) { struct batadv_priv *bat_priv = orig->bat_priv; - if (!(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST)) + if (!(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST) && + orig->capa_initialized & BATADV_ORIG_CAPA_HAS_MCAST) atomic_dec(&bat_priv->mcast.num_disabled); batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS); diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 73b5d45819c1..3a44ebdb43cb 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -50,7 +50,6 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node); static inline void batadv_mcast_mla_update(struct batadv_priv *bat_priv) { - return; } static inline enum batadv_forw_mode @@ -67,12 +66,10 @@ static inline int batadv_mcast_init(struct batadv_priv *bat_priv) static inline void batadv_mcast_free(struct batadv_priv *bat_priv) { - return; } static inline void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node) { - return; } #endif /* CONFIG_BATMAN_ADV_MCAST */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 8d04d174669e..127cc4d7380a 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -133,7 +133,7 @@ int batadv_nc_mesh_init(struct batadv_priv *bat_priv) if (!bat_priv->nc.decoding_hash) goto err; - batadv_hash_set_lock_class(bat_priv->nc.coding_hash, + batadv_hash_set_lock_class(bat_priv->nc.decoding_hash, &batadv_nc_decoding_hash_lock_class_key); INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker); @@ -1212,8 +1212,7 @@ static bool batadv_nc_skb_coding_possible(struct sk_buff *skb, { if (BATADV_SKB_CB(skb)->decoded && !batadv_compare_eth(dst, src)) return false; - else - return true; + return true; } /** diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 6a484514cd3e..90e805aba379 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -570,9 +570,6 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) batadv_frag_purge_orig(orig_node, NULL); - batadv_tt_global_del_orig(orig_node->bat_priv, orig_node, -1, - "originator timed out"); - if (orig_node->bat_priv->bat_algo_ops->bat_orig_free) orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node); @@ -678,6 +675,7 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, atomic_set(&orig_node->last_ttvn, 0); orig_node->tt_buff = NULL; orig_node->tt_buff_len = 0; + orig_node->last_seen = jiffies; reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); orig_node->bcast_seqno_reset = reset_time; #ifdef CONFIG_BATMAN_ADV_MCAST @@ -799,7 +797,6 @@ batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv, return ifinfo_purged; } - /** * batadv_purge_orig_neighbors - purges neighbors from originator * @bat_priv: the bat priv with all the soft interface information @@ -977,6 +974,9 @@ static void _batadv_purge_orig(struct batadv_priv *bat_priv) if (batadv_purge_orig_node(bat_priv, orig_node)) { batadv_gw_node_delete(bat_priv, orig_node); hlist_del_rcu(&orig_node->hash_entry); + batadv_tt_global_del_orig(orig_node->bat_priv, + orig_node, -1, + "originator timed out"); batadv_orig_node_free_ref(orig_node); continue; } diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index db3a9ed734cb..aa4a43696295 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -70,7 +70,6 @@ batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node, unsigned short vid); void batadv_orig_node_vlan_free_ref(struct batadv_orig_node_vlan *orig_vlan); - /* hashfunction to choose an entry in a hash table of given size * hash algorithm from http://en.wikipedia.org/wiki/Hash_table */ diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 34e096d2dce1..b81fbbf21a63 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -198,6 +198,7 @@ struct batadv_bla_claim_dst { uint8_t type; /* bla_claimframe */ __be16 group; /* group id */ }; + #pragma pack() /** @@ -376,7 +377,7 @@ struct batadv_frag_packet { uint8_t reserved:4; uint8_t no:4; #else -#error "unknown bitfield endianess" +#error "unknown bitfield endianness" #endif uint8_t dest[ETH_ALEN]; uint8_t orig[ETH_ALEN]; @@ -452,7 +453,7 @@ struct batadv_coded_packet { * @src: address of the source * @dst: address of the destination * @tvlv_len: length of tvlv data following the unicast tvlv header - * @align: 2 bytes to align the header to a 4 byte boundry + * @align: 2 bytes to align the header to a 4 byte boundary */ struct batadv_unicast_tvlv_packet { uint8_t packet_type; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 35f76f2f7824..da83982bf974 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -292,7 +292,6 @@ out: return ret; } - int batadv_recv_icmp_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if) { @@ -443,11 +442,13 @@ batadv_find_router(struct batadv_priv *bat_priv, router = batadv_orig_router_get(orig_node, recv_if); + if (!router) + return router; + /* only consider bonding for recv_if == BATADV_IF_DEFAULT (first hop) * and if activated. */ - if (recv_if == BATADV_IF_DEFAULT || !atomic_read(&bat_priv->bonding) || - !router) + if (!(recv_if == BATADV_IF_DEFAULT && atomic_read(&bat_priv->bonding))) return router; /* bonding: loop through the list of possible routers found @@ -455,7 +456,7 @@ batadv_find_router(struct batadv_priv *bat_priv, * the last chosen bonding candidate (next_candidate). If no such * router is found, use the first candidate found (the previously * chosen bonding candidate might have been the last one in the list). - * If this can't be found either, return the previously choosen + * If this can't be found either, return the previously chosen * router - obviously there are no other candidates. */ rcu_read_lock(); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 5467955eb27c..5ec31d7de24f 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -36,7 +36,6 @@ #include "bridge_loop_avoidance.h" #include "network-coding.h" - 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); diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index f40cb0436eba..a75dc12f96f8 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -151,7 +151,6 @@ ssize_t batadv_show_##_name(struct kobject *kobj, \ static BATADV_ATTR(_name, _mode, batadv_show_##_name, \ batadv_store_##_name) - #define BATADV_ATTR_SIF_STORE_UINT(_name, _min, _max, _post_func) \ ssize_t batadv_store_##_name(struct kobject *kobj, \ struct attribute *attr, char *buff, \ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 5f59e7f899a0..07b263a437d1 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1780,7 +1780,6 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv, batadv_tt_global_del_roaming(bat_priv, tt_global_entry, orig_node, message); - out: if (tt_global_entry) batadv_tt_global_entry_free_ref(tt_global_entry); @@ -2769,9 +2768,8 @@ static bool batadv_send_tt_response(struct batadv_priv *bat_priv, { if (batadv_is_my_mac(bat_priv, req_dst)) return batadv_send_my_tt_response(bat_priv, tt_data, req_src); - else - return batadv_send_other_tt_response(bat_priv, tt_data, - req_src, req_dst); + return batadv_send_other_tt_response(bat_priv, tt_data, req_src, + req_dst); } static void _batadv_tt_update_changes(struct batadv_priv *bat_priv, @@ -2854,7 +2852,7 @@ static void batadv_tt_update_changes(struct batadv_priv *bat_priv, /** * batadv_is_my_client - check if a client is served by the local node * @bat_priv: the bat priv with all the soft interface information - * @addr: the mac adress of the client to check + * @addr: the mac address of the client to check * @vid: VLAN identifier * * Returns true if the client is served by this node, false otherwise. diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 8854c05622a9..9398c3fb4174 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -199,7 +199,6 @@ struct batadv_orig_bat_iv { /** * struct batadv_orig_node - structure for orig_list maintaining nodes of mesh * @orig: originator ethernet address - * @primary_addr: hosts primary interface address * @ifinfo_list: list for routers per outgoing interface * @last_bonding_candidate: pointer to last ifinfo of last used router * @batadv_dat_addr_t: address of the orig node in the distributed hash @@ -244,7 +243,6 @@ struct batadv_orig_bat_iv { */ struct batadv_orig_node { uint8_t orig[ETH_ALEN]; - uint8_t primary_addr[ETH_ALEN]; struct hlist_head ifinfo_list; struct batadv_orig_ifinfo *last_bonding_candidate; #ifdef CONFIG_BATMAN_ADV_DAT @@ -970,7 +968,7 @@ struct batadv_tt_orig_list_entry { }; /** - * struct batadv_tt_change_node - structure for tt changes occured + * struct batadv_tt_change_node - structure for tt changes occurred * @list: list node for batadv_priv_tt::changes_list * @change: holds the actual translation table diff data */ diff --git a/net/bridge/br.c b/net/bridge/br.c index 44425aff7cba..fb57ab6b24f9 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -19,6 +19,7 @@ #include <linux/llc.h> #include <net/llc.h> #include <net/stp.h> +#include <net/switchdev.h> #include "br_private.h" @@ -120,6 +121,48 @@ static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; +static int br_netdev_switch_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_switch_notifier_info_to_dev(ptr); + struct net_bridge_port *p; + struct net_bridge *br; + struct netdev_switch_notifier_fdb_info *fdb_info; + int err = NOTIFY_DONE; + + rtnl_lock(); + p = br_port_get_rtnl(dev); + if (!p) + goto out; + + br = p->br; + + switch (event) { + case NETDEV_SWITCH_FDB_ADD: + fdb_info = ptr; + err = br_fdb_external_learn_add(br, p, fdb_info->addr, + fdb_info->vid); + if (err) + err = notifier_from_errno(err); + break; + case NETDEV_SWITCH_FDB_DEL: + fdb_info = ptr; + err = br_fdb_external_learn_del(br, p, fdb_info->addr, + fdb_info->vid); + if (err) + err = notifier_from_errno(err); + break; + } + +out: + rtnl_unlock(); + return err; +} + +static struct notifier_block br_netdev_switch_notifier = { + .notifier_call = br_netdev_switch_event, +}; + static void __net_exit br_net_exit(struct net *net) { struct net_device *dev; @@ -169,10 +212,14 @@ static int __init br_init(void) if (err) goto err_out3; - err = br_netlink_init(); + err = register_netdev_switch_notifier(&br_netdev_switch_notifier); if (err) goto err_out4; + err = br_netlink_init(); + if (err) + goto err_out5; + brioctl_set(br_ioctl_deviceless_stub); #if IS_ENABLED(CONFIG_ATM_LANE) @@ -185,6 +232,8 @@ static int __init br_init(void) return 0; +err_out5: + unregister_netdev_switch_notifier(&br_netdev_switch_notifier); err_out4: unregister_netdevice_notifier(&br_device_notifier); err_out3: @@ -202,6 +251,7 @@ static void __exit br_deinit(void) { stp_proto_unregister(&br_stp_proto); br_netlink_fini(); + unregister_netdev_switch_notifier(&br_netdev_switch_notifier); unregister_netdevice_notifier(&br_device_notifier); brioctl_set(NULL); unregister_pernet_subsys(&br_net_ops); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index cc36e59db7d7..03667e65cc29 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -686,6 +686,9 @@ int br_fdb_dump(struct sk_buff *skb, if (!(dev->priv_flags & IFF_EBRIDGE)) goto out; + if (!filter_dev) + idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); + for (i = 0; i < BR_HASH_SIZE; i++) { struct net_bridge_fdb_entry *f; @@ -697,7 +700,7 @@ int br_fdb_dump(struct sk_buff *skb, (!f->dst || f->dst->dev != filter_dev)) { if (filter_dev != dev) goto skip; - /* !f->dst is a speacial case for bridge + /* !f->dst is a special case for bridge * It means the MAC belongs to the bridge * Therefore need a little more filtering * we only want to dump the !f->dst case @@ -705,6 +708,8 @@ int br_fdb_dump(struct sk_buff *skb, if (f->dst) goto skip; } + if (!filter_dev && f->dst) + goto skip; if (fdb_fill_info(skb, br, f, NETLINK_CB(cb->skb).portid, @@ -985,26 +990,14 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) } } -int br_fdb_external_learn_add(struct net_device *dev, +int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid) { - struct net_bridge_port *p; - struct net_bridge *br; struct hlist_head *head; struct net_bridge_fdb_entry *fdb; int err = 0; - rtnl_lock(); - - p = br_port_get_rtnl(dev); - if (!p) { - pr_info("bridge: %s not a bridge port\n", dev->name); - err = -EINVAL; - goto err_rtnl_unlock; - } - - br = p->br; - + ASSERT_RTNL(); spin_lock_bh(&br->hash_lock); head = &br->hash[br_mac_hash(addr, vid)]; @@ -1029,33 +1022,18 @@ int br_fdb_external_learn_add(struct net_device *dev, err_unlock: spin_unlock_bh(&br->hash_lock); -err_rtnl_unlock: - rtnl_unlock(); return err; } -EXPORT_SYMBOL(br_fdb_external_learn_add); -int br_fdb_external_learn_del(struct net_device *dev, +int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid) { - struct net_bridge_port *p; - struct net_bridge *br; struct hlist_head *head; struct net_bridge_fdb_entry *fdb; int err = 0; - rtnl_lock(); - - p = br_port_get_rtnl(dev); - if (!p) { - pr_info("bridge: %s not a bridge port\n", dev->name); - err = -EINVAL; - goto err_rtnl_unlock; - } - - br = p->br; - + ASSERT_RTNL(); spin_lock_bh(&br->hash_lock); head = &br->hash[br_mac_hash(addr, vid)]; @@ -1066,9 +1044,6 @@ int br_fdb_external_learn_del(struct net_device *dev, err = -ENOENT; spin_unlock_bh(&br->hash_lock); -err_rtnl_unlock: - rtnl_unlock(); return err; } -EXPORT_SYMBOL(br_fdb_external_learn_del); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index ed307db7a12b..81e49fb73169 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -424,6 +424,7 @@ netdev_features_t br_features_recompute(struct net_bridge *br, features = netdev_increment_features(features, p->dev->features, mask); } + features = netdev_add_tso_features(features, mask); return features; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 1f1de715197c..e2aa7be3a847 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -154,7 +154,8 @@ int br_handle_frame_finish(struct sk_buff *skb) dst = NULL; if (is_broadcast_ether_addr(dest)) { - if (p->flags & BR_PROXYARP && + if (IS_ENABLED(CONFIG_INET) && + p->flags & BR_PROXYARP && skb->protocol == htons(ETH_P_ARP)) br_do_proxy_arp(skb, br, vid); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 5df05269d17a..fed61c971b17 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -276,7 +276,7 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, struct net_device *dev; int err; - err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY, NULL); + err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY_MAX, NULL); if (err < 0) return err; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index c190d22b6b3d..65728e0dc4ff 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -66,17 +66,17 @@ static int brnf_pass_vlan_indev __read_mostly = 0; #endif #define IS_IP(skb) \ - (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IP)) + (!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IP)) #define IS_IPV6(skb) \ - (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6)) + (!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6)) #define IS_ARP(skb) \ - (!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_ARP)) + (!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_ARP)) static inline __be16 vlan_proto(const struct sk_buff *skb) { - if (vlan_tx_tag_present(skb)) + if (skb_vlan_tag_present(skb)) return skb->protocol; else if (skb->protocol == htons(ETH_P_8021Q)) return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; @@ -436,11 +436,11 @@ static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct struct net_device *vlan, *br; br = bridge_parent(dev); - if (brnf_pass_vlan_indev == 0 || !vlan_tx_tag_present(skb)) + if (brnf_pass_vlan_indev == 0 || !skb_vlan_tag_present(skb)) return br; vlan = __vlan_find_dev_deep_rcu(br, skb->vlan_proto, - vlan_tx_tag_get(skb) & VLAN_VID_MASK); + skb_vlan_tag_get(skb) & VLAN_VID_MASK); return vlan ? vlan : br; } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 9f5eb55a4d3a..163950b10d8c 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -67,6 +67,120 @@ static int br_port_fill_attrs(struct sk_buff *skb, return 0; } +static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start, + u16 vid_end, u16 flags) +{ + struct bridge_vlan_info vinfo; + + if ((vid_end - vid_start) > 0) { + /* add range to skb */ + vinfo.vid = vid_start; + vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_BEGIN; + if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, + sizeof(vinfo), &vinfo)) + goto nla_put_failure; + + vinfo.flags &= ~BRIDGE_VLAN_INFO_RANGE_BEGIN; + + vinfo.vid = vid_end; + vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END; + if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, + sizeof(vinfo), &vinfo)) + goto nla_put_failure; + } else { + vinfo.vid = vid_start; + vinfo.flags = flags; + if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, + sizeof(vinfo), &vinfo)) + goto nla_put_failure; + } + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, + const struct net_port_vlans *pv) +{ + u16 vid_range_start = 0, vid_range_end = 0; + u16 vid_range_flags = 0; + u16 pvid, vid, flags; + int err = 0; + + /* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan + * and mark vlan info with begin and end flags + * if vlaninfo represents a range + */ + pvid = br_get_pvid(pv); + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + flags = 0; + if (vid == pvid) + flags |= BRIDGE_VLAN_INFO_PVID; + + if (test_bit(vid, pv->untagged_bitmap)) + flags |= BRIDGE_VLAN_INFO_UNTAGGED; + + if (vid_range_start == 0) { + goto initvars; + } else if ((vid - vid_range_end) == 1 && + flags == vid_range_flags) { + vid_range_end = vid; + continue; + } else { + err = br_fill_ifvlaninfo_range(skb, vid_range_start, + vid_range_end, + vid_range_flags); + if (err) + return err; + } + +initvars: + vid_range_start = vid; + vid_range_end = vid; + vid_range_flags = flags; + } + + if (vid_range_start != 0) { + /* Call it once more to send any left over vlans */ + err = br_fill_ifvlaninfo_range(skb, vid_range_start, + vid_range_end, + vid_range_flags); + if (err) + return err; + } + + return 0; +} + +static int br_fill_ifvlaninfo(struct sk_buff *skb, + const struct net_port_vlans *pv) +{ + struct bridge_vlan_info vinfo; + u16 pvid, vid; + + pvid = br_get_pvid(pv); + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + vinfo.vid = vid; + vinfo.flags = 0; + if (vid == pvid) + vinfo.flags |= BRIDGE_VLAN_INFO_PVID; + + if (test_bit(vid, pv->untagged_bitmap)) + vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; + + if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, + sizeof(vinfo), &vinfo)) + goto nla_put_failure; + } + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + /* * Create one netlink message for one interface * Contains port and master info as well as carrier and bridge state. @@ -121,12 +235,11 @@ static int br_fill_ifinfo(struct sk_buff *skb, } /* Check if the VID information is requested */ - if (filter_mask & RTEXT_FILTER_BRVLAN) { - struct nlattr *af; + if ((filter_mask & RTEXT_FILTER_BRVLAN) || + (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { const struct net_port_vlans *pv; - struct bridge_vlan_info vinfo; - u16 vid; - u16 pvid; + struct nlattr *af; + int err; if (port) pv = nbp_get_vlan_info(port); @@ -140,21 +253,12 @@ static int br_fill_ifinfo(struct sk_buff *skb, if (!af) goto nla_put_failure; - pvid = br_get_pvid(pv); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - vinfo.vid = vid; - vinfo.flags = 0; - if (vid == pvid) - vinfo.flags |= BRIDGE_VLAN_INFO_PVID; - - if (test_bit(vid, pv->untagged_bitmap)) - vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; - - if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, - sizeof(vinfo), &vinfo)) - goto nla_put_failure; - } - + if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) + err = br_fill_ifvlaninfo_compressed(skb, pv); + else + err = br_fill_ifvlaninfo(skb, pv); + if (err) + goto nla_put_failure; nla_nest_end(skb, af); } @@ -209,7 +313,8 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, int err = 0; struct net_bridge_port *port = br_port_get_rtnl(dev); - if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN)) + if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) && + !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) goto out; err = br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI, @@ -218,57 +323,89 @@ out: return err; } -static const struct nla_policy ifla_br_policy[IFLA_MAX+1] = { - [IFLA_BRIDGE_FLAGS] = { .type = NLA_U16 }, - [IFLA_BRIDGE_MODE] = { .type = NLA_U16 }, - [IFLA_BRIDGE_VLAN_INFO] = { .type = NLA_BINARY, - .len = sizeof(struct bridge_vlan_info), }, -}; +static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, + int cmd, struct bridge_vlan_info *vinfo) +{ + int err = 0; + + switch (cmd) { + case RTM_SETLINK: + if (p) { + err = nbp_vlan_add(p, vinfo->vid, vinfo->flags); + if (err) + break; + + if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) + err = br_vlan_add(p->br, vinfo->vid, + vinfo->flags); + } else { + err = br_vlan_add(br, vinfo->vid, vinfo->flags); + } + break; + + case RTM_DELLINK: + if (p) { + nbp_vlan_delete(p, vinfo->vid); + if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) + br_vlan_delete(p->br, vinfo->vid); + } else { + br_vlan_delete(br, vinfo->vid); + } + break; + } + + return err; +} static int br_afspec(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *af_spec, int cmd) { - struct nlattr *tb[IFLA_BRIDGE_MAX+1]; + struct bridge_vlan_info *vinfo_start = NULL; + struct bridge_vlan_info *vinfo = NULL; + struct nlattr *attr; int err = 0; + int rem; - err = nla_parse_nested(tb, IFLA_BRIDGE_MAX, af_spec, ifla_br_policy); - if (err) - return err; + nla_for_each_nested(attr, af_spec, rem) { + if (nla_type(attr) != IFLA_BRIDGE_VLAN_INFO) + continue; + if (nla_len(attr) != sizeof(struct bridge_vlan_info)) + return -EINVAL; + vinfo = nla_data(attr); + if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { + if (vinfo_start) + return -EINVAL; + vinfo_start = vinfo; + continue; + } - if (tb[IFLA_BRIDGE_VLAN_INFO]) { - struct bridge_vlan_info *vinfo; + if (vinfo_start) { + struct bridge_vlan_info tmp_vinfo; + int v; - vinfo = nla_data(tb[IFLA_BRIDGE_VLAN_INFO]); + if (!(vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END)) + return -EINVAL; - if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK) - return -EINVAL; + if (vinfo->vid <= vinfo_start->vid) + return -EINVAL; + + memcpy(&tmp_vinfo, vinfo_start, + sizeof(struct bridge_vlan_info)); - switch (cmd) { - case RTM_SETLINK: - if (p) { - err = nbp_vlan_add(p, vinfo->vid, vinfo->flags); + for (v = vinfo_start->vid; v <= vinfo->vid; v++) { + tmp_vinfo.vid = v; + err = br_vlan_info(br, p, cmd, &tmp_vinfo); if (err) break; - - if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) - err = br_vlan_add(p->br, vinfo->vid, - vinfo->flags); - } else - err = br_vlan_add(br, vinfo->vid, vinfo->flags); - - break; - - case RTM_DELLINK: - if (p) { - nbp_vlan_delete(p, vinfo->vid); - if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) - br_vlan_delete(p->br, vinfo->vid); - } else - br_vlan_delete(br, vinfo->vid); - break; + } + vinfo_start = NULL; + } else { + err = br_vlan_info(br, p, cmd, vinfo); } + if (err) + break; } return err; @@ -432,6 +569,11 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh) err = br_afspec((struct net_bridge *)netdev_priv(dev), p, afspec, RTM_DELLINK); + if (err == 0) + /* Send RTM_NEWLINK because userspace + * expects RTM_NEWLINK for vlan dels + */ + br_ifinfo_notify(RTM_NEWLINK, p); return err; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index aea3d1339b3f..e8e3f3681680 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -402,6 +402,10 @@ int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *fdev, int idx); int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); +int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, + const unsigned char *addr, u16 vid); +int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, + const unsigned char *addr, u16 vid); /* br_forward.c */ void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb); @@ -628,8 +632,8 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid) { int err = 0; - if (vlan_tx_tag_present(skb)) - *vid = vlan_tx_tag_get(skb) & VLAN_VID_MASK; + if (skb_vlan_tag_present(skb)) + *vid = skb_vlan_tag_get(skb) & VLAN_VID_MASK; else { *vid = 0; err = -EINVAL; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 97b8ddf57363..13013fe8db24 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -187,7 +187,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, * sent from vlan device on the bridge device, it does not have * HW accelerated vlan tag. */ - if (unlikely(!vlan_tx_tag_present(skb) && + if (unlikely(!skb_vlan_tag_present(skb) && skb->protocol == proto)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) @@ -200,7 +200,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, /* Protocol-mismatch, empty out vlan_tci for new tag */ skb_push(skb, ETH_HLEN); skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, - vlan_tx_tag_get(skb)); + skb_vlan_tag_get(skb)); if (unlikely(!skb)) return false; diff --git a/net/bridge/netfilter/ebt_vlan.c b/net/bridge/netfilter/ebt_vlan.c index 8d3f8c7651f0..618568888128 100644 --- a/net/bridge/netfilter/ebt_vlan.c +++ b/net/bridge/netfilter/ebt_vlan.c @@ -45,8 +45,8 @@ ebt_vlan_mt(const struct sk_buff *skb, struct xt_action_param *par) /* VLAN encapsulated Type/Length field, given from orig frame */ __be16 encap; - if (vlan_tx_tag_present(skb)) { - TCI = vlan_tx_tag_get(skb); + if (skb_vlan_tag_present(skb)) { + TCI = skb_vlan_tag_get(skb); encap = skb->protocol; } else { const struct vlan_hdr *fp; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index d9a8c05d995d..91180a7fc943 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -133,7 +133,7 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb, __be16 ethproto; int verdict, i; - if (vlan_tx_tag_present(skb)) + if (skb_vlan_tag_present(skb)) ethproto = htons(ETH_P_8021Q); else ethproto = h->h_proto; diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 15845814a0f2..ba6eb17226da 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -676,7 +676,7 @@ static int calcu_signature(struct ceph_x_authorizer *au, int ret; char tmp_enc[40]; __le32 tmp[5] = { - 16u, msg->hdr.crc, msg->footer.front_crc, + cpu_to_le32(16), msg->hdr.crc, msg->footer.front_crc, msg->footer.middle_crc, msg->footer.data_crc, }; ret = ceph_x_encrypt(&au->session_key, &tmp, sizeof(tmp), diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index a83062ceeec9..f2148e22b148 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -717,7 +717,7 @@ static int get_poolop_reply_buf(const char *src, size_t src_len, if (src_len != sizeof(u32) + dst_len) return -EINVAL; - buf_len = le32_to_cpu(*(u32 *)src); + buf_len = le32_to_cpu(*(__le32 *)src); if (buf_len != dst_len) return -EINVAL; diff --git a/net/core/dev.c b/net/core/dev.c index 683d493aa1bf..1e325adc4367 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2578,7 +2578,7 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) if (skb->encapsulation) features &= dev->hw_enc_features; - if (!vlan_tx_tag_present(skb)) { + if (!skb_vlan_tag_present(skb)) { if (unlikely(protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; @@ -2659,7 +2659,7 @@ out: static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) { - if (vlan_tx_tag_present(skb) && + if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) skb = __vlan_hwaccel_push_inside(skb); return skb; @@ -3676,7 +3676,7 @@ ncls: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; - if (vlan_tx_tag_present(skb)) { + if (skb_vlan_tag_present(skb)) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; @@ -3708,8 +3708,8 @@ ncls: } } - if (unlikely(vlan_tx_tag_present(skb))) { - if (vlan_tx_tag_get_id(skb)) + if (unlikely(skb_vlan_tag_present(skb))) { + if (skb_vlan_tag_get_id(skb)) skb->pkt_type = PACKET_OTHERHOST; /* Note: we might in the future use prio bits * and set skb->priority like in vlan_do_receive() @@ -6172,13 +6172,16 @@ static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; struct netdev_rx_queue *rx; + size_t sz = count * sizeof(*rx); BUG_ON(count < 1); - rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL); - if (!rx) - return -ENOMEM; - + rx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + if (!rx) { + rx = vzalloc(sz); + if (!rx) + return -ENOMEM; + } dev->_rx = rx; for (i = 0; i < count; i++) @@ -6808,7 +6811,7 @@ void free_netdev(struct net_device *dev) netif_free_tx_queues(dev); #ifdef CONFIG_SYSFS - kfree(dev->_rx); + kvfree(dev->_rx); #endif kfree(rcu_dereference_protected(dev->ingress_queue, 1)); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 550892cd6b3f..91f74f3eb204 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1597,20 +1597,31 @@ static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) return err; } +static int __ethtool_get_module_info(struct net_device *dev, + struct ethtool_modinfo *modinfo) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct phy_device *phydev = dev->phydev; + + if (phydev && phydev->drv && phydev->drv->module_info) + return phydev->drv->module_info(phydev, modinfo); + + if (ops->get_module_info) + return ops->get_module_info(dev, modinfo); + + return -EOPNOTSUPP; +} + static int ethtool_get_module_info(struct net_device *dev, void __user *useraddr) { int ret; struct ethtool_modinfo modinfo; - const struct ethtool_ops *ops = dev->ethtool_ops; - - if (!ops->get_module_info) - return -EOPNOTSUPP; if (copy_from_user(&modinfo, useraddr, sizeof(modinfo))) return -EFAULT; - ret = ops->get_module_info(dev, &modinfo); + ret = __ethtool_get_module_info(dev, &modinfo); if (ret) return ret; @@ -1620,21 +1631,33 @@ static int ethtool_get_module_info(struct net_device *dev, return 0; } +static int __ethtool_get_module_eeprom(struct net_device *dev, + struct ethtool_eeprom *ee, u8 *data) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct phy_device *phydev = dev->phydev; + + if (phydev && phydev->drv && phydev->drv->module_eeprom) + return phydev->drv->module_eeprom(phydev, ee, data); + + if (ops->get_module_eeprom) + return ops->get_module_eeprom(dev, ee, data); + + return -EOPNOTSUPP; +} + static int ethtool_get_module_eeprom(struct net_device *dev, void __user *useraddr) { int ret; struct ethtool_modinfo modinfo; - const struct ethtool_ops *ops = dev->ethtool_ops; - - if (!ops->get_module_info || !ops->get_module_eeprom) - return -EOPNOTSUPP; - ret = ops->get_module_info(dev, &modinfo); + ret = __ethtool_get_module_info(dev, &modinfo); if (ret) return ret; - return ethtool_get_any_eeprom(dev, useraddr, ops->get_module_eeprom, + return ethtool_get_any_eeprom(dev, useraddr, + __ethtool_get_module_eeprom, modinfo.eeprom_len); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8e38f17288d3..8d614c93f86a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2043,6 +2043,12 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh) case NDTPA_BASE_REACHABLE_TIME: NEIGH_VAR_SET(p, BASE_REACHABLE_TIME, nla_get_msecs(tbp[i])); + /* update reachable_time as well, otherwise, the change will + * only be effective after the next time neigh_periodic_work + * decides to recompute it (can be multiple minutes) + */ + p->reachable_time = + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); break; case NDTPA_GC_STALETIME: NEIGH_VAR_SET(p, GC_STALETIME, @@ -2921,6 +2927,31 @@ static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write, return ret; } +static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + struct neigh_parms *p = ctl->extra2; + int ret; + + if (strcmp(ctl->procname, "base_reachable_time") == 0) + ret = neigh_proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); + else if (strcmp(ctl->procname, "base_reachable_time_ms") == 0) + ret = neigh_proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); + else + ret = -1; + + if (write && ret == 0) { + /* update reachable_time as well, otherwise, the change will + * only be effective after the next time neigh_periodic_work + * decides to recompute it + */ + p->reachable_time = + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); + } + return ret; +} + #define NEIGH_PARMS_DATA_OFFSET(index) \ (&((struct neigh_parms *) 0)->data[index]) @@ -3047,6 +3078,19 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler; /* ReachableTime (in milliseconds) */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler; + } else { + /* Those handlers will update p->reachable_time after + * base_reachable_time(_ms) is set to ensure the new timer starts being + * applied after the next neighbour update instead of waiting for + * neigh_periodic_work to update its value (can be multiple minutes) + * So any handler that replaces them should do this as well + */ + /* ReachableTime */ + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = + neigh_proc_base_reachable_time; + /* ReachableTime (in milliseconds) */ + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = + neigh_proc_base_reachable_time; } /* Don't export sysctls to unprivileged users */ diff --git a/net/core/netpoll.c b/net/core/netpoll.c index e0ad5d16c9c5..c126a878c47c 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -77,7 +77,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev, features = netif_skb_features(skb); - if (vlan_tx_tag_present(skb) && + if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) { skb = __vlan_hwaccel_push_inside(skb); if (unlikely(!skb)) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9cf6fe9ddc0c..eadc5c0e2dfa 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -50,6 +50,7 @@ #include <net/arp.h> #include <net/route.h> #include <net/udp.h> +#include <net/tcp.h> #include <net/sock.h> #include <net/pkt_sched.h> #include <net/fib_rules.h> @@ -669,9 +670,19 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) for (i = 0; i < RTAX_MAX; i++) { if (metrics[i]) { + if (i == RTAX_CC_ALGO - 1) { + char tmp[TCP_CA_NAME_MAX], *name; + + name = tcp_ca_get_name_by_key(metrics[i], tmp); + if (!name) + continue; + if (nla_put_string(skb, i + 1, name)) + goto nla_put_failure; + } else { + if (nla_put_u32(skb, i + 1, metrics[i])) + goto nla_put_failure; + } valid++; - if (nla_put_u32(skb, i+1, metrics[i])) - goto nla_put_failure; } } @@ -2698,10 +2709,11 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) idx); } - idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); if (dev->netdev_ops->ndo_fdb_dump) - idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, bdev, dev, + idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL, idx); + else + idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); cops = NULL; } @@ -2868,32 +2880,24 @@ static inline size_t bridge_nlmsg_size(void) + nla_total_size(sizeof(u16)); /* IFLA_BRIDGE_MODE */ } -static int rtnl_bridge_notify(struct net_device *dev, u16 flags) +static int rtnl_bridge_notify(struct net_device *dev) { struct net *net = dev_net(dev); - struct net_device *br_dev = netdev_master_upper_dev_get(dev); struct sk_buff *skb; int err = -EOPNOTSUPP; + if (!dev->netdev_ops->ndo_bridge_getlink) + return 0; + skb = nlmsg_new(bridge_nlmsg_size(), GFP_ATOMIC); if (!skb) { err = -ENOMEM; goto errout; } - if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) && - br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { - err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); - if (err < 0) - goto errout; - } - - if ((flags & BRIDGE_FLAGS_SELF) && - dev->netdev_ops->ndo_bridge_getlink) { - err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); - if (err < 0) - goto errout; - } + err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); + if (err < 0) + goto errout; rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0; @@ -2963,16 +2967,18 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) err = -EOPNOTSUPP; else err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh); - - if (!err) + if (!err) { flags &= ~BRIDGE_FLAGS_SELF; + + /* Generate event to notify upper layer of bridge + * change + */ + err = rtnl_bridge_notify(dev); + } } if (have_flags) memcpy(nla_data(attr), &flags, sizeof(flags)); - /* Generate event to notify upper layer of bridge change */ - if (!err) - err = rtnl_bridge_notify(dev, oflags); out: return err; } @@ -3037,15 +3043,18 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) else err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh); - if (!err) + if (!err) { flags &= ~BRIDGE_FLAGS_SELF; + + /* Generate event to notify upper layer of bridge + * change + */ + err = rtnl_bridge_notify(dev); + } } if (have_flags) memcpy(nla_data(attr), &flags, sizeof(flags)); - /* Generate event to notify upper layer of bridge change */ - if (!err) - err = rtnl_bridge_notify(dev, oflags); out: return err; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5a2a2e887a12..56db472e9b86 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4197,7 +4197,7 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb) struct vlan_hdr *vhdr; u16 vlan_tci; - if (unlikely(vlan_tx_tag_present(skb))) { + if (unlikely(skb_vlan_tag_present(skb))) { /* vlan_tci is already set-up so leave this for another time */ return skb; } @@ -4283,7 +4283,7 @@ int skb_vlan_pop(struct sk_buff *skb) __be16 vlan_proto; int err; - if (likely(vlan_tx_tag_present(skb))) { + if (likely(skb_vlan_tag_present(skb))) { skb->vlan_tci = 0; } else { if (unlikely((skb->protocol != htons(ETH_P_8021Q) && @@ -4313,7 +4313,7 @@ EXPORT_SYMBOL(skb_vlan_pop); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { - if (vlan_tx_tag_present(skb)) { + if (skb_vlan_tag_present(skb)) { unsigned int offset = skb->data - skb_mac_header(skb); int err; @@ -4323,7 +4323,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) */ __skb_push(skb, offset); err = __vlan_insert_tag(skb, skb->vlan_proto, - vlan_tx_tag_get(skb)); + skb_vlan_tag_get(skb)); if (err) return err; skb->protocol = skb->vlan_proto; diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index d332aefb0846..df4803437888 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -298,7 +298,8 @@ struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct nlattr *att int type = nla_type(attr); if (type) { - if (type > RTAX_MAX || nla_len(attr) < 4) + if (type > RTAX_MAX || type == RTAX_CC_ALGO || + nla_len(attr) < 4) goto err_inval; fi->fib_metrics[type-1] = nla_get_u32(attr); diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 86e3807052e9..3f19fcbf126d 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -29,6 +29,7 @@ #include <linux/route.h> /* RTF_xxx */ #include <net/neighbour.h> #include <net/netlink.h> +#include <net/tcp.h> #include <net/dst.h> #include <net/flow.h> #include <net/fib_rules.h> @@ -273,7 +274,8 @@ static inline size_t dn_fib_nlmsg_size(struct dn_fib_info *fi) size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(2) /* RTA_DST */ - + nla_total_size(4); /* RTA_PRIORITY */ + + nla_total_size(4) /* RTA_PRIORITY */ + + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */ /* space for nested metrics */ payload += nla_total_size((RTAX_MAX * nla_total_size(4))); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f99f41bd15b8..d2b7b5521b1b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -360,7 +360,8 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi) + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(4) /* RTA_DST */ + nla_total_size(4) /* RTA_PRIORITY */ - + nla_total_size(4); /* RTA_PREFSRC */ + + nla_total_size(4) /* RTA_PREFSRC */ + + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */ /* space for nested metrics */ payload += nla_total_size((RTAX_MAX * nla_total_size(4))); @@ -859,7 +860,16 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (type > RTAX_MAX) goto err_inval; - val = nla_get_u32(nla); + if (type == RTAX_CC_ALGO) { + char tmp[TCP_CA_NAME_MAX]; + + nla_strlcpy(tmp, nla, sizeof(tmp)); + val = tcp_ca_get_key_by_name(tmp); + if (val == TCP_CA_UNSPEC) + goto err_inval; + } else { + val = nla_get_u32(nla); + } if (type == RTAX_ADVMSS && val > 65535 - 40) val = 65535 - 40; if (type == RTAX_MTU && val > 65535 - 15) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index b986298a7ba3..3bc0cf07661c 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -174,7 +174,8 @@ drop: } static struct sk_buff **fou_gro_receive(struct sk_buff **head, - struct sk_buff *skb) + struct sk_buff *skb, + struct udp_offload *uoff) { const struct net_offload *ops; struct sk_buff **pp = NULL; @@ -195,7 +196,8 @@ out_unlock: return pp; } -static int fou_gro_complete(struct sk_buff *skb, int nhoff) +static int fou_gro_complete(struct sk_buff *skb, int nhoff, + struct udp_offload *uoff) { const struct net_offload *ops; u8 proto = NAPI_GRO_CB(skb)->proto; @@ -254,7 +256,8 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, } static struct sk_buff **gue_gro_receive(struct sk_buff **head, - struct sk_buff *skb) + struct sk_buff *skb, + struct udp_offload *uoff) { const struct net_offload **offloads; const struct net_offload *ops; @@ -360,7 +363,8 @@ out: return pp; } -static int gue_gro_complete(struct sk_buff *skb, int nhoff) +static int gue_gro_complete(struct sk_buff *skb, int nhoff, + struct udp_offload *uoff) { const struct net_offload **offloads; struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff); @@ -490,7 +494,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg, sk->sk_user_data = fou; fou->sock = sock; - udp_set_convert_csum(sk, true); + inet_inc_convert_csum(sk); sk->sk_allocation = GFP_ATOMIC; diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c index 19e256e1dd92..9568594ca2f1 100644 --- a/net/ipv4/geneve.c +++ b/net/ipv4/geneve.c @@ -17,7 +17,7 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/skbuff.h> -#include <linux/rculist.h> +#include <linux/list.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/ip.h> @@ -26,8 +26,8 @@ #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> -#include <linux/hash.h> #include <linux/ethtool.h> +#include <linux/mutex.h> #include <net/arp.h> #include <net/ndisc.h> #include <net/ip.h> @@ -50,38 +50,30 @@ #include <net/ip6_checksum.h> #endif -#define PORT_HASH_BITS 8 -#define PORT_HASH_SIZE (1<<PORT_HASH_BITS) +/* Protects sock_list and refcounts. */ +static DEFINE_MUTEX(geneve_mutex); /* per-network namespace private data for this module */ struct geneve_net { - struct hlist_head sock_list[PORT_HASH_SIZE]; - spinlock_t sock_lock; /* Protects sock_list */ + struct list_head sock_list; }; static int geneve_net_id; -static struct workqueue_struct *geneve_wq; - static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) { return (struct genevehdr *)(udp_hdr(skb) + 1); } -static struct hlist_head *gs_head(struct net *net, __be16 port) +static struct geneve_sock *geneve_find_sock(struct net *net, + sa_family_t family, __be16 port) { struct geneve_net *gn = net_generic(net, geneve_net_id); - - return &gn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)]; -} - -/* Find geneve socket based on network namespace and UDP port */ -static struct geneve_sock *geneve_find_sock(struct net *net, __be16 port) -{ struct geneve_sock *gs; - hlist_for_each_entry_rcu(gs, gs_head(net, port), hlist) { - if (inet_sk(gs->sock->sk)->inet_sport == port) + list_for_each_entry(gs, &gn->sock_list, list) { + if (inet_sk(gs->sock->sk)->inet_sport == port && + inet_sk(gs->sock->sk)->sk.sk_family == family) return gs; } @@ -127,7 +119,7 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt, min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr) - + (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0); + + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); err = skb_cow_head(skb, min_headroom); if (unlikely(err)) { @@ -155,7 +147,8 @@ static int geneve_hlen(struct genevehdr *gh) } static struct sk_buff **geneve_gro_receive(struct sk_buff **head, - struct sk_buff *skb) + struct sk_buff *skb, + struct udp_offload *uoff) { struct sk_buff *p, **pp = NULL; struct genevehdr *gh, *gh2; @@ -219,7 +212,8 @@ out: return pp; } -static int geneve_gro_complete(struct sk_buff *skb, int nhoff) +static int geneve_gro_complete(struct sk_buff *skb, int nhoff, + struct udp_offload *uoff) { struct genevehdr *gh; struct packet_offload *ptype; @@ -307,15 +301,6 @@ error: return 1; } -static void geneve_del_work(struct work_struct *work) -{ - struct geneve_sock *gs = container_of(work, struct geneve_sock, - del_work); - - udp_tunnel_sock_release(gs->sock); - kfree_rcu(gs, rcu); -} - static struct socket *geneve_create_sock(struct net *net, bool ipv6, __be16 port) { @@ -356,8 +341,6 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, if (!gs) return ERR_PTR(-ENOMEM); - INIT_WORK(&gs->del_work, geneve_del_work); - sock = geneve_create_sock(net, ipv6, port); if (IS_ERR(sock)) { kfree(gs); @@ -365,7 +348,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, } gs->sock = sock; - atomic_set(&gs->refcnt, 1); + gs->refcnt = 1; gs->rcv = rcv; gs->rcv_data = data; @@ -373,11 +356,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, gs->udp_offloads.port = port; gs->udp_offloads.callbacks.gro_receive = geneve_gro_receive; gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete; - - spin_lock(&gn->sock_lock); - hlist_add_head_rcu(&gs->hlist, gs_head(net, port)); geneve_notify_add_rx_port(gs); - spin_unlock(&gn->sock_lock); /* Mark socket as an encapsulation socket */ tunnel_cfg.sk_user_data = gs; @@ -386,6 +365,8 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, tunnel_cfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, sock, &tunnel_cfg); + list_add(&gs->list, &gn->sock_list); + return gs; } @@ -393,25 +374,21 @@ struct geneve_sock *geneve_sock_add(struct net *net, __be16 port, geneve_rcv_t *rcv, void *data, bool no_share, bool ipv6) { - struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; - gs = geneve_socket_create(net, port, rcv, data, ipv6); - if (!IS_ERR(gs)) - return gs; - - if (no_share) /* Return error if sharing is not allowed. */ - return ERR_PTR(-EINVAL); + mutex_lock(&geneve_mutex); - spin_lock(&gn->sock_lock); - gs = geneve_find_sock(net, port); - if (gs && ((gs->rcv != rcv) || - !atomic_add_unless(&gs->refcnt, 1, 0))) + gs = geneve_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port); + if (gs) { + if (!no_share && gs->rcv == rcv) + gs->refcnt++; + else gs = ERR_PTR(-EBUSY); - spin_unlock(&gn->sock_lock); + } else { + gs = geneve_socket_create(net, port, rcv, data, ipv6); + } - if (!gs) - gs = ERR_PTR(-EINVAL); + mutex_unlock(&geneve_mutex); return gs; } @@ -419,37 +396,32 @@ EXPORT_SYMBOL_GPL(geneve_sock_add); void geneve_sock_release(struct geneve_sock *gs) { - struct net *net = sock_net(gs->sock->sk); - struct geneve_net *gn = net_generic(net, geneve_net_id); + mutex_lock(&geneve_mutex); - if (!atomic_dec_and_test(&gs->refcnt)) - return; + if (--gs->refcnt) + goto unlock; - spin_lock(&gn->sock_lock); - hlist_del_rcu(&gs->hlist); + list_del(&gs->list); geneve_notify_del_rx_port(gs); - spin_unlock(&gn->sock_lock); + udp_tunnel_sock_release(gs->sock); + kfree_rcu(gs, rcu); - queue_work(geneve_wq, &gs->del_work); +unlock: + mutex_unlock(&geneve_mutex); } EXPORT_SYMBOL_GPL(geneve_sock_release); static __net_init int geneve_init_net(struct net *net) { struct geneve_net *gn = net_generic(net, geneve_net_id); - unsigned int h; - spin_lock_init(&gn->sock_lock); - - for (h = 0; h < PORT_HASH_SIZE; ++h) - INIT_HLIST_HEAD(&gn->sock_list[h]); + INIT_LIST_HEAD(&gn->sock_list); return 0; } static struct pernet_operations geneve_net_ops = { .init = geneve_init_net, - .exit = NULL, .id = &geneve_net_id, .size = sizeof(struct geneve_net), }; @@ -458,10 +430,6 @@ static int __init geneve_init_module(void) { int rc; - geneve_wq = alloc_workqueue("geneve", 0, 0); - if (!geneve_wq) - return -ENOMEM; - rc = register_pernet_subsys(&geneve_net_ops); if (rc) return rc; @@ -470,11 +438,10 @@ static int __init geneve_init_module(void) return 0; } -late_initcall(geneve_init_module); +module_init(geneve_init_module); static void __exit geneve_cleanup_module(void) { - destroy_workqueue(geneve_wq); unregister_pernet_subsys(&geneve_net_ops); } module_exit(geneve_cleanup_module); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 8a89c738b7a3..a317797b3cd0 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -37,6 +37,7 @@ #include <net/route.h> #include <net/xfrm.h> #include <net/compat.h> +#include <net/checksum.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/transp_v6.h> #endif @@ -45,14 +46,6 @@ #include <linux/errqueue.h> #include <asm/uaccess.h> -#define IP_CMSG_PKTINFO 1 -#define IP_CMSG_TTL 2 -#define IP_CMSG_TOS 4 -#define IP_CMSG_RECVOPTS 8 -#define IP_CMSG_RETOPTS 16 -#define IP_CMSG_PASSSEC 32 -#define IP_CMSG_ORIGDSTADDR 64 - /* * SOL_IP control messages. */ @@ -104,6 +97,20 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data); } +static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, + int offset) +{ + __wsum csum = skb->csum; + + if (skb->ip_summed != CHECKSUM_COMPLETE) + return; + + if (offset != 0) + csum = csum_sub(csum, csum_partial(skb->data, offset, 0)); + + put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum); +} + static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) { char *secdata; @@ -144,47 +151,73 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin); } -void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) +void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, + int offset) { struct inet_sock *inet = inet_sk(skb->sk); unsigned int flags = inet->cmsg_flags; /* Ordered by supposed usage frequency */ - if (flags & 1) + if (flags & IP_CMSG_PKTINFO) { ip_cmsg_recv_pktinfo(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_PKTINFO; + if (!flags) + return; + } + + if (flags & IP_CMSG_TTL) { ip_cmsg_recv_ttl(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_TTL; + if (!flags) + return; + } + + if (flags & IP_CMSG_TOS) { ip_cmsg_recv_tos(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_TOS; + if (!flags) + return; + } + + if (flags & IP_CMSG_RECVOPTS) { ip_cmsg_recv_opts(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_RECVOPTS; + if (!flags) + return; + } + + if (flags & IP_CMSG_RETOPTS) { ip_cmsg_recv_retopts(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_RETOPTS; + if (!flags) + return; + } + + if (flags & IP_CMSG_PASSSEC) { ip_cmsg_recv_security(msg, skb); - if ((flags >>= 1) == 0) - return; - if (flags & 1) + flags &= ~IP_CMSG_PASSSEC; + if (!flags) + return; + } + + if (flags & IP_CMSG_ORIGDSTADDR) { ip_cmsg_recv_dstaddr(msg, skb); + flags &= ~IP_CMSG_ORIGDSTADDR; + if (!flags) + return; + } + + if (flags & IP_CMSG_CHECKSUM) + ip_cmsg_recv_checksum(msg, skb, offset); } -EXPORT_SYMBOL(ip_cmsg_recv); +EXPORT_SYMBOL(ip_cmsg_recv_offset); int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, bool allow_ipv6) @@ -522,6 +555,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, case IP_MULTICAST_ALL: case IP_MULTICAST_LOOP: case IP_RECVORIGDSTADDR: + case IP_CHECKSUM: if (optlen >= sizeof(int)) { if (get_user(val, (int __user *) optval)) return -EFAULT; @@ -619,6 +653,19 @@ static int do_ip_setsockopt(struct sock *sk, int level, else inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR; break; + case IP_CHECKSUM: + if (val) { + if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) { + inet_inc_convert_csum(sk); + inet->cmsg_flags |= IP_CMSG_CHECKSUM; + } + } else { + if (inet->cmsg_flags & IP_CMSG_CHECKSUM) { + inet_dec_convert_csum(sk); + inet->cmsg_flags &= ~IP_CMSG_CHECKSUM; + } + } + break; case IP_TOS: /* This sets both TOS and Precedence */ if (sk->sk_type == SOCK_STREAM) { val &= ~INET_ECN_MASK; @@ -1222,6 +1269,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_RECVORIGDSTADDR: val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0; break; + case IP_CHECKSUM: + val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0; + break; case IP_TOS: val = inet->tos; break; diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c index ff2d23d8c87a..6ecfce63201a 100644 --- a/net/ipv4/netfilter/nft_redir_ipv4.c +++ b/net/ipv4/netfilter/nft_redir_ipv4.c @@ -27,10 +27,10 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr, memset(&mr, 0, sizeof(mr)); if (priv->sreg_proto_min) { - mr.range[0].min.all = (__force __be16) - data[priv->sreg_proto_min].data[0]; - mr.range[0].max.all = (__force __be16) - data[priv->sreg_proto_max].data[0]; + mr.range[0].min.all = + *(__be16 *)&data[priv->sreg_proto_min].data[0]; + mr.range[0].max.all = + *(__be16 *)&data[priv->sreg_proto_max].data[0]; mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6a2155b02602..ce112d0f2698 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1325,14 +1325,22 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt) return ret; } -static DEFINE_SPINLOCK(rt_uncached_lock); -static LIST_HEAD(rt_uncached_list); +struct uncached_list { + spinlock_t lock; + struct list_head head; +}; + +static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); static void rt_add_uncached_list(struct rtable *rt) { - spin_lock_bh(&rt_uncached_lock); - list_add_tail(&rt->rt_uncached, &rt_uncached_list); - spin_unlock_bh(&rt_uncached_lock); + struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); + + rt->rt_uncached_list = ul; + + spin_lock_bh(&ul->lock); + list_add_tail(&rt->rt_uncached, &ul->head); + spin_unlock_bh(&ul->lock); } static void ipv4_dst_destroy(struct dst_entry *dst) @@ -1340,27 +1348,32 @@ static void ipv4_dst_destroy(struct dst_entry *dst) struct rtable *rt = (struct rtable *) dst; if (!list_empty(&rt->rt_uncached)) { - spin_lock_bh(&rt_uncached_lock); + struct uncached_list *ul = rt->rt_uncached_list; + + spin_lock_bh(&ul->lock); list_del(&rt->rt_uncached); - spin_unlock_bh(&rt_uncached_lock); + spin_unlock_bh(&ul->lock); } } void rt_flush_dev(struct net_device *dev) { - if (!list_empty(&rt_uncached_list)) { - struct net *net = dev_net(dev); - struct rtable *rt; + struct net *net = dev_net(dev); + struct rtable *rt; + int cpu; + + for_each_possible_cpu(cpu) { + struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); - spin_lock_bh(&rt_uncached_lock); - list_for_each_entry(rt, &rt_uncached_list, rt_uncached) { + spin_lock_bh(&ul->lock); + list_for_each_entry(rt, &ul->head, rt_uncached) { if (rt->dst.dev != dev) continue; rt->dst.dev = net->loopback_dev; dev_hold(rt->dst.dev); dev_put(dev); } - spin_unlock_bh(&rt_uncached_lock); + spin_unlock_bh(&ul->lock); } } @@ -2717,6 +2730,7 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; int __init ip_rt_init(void) { int rc = 0; + int cpu; ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL); if (!ip_idents) @@ -2724,6 +2738,12 @@ int __init ip_rt_init(void) prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents)); + for_each_possible_cpu(cpu) { + struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); + + INIT_LIST_HEAD(&ul->head); + spin_lock_init(&ul->lock); + } #ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 27ead0dd16bc..63c29dba68a8 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -13,6 +13,7 @@ #include <linux/types.h> #include <linux/list.h> #include <linux/gfp.h> +#include <linux/jhash.h> #include <net/tcp.h> static DEFINE_SPINLOCK(tcp_cong_list_lock); @@ -31,6 +32,34 @@ static struct tcp_congestion_ops *tcp_ca_find(const char *name) return NULL; } +/* Must be called with rcu lock held */ +static const struct tcp_congestion_ops *__tcp_ca_find_autoload(const char *name) +{ + const struct tcp_congestion_ops *ca = tcp_ca_find(name); +#ifdef CONFIG_MODULES + if (!ca && capable(CAP_NET_ADMIN)) { + rcu_read_unlock(); + request_module("tcp_%s", name); + rcu_read_lock(); + ca = tcp_ca_find(name); + } +#endif + return ca; +} + +/* Simple linear search, not much in here. */ +struct tcp_congestion_ops *tcp_ca_find_key(u32 key) +{ + struct tcp_congestion_ops *e; + + list_for_each_entry_rcu(e, &tcp_cong_list, list) { + if (e->key == key) + return e; + } + + return NULL; +} + /* * Attach new congestion control algorithm to the list * of available options. @@ -45,9 +74,12 @@ int tcp_register_congestion_control(struct tcp_congestion_ops *ca) return -EINVAL; } + ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); + spin_lock(&tcp_cong_list_lock); - if (tcp_ca_find(ca->name)) { - pr_notice("%s already registered\n", ca->name); + if (ca->key == TCP_CA_UNSPEC || tcp_ca_find_key(ca->key)) { + pr_notice("%s already registered or non-unique key\n", + ca->name); ret = -EEXIST; } else { list_add_tail_rcu(&ca->list, &tcp_cong_list); @@ -70,9 +102,50 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca) spin_lock(&tcp_cong_list_lock); list_del_rcu(&ca->list); spin_unlock(&tcp_cong_list_lock); + + /* Wait for outstanding readers to complete before the + * module gets removed entirely. + * + * A try_module_get() should fail by now as our module is + * in "going" state since no refs are held anymore and + * module_exit() handler being called. + */ + synchronize_rcu(); } EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); +u32 tcp_ca_get_key_by_name(const char *name) +{ + const struct tcp_congestion_ops *ca; + u32 key; + + might_sleep(); + + rcu_read_lock(); + ca = __tcp_ca_find_autoload(name); + key = ca ? ca->key : TCP_CA_UNSPEC; + rcu_read_unlock(); + + return key; +} +EXPORT_SYMBOL_GPL(tcp_ca_get_key_by_name); + +char *tcp_ca_get_name_by_key(u32 key, char *buffer) +{ + const struct tcp_congestion_ops *ca; + char *ret = NULL; + + rcu_read_lock(); + ca = tcp_ca_find_key(key); + if (ca) + ret = strncpy(buffer, ca->name, + TCP_CA_NAME_MAX); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL_GPL(tcp_ca_get_name_by_key); + /* Assign choice of congestion control. */ void tcp_assign_congestion_control(struct sock *sk) { @@ -107,6 +180,18 @@ void tcp_init_congestion_control(struct sock *sk) icsk->icsk_ca_ops->init(sk); } +static void tcp_reinit_congestion_control(struct sock *sk, + const struct tcp_congestion_ops *ca) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + tcp_cleanup_congestion_control(sk); + icsk->icsk_ca_ops = ca; + + if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init) + icsk->icsk_ca_ops->init(sk); +} + /* Manage refcounts on socket close. */ void tcp_cleanup_congestion_control(struct sock *sk) { @@ -241,42 +326,26 @@ out: int tcp_set_congestion_control(struct sock *sk, const char *name) { struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_congestion_ops *ca; + const struct tcp_congestion_ops *ca; int err = 0; - rcu_read_lock(); - ca = tcp_ca_find(name); + if (icsk->icsk_ca_dst_locked) + return -EPERM; - /* no change asking for existing value */ + rcu_read_lock(); + ca = __tcp_ca_find_autoload(name); + /* No change asking for existing value */ if (ca == icsk->icsk_ca_ops) goto out; - -#ifdef CONFIG_MODULES - /* not found attempt to autoload module */ - if (!ca && capable(CAP_NET_ADMIN)) { - rcu_read_unlock(); - request_module("tcp_%s", name); - rcu_read_lock(); - ca = tcp_ca_find(name); - } -#endif if (!ca) err = -ENOENT; - else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) err = -EPERM; - else if (!try_module_get(ca->owner)) err = -EBUSY; - - else { - tcp_cleanup_congestion_control(sk); - icsk->icsk_ca_ops = ca; - - if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init) - icsk->icsk_ca_ops->init(sk); - } + else + tcp_reinit_congestion_control(sk, ca); out: rcu_read_unlock(); return err; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 075ab4d5af5e..71fb37c70581 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3358,34 +3358,34 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) } /* This routine deals with acks during a TLP episode. + * We mark the end of a TLP episode on receiving TLP dupack or when + * ack is after tlp_high_seq. * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe. */ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) { struct tcp_sock *tp = tcp_sk(sk); - bool is_tlp_dupack = (ack == tp->tlp_high_seq) && - !(flag & (FLAG_SND_UNA_ADVANCED | - FLAG_NOT_DUP | FLAG_DATA_SACKED)); - /* Mark the end of TLP episode on receiving TLP dupack or when - * ack is after tlp_high_seq. - */ - if (is_tlp_dupack) { - tp->tlp_high_seq = 0; + if (before(ack, tp->tlp_high_seq)) return; - } - if (after(ack, tp->tlp_high_seq)) { + if (flag & FLAG_DSACKING_ACK) { + /* This DSACK means original and TLP probe arrived; no loss */ + tp->tlp_high_seq = 0; + } else if (after(ack, tp->tlp_high_seq)) { + /* ACK advances: there was a loss, so reduce cwnd. Reset + * tlp_high_seq in tcp_init_cwnd_reduction() + */ + tcp_init_cwnd_reduction(sk); + tcp_set_ca_state(sk, TCP_CA_CWR); + tcp_end_cwnd_reduction(sk); + tcp_try_keep_open(sk); + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPLOSSPROBERECOVERY); + } else if (!(flag & (FLAG_SND_UNA_ADVANCED | + FLAG_NOT_DUP | FLAG_DATA_SACKED))) { + /* Pure dupack: original and TLP probe arrived; no loss */ tp->tlp_high_seq = 0; - /* Don't reduce cwnd if DSACK arrives for TLP retrans. */ - if (!(flag & FLAG_DSACKING_ACK)) { - tcp_init_cwnd_reduction(sk); - tcp_set_ca_state(sk, TCP_CA_CWR); - tcp_end_cwnd_reduction(sk); - tcp_try_keep_open(sk); - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPLOSSPROBERECOVERY); - } } } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a3f72d7fc06c..ad3e65bdd368 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1340,6 +1340,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } sk_setup_caps(newsk, dst); + tcp_ca_openreq_child(newsk, dst); + tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric_advmss(dst); if (tcp_sk(sk)->rx_opt.user_mss && diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 63d2680b65db..bc9216dc9de1 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -399,6 +399,32 @@ static void tcp_ecn_openreq_child(struct tcp_sock *tp, tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0; } +void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + u32 ca_key = dst_metric(dst, RTAX_CC_ALGO); + bool ca_got_dst = false; + + if (ca_key != TCP_CA_UNSPEC) { + const struct tcp_congestion_ops *ca; + + rcu_read_lock(); + ca = tcp_ca_find_key(ca_key); + if (likely(ca && try_module_get(ca->owner))) { + icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); + icsk->icsk_ca_ops = ca; + ca_got_dst = true; + } + rcu_read_unlock(); + } + + if (!ca_got_dst && !try_module_get(icsk->icsk_ca_ops->owner)) + tcp_assign_congestion_control(sk); + + tcp_set_ca_state(sk, TCP_CA_Open); +} +EXPORT_SYMBOL_GPL(tcp_ca_openreq_child); + /* This is not only more efficient than what we used to do, it eliminates * a lot of code duplication between IPv4/IPv6 SYN recv processing. -DaveM * @@ -451,10 +477,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->snd_cwnd = TCP_INIT_CWND; newtp->snd_cwnd_cnt = 0; - if (!try_module_get(newicsk->icsk_ca_ops->owner)) - tcp_assign_congestion_control(newsk); - - tcp_set_ca_state(newsk, TCP_CA_Open); tcp_init_xmit_timers(newsk); __skb_queue_head_init(&newtp->out_of_order_queue); newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7f18262e2326..20ab06b228ac 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2019,7 +2019,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) break; - if (tso_segs == 1) { + if (tso_segs == 1 || !max_segs) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? nonagle : TCP_NAGLE_PUSH)))) @@ -2032,7 +2032,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } limit = mss_now; - if (tso_segs > 1 && !tcp_urg_mode(tp)) + if (tso_segs > 1 && max_segs && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, min_t(unsigned int, cwnd_quota, @@ -2939,6 +2939,25 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, } EXPORT_SYMBOL(tcp_make_synack); +static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_congestion_ops *ca; + u32 ca_key = dst_metric(dst, RTAX_CC_ALGO); + + if (ca_key == TCP_CA_UNSPEC) + return; + + rcu_read_lock(); + ca = tcp_ca_find_key(ca_key); + if (likely(ca && try_module_get(ca->owner))) { + module_put(icsk->icsk_ca_ops->owner); + icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); + icsk->icsk_ca_ops = ca; + } + rcu_read_unlock(); +} + /* Do all connect socket setups that can be done AF independent. */ static void tcp_connect_init(struct sock *sk) { @@ -2964,6 +2983,8 @@ static void tcp_connect_init(struct sock *sk) tcp_mtup_init(sk); tcp_sync_mss(sk, dst_mtu(dst)); + tcp_ca_dst_init(sk, dst); + if (!tp->window_clamp) tp->window_clamp = dst_metric(dst, RTAX_WINDOW); tp->advmss = dst_metric_advmss(dst); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 13b4dcf86ef6..97ef1f8b7be8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1329,7 +1329,7 @@ try_again: *addr_len = sizeof(*sin); } if (inet->cmsg_flags) - ip_cmsg_recv(msg, skb); + ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr)); err = copied; if (flags & MSG_TRUNC) @@ -1806,7 +1806,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (sk != NULL) { int ret; - if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk)) + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, inet_compute_pseudo); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index d3e537ef6b7f..d10f6f4ead27 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -339,7 +339,8 @@ unflush: skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto; - pp = uo_priv->offload->callbacks.gro_receive(head, skb); + pp = uo_priv->offload->callbacks.gro_receive(head, skb, + uo_priv->offload); out_unlock: rcu_read_unlock(); @@ -395,7 +396,9 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff) if (uo_priv != NULL) { NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto; - err = uo_priv->offload->callbacks.gro_complete(skb, nhoff + sizeof(struct udphdr)); + err = uo_priv->offload->callbacks.gro_complete(skb, + nhoff + sizeof(struct udphdr), + uo_priv->offload); } rcu_read_unlock(); diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 1671263e5fa0..9996e63ed304 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -63,7 +63,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, inet_sk(sk)->mc_loop = 0; /* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */ - udp_set_convert_csum(sk, true); + inet_inc_convert_csum(sk); rcu_assign_sk_user_data(sk, cfg->sk_user_data); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index d674152b6ede..a5e95199585e 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -427,7 +427,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) * Dest addr check */ - if ((addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST)) { + if (addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST) { if (type != ICMPV6_PKT_TOOBIG && !(type == ICMPV6_PARAMPROB && code == ICMPV6_UNK_OPTION && diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index b2d1838897c9..03c520a4ebeb 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -630,32 +630,35 @@ static bool rt6_qualify_for_ecmp(struct rt6_info *rt) RTF_GATEWAY; } -static int fib6_commit_metrics(struct dst_entry *dst, - struct nlattr *mx, int mx_len) +static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc) { - struct nlattr *nla; - int remaining; - u32 *mp; + int i; - if (dst->flags & DST_HOST) { - mp = dst_metrics_write_ptr(dst); - } else { - mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC); - if (!mp) - return -ENOMEM; - dst_init_metrics(dst, mp, 0); + for (i = 0; i < RTAX_MAX; i++) { + if (test_bit(i, mxc->mx_valid)) + mp[i] = mxc->mx[i]; } +} - nla_for_each_attr(nla, mx, mx_len, remaining) { - int type = nla_type(nla); +static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc) +{ + if (!mxc->mx) + return 0; - if (type) { - if (type > RTAX_MAX) - return -EINVAL; + if (dst->flags & DST_HOST) { + u32 *mp = dst_metrics_write_ptr(dst); - mp[type - 1] = nla_get_u32(nla); - } + if (unlikely(!mp)) + return -ENOMEM; + + fib6_copy_metrics(mp, mxc); + } else { + dst_init_metrics(dst, mxc->mx, false); + + /* We've stolen mx now. */ + mxc->mx = NULL; } + return 0; } @@ -664,7 +667,7 @@ static int fib6_commit_metrics(struct dst_entry *dst, */ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, - struct nl_info *info, struct nlattr *mx, int mx_len) + struct nl_info *info, struct mx6_config *mxc) { struct rt6_info *iter = NULL; struct rt6_info **ins; @@ -773,11 +776,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: - if (mx) { - err = fib6_commit_metrics(&rt->dst, mx, mx_len); - if (err) - return err; - } + err = fib6_commit_metrics(&rt->dst, mxc); + if (err) + return err; + rt->dst.rt6_next = iter; *ins = rt; rt->rt6i_node = fn; @@ -797,11 +799,11 @@ add: pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); return -ENOENT; } - if (mx) { - err = fib6_commit_metrics(&rt->dst, mx, mx_len); - if (err) - return err; - } + + err = fib6_commit_metrics(&rt->dst, mxc); + if (err) + return err; + *ins = rt; rt->rt6i_node = fn; rt->dst.rt6_next = iter->dst.rt6_next; @@ -838,8 +840,8 @@ void fib6_force_start_gc(struct net *net) * with source addr info in sub-trees */ -int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info, - struct nlattr *mx, int mx_len) +int fib6_add(struct fib6_node *root, struct rt6_info *rt, + struct nl_info *info, struct mx6_config *mxc) { struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; @@ -934,7 +936,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info, } #endif - err = fib6_add_rt2node(fn, rt, info, mx, mx_len); + err = fib6_add_rt2node(fn, rt, info, mxc); if (!err) { fib6_start_gc(info->nl_net, rt); if (!(rt->rt6i_flags & RTF_CACHE)) diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c index 2433a6bfb191..11820b6b3613 100644 --- a/net/ipv6/netfilter/nft_redir_ipv6.c +++ b/net/ipv6/netfilter/nft_redir_ipv6.c @@ -27,10 +27,10 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); if (priv->sreg_proto_min) { - range.min_proto.all = (__force __be16) - data[priv->sreg_proto_min].data[0]; - range.max_proto.all = (__force __be16) - data[priv->sreg_proto_max].data[0]; + range.min_proto.all = + *(__be16 *)&data[priv->sreg_proto_min].data[0]; + range.max_proto.all = + *(__be16 *)&data[priv->sreg_proto_max].data[0]; range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c91083156edb..34dcbb59df75 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -853,14 +853,14 @@ EXPORT_SYMBOL(rt6_lookup); */ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, - struct nlattr *mx, int mx_len) + struct mx6_config *mxc) { int err; struct fib6_table *table; table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); - err = fib6_add(&table->tb6_root, rt, info, mx, mx_len); + err = fib6_add(&table->tb6_root, rt, info, mxc); write_unlock_bh(&table->tb6_lock); return err; @@ -868,10 +868,10 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, int ip6_ins_rt(struct rt6_info *rt) { - struct nl_info info = { - .nl_net = dev_net(rt->dst.dev), - }; - return __ip6_ins_rt(rt, &info, NULL, 0); + struct nl_info info = { .nl_net = dev_net(rt->dst.dev), }; + struct mx6_config mxc = { .mx = NULL, }; + + return __ip6_ins_rt(rt, &info, &mxc); } static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, @@ -1470,9 +1470,51 @@ out: return entries > rt_max_size; } -/* - * - */ +static int ip6_convert_metrics(struct mx6_config *mxc, + const struct fib6_config *cfg) +{ + struct nlattr *nla; + int remaining; + u32 *mp; + + if (cfg->fc_mx == NULL) + return 0; + + mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); + if (unlikely(!mp)) + return -ENOMEM; + + nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { + int type = nla_type(nla); + + if (type) { + u32 val; + + if (unlikely(type > RTAX_MAX)) + goto err; + if (type == RTAX_CC_ALGO) { + char tmp[TCP_CA_NAME_MAX]; + + nla_strlcpy(tmp, nla, sizeof(tmp)); + val = tcp_ca_get_key_by_name(tmp); + if (val == TCP_CA_UNSPEC) + goto err; + } else { + val = nla_get_u32(nla); + } + + mp[type - 1] = val; + __set_bit(type - 1, mxc->mx_valid); + } + } + + mxc->mx = mp; + + return 0; + err: + kfree(mp); + return -EINVAL; +} int ip6_route_add(struct fib6_config *cfg) { @@ -1482,6 +1524,7 @@ int ip6_route_add(struct fib6_config *cfg) struct net_device *dev = NULL; struct inet6_dev *idev = NULL; struct fib6_table *table; + struct mx6_config mxc = { .mx = NULL, }; int addr_type; if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) @@ -1677,8 +1720,14 @@ install_route: cfg->fc_nlinfo.nl_net = dev_net(dev); - return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len); + err = ip6_convert_metrics(&mxc, cfg); + if (err) + goto out; + + err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc); + kfree(mxc.mx); + return err; out: if (dev) dev_put(dev); @@ -2534,7 +2583,8 @@ static inline size_t rt6_nlmsg_size(void) + nla_total_size(4) /* RTA_OIF */ + nla_total_size(4) /* RTA_PRIORITY */ + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ - + nla_total_size(sizeof(struct rta_cacheinfo)); + + nla_total_size(sizeof(struct rta_cacheinfo)) + + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */ } static int rt6_fill_node(struct net *net, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 9c0b54e87b47..5d46832c6f72 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1199,6 +1199,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + newnp->opt->opt_flen); + tcp_ca_openreq_child(newsk, dst); + tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric_advmss(dst); if (tcp_sk(sk)->rx_opt.user_mss && diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 189dc4ae3eca..e41f017cd479 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -909,7 +909,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, goto csum_error; } - if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk)) + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, ip6_compute_pseudo); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index e75d5c53e97b..fd6860d7f557 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -678,7 +678,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_BEACON_ENABLED | BSS_CHANGED_BEACON | BSS_CHANGED_SSID | - BSS_CHANGED_P2P_PS; + BSS_CHANGED_P2P_PS | + BSS_CHANGED_TXPOWER; int err; old = sdata_dereference(sdata->u.ap.beacon, sdata); @@ -2556,7 +2557,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, /* if there's one pending or we're scanning, queue this one */ if (!list_empty(&local->roc_list) || - local->scanning || local->radar_detect_enabled) + local->scanning || ieee80211_is_radar_required(local)) goto out_check_combine; /* if not HW assist, just queue & schedule work */ @@ -3664,7 +3665,7 @@ static int ieee80211_del_tx_ts(struct wiphy *wiphy, struct net_device *dev, * queues. */ synchronize_net(); - ieee80211_flush_queues(local, sdata); + ieee80211_flush_queues(local, sdata, false); /* restore the normal QoS parameters * (unconditionally to avoid races) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index da1c12c34487..35b11e11e0c4 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -388,7 +388,7 @@ ieee80211_find_chanctx(struct ieee80211_local *local, return NULL; } -static bool ieee80211_is_radar_required(struct ieee80211_local *local) +bool ieee80211_is_radar_required(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; @@ -406,6 +406,34 @@ static bool ieee80211_is_radar_required(struct ieee80211_local *local) return false; } +static bool +ieee80211_chanctx_radar_required(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) +{ + struct ieee80211_chanctx_conf *conf = &ctx->conf; + struct ieee80211_sub_if_data *sdata; + bool required = false; + + lockdep_assert_held(&local->chanctx_mtx); + lockdep_assert_held(&local->mtx); + + rcu_read_lock(); + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (!ieee80211_sdata_running(sdata)) + continue; + if (rcu_access_pointer(sdata->vif.chanctx_conf) != conf) + continue; + if (!sdata->radar_required) + continue; + + required = true; + break; + } + rcu_read_unlock(); + + return required; +} + static struct ieee80211_chanctx * ieee80211_alloc_chanctx(struct ieee80211_local *local, const struct cfg80211_chan_def *chandef, @@ -425,7 +453,7 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local, ctx->conf.rx_chains_static = 1; ctx->conf.rx_chains_dynamic = 1; ctx->mode = mode; - ctx->conf.radar_enabled = ieee80211_is_radar_required(local); + ctx->conf.radar_enabled = false; ieee80211_recalc_chanctx_min_def(local, ctx); return ctx; @@ -567,16 +595,15 @@ static void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local, bool radar_enabled; lockdep_assert_held(&local->chanctx_mtx); - /* for setting local->radar_detect_enabled */ + /* for ieee80211_is_radar_required */ lockdep_assert_held(&local->mtx); - radar_enabled = ieee80211_is_radar_required(local); + radar_enabled = ieee80211_chanctx_radar_required(local, chanctx); if (radar_enabled == chanctx->conf.radar_enabled) return; chanctx->conf.radar_enabled = radar_enabled; - local->radar_detect_enabled = chanctx->conf.radar_enabled; if (!local->use_chanctx) { local->hw.conf.radar_enabled = chanctx->conf.radar_enabled; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 54a189f0393e..eeb0bbd69d98 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -303,8 +303,6 @@ static ssize_t hwflags_read(struct file *file, char __user *user_buf, sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_DYNAMIC_PS\n"); if (local->hw.flags & IEEE80211_HW_MFP_CAPABLE) sf += scnprintf(buf + sf, mxln - sf, "MFP_CAPABLE\n"); - if (local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD) - sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_UAPSD\n"); if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) sf += scnprintf(buf + sf, mxln - sf, "REPORTS_TX_ACK_STATUS\n"); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 2ebc9ead9695..fdeda17b8dd2 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -639,6 +639,21 @@ static inline void drv_sta_rate_tbl_update(struct ieee80211_local *local, trace_drv_return_void(local); } +static inline void drv_sta_statistics(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, + struct station_info *sinfo) +{ + sdata = get_bss_sdata(sdata); + if (!check_sdata_in_driver(sdata)) + return; + + trace_drv_sta_statistics(local, sdata, sta); + if (local->ops->sta_statistics) + local->ops->sta_statistics(&local->hw, &sdata->vif, sta, sinfo); + trace_drv_return_void(local); +} + static inline int drv_conf_tx(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, u16 ac, const struct ieee80211_tx_queue_params *params) @@ -966,21 +981,6 @@ drv_allow_buffered_frames(struct ieee80211_local *local, trace_drv_return_void(local); } -static inline int drv_get_rssi(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - struct ieee80211_sta *sta, - s8 *rssi_dbm) -{ - int ret; - - might_sleep(); - - ret = local->ops->get_rssi(&local->hw, &sdata->vif, sta, rssi_dbm); - trace_drv_get_rssi(local, sta, *rssi_dbm, ret); - - return ret; -} - static inline void drv_mgd_prepare_tx(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c index ebfc8091557b..52bcea6ad9e8 100644 --- a/net/mac80211/ethtool.c +++ b/net/mac80211/ethtool.c @@ -117,16 +117,16 @@ static void ieee80211_get_stats(struct net_device *dev, data[i++] = sta->sta_state; - if (sinfo.filled & STATION_INFO_TX_BITRATE) + if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)) data[i] = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate); i++; - if (sinfo.filled & STATION_INFO_RX_BITRATE) + if (sinfo.filled & BIT(NL80211_STA_INFO_RX_BITRATE)) data[i] = 100000 * cfg80211_calculate_bitrate(&sinfo.rxrate); i++; - if (sinfo.filled & STATION_INFO_SIGNAL_AVG) + if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL_AVG)) data[i] = (u8)sinfo.signal_avg; i++; } else { @@ -175,24 +175,24 @@ do_survey: data[i++] = (u8)survey.noise; else data[i++] = -1LL; - if (survey.filled & SURVEY_INFO_CHANNEL_TIME) - data[i++] = survey.channel_time; + if (survey.filled & SURVEY_INFO_TIME) + data[i++] = survey.time; else data[i++] = -1LL; - if (survey.filled & SURVEY_INFO_CHANNEL_TIME_BUSY) - data[i++] = survey.channel_time_busy; + if (survey.filled & SURVEY_INFO_TIME_BUSY) + data[i++] = survey.time_busy; else data[i++] = -1LL; - if (survey.filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY) - data[i++] = survey.channel_time_ext_busy; + if (survey.filled & SURVEY_INFO_TIME_EXT_BUSY) + data[i++] = survey.time_ext_busy; else data[i++] = -1LL; - if (survey.filled & SURVEY_INFO_CHANNEL_TIME_RX) - data[i++] = survey.channel_time_rx; + if (survey.filled & SURVEY_INFO_TIME_RX) + data[i++] = survey.time_rx; else data[i++] = -1LL; - if (survey.filled & SURVEY_INFO_CHANNEL_TIME_TX) - data[i++] = survey.channel_time_tx; + if (survey.filled & SURVEY_INFO_TIME_TX) + data[i++] = survey.time_tx; else data[i++] = -1LL; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 509bc157ce55..b606b53a49a7 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1069,9 +1069,16 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, } if (sta && rates_updated) { - drv_sta_rc_update(local, sdata, &sta->sta, - IEEE80211_RC_SUPP_RATES_CHANGED); + u32 changed = IEEE80211_RC_SUPP_RATES_CHANGED; + u8 rx_nss = sta->sta.rx_nss; + + /* Force rx_nss recalculation */ + sta->sta.rx_nss = 0; rate_control_rate_init(sta); + if (sta->sta.rx_nss != rx_nss) + changed |= IEEE80211_RC_NSS_CHANGED; + + drv_sta_rc_update(local, sdata, &sta->sta, changed); } rcu_read_unlock(); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index cc6e964d9837..156ea79e0157 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1168,8 +1168,6 @@ struct ieee80211_local { /* wowlan is enabled -- don't reconfig on resume */ bool wowlan; - /* DFS/radar detection is enabled */ - bool radar_detect_enabled; struct work_struct radar_detected_work; /* number of RX chains the hardware has */ @@ -1704,6 +1702,7 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, const struct ieee80211_vht_cap *vht_cap_ie, struct sta_info *sta); +enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct sta_info *sta); enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta); void ieee80211_sta_set_rx_nss(struct sta_info *sta); u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, @@ -1881,10 +1880,10 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local, void ieee80211_add_pending_skbs(struct ieee80211_local *local, struct sk_buff_head *skbs); void ieee80211_flush_queues(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata); + struct ieee80211_sub_if_data *sdata, bool drop); void __ieee80211_flush_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - unsigned int queues); + unsigned int queues, bool drop); void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, u16 status, @@ -1981,6 +1980,7 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *chanctx); void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, struct ieee80211_chanctx *ctx); +bool ieee80211_is_radar_required(struct ieee80211_local *local); void ieee80211_dfs_cac_timer(unsigned long data); void ieee80211_dfs_cac_timer_work(struct work_struct *work); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 417355390873..677422e11e07 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -93,7 +93,7 @@ static u32 __ieee80211_idle_on(struct ieee80211_local *local) if (local->hw.conf.flags & IEEE80211_CONF_IDLE) return 0; - ieee80211_flush_queues(local, NULL); + ieee80211_flush_queues(local, NULL, false); local->hw.conf.flags |= IEEE80211_CONF_IDLE; return IEEE80211_CONF_CHANGE_IDLE; diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 0bb7038121ac..f8d9f0ee59bf 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -140,7 +140,8 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) if (!ret) { key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE; - if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC)) + if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) || + (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) sdata->crypto_tx_tailroom_needed_cnt--; WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) && @@ -188,7 +189,8 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) sta = key->sta; sdata = key->sdata; - if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC)) + if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) || + (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) increment_tailroom_need_count(sdata); ret = drv_set_key(key->local, DISABLE_KEY, sdata, @@ -884,7 +886,8 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf) if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) { key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; - if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC)) + if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) || + (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) increment_tailroom_need_count(key->sdata); } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 6ab99da38db9..d9ce33663c73 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -916,10 +916,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) } } - WARN((local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD) - && (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK), - "U-APSD not supported with HW_PS_NULLFUNC_STACK\n"); - /* * Calculate scan IE length -- we need this to alloc * memory and to subtract from the driver limit. It diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index b488e1859b18..fa94ca15ba95 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -523,6 +523,13 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, sdata->u.mesh.mshcfg.auto_open_plinks && rssi_threshold_check(sdata, sta)) changed = mesh_plink_open(sta); + else if (sta->plink_state == NL80211_PLINK_LISTEN && + (sdata->u.mesh.user_mpm || + sdata->u.mesh.security & IEEE80211_MESH_SEC_AUTHED)) + cfg80211_notify_new_peer_candidate(sdata->dev, hw_addr, + elems->ie_start, + elems->total_len, + GFP_ATOMIC); ieee80211_mps_frame_release(sta, elems); out: diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 2c36c4765f47..c0711082a2b8 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -157,14 +157,18 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct cfg80211_chan_def vht_chandef; + struct ieee80211_sta_ht_cap sta_ht_cap; u32 ht_cfreq, ret; + memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap)); + ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap); + chandef->chan = channel; chandef->width = NL80211_CHAN_WIDTH_20_NOHT; chandef->center_freq1 = channel->center_freq; chandef->center_freq2 = 0; - if (!ht_cap || !ht_oper || !sband->ht_cap.ht_supported) { + if (!ht_cap || !ht_oper || !sta_ht_cap.ht_supported) { ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; goto out; } @@ -198,7 +202,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, } /* check 40 MHz support, if we have it */ - if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) { + if (sta_ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) { switch (ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET) { case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: chandef->width = NL80211_CHAN_WIDTH_40; @@ -1054,8 +1058,6 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_sub_if_data *sdata) sdata->csa_block_tx = false; } - cfg80211_ch_switch_notify(sdata->dev, &sdata->reserved_chandef); - sdata->vif.csa_active = false; ifmgd->csa_waiting_bcn = false; @@ -1067,6 +1069,8 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_sub_if_data *sdata) &ifmgd->csa_connection_drop_work); return; } + + cfg80211_ch_switch_notify(sdata->dev, &sdata->reserved_chandef); } void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success) @@ -1284,8 +1288,11 @@ ieee80211_find_80211h_pwr_constr(struct ieee80211_sub_if_data *sdata, country_ie_len -= 3; } - if (have_chan_pwr) + if (have_chan_pwr && pwr_constr_elem) *pwr_reduction = *pwr_constr_elem; + else + *pwr_reduction = 0; + return have_chan_pwr; } @@ -1314,10 +1321,11 @@ static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, int chan_pwr = 0, pwr_reduction_80211h = 0; int pwr_level_cisco, pwr_level_80211h; int new_ap_level; + __le16 capab = mgmt->u.probe_resp.capab_info; - if (country_ie && pwr_constr_ie && - mgmt->u.probe_resp.capab_info & - cpu_to_le16(WLAN_CAPABILITY_SPECTRUM_MGMT)) { + if (country_ie && + (capab & cpu_to_le16(WLAN_CAPABILITY_SPECTRUM_MGMT) || + capab & cpu_to_le16(WLAN_CAPABILITY_RADIO_MEASURE))) { has_80211h_pwr = ieee80211_find_80211h_pwr_constr( sdata, channel, country_ie, country_ie_len, pwr_constr_ie, &chan_pwr, &pwr_reduction_80211h); @@ -1596,7 +1604,7 @@ void ieee80211_dynamic_ps_enable_work(struct work_struct *work) } else { ieee80211_send_nullfunc(local, sdata, 1); /* Flush to get the tx status of nullfunc frame */ - ieee80211_flush_queues(local, sdata); + ieee80211_flush_queues(local, sdata, false); } } @@ -2003,18 +2011,23 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, /* disable per-vif ps */ ieee80211_recalc_ps_vif(sdata); - /* flush out any pending frame (e.g. DELBA) before deauth/disassoc */ + /* + * drop any frame before deauth/disassoc, this can be data or + * management frame. Since we are disconnecting, we should not + * insist sending these frames which can take time and delay + * the disconnection and possible the roaming. + */ if (tx) - ieee80211_flush_queues(local, sdata); + ieee80211_flush_queues(local, sdata, true); /* deauthenticate/disassociate now */ if (tx || frame_buf) ieee80211_send_deauth_disassoc(sdata, ifmgd->bssid, stype, reason, tx, frame_buf); - /* flush out frame */ + /* flush out frame - make sure the deauth was actually sent */ if (tx) - ieee80211_flush_queues(local, sdata); + ieee80211_flush_queues(local, sdata, false); /* clear bssid only after building the needed mgmt frames */ memset(ifmgd->bssid, 0, ETH_ALEN); @@ -4197,9 +4210,13 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_bss *bss = (void *)cbss->priv; struct sta_info *new_sta = NULL; - bool have_sta = false; + struct ieee80211_supported_band *sband; + struct ieee80211_sta_ht_cap sta_ht_cap; + bool have_sta = false, is_override = false; int err; + sband = local->hw.wiphy->bands[cbss->channel->band]; + if (WARN_ON(!ifmgd->auth_data && !ifmgd->assoc_data)) return -EINVAL; @@ -4214,25 +4231,32 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, if (!new_sta) return -ENOMEM; } + + memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap)); + ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap); + + is_override = (sta_ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) != + (sband->ht_cap.cap & + IEEE80211_HT_CAP_SUP_WIDTH_20_40); + + if (new_sta || is_override) { + err = ieee80211_prep_channel(sdata, cbss); + if (err) { + if (new_sta) + sta_info_free(local, new_sta); + return -EINVAL; + } + } + if (new_sta) { u32 rates = 0, basic_rates = 0; bool have_higher_than_11mbit; int min_rate = INT_MAX, min_rate_index = -1; struct ieee80211_chanctx_conf *chanctx_conf; - struct ieee80211_supported_band *sband; const struct cfg80211_bss_ies *ies; - int shift; + int shift = ieee80211_vif_get_shift(&sdata->vif); u32 rate_flags; - sband = local->hw.wiphy->bands[cbss->channel->band]; - - err = ieee80211_prep_channel(sdata, cbss); - if (err) { - sta_info_free(local, new_sta); - return -EINVAL; - } - shift = ieee80211_vif_get_shift(&sdata->vif); - rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); if (WARN_ON(!chanctx_conf)) { @@ -4668,8 +4692,13 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; rcu_read_unlock(); + if (WARN((sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_UAPSD) && + (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK), + "U-APSD not supported with HW_PS_NULLFUNC_STACK\n")) + sdata->vif.driver_flags &= ~IEEE80211_VIF_SUPPORTS_UAPSD; + if (bss->wmm_used && bss->uapsd_supported && - (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) { + (sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_UAPSD)) { assoc_data->uapsd = true; ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED; } else { diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index ff20b2ebdb30..683f0e3cb124 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -121,7 +121,7 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local) ieee80211_stop_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL, false); - ieee80211_flush_queues(local, NULL); + ieee80211_flush_queues(local, NULL, false); mutex_lock(&local->iflist_mtx); list_for_each_entry(sdata, &local->interfaces, list) { @@ -398,7 +398,7 @@ void ieee80211_sw_roc_work(struct work_struct *work) ieee80211_roc_notify_destroy(roc, !roc->abort); if (started && !on_channel) { - ieee80211_flush_queues(local, NULL); + ieee80211_flush_queues(local, NULL, false); local->tmp_channel = NULL; ieee80211_hw_config(local, 0); diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 4c5192e0d66c..8c8c67819072 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -41,7 +41,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) /* flush out all packets */ synchronize_net(); - ieee80211_flush_queues(local, NULL); + ieee80211_flush_queues(local, NULL, true); local->quiescing = true; /* make quiescing visible to timers everywhere */ diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index d51f6b1c549b..7c86a002df95 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -263,12 +263,12 @@ static inline unsigned int minstrel_get_retry_count(struct minstrel_rate *mr, struct ieee80211_tx_info *info) { - unsigned int retry = mr->adjusted_retry_count; + u8 retry = mr->adjusted_retry_count; if (info->control.use_rts) - retry = max(2U, min(mr->stats.retry_count_rtscts, retry)); + retry = max_t(u8, 2, min(mr->stats.retry_count_rtscts, retry)); else if (info->control.use_cts_prot) - retry = max(2U, min(mr->retry_count_cts, retry)); + retry = max_t(u8, 2, min(mr->retry_count_cts, retry)); return retry; } diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h index 97eca86a4af0..410efe620c57 100644 --- a/net/mac80211/rc80211_minstrel.h +++ b/net/mac80211/rc80211_minstrel.h @@ -33,8 +33,8 @@ minstrel_ewma(int old, int new, int weight) struct minstrel_rate_stats { /* current / last sampling period attempts/success counters */ - unsigned int attempts, last_attempts; - unsigned int success, last_success; + u16 attempts, last_attempts; + u16 success, last_success; /* total attempts/success counters */ u64 att_hist, succ_hist; @@ -46,8 +46,8 @@ struct minstrel_rate_stats { unsigned int cur_prob, probability; /* maximum retry counts */ - unsigned int retry_count; - unsigned int retry_count_rtscts; + u8 retry_count; + u8 retry_count_rtscts; u8 sample_skipped; bool retry_updated; @@ -55,14 +55,15 @@ struct minstrel_rate_stats { struct minstrel_rate { int bitrate; - int rix; + + s8 rix; + u8 retry_count_cts; + u8 adjusted_retry_count; unsigned int perfect_tx_time; unsigned int ack_time; int sample_limit; - unsigned int retry_count_cts; - unsigned int adjusted_retry_count; struct minstrel_rate_stats stats; }; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 683b10f46505..3a1a3ba40bd8 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2314,6 +2314,15 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) return RX_DROP_MONITOR; + if (rx->sta) { + /* The security index has the same property as needed + * for the rx_msdu field, i.e. it is IEEE80211_NUM_TIDS + * for non-QoS-data frames. Here we know it's a data + * frame, so count MSDUs. + */ + rx->sta->rx_msdu[rx->security_idx]++; + } + /* * Send unexpected-4addr-frame event to hostapd. For older versions, * also drop the frame to cooked monitor interfaces. @@ -2598,7 +2607,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) case WLAN_HT_ACTION_NOTIFY_CHANWIDTH: { struct ieee80211_supported_band *sband; u8 chanwidth = mgmt->u.action.u.ht_notify_cw.chanwidth; - enum ieee80211_sta_rx_bandwidth new_bw; + enum ieee80211_sta_rx_bandwidth max_bw, new_bw; /* If it doesn't support 40 MHz it can't change ... */ if (!(rx->sta->sta.ht_cap.cap & @@ -2606,13 +2615,18 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) goto handled; if (chanwidth == IEEE80211_HT_CHANWIDTH_20MHZ) - new_bw = IEEE80211_STA_RX_BW_20; + max_bw = IEEE80211_STA_RX_BW_20; else - new_bw = ieee80211_sta_cur_vht_bw(rx->sta); + max_bw = ieee80211_sta_cap_rx_bw(rx->sta); + + /* set cur_max_bandwidth and recalc sta bw */ + rx->sta->cur_max_bandwidth = max_bw; + new_bw = ieee80211_sta_cur_vht_bw(rx->sta); if (rx->sta->sta.bandwidth == new_bw) goto handled; + rx->sta->sta.bandwidth = new_bw; sband = rx->local->hw.wiphy->bands[status->band]; rate_control_rate_update(local, sband, rx->sta, diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index ae842678b629..7807fa42ed3f 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -416,7 +416,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local, ieee80211_offchannel_stop_vifs(local); /* ensure nullfunc is transmitted before leaving operating channel */ - ieee80211_flush_queues(local, NULL); + ieee80211_flush_queues(local, NULL, false); ieee80211_configure_filter(local); @@ -432,7 +432,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local, static bool ieee80211_can_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { - if (local->radar_detect_enabled) + if (ieee80211_is_radar_required(local)) return false; if (!list_empty(&local->roc_list)) @@ -505,7 +505,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, lockdep_assert_held(&local->mtx); - if (local->scan_req) + if (local->scan_req || ieee80211_is_radar_required(local)) return -EBUSY; if (!ieee80211_can_scan(local, sdata)) { @@ -805,7 +805,7 @@ static void ieee80211_scan_state_resume(struct ieee80211_local *local, ieee80211_offchannel_stop_vifs(local); if (local->ops->flush) { - ieee80211_flush_queues(local, NULL); + ieee80211_flush_queues(local, NULL, false); *next_delay = 0; } else *next_delay = HZ / 10; diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index efeba56c913b..06e6ac8cc693 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -34,19 +34,15 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, struct cfg80211_chan_def new_vht_chandef = {}; const struct ieee80211_sec_chan_offs_ie *sec_chan_offs; const struct ieee80211_wide_bw_chansw_ie *wide_bw_chansw_ie; - const struct ieee80211_ht_operation *ht_oper; int secondary_channel_offset = -1; sec_chan_offs = elems->sec_chan_offs; wide_bw_chansw_ie = elems->wide_bw_chansw_ie; - ht_oper = elems->ht_operation; if (sta_flags & (IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_40MHZ)) { sec_chan_offs = NULL; wide_bw_chansw_ie = NULL; - /* only used for bandwidth here */ - ht_oper = NULL; } if (sta_flags & IEEE80211_STA_DISABLE_VHT) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index a42f5b2b024d..79383ef0c264 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -116,7 +116,6 @@ static void __cleanup_single_sta(struct sta_info *sta) clear_sta_flag(sta, WLAN_STA_PS_DELIVER); atomic_dec(&ps->num_sta_ps); - sta_info_recalc_tim(sta); } for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { @@ -625,7 +624,7 @@ static unsigned long ieee80211_tids_for_ac(int ac) } } -void sta_info_recalc_tim(struct sta_info *sta) +static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending) { struct ieee80211_local *local = sta->local; struct ps_data *ps; @@ -667,6 +666,9 @@ void sta_info_recalc_tim(struct sta_info *sta) if (ignore_for_tim == BIT(IEEE80211_NUM_ACS) - 1) ignore_for_tim = 0; + if (ignore_pending) + ignore_for_tim = BIT(IEEE80211_NUM_ACS) - 1; + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { unsigned long tids; @@ -695,7 +697,7 @@ void sta_info_recalc_tim(struct sta_info *sta) else __bss_tim_clear(ps->tim, id); - if (local->ops->set_tim) { + if (local->ops->set_tim && !WARN_ON(sta->dead)) { local->tim_in_locked_section = true; drv_set_tim(local, &sta->sta, indicate_tim); local->tim_in_locked_section = false; @@ -705,6 +707,11 @@ out_unlock: spin_unlock_bh(&local->tim_lock); } +void sta_info_recalc_tim(struct sta_info *sta) +{ + __sta_info_recalc_tim(sta, false); +} + static bool sta_info_buffer_expired(struct sta_info *sta, struct sk_buff *skb) { struct ieee80211_tx_info *info; @@ -874,6 +881,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta) { struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; + struct station_info sinfo = {}; int ret; /* @@ -887,6 +895,9 @@ static void __sta_info_destroy_part2(struct sta_info *sta) /* now keys can no longer be reached */ ieee80211_free_sta_keys(local, sta); + /* disable TIM bit - last chance to tell driver */ + __sta_info_recalc_tim(sta, true); + sta->dead = true; local->num_sta--; @@ -908,7 +919,8 @@ static void __sta_info_destroy_part2(struct sta_info *sta) sta_dbg(sdata, "Removed STA %pM\n", sta->sta.addr); - cfg80211_del_sta(sdata->dev, sta->sta.addr, GFP_KERNEL); + sta_set_sinfo(sta, &sinfo); + cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL); rate_control_remove_sta_debugfs(sta); ieee80211_sta_debugfs_remove(sta); @@ -1243,10 +1255,11 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata, * ends the poll/service period. */ info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER | - IEEE80211_TX_CTL_PS_RESPONSE | IEEE80211_TX_STATUS_EOSP | IEEE80211_TX_CTL_REQ_TX_STATUS; + info->control.flags |= IEEE80211_TX_CTRL_PS_RESPONSE; + if (call_driver) drv_allow_buffered_frames(local, sta, BIT(tid), 1, reason, false); @@ -1395,8 +1408,8 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, * STA may still remain is PS mode after this frame * exchange. */ - info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER | - IEEE80211_TX_CTL_PS_RESPONSE; + info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; + info->control.flags |= IEEE80211_TX_CTRL_PS_RESPONSE; /* * Use MoreData flag to indicate whether there are @@ -1743,7 +1756,6 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) struct ieee80211_local *local = sdata->local; struct rate_control_ref *ref = NULL; struct timespec uptime; - u64 packets = 0; u32 thr = 0; int i, ac; @@ -1752,49 +1764,76 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->generation = sdata->local->sta_generation; - sinfo->filled = STATION_INFO_INACTIVE_TIME | - STATION_INFO_RX_BYTES64 | - STATION_INFO_TX_BYTES64 | - STATION_INFO_RX_PACKETS | - STATION_INFO_TX_PACKETS | - STATION_INFO_TX_RETRIES | - STATION_INFO_TX_FAILED | - STATION_INFO_TX_BITRATE | - STATION_INFO_RX_BITRATE | - STATION_INFO_RX_DROP_MISC | - STATION_INFO_BSS_PARAM | - STATION_INFO_CONNECTED_TIME | - STATION_INFO_STA_FLAGS | - STATION_INFO_BEACON_LOSS_COUNT; + drv_sta_statistics(local, sdata, &sta->sta, sinfo); + + sinfo->filled |= BIT(NL80211_STA_INFO_INACTIVE_TIME) | + BIT(NL80211_STA_INFO_STA_FLAGS) | + BIT(NL80211_STA_INFO_BSS_PARAM) | + BIT(NL80211_STA_INFO_CONNECTED_TIME) | + BIT(NL80211_STA_INFO_RX_DROP_MISC) | + BIT(NL80211_STA_INFO_BEACON_LOSS); ktime_get_ts(&uptime); sinfo->connected_time = uptime.tv_sec - sta->last_connected; - sinfo->inactive_time = jiffies_to_msecs(jiffies - sta->last_rx); - sinfo->tx_bytes = 0; - for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - sinfo->tx_bytes += sta->tx_bytes[ac]; - packets += sta->tx_packets[ac]; + + if (!(sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES64) | + BIT(NL80211_STA_INFO_TX_BYTES)))) { + sinfo->tx_bytes = 0; + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) + sinfo->tx_bytes += sta->tx_bytes[ac]; + sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES64); + } + + if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_PACKETS))) { + sinfo->tx_packets = 0; + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) + sinfo->tx_packets += sta->tx_packets[ac]; + sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS); + } + + if (!(sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES64) | + BIT(NL80211_STA_INFO_RX_BYTES)))) { + sinfo->rx_bytes = sta->rx_bytes; + sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64); + } + + if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_PACKETS))) { + sinfo->rx_packets = sta->rx_packets; + sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS); + } + + if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_RETRIES))) { + sinfo->tx_retries = sta->tx_retry_count; + sinfo->filled |= BIT(NL80211_STA_INFO_TX_RETRIES); } - sinfo->tx_packets = packets; - sinfo->rx_bytes = sta->rx_bytes; - sinfo->rx_packets = sta->rx_packets; - sinfo->tx_retries = sta->tx_retry_count; - sinfo->tx_failed = sta->tx_retry_failed; + + if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_FAILED))) { + sinfo->tx_failed = sta->tx_retry_failed; + sinfo->filled |= BIT(NL80211_STA_INFO_TX_FAILED); + } + sinfo->rx_dropped_misc = sta->rx_dropped; sinfo->beacon_loss_count = sta->beacon_loss_count; if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) || (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) { - sinfo->filled |= STATION_INFO_SIGNAL | STATION_INFO_SIGNAL_AVG; - if (!local->ops->get_rssi || - drv_get_rssi(local, sdata, &sta->sta, &sinfo->signal)) + if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL))) { sinfo->signal = (s8)sta->last_signal; - sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal); + sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL); + } + + if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))) { + sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal); + sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG); + } } - if (sta->chains) { - sinfo->filled |= STATION_INFO_CHAIN_SIGNAL | - STATION_INFO_CHAIN_SIGNAL_AVG; + + if (sta->chains && + !(sinfo->filled & (BIT(NL80211_STA_INFO_CHAIN_SIGNAL) | + BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) { + sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL) | + BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG); sinfo->chains = sta->chains; for (i = 0; i < ARRAY_SIZE(sinfo->chain_signal); i++) { @@ -1804,23 +1843,61 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) } } - sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate); - sta_set_rate_info_rx(sta, &sinfo->rxrate); + if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE))) { + sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate); + sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE); + } + + if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE))) { + sta_set_rate_info_rx(sta, &sinfo->rxrate); + sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE); + } + + sinfo->filled |= BIT(NL80211_STA_INFO_TID_STATS); + for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) { + struct cfg80211_tid_stats *tidstats = &sinfo->pertid[i]; + + if (!(tidstats->filled & BIT(NL80211_TID_STATS_RX_MSDU))) { + tidstats->filled |= BIT(NL80211_TID_STATS_RX_MSDU); + tidstats->rx_msdu = sta->rx_msdu[i]; + } + + if (!(tidstats->filled & BIT(NL80211_TID_STATS_TX_MSDU))) { + tidstats->filled |= BIT(NL80211_TID_STATS_TX_MSDU); + tidstats->tx_msdu = sta->tx_msdu[i]; + } + + if (!(tidstats->filled & + BIT(NL80211_TID_STATS_TX_MSDU_RETRIES)) && + local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) { + tidstats->filled |= + BIT(NL80211_TID_STATS_TX_MSDU_RETRIES); + tidstats->tx_msdu_retries = sta->tx_msdu_retries[i]; + } + + if (!(tidstats->filled & + BIT(NL80211_TID_STATS_TX_MSDU_FAILED)) && + local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) { + tidstats->filled |= + BIT(NL80211_TID_STATS_TX_MSDU_FAILED); + tidstats->tx_msdu_failed = sta->tx_msdu_failed[i]; + } + } if (ieee80211_vif_is_mesh(&sdata->vif)) { #ifdef CONFIG_MAC80211_MESH - sinfo->filled |= STATION_INFO_LLID | - STATION_INFO_PLID | - STATION_INFO_PLINK_STATE | - STATION_INFO_LOCAL_PM | - STATION_INFO_PEER_PM | - STATION_INFO_NONPEER_PM; + sinfo->filled |= BIT(NL80211_STA_INFO_LLID) | + BIT(NL80211_STA_INFO_PLID) | + BIT(NL80211_STA_INFO_PLINK_STATE) | + BIT(NL80211_STA_INFO_LOCAL_PM) | + BIT(NL80211_STA_INFO_PEER_PM) | + BIT(NL80211_STA_INFO_NONPEER_PM); sinfo->llid = sta->llid; sinfo->plid = sta->plid; sinfo->plink_state = sta->plink_state; if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { - sinfo->filled |= STATION_INFO_T_OFFSET; + sinfo->filled |= BIT(NL80211_STA_INFO_T_OFFSET); sinfo->t_offset = sta->t_offset; } sinfo->local_pm = sta->local_pm; @@ -1869,7 +1946,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) thr = drv_get_expected_throughput(local, &sta->sta); if (thr != 0) { - sinfo->filled |= STATION_INFO_EXPECTED_THROUGHPUT; + sinfo->filled |= BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT); sinfo->expected_throughput = thr; } } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 4f052bb2a5ad..925e68fe64c7 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -346,6 +346,14 @@ struct ieee80211_tx_latency_stat { * @cipher_scheme: optional cipher scheme for this station * @last_tdls_pkt_time: holds the time in jiffies of last TDLS pkt ACKed * @reserved_tid: reserved TID (if any, otherwise IEEE80211_TID_UNRESERVED) + * @tx_msdu: MSDUs transmitted to this station, using IEEE80211_NUM_TID + * entry for non-QoS frames + * @tx_msdu_retries: MSDU retries for transmissions to to this station, + * using IEEE80211_NUM_TID entry for non-QoS frames + * @tx_msdu_failed: MSDU failures for transmissions to to this station, + * using IEEE80211_NUM_TID entry for non-QoS frames + * @rx_msdu: MSDUs received from this station, using IEEE80211_NUM_TID + * entry for non-QoS frames */ struct sta_info { /* General information, mostly static */ @@ -416,6 +424,10 @@ struct sta_info { u32 last_rx_rate_vht_flag; u8 last_rx_rate_vht_nss; u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; + u64 tx_msdu[IEEE80211_NUM_TIDS + 1]; + u64 tx_msdu_retries[IEEE80211_NUM_TIDS + 1]; + u64 tx_msdu_failed[IEEE80211_NUM_TIDS + 1]; + u64 rx_msdu[IEEE80211_NUM_TIDS + 1]; /* * Aggregation information, locked with lock. diff --git a/net/mac80211/status.c b/net/mac80211/status.c index bb146f377ee4..788707f05516 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -664,13 +664,15 @@ void ieee80211_tx_status_noskb(struct ieee80211_hw *hw, struct ieee80211_supported_band *sband; int retry_count; int rates_idx; - bool acked; + bool acked, noack_success; rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count); sband = hw->wiphy->bands[info->band]; acked = !!(info->flags & IEEE80211_TX_STAT_ACK); + noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED); + if (pubsta) { struct sta_info *sta; @@ -696,7 +698,7 @@ void ieee80211_tx_status_noskb(struct ieee80211_hw *hw, rate_control_tx_status_noskb(local, sband, sta, info); } - if (acked) { + if (acked || noack_success) { local->dot11TransmittedFrameCount++; if (!pubsta) local->dot11MulticastTransmittedFrameCount++; @@ -728,6 +730,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) struct ieee80211_bar *bar; int rtap_len; int shift = 0; + int tid = IEEE80211_NUM_TIDS;; rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count); @@ -771,7 +774,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if ((info->flags & IEEE80211_TX_STAT_AMPDU_NO_BACK) && (ieee80211_is_data_qos(fc))) { - u16 tid, ssn; + u16 ssn; u8 *qc; qc = ieee80211_get_qos_ctl(hdr); @@ -780,10 +783,14 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) & IEEE80211_SCTL_SEQ); ieee80211_send_bar(&sta->sdata->vif, hdr->addr1, tid, ssn); + } else if (ieee80211_is_data_qos(fc)) { + u8 *qc = ieee80211_get_qos_ctl(hdr); + + tid = qc[0] & 0xf; } if (!acked && ieee80211_is_back_req(fc)) { - u16 tid, control; + u16 control; /* * BAR failed, store the last SSN and retry sending @@ -811,6 +818,12 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if (!acked) sta->tx_retry_failed++; sta->tx_retry_count += retry_count; + + if (ieee80211_is_data_present(fc)) { + if (!acked) + sta->tx_msdu_failed[tid]++; + sta->tx_msdu_retries[tid] += retry_count; + } } rate_control_tx_status(local, sband, sta, skb); @@ -856,10 +869,11 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) * Fragments are passed to low-level drivers as separate skbs, so these * are actually fragments, not frames. Update frame counters only for * the first fragment of the frame. */ - if (info->flags & IEEE80211_TX_STAT_ACK) { + if ((info->flags & IEEE80211_TX_STAT_ACK) || + (info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED)) { if (ieee80211_is_first_frag(hdr->seq_ctrl)) { local->dot11TransmittedFrameCount++; - if (is_multicast_ether_addr(hdr->addr1)) + if (is_multicast_ether_addr(ieee80211_get_DA(hdr))) local->dot11MulticastTransmittedFrameCount++; if (retry_count > 0) local->dot11RetryCount++; diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 55ddd77b865d..917088dfd696 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -68,17 +68,24 @@ ieee80211_tdls_add_subband(struct ieee80211_sub_if_data *sdata, ch = ieee80211_get_channel(sdata->local->hw.wiphy, i); if (ch) { /* we will be active on the channel */ - u32 flags = IEEE80211_CHAN_DISABLED | - IEEE80211_CHAN_NO_IR; cfg80211_chandef_create(&chandef, ch, - NL80211_CHAN_HT20); - if (cfg80211_chandef_usable(sdata->local->hw.wiphy, - &chandef, flags)) { + NL80211_CHAN_NO_HT); + if (cfg80211_reg_can_beacon(sdata->local->hw.wiphy, + &chandef, + sdata->wdev.iftype)) { ch_cnt++; + /* + * check if the next channel is also part of + * this allowed range + */ continue; } } + /* + * we've reached the end of a range, with allowed channels + * found + */ if (ch_cnt) { u8 *pos = skb_put(skb, 2); *pos++ = ieee80211_frequency_to_channel(subband_start); @@ -89,6 +96,15 @@ ieee80211_tdls_add_subband(struct ieee80211_sub_if_data *sdata, } } + /* all channels in the requested range are allowed - add them here */ + if (ch_cnt) { + u8 *pos = skb_put(skb, 2); + *pos++ = ieee80211_frequency_to_channel(subband_start); + *pos++ = ch_cnt; + + subband_cnt++; + } + return subband_cnt; } @@ -912,7 +928,7 @@ ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev, rcu_read_unlock(); } - ieee80211_flush_queues(local, sdata); + ieee80211_flush_queues(local, sdata, false); ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, action_code, dialog_token, status_code, @@ -952,7 +968,7 @@ ieee80211_tdls_mgmt_teardown(struct wiphy *wiphy, struct net_device *dev, */ ieee80211_stop_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN); - ieee80211_flush_queues(local, sdata); + ieee80211_flush_queues(local, sdata, false); ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, action_code, dialog_token, status_code, @@ -1098,7 +1114,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, */ tasklet_kill(&local->tx_pending_tasklet); /* flush a potentially queued teardown packet */ - ieee80211_flush_queues(local, sdata); + ieee80211_flush_queues(local, sdata, false); ret = sta_info_destroy_addr(sdata, peer); break; diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 8e461a02c6a8..263a9561eb26 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -825,6 +825,13 @@ DECLARE_EVENT_CLASS(sta_event, ) ); +DEFINE_EVENT(sta_event, drv_sta_statistics, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta), + TP_ARGS(local, sdata, sta) +); + DEFINE_EVENT(sta_event, drv_sta_add, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, @@ -1329,32 +1336,6 @@ DEFINE_EVENT(release_evt, drv_allow_buffered_frames, TP_ARGS(local, sta, tids, num_frames, reason, more_data) ); -TRACE_EVENT(drv_get_rssi, - TP_PROTO(struct ieee80211_local *local, struct ieee80211_sta *sta, - s8 rssi, int ret), - - TP_ARGS(local, sta, rssi, ret), - - TP_STRUCT__entry( - LOCAL_ENTRY - STA_ENTRY - __field(s8, rssi) - __field(int, ret) - ), - - TP_fast_assign( - LOCAL_ASSIGN; - STA_ASSIGN; - __entry->rssi = rssi; - __entry->ret = ret; - ), - - TP_printk( - LOCAL_PR_FMT STA_PR_FMT " rssi:%d ret:%d", - LOCAL_PR_ARG, STA_PR_ARG, __entry->rssi, __entry->ret - ) -); - DEFINE_EVENT(local_sdata_evt, drv_mgd_prepare_tx, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata), diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 058686a721a1..02ed6f60629a 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -815,6 +815,8 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) /* for pure STA mode without beacons, we can do it */ hdr->seq_ctrl = cpu_to_le16(tx->sdata->sequence_number); tx->sdata->sequence_number += 0x10; + if (tx->sta) + tx->sta->tx_msdu[IEEE80211_NUM_TIDS]++; return TX_CONTINUE; } @@ -831,6 +833,7 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) qc = ieee80211_get_qos_ctl(hdr); tid = *qc & IEEE80211_QOS_CTL_TID_MASK; seq = &tx->sta->tid_seq[tid]; + tx->sta->tx_msdu[tid]++; hdr->seq_ctrl = cpu_to_le16(*seq); @@ -3152,7 +3155,7 @@ int ieee80211_reserve_tid(struct ieee80211_sta *pubsta, u8 tid) } queues = BIT(sdata->vif.hw_queue[ieee802_1d_to_ac[tid]]); - __ieee80211_flush_queues(local, sdata, queues); + __ieee80211_flush_queues(local, sdata, queues, false); sta->reserved_tid = tid; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 974ebe70f5b0..83ba6cd9cf8d 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -578,7 +578,7 @@ ieee80211_get_vif_queues(struct ieee80211_local *local, void __ieee80211_flush_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - unsigned int queues) + unsigned int queues, bool drop) { if (!local->ops->flush) return; @@ -594,7 +594,7 @@ void __ieee80211_flush_queues(struct ieee80211_local *local, IEEE80211_QUEUE_STOP_REASON_FLUSH, false); - drv_flush(local, sdata, queues, false); + drv_flush(local, sdata, queues, drop); ieee80211_wake_queues_by_reason(&local->hw, queues, IEEE80211_QUEUE_STOP_REASON_FLUSH, @@ -602,9 +602,9 @@ void __ieee80211_flush_queues(struct ieee80211_local *local, } void ieee80211_flush_queues(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) + struct ieee80211_sub_if_data *sdata, bool drop) { - __ieee80211_flush_queues(local, sdata, 0); + __ieee80211_flush_queues(local, sdata, 0, drop); } void ieee80211_stop_vif_queues(struct ieee80211_local *local, @@ -1470,10 +1470,12 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, /* Check if any channel in this sband supports at least 80 MHz */ for (i = 0; i < sband->n_channels; i++) { - if (!(sband->channels[i].flags & IEEE80211_CHAN_NO_80MHZ)) { - have_80mhz = true; - break; - } + if (sband->channels[i].flags & (IEEE80211_CHAN_DISABLED | + IEEE80211_CHAN_NO_80MHZ)) + continue; + + have_80mhz = true; + break; } if (sband->vht_cap.vht_supported && have_80mhz) { @@ -1735,6 +1737,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) struct cfg80211_sched_scan_request *sched_scan_req; bool sched_scan_stopped = false; + /* nothing to do if HW shouldn't run */ + if (!local->open_count) + goto wake_up; + #ifdef CONFIG_PM if (local->suspended) local->resuming = true; @@ -1756,9 +1762,6 @@ int ieee80211_reconfig(struct ieee80211_local *local) reconfig_due_to_wowlan = true; } #endif - /* everything else happens only if HW was up & running */ - if (!local->open_count) - goto wake_up; /* * Upon resume hardware can sometimes be goofy due to @@ -2042,7 +2045,7 @@ 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 || reconfig_due_to_wowlan) + if (local->open_count && (!local->suspended || reconfig_due_to_wowlan)) drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART); if (!local->suspended) @@ -2054,7 +2057,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) mb(); local->resuming = false; - if (!reconfig_due_to_wowlan) + if (local->open_count && !reconfig_due_to_wowlan) drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_SUSPEND); list_for_each_entry(sdata, &local->interfaces, list) { diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index bc9e8fc48785..85f9596da07b 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -269,51 +269,54 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, sta->sta.bandwidth = ieee80211_sta_cur_vht_bw(sta); } -enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) +enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct sta_info *sta) { - struct ieee80211_sub_if_data *sdata = sta->sdata; - u32 cap = sta->sta.vht_cap.cap; - enum ieee80211_sta_rx_bandwidth bw; + struct ieee80211_sta_vht_cap *vht_cap = &sta->sta.vht_cap; + u32 cap_width; - if (!sta->sta.vht_cap.vht_supported) { - bw = sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? - IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20; - goto check_max; - } + if (!vht_cap->vht_supported) + return sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? + IEEE80211_STA_RX_BW_40 : + IEEE80211_STA_RX_BW_20; - switch (sdata->vif.bss_conf.chandef.width) { - default: - WARN_ON_ONCE(1); - /* fall through */ + cap_width = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; + + if (cap_width == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ || + cap_width == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) + return IEEE80211_STA_RX_BW_160; + + return IEEE80211_STA_RX_BW_80; +} + +static enum ieee80211_sta_rx_bandwidth +ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width) +{ + switch (width) { case NL80211_CHAN_WIDTH_20_NOHT: case NL80211_CHAN_WIDTH_20: - bw = IEEE80211_STA_RX_BW_20; - break; + return IEEE80211_STA_RX_BW_20; case NL80211_CHAN_WIDTH_40: - bw = sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? - IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20; - break; + return IEEE80211_STA_RX_BW_40; + case NL80211_CHAN_WIDTH_80: + return IEEE80211_STA_RX_BW_80; case NL80211_CHAN_WIDTH_160: - if ((cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) == - IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ) { - bw = IEEE80211_STA_RX_BW_160; - break; - } - /* fall through */ case NL80211_CHAN_WIDTH_80P80: - if ((cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) == - IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) { - bw = IEEE80211_STA_RX_BW_160; - break; - } - /* fall through */ - case NL80211_CHAN_WIDTH_80: - bw = IEEE80211_STA_RX_BW_80; + return IEEE80211_STA_RX_BW_160; + default: + WARN_ON_ONCE(1); + return IEEE80211_STA_RX_BW_20; } +} + +enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) +{ + struct ieee80211_sub_if_data *sdata = sta->sdata; + enum ieee80211_sta_rx_bandwidth bw; + + bw = ieee80211_chan_width_to_rx_bw(sdata->vif.bss_conf.chandef.width); + bw = min(bw, ieee80211_sta_cap_rx_bw(sta)); + bw = min(bw, sta->cur_max_bandwidth); - check_max: - if (bw > sta->cur_max_bandwidth) - bw = sta->cur_max_bandwidth; return bw; } diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 1d5341f3761d..5d3daae98bf0 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -183,6 +183,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, struct nf_conn *ct; struct net *net; + *diff = 0; + #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, * so turn this into a no-op for IPv6 packets @@ -191,8 +193,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; #endif - *diff = 0; - /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; @@ -322,6 +322,9 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, struct ip_vs_conn *n_cp; struct net *net; + /* no diff required for incoming packets */ + *diff = 0; + #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, * so turn this into a no-op for IPv6 packets @@ -330,9 +333,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; #endif - /* no diff required for incoming packets */ - *diff = 0; - /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index a11674806707..13fad8668f83 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -611,16 +611,15 @@ __nf_conntrack_confirm(struct sk_buff *skb) */ NF_CT_ASSERT(!nf_ct_is_confirmed(ct)); pr_debug("Confirming conntrack %p\n", ct); - /* We have to check the DYING flag inside the lock to prevent - a race against nf_ct_get_next_corpse() possibly called from - user context, else we insert an already 'dead' hash, blocking - further use of that particular connection -JM */ + /* We have to check the DYING flag after unlink to prevent + * a race against nf_ct_get_next_corpse() possibly called from + * user context, else we insert an already 'dead' hash, blocking + * further use of that particular connection -JM. + */ + nf_ct_del_from_dying_or_unconfirmed_list(ct); - if (unlikely(nf_ct_is_dying(ct))) { - nf_conntrack_double_unlock(hash, reply_hash); - local_bh_enable(); - return NF_ACCEPT; - } + if (unlikely(nf_ct_is_dying(ct))) + goto out; /* See if there's one in the list already, including reverse: NAT could have grabbed it without realizing, since we're @@ -636,8 +635,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) goto out; - nf_ct_del_from_dying_or_unconfirmed_list(ct); - /* Timer relative to confirmation time, not original setting time, otherwise we'd get timer wrap in weird delay cases. */ @@ -673,6 +670,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) return NF_ACCEPT; out: + nf_ct_add_to_dying_list(ct); nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert_failed); local_bh_enable(); @@ -1426,12 +1424,6 @@ void nf_ct_free_hashtable(void *hash, unsigned int size) } EXPORT_SYMBOL_GPL(nf_ct_free_hashtable); -void nf_conntrack_flush_report(struct net *net, u32 portid, int report) -{ - nf_ct_iterate_cleanup(net, kill_all, NULL, portid, report); -} -EXPORT_SYMBOL_GPL(nf_conntrack_flush_report); - static int untrack_refs(void) { int cnt = 0, cpu; @@ -1624,13 +1616,18 @@ int nf_conntrack_init_start(void) for (i = 0; i < CONNTRACK_LOCKS; i++) spin_lock_init(&nf_conntrack_locks[i]); - /* Idea from tcp.c: use 1/16384 of memory. On i386: 32MB - * machine has 512 buckets. >= 1GB machines have 16384 buckets. */ if (!nf_conntrack_htable_size) { + /* Idea from tcp.c: use 1/16384 of memory. + * On i386: 32MB machine has 512 buckets. + * >= 1GB machines have 16384 buckets. + * >= 4GB machines have 65536 buckets. + */ nf_conntrack_htable_size = (((totalram_pages << PAGE_SHIFT) / 16384) / sizeof(struct hlist_head)); - if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE)) + if (totalram_pages > (4 * (1024 * 1024 * 1024 / PAGE_SIZE))) + nf_conntrack_htable_size = 65536; + else if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE)) nf_conntrack_htable_size = 16384; if (nf_conntrack_htable_size < 32) nf_conntrack_htable_size = 32; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 1bd9ed9e62f6..d1c23940a86a 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -749,13 +749,47 @@ static int ctnetlink_done(struct netlink_callback *cb) return 0; } -struct ctnetlink_dump_filter { +struct ctnetlink_filter { struct { u_int32_t val; u_int32_t mask; } mark; }; +static struct ctnetlink_filter * +ctnetlink_alloc_filter(const struct nlattr * const cda[]) +{ +#ifdef CONFIG_NF_CONNTRACK_MARK + struct ctnetlink_filter *filter; + + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (filter == NULL) + return ERR_PTR(-ENOMEM); + + filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK])); + filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); + + return filter; +#else + return ERR_PTR(-EOPNOTSUPP); +#endif +} + +static int ctnetlink_filter_match(struct nf_conn *ct, void *data) +{ + struct ctnetlink_filter *filter = data; + + if (filter == NULL) + return 1; + +#ifdef CONFIG_NF_CONNTRACK_MARK + if ((ct->mark & filter->mark.mask) == filter->mark.val) + return 1; +#endif + + return 0; +} + static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { @@ -768,10 +802,6 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) int res; spinlock_t *lockp; -#ifdef CONFIG_NF_CONNTRACK_MARK - const struct ctnetlink_dump_filter *filter = cb->data; -#endif - last = (struct nf_conn *)cb->args[1]; local_bh_disable(); @@ -798,12 +828,9 @@ restart: continue; cb->args[1] = 0; } -#ifdef CONFIG_NF_CONNTRACK_MARK - if (filter && !((ct->mark & filter->mark.mask) == - filter->mark.val)) { + if (!ctnetlink_filter_match(ct, cb->data)) continue; - } -#endif + rcu_read_lock(); res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, @@ -1001,6 +1028,25 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { .len = NF_CT_LABELS_MAX_SIZE }, }; +static int ctnetlink_flush_conntrack(struct net *net, + const struct nlattr * const cda[], + u32 portid, int report) +{ + struct ctnetlink_filter *filter = NULL; + + if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) { + filter = ctnetlink_alloc_filter(cda); + if (IS_ERR(filter)) + return PTR_ERR(filter); + } + + nf_ct_iterate_cleanup(net, ctnetlink_filter_match, filter, + portid, report); + kfree(filter); + + return 0; +} + static int ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, @@ -1024,11 +1070,9 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3); else { - /* Flush the whole table */ - nf_conntrack_flush_report(net, - NETLINK_CB(skb).portid, - nlmsg_report(nlh)); - return 0; + return ctnetlink_flush_conntrack(net, cda, + NETLINK_CB(skb).portid, + nlmsg_report(nlh)); } if (err < 0) @@ -1076,21 +1120,16 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, .dump = ctnetlink_dump_table, .done = ctnetlink_done, }; -#ifdef CONFIG_NF_CONNTRACK_MARK + if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) { - struct ctnetlink_dump_filter *filter; + struct ctnetlink_filter *filter; - filter = kzalloc(sizeof(struct ctnetlink_dump_filter), - GFP_ATOMIC); - if (filter == NULL) - return -ENOMEM; + filter = ctnetlink_alloc_filter(cda); + if (IS_ERR(filter)) + return PTR_ERR(filter); - filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK])); - filter->mark.mask = - ntohl(nla_get_be32(cda[CTA_MARK_MASK])); c.data = filter; } -#endif return netlink_dump_start(ctnl, skb, nlh, &c); } diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index f6e2ae91a80b..ce3e840c8704 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -98,9 +98,9 @@ static void nf_ct_sack_block_adjust(struct sk_buff *skb, new_end_seq = htonl(ntohl(sack->end_seq) - seq->offset_before); - pr_debug("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n", - ntohl(sack->start_seq), new_start_seq, - ntohl(sack->end_seq), new_end_seq); + pr_debug("sack_adjust: start_seq: %u->%u, end_seq: %u->%u\n", + ntohl(sack->start_seq), ntohl(new_start_seq), + ntohl(sack->end_seq), ntohl(new_end_seq)); inet_proto_csum_replace4(&tcph->check, skb, sack->start_seq, new_start_seq, 0); diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 43c926cae9c0..0d8448f19dfe 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -425,8 +425,7 @@ static int netfilter_log_sysctl_init(struct net *net) nf_log_sysctl_table[i].procname = nf_log_sysctl_fnames[i]; nf_log_sysctl_table[i].data = NULL; - nf_log_sysctl_table[i].maxlen = - NFLOGGER_NAME_LEN * sizeof(char); + nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN; nf_log_sysctl_table[i].mode = 0644; nf_log_sysctl_table[i].proc_handler = nf_log_proc_dostring; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 129a8daa4abf..3b3ddb4fb9ee 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -713,16 +713,12 @@ static int nft_flush_table(struct nft_ctx *ctx) struct nft_chain *chain, *nc; struct nft_set *set, *ns; - list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) { + list_for_each_entry(chain, &ctx->table->chains, list) { ctx->chain = chain; err = nft_delrule_by_chain(ctx); if (err < 0) goto out; - - err = nft_delchain(ctx); - if (err < 0) - goto out; } list_for_each_entry_safe(set, ns, &ctx->table->sets, list) { @@ -735,6 +731,14 @@ static int nft_flush_table(struct nft_ctx *ctx) goto out; } + list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) { + ctx->chain = chain; + + err = nft_delchain(ctx); + if (err < 0) + goto out; + } + err = nft_deltable(ctx); out: return err; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index cde4a6702fa3..8b117c90ecd7 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -272,7 +272,7 @@ static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb) static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, u_int16_t subsys_id) { - struct sk_buff *nskb, *oskb = skb; + struct sk_buff *oskb = skb; struct net *net = sock_net(skb->sk); const struct nfnetlink_subsystem *ss; const struct nfnl_callback *nc; @@ -283,12 +283,11 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, if (subsys_id >= NFNL_SUBSYS_COUNT) return netlink_ack(skb, nlh, -EINVAL); replay: - nskb = netlink_skb_clone(oskb, GFP_KERNEL); - if (!nskb) + skb = netlink_skb_clone(oskb, GFP_KERNEL); + if (!skb) return netlink_ack(oskb, nlh, -ENOMEM); - nskb->sk = oskb->sk; - skb = nskb; + skb->sk = oskb->sk; nfnl_lock(subsys_id); ss = rcu_dereference_protected(table[subsys_id].subsys, @@ -305,7 +304,7 @@ replay: { nfnl_unlock(subsys_id); netlink_ack(skb, nlh, -EOPNOTSUPP); - return kfree_skb(nskb); + return kfree_skb(skb); } } @@ -321,7 +320,8 @@ replay: nlh = nlmsg_hdr(skb); err = 0; - if (nlh->nlmsg_len < NLMSG_HDRLEN) { + if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) || + skb->len < nlh->nlmsg_len) { err = -EINVAL; goto ack; } @@ -385,7 +385,7 @@ replay: nfnl_err_reset(&err_list); ss->abort(oskb); nfnl_unlock(subsys_id); - kfree_skb(nskb); + kfree_skb(skb); goto replay; } } @@ -426,7 +426,7 @@ done: nfnl_err_deliver(&err_list, oskb); nfnl_unlock(subsys_id); - kfree_skb(nskb); + kfree_skb(skb); } static void nfnetlink_rcv(struct sk_buff *skb) @@ -469,7 +469,7 @@ static int nfnetlink_bind(struct net *net, int group) int type; if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX) - return -EINVAL; + return 0; type = nfnl_group2type[group]; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 9e287cb56a04..a5599fc51a6f 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -86,7 +86,7 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple, static int nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct) { - const struct nf_conn_help *help = nfct_help(ct); + struct nf_conn_help *help = nfct_help(ct); if (attr == NULL) return -EINVAL; @@ -94,7 +94,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct) if (help->helper->data_len == 0) return -EINVAL; - memcpy(&help->data, nla_data(attr), help->helper->data_len); + memcpy(help->data, nla_data(attr), help->helper->data_len); return 0; } diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 1e316ce4cb5d..75887d7d2c6a 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -33,7 +33,7 @@ static bool nft_hash_lookup(const struct nft_set *set, const struct nft_data *key, struct nft_data *data) { - const struct rhashtable *priv = nft_set_priv(set); + struct rhashtable *priv = nft_set_priv(set); const struct nft_hash_elem *he; he = rhashtable_lookup(priv, key); @@ -83,46 +83,53 @@ static void nft_hash_remove(const struct nft_set *set, const struct nft_set_elem *elem) { struct rhashtable *priv = nft_set_priv(set); - struct rhash_head *he, __rcu **pprev; - pprev = elem->cookie; - he = rht_dereference((*pprev), priv); + rhashtable_remove(priv, elem->cookie); + synchronize_rcu(); + kfree(elem->cookie); +} - rhashtable_remove_pprev(priv, he, pprev); +struct nft_compare_arg { + const struct nft_set *set; + struct nft_set_elem *elem; +}; - synchronize_rcu(); - kfree(he); +static bool nft_hash_compare(void *ptr, void *arg) +{ + struct nft_hash_elem *he = ptr; + struct nft_compare_arg *x = arg; + + if (!nft_data_cmp(&he->key, &x->elem->key, x->set->klen)) { + x->elem->cookie = he; + x->elem->flags = 0; + if (x->set->flags & NFT_SET_MAP) + nft_data_copy(&x->elem->data, he->data); + + return true; + } + + return false; } static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem) { - const struct rhashtable *priv = nft_set_priv(set); - const struct bucket_table *tbl = rht_dereference_rcu(priv->tbl, priv); - struct rhash_head __rcu * const *pprev; - struct nft_hash_elem *he; - u32 h; - - h = rhashtable_hashfn(priv, &elem->key, set->klen); - pprev = &tbl->buckets[h]; - rht_for_each_entry_rcu(he, tbl->buckets[h], node) { - if (nft_data_cmp(&he->key, &elem->key, set->klen)) { - pprev = &he->node.next; - continue; - } + struct rhashtable *priv = nft_set_priv(set); + struct nft_compare_arg arg = { + .set = set, + .elem = elem, + }; - elem->cookie = (void *)pprev; - elem->flags = 0; - if (set->flags & NFT_SET_MAP) - nft_data_copy(&elem->data, he->data); + if (rhashtable_lookup_compare(priv, &elem->key, + &nft_hash_compare, &arg)) return 0; - } + return -ENOENT; } static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, struct nft_set_iter *iter) { - const struct rhashtable *priv = nft_set_priv(set); + struct rhashtable *priv = nft_set_priv(set); const struct bucket_table *tbl; const struct nft_hash_elem *he; struct nft_set_elem elem; @@ -130,7 +137,9 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, tbl = rht_dereference_rcu(priv->tbl, priv); for (i = 0; i < tbl->size; i++) { - rht_for_each_entry_rcu(he, tbl->buckets[i], node) { + struct rhash_head *pos; + + rht_for_each_entry_rcu(he, pos, tbl, i, node) { if (iter->count < iter->skip) goto cont; @@ -153,13 +162,6 @@ static unsigned int nft_hash_privsize(const struct nlattr * const nla[]) return sizeof(struct rhashtable); } -#ifdef CONFIG_PROVE_LOCKING -static int lockdep_nfnl_lock_is_held(void *parent) -{ - return lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES); -} -#endif - static int nft_hash_init(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const tb[]) @@ -173,9 +175,6 @@ static int nft_hash_init(const struct nft_set *set, .hashfn = jhash, .grow_decision = rht_grow_above_75, .shrink_decision = rht_shrink_below_30, -#ifdef CONFIG_PROVE_LOCKING - .mutex_is_held = lockdep_nfnl_lock_is_held, -#endif }; return rhashtable_init(priv, ¶ms); @@ -183,18 +182,23 @@ static int nft_hash_init(const struct nft_set *set, static void nft_hash_destroy(const struct nft_set *set) { - const struct rhashtable *priv = nft_set_priv(set); - const struct bucket_table *tbl = priv->tbl; - struct nft_hash_elem *he, *next; + struct rhashtable *priv = nft_set_priv(set); + const struct bucket_table *tbl; + struct nft_hash_elem *he; + struct rhash_head *pos, *next; unsigned int i; + /* Stop an eventual async resizing */ + priv->being_destroyed = true; + mutex_lock(&priv->mutex); + + tbl = rht_dereference(priv->tbl, priv); for (i = 0; i < tbl->size; i++) { - for (he = rht_entry(tbl->buckets[i], struct nft_hash_elem, node); - he != NULL; he = next) { - next = rht_entry(he->node.next, struct nft_hash_elem, node); + rht_for_each_entry_safe(he, pos, next, tbl, i, node) nft_hash_elem_destroy(set, he); - } } + mutex_unlock(&priv->mutex); + rhashtable_destroy(priv); } diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index afe2b0b45ec4..aff54fb1c8a0 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -65,10 +65,10 @@ static void nft_nat_eval(const struct nft_expr *expr, } if (priv->sreg_proto_min) { - range.min_proto.all = (__force __be16) - data[priv->sreg_proto_min].data[0]; - range.max_proto.all = (__force __be16) - data[priv->sreg_proto_max].data[0]; + range.min_proto.all = + *(__be16 *)&data[priv->sreg_proto_min].data[0]; + range.max_proto.all = + *(__be16 *)&data[priv->sreg_proto_max].data[0]; range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index c529161cdbf8..0778855ea5e7 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -225,6 +225,8 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) rcu_read_lock(); list_for_each_entry_rcu(kf, &xt_osf_fingers[df], finger_entry) { + int foptsize, optnum; + f = &kf->finger; if (!(info->flags & XT_OSF_LOG) && strcmp(info->genre, f->genre)) @@ -233,110 +235,109 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) optp = _optp; fmatch = FMATCH_WRONG; - if (totlen == f->ss && xt_osf_ttl(skb, info, f->ttl)) { - int foptsize, optnum; + if (totlen != f->ss || !xt_osf_ttl(skb, info, f->ttl)) + continue; - /* - * Should not happen if userspace parser was written correctly. - */ - if (f->wss.wc >= OSF_WSS_MAX) - continue; + /* + * Should not happen if userspace parser was written correctly. + */ + if (f->wss.wc >= OSF_WSS_MAX) + continue; - /* Check options */ + /* Check options */ - foptsize = 0; - for (optnum = 0; optnum < f->opt_num; ++optnum) - foptsize += f->opt[optnum].length; + foptsize = 0; + for (optnum = 0; optnum < f->opt_num; ++optnum) + foptsize += f->opt[optnum].length; - if (foptsize > MAX_IPOPTLEN || - optsize > MAX_IPOPTLEN || - optsize != foptsize) - continue; + if (foptsize > MAX_IPOPTLEN || + optsize > MAX_IPOPTLEN || + optsize != foptsize) + continue; - check_WSS = f->wss.wc; + check_WSS = f->wss.wc; - for (optnum = 0; optnum < f->opt_num; ++optnum) { - if (f->opt[optnum].kind == (*optp)) { - __u32 len = f->opt[optnum].length; - const __u8 *optend = optp + len; - int loop_cont = 0; + for (optnum = 0; optnum < f->opt_num; ++optnum) { + if (f->opt[optnum].kind == (*optp)) { + __u32 len = f->opt[optnum].length; + const __u8 *optend = optp + len; + int loop_cont = 0; - fmatch = FMATCH_OK; + fmatch = FMATCH_OK; - switch (*optp) { - case OSFOPT_MSS: - mss = optp[3]; - mss <<= 8; - mss |= optp[2]; + switch (*optp) { + case OSFOPT_MSS: + mss = optp[3]; + mss <<= 8; + mss |= optp[2]; - mss = ntohs((__force __be16)mss); - break; - case OSFOPT_TS: - loop_cont = 1; - break; - } + mss = ntohs((__force __be16)mss); + break; + case OSFOPT_TS: + loop_cont = 1; + break; + } - optp = optend; - } else - fmatch = FMATCH_OPT_WRONG; + optp = optend; + } else + fmatch = FMATCH_OPT_WRONG; - if (fmatch != FMATCH_OK) - break; - } + if (fmatch != FMATCH_OK) + break; + } - if (fmatch != FMATCH_OPT_WRONG) { - fmatch = FMATCH_WRONG; + if (fmatch != FMATCH_OPT_WRONG) { + fmatch = FMATCH_WRONG; - switch (check_WSS) { - case OSF_WSS_PLAIN: - if (f->wss.val == 0 || window == f->wss.val) - fmatch = FMATCH_OK; - break; - case OSF_WSS_MSS: - /* - * Some smart modems decrease mangle MSS to - * SMART_MSS_2, so we check standard, decreased - * and the one provided in the fingerprint MSS - * values. - */ + switch (check_WSS) { + case OSF_WSS_PLAIN: + if (f->wss.val == 0 || window == f->wss.val) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MSS: + /* + * Some smart modems decrease mangle MSS to + * SMART_MSS_2, so we check standard, decreased + * and the one provided in the fingerprint MSS + * values. + */ #define SMART_MSS_1 1460 #define SMART_MSS_2 1448 - if (window == f->wss.val * mss || - window == f->wss.val * SMART_MSS_1 || - window == f->wss.val * SMART_MSS_2) - fmatch = FMATCH_OK; - break; - case OSF_WSS_MTU: - if (window == f->wss.val * (mss + 40) || - window == f->wss.val * (SMART_MSS_1 + 40) || - window == f->wss.val * (SMART_MSS_2 + 40)) - fmatch = FMATCH_OK; - break; - case OSF_WSS_MODULO: - if ((window % f->wss.val) == 0) - fmatch = FMATCH_OK; - break; - } + if (window == f->wss.val * mss || + window == f->wss.val * SMART_MSS_1 || + window == f->wss.val * SMART_MSS_2) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MTU: + if (window == f->wss.val * (mss + 40) || + window == f->wss.val * (SMART_MSS_1 + 40) || + window == f->wss.val * (SMART_MSS_2 + 40)) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MODULO: + if ((window % f->wss.val) == 0) + fmatch = FMATCH_OK; + break; } + } - if (fmatch != FMATCH_OK) - continue; + if (fmatch != FMATCH_OK) + continue; - fcount++; + fcount++; - if (info->flags & XT_OSF_LOG) - nf_log_packet(net, p->family, p->hooknum, skb, - p->in, p->out, NULL, - "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n", - f->genre, f->version, f->subtype, - &ip->saddr, ntohs(tcp->source), - &ip->daddr, ntohs(tcp->dest), - f->ttl - ip->ttl); + if (info->flags & XT_OSF_LOG) + nf_log_packet(net, p->family, p->hooknum, skb, + p->in, p->out, NULL, + "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n", + f->genre, f->version, f->subtype, + &ip->saddr, ntohs(tcp->source), + &ip->daddr, ntohs(tcp->dest), + f->ttl - ip->ttl); - if ((info->flags & XT_OSF_LOG) && - info->loglevel == XT_OSF_LOGLEVEL_FIRST) - break; - } + if ((info->flags & XT_OSF_LOG) && + info->loglevel == XT_OSF_LOGLEVEL_FIRST) + break; } rcu_read_unlock(); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 84ea76ca3f1f..7a94185bde6b 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -97,12 +97,12 @@ static int netlink_dump(struct sock *sk); static void netlink_skb_destructor(struct sk_buff *skb); /* nl_table locking explained: - * Lookup and traversal are protected with nl_sk_hash_lock or nl_table_lock - * combined with an RCU read-side lock. Insertion and removal are protected - * with nl_sk_hash_lock while using RCU list modification primitives and may - * run in parallel to nl_table_lock protected lookups. Destruction of the - * Netlink socket may only occur *after* nl_table_lock has been acquired - * either during or after the socket has been removed from the list. + * Lookup and traversal are protected with an RCU read-side lock. Insertion + * and removal are protected with per bucket lock while using RCU list + * modification primitives and may run in parallel to RCU protected lookups. + * Destruction of the Netlink socket may only occur *after* nl_table_lock has + * been acquired * either during or after the socket has been removed from + * the list and after an RCU grace period. */ DEFINE_RWLOCK(nl_table_lock); EXPORT_SYMBOL_GPL(nl_table_lock); @@ -110,19 +110,6 @@ static atomic_t nl_table_users = ATOMIC_INIT(0); #define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock)); -/* Protects netlink socket hash table mutations */ -DEFINE_MUTEX(nl_sk_hash_lock); -EXPORT_SYMBOL_GPL(nl_sk_hash_lock); - -#ifdef CONFIG_PROVE_LOCKING -static int lockdep_nl_sk_hash_is_held(void *parent) -{ - if (debug_locks) - return lockdep_is_held(&nl_sk_hash_lock) || lockdep_is_held(&nl_table_lock); - return 1; -} -#endif - static ATOMIC_NOTIFIER_HEAD(netlink_chain); static DEFINE_SPINLOCK(netlink_tap_lock); @@ -1002,26 +989,34 @@ static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid, .net = net, .portid = portid, }; - u32 hash; - hash = rhashtable_hashfn(&table->hash, &portid, sizeof(portid)); - - return rhashtable_lookup_compare(&table->hash, hash, + return rhashtable_lookup_compare(&table->hash, &portid, &netlink_compare, &arg); } +static bool __netlink_insert(struct netlink_table *table, struct sock *sk, + struct net *net) +{ + struct netlink_compare_arg arg = { + .net = net, + .portid = nlk_sk(sk)->portid, + }; + + return rhashtable_lookup_compare_insert(&table->hash, + &nlk_sk(sk)->node, + &netlink_compare, &arg); +} + static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) { struct netlink_table *table = &nl_table[protocol]; struct sock *sk; - read_lock(&nl_table_lock); rcu_read_lock(); sk = __netlink_lookup(table, portid, net); if (sk) sock_hold(sk); rcu_read_unlock(); - read_unlock(&nl_table_lock); return sk; } @@ -1055,26 +1050,30 @@ netlink_update_listeners(struct sock *sk) static int netlink_insert(struct sock *sk, struct net *net, u32 portid) { struct netlink_table *table = &nl_table[sk->sk_protocol]; - int err = -EADDRINUSE; + int err; - mutex_lock(&nl_sk_hash_lock); - if (__netlink_lookup(table, portid, net)) - goto err; + lock_sock(sk); err = -EBUSY; if (nlk_sk(sk)->portid) goto err; err = -ENOMEM; - if (BITS_PER_LONG > 32 && unlikely(table->hash.nelems >= UINT_MAX)) + if (BITS_PER_LONG > 32 && + unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX)) goto err; nlk_sk(sk)->portid = portid; sock_hold(sk); - rhashtable_insert(&table->hash, &nlk_sk(sk)->node); + err = 0; + if (!__netlink_insert(table, sk, net)) { + err = -EADDRINUSE; + sock_put(sk); + } + err: - mutex_unlock(&nl_sk_hash_lock); + release_sock(sk); return err; } @@ -1082,13 +1081,11 @@ static void netlink_remove(struct sock *sk) { struct netlink_table *table; - mutex_lock(&nl_sk_hash_lock); table = &nl_table[sk->sk_protocol]; if (rhashtable_remove(&table->hash, &nlk_sk(sk)->node)) { WARN_ON(atomic_read(&sk->sk_refcnt) == 1); __sock_put(sk); } - mutex_unlock(&nl_sk_hash_lock); netlink_table_grab(); if (nlk_sk(sk)->subscriptions) { @@ -1194,6 +1191,13 @@ out_module: goto out; } +static void deferred_put_nlk_sk(struct rcu_head *head) +{ + struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); + + sock_put(&nlk->sk); +} + static int netlink_release(struct socket *sock) { struct sock *sk = sock->sk; @@ -1259,7 +1263,7 @@ static int netlink_release(struct socket *sock) local_bh_disable(); sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); local_bh_enable(); - sock_put(sk); + call_rcu(&nlk->rcu, deferred_put_nlk_sk); return 0; } @@ -1274,7 +1278,6 @@ static int netlink_autobind(struct socket *sock) retry: cond_resched(); - netlink_table_grab(); rcu_read_lock(); if (__netlink_lookup(table, portid, net)) { /* Bind collision, search negative portid values. */ @@ -1282,11 +1285,9 @@ retry: if (rover > -4097) rover = -4097; rcu_read_unlock(); - netlink_table_ungrab(); goto retry; } rcu_read_unlock(); - netlink_table_ungrab(); err = netlink_insert(sk, net, portid); if (err == -EADDRINUSE) @@ -2901,7 +2902,9 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); for (j = 0; j < tbl->size; j++) { - rht_for_each_entry_rcu(nlk, tbl->buckets[j], node) { + struct rhash_head *node; + + rht_for_each_entry_rcu(nlk, node, tbl, j, node) { s = (struct sock *)nlk; if (sock_net(s) != seq_file_net(seq)) @@ -2919,9 +2922,8 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) } static void *netlink_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(nl_table_lock) __acquires(RCU) + __acquires(RCU) { - read_lock(&nl_table_lock); rcu_read_lock(); return *pos ? netlink_seq_socket_idx(seq, *pos - 1) : SEQ_START_TOKEN; } @@ -2929,6 +2931,8 @@ static void *netlink_seq_start(struct seq_file *seq, loff_t *pos) static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct rhashtable *ht; + const struct bucket_table *tbl; + struct rhash_head *node; struct netlink_sock *nlk; struct nl_seq_iter *iter; struct net *net; @@ -2945,17 +2949,17 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) i = iter->link; ht = &nl_table[i].hash; - rht_for_each_entry(nlk, nlk->node.next, ht, node) + tbl = rht_dereference_rcu(ht->tbl, ht); + rht_for_each_entry_rcu_continue(nlk, node, nlk->node.next, tbl, iter->hash_idx, node) if (net_eq(sock_net((struct sock *)nlk), net)) return nlk; j = iter->hash_idx + 1; do { - const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); for (; j < tbl->size; j++) { - rht_for_each_entry(nlk, tbl->buckets[j], ht, node) { + rht_for_each_entry_rcu(nlk, node, tbl, j, node) { if (net_eq(sock_net((struct sock *)nlk), net)) { iter->link = i; iter->hash_idx = j; @@ -2971,10 +2975,9 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void netlink_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) __releases(nl_table_lock) + __releases(RCU) { rcu_read_unlock(); - read_unlock(&nl_table_lock); } @@ -3121,9 +3124,6 @@ static int __init netlink_proto_init(void) .max_shift = 16, /* 64K */ .grow_decision = rht_grow_above_75, .shrink_decision = rht_shrink_below_30, -#ifdef CONFIG_PROVE_LOCKING - .mutex_is_held = lockdep_nl_sk_hash_is_held, -#endif }; if (err != 0) diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index f123a88496f8..7518375782f5 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -50,6 +50,7 @@ struct netlink_sock { #endif /* CONFIG_NETLINK_MMAP */ struct rhash_head node; + struct rcu_head rcu; }; static inline struct netlink_sock *nlk_sk(struct sock *sk) @@ -73,6 +74,5 @@ struct netlink_table { extern struct netlink_table *nl_table; extern rwlock_t nl_table_lock; -extern struct mutex nl_sk_hash_lock; #endif diff --git a/net/netlink/diag.c b/net/netlink/diag.c index de8c74a3c061..bb59a7ed0859 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -103,7 +103,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, { struct netlink_table *tbl = &nl_table[protocol]; struct rhashtable *ht = &tbl->hash; - const struct bucket_table *htbl = rht_dereference(ht->tbl, ht); + const struct bucket_table *htbl = rht_dereference_rcu(ht->tbl, ht); struct net *net = sock_net(skb->sk); struct netlink_diag_req *req; struct netlink_sock *nlsk; @@ -113,7 +113,9 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, req = nlmsg_data(cb->nlh); for (i = 0; i < htbl->size; i++) { - rht_for_each_entry(nlsk, htbl->buckets[i], ht, node) { + struct rhash_head *pos; + + rht_for_each_entry_rcu(nlsk, pos, htbl, i, node) { sk = (struct sock *)nlsk; if (!net_eq(sock_net(sk), net)) @@ -170,7 +172,7 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) req = nlmsg_data(cb->nlh); - mutex_lock(&nl_sk_hash_lock); + rcu_read_lock(); read_lock(&nl_table_lock); if (req->sdiag_protocol == NDIAG_PROTO_ALL) { @@ -184,7 +186,7 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) } else { if (req->sdiag_protocol >= MAX_LINKS) { read_unlock(&nl_table_lock); - mutex_unlock(&nl_sk_hash_lock); + rcu_read_unlock(); return -ENOENT; } @@ -192,7 +194,7 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) } read_unlock(&nl_table_lock); - mutex_unlock(&nl_sk_hash_lock); + rcu_read_unlock(); return skb->len; } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 770064c83711..b4cffe686126 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -212,7 +212,7 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key) int err; err = skb_vlan_pop(skb); - if (vlan_tx_tag_present(skb)) + if (skb_vlan_tag_present(skb)) invalidate_flow_key(key); else key->eth.tci = 0; @@ -222,7 +222,7 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key) static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_action_push_vlan *vlan) { - if (vlan_tx_tag_present(skb)) + if (skb_vlan_tag_present(skb)) invalidate_flow_key(key); else key->eth.tci = vlan->vlan_tci; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 4e9a5f035cbc..8bda3cc12344 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -419,7 +419,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, if (!dp_ifindex) return -ENODEV; - if (vlan_tx_tag_present(skb)) { + if (skb_vlan_tag_present(skb)) { nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; @@ -524,7 +524,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) struct vport *input_vport; int len; int err; - bool log = !a[OVS_FLOW_ATTR_PROBE]; + bool log = !a[OVS_PACKET_ATTR_PROBE]; err = -EINVAL; if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] || @@ -610,6 +610,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = { [OVS_PACKET_ATTR_PACKET] = { .len = ETH_HLEN }, [OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED }, [OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED }, + [OVS_PACKET_ATTR_PROBE] = { .type = NLA_FLAG }, }; static const struct genl_ops dp_packet_genl_ops[] = { diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 70bef2ab7f2b..e2c348b8baca 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -70,6 +70,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, { struct flow_stats *stats; int node = numa_node_id(); + int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); stats = rcu_dereference(flow->stats[node]); @@ -105,7 +106,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, if (likely(new_stats)) { new_stats->used = jiffies; new_stats->packet_count = 1; - new_stats->byte_count = skb->len; + new_stats->byte_count = len; new_stats->tcp_flags = tcp_flags; spin_lock_init(&new_stats->lock); @@ -120,7 +121,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, stats->used = jiffies; stats->packet_count++; - stats->byte_count += skb->len; + stats->byte_count += len; stats->tcp_flags |= tcp_flags; unlock: spin_unlock(&stats->lock); @@ -471,7 +472,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) */ key->eth.tci = 0; - if (vlan_tx_tag_present(skb)) + if (skb_vlan_tag_present(skb)) key->eth.tci = htons(skb->vlan_tci); else if (eth->h_proto == htons(ETH_P_8021Q)) if (unlikely(parse_vlan(skb, key))) @@ -690,7 +691,7 @@ int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info, BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) * 8)) - 1 > sizeof(key->tun_opts)); - memcpy(GENEVE_OPTS(key, tun_info->options_len), + memcpy(TUN_METADATA_OPTS(key, tun_info->options_len), tun_info->options, tun_info->options_len); key->tun_opts_len = tun_info->options_len; } else { diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index a8b30f334388..d3d0a406562d 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -53,7 +53,7 @@ struct ovs_key_ipv4_tunnel { struct ovs_tunnel_info { struct ovs_key_ipv4_tunnel tunnel; - const struct geneve_opt *options; + const void *options; u8 options_len; }; @@ -61,10 +61,10 @@ struct ovs_tunnel_info { * maximum size. This allows us to get the benefits of variable length * matching for small options. */ -#define GENEVE_OPTS(flow_key, opt_len) \ - ((struct geneve_opt *)((flow_key)->tun_opts + \ - FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \ - opt_len)) +#define TUN_METADATA_OFFSET(opt_len) \ + (FIELD_SIZEOF(struct sw_flow_key, tun_opts) - opt_len) +#define TUN_METADATA_OPTS(flow_key, opt_len) \ + ((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len))) static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, __be32 saddr, __be32 daddr, @@ -73,7 +73,7 @@ static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, __be16 tp_dst, __be64 tun_id, __be16 tun_flags, - const struct geneve_opt *opts, + const void *opts, u8 opts_len) { tun_info->tunnel.tun_id = tun_id; @@ -105,7 +105,7 @@ static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, __be16 tp_dst, __be64 tun_id, __be16 tun_flags, - const struct geneve_opt *opts, + const void *opts, u8 opts_len) { __ovs_flow_tun_info_init(tun_info, iph->saddr, iph->daddr, diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index d1eecf707613..d210d1be3470 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -49,6 +49,14 @@ #include <net/mpls.h> #include "flow_netlink.h" +#include "vport-vxlan.h" + +struct ovs_len_tbl { + int len; + const struct ovs_len_tbl *next; +}; + +#define OVS_ATTR_NESTED -1 static void update_range(struct sw_flow_match *match, size_t offset, size_t size, bool is_mask) @@ -261,6 +269,9 @@ size_t ovs_tun_key_attr_size(void) + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_OAM */ + nla_total_size(256) /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */ + /* OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS is mutually exclusive with + * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it. + */ + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */ + nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */ } @@ -289,29 +300,45 @@ size_t ovs_key_attr_size(void) + nla_total_size(28); /* OVS_KEY_ATTR_ND */ } +static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = { + [OVS_TUNNEL_KEY_ATTR_ID] = { .len = sizeof(u64) }, + [OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = { .len = sizeof(u32) }, + [OVS_TUNNEL_KEY_ATTR_IPV4_DST] = { .len = sizeof(u32) }, + [OVS_TUNNEL_KEY_ATTR_TOS] = { .len = 1 }, + [OVS_TUNNEL_KEY_ATTR_TTL] = { .len = 1 }, + [OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = { .len = 0 }, + [OVS_TUNNEL_KEY_ATTR_CSUM] = { .len = 0 }, + [OVS_TUNNEL_KEY_ATTR_TP_SRC] = { .len = sizeof(u16) }, + [OVS_TUNNEL_KEY_ATTR_TP_DST] = { .len = sizeof(u16) }, + [OVS_TUNNEL_KEY_ATTR_OAM] = { .len = 0 }, + [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_NESTED }, + [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED }, +}; + /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ -static const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { - [OVS_KEY_ATTR_ENCAP] = -1, - [OVS_KEY_ATTR_PRIORITY] = sizeof(u32), - [OVS_KEY_ATTR_IN_PORT] = sizeof(u32), - [OVS_KEY_ATTR_SKB_MARK] = sizeof(u32), - [OVS_KEY_ATTR_ETHERNET] = sizeof(struct ovs_key_ethernet), - [OVS_KEY_ATTR_VLAN] = sizeof(__be16), - [OVS_KEY_ATTR_ETHERTYPE] = sizeof(__be16), - [OVS_KEY_ATTR_IPV4] = sizeof(struct ovs_key_ipv4), - [OVS_KEY_ATTR_IPV6] = sizeof(struct ovs_key_ipv6), - [OVS_KEY_ATTR_TCP] = sizeof(struct ovs_key_tcp), - [OVS_KEY_ATTR_TCP_FLAGS] = sizeof(__be16), - [OVS_KEY_ATTR_UDP] = sizeof(struct ovs_key_udp), - [OVS_KEY_ATTR_SCTP] = sizeof(struct ovs_key_sctp), - [OVS_KEY_ATTR_ICMP] = sizeof(struct ovs_key_icmp), - [OVS_KEY_ATTR_ICMPV6] = sizeof(struct ovs_key_icmpv6), - [OVS_KEY_ATTR_ARP] = sizeof(struct ovs_key_arp), - [OVS_KEY_ATTR_ND] = sizeof(struct ovs_key_nd), - [OVS_KEY_ATTR_RECIRC_ID] = sizeof(u32), - [OVS_KEY_ATTR_DP_HASH] = sizeof(u32), - [OVS_KEY_ATTR_TUNNEL] = -1, - [OVS_KEY_ATTR_MPLS] = sizeof(struct ovs_key_mpls), +static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { + [OVS_KEY_ATTR_ENCAP] = { .len = OVS_ATTR_NESTED }, + [OVS_KEY_ATTR_PRIORITY] = { .len = sizeof(u32) }, + [OVS_KEY_ATTR_IN_PORT] = { .len = sizeof(u32) }, + [OVS_KEY_ATTR_SKB_MARK] = { .len = sizeof(u32) }, + [OVS_KEY_ATTR_ETHERNET] = { .len = sizeof(struct ovs_key_ethernet) }, + [OVS_KEY_ATTR_VLAN] = { .len = sizeof(__be16) }, + [OVS_KEY_ATTR_ETHERTYPE] = { .len = sizeof(__be16) }, + [OVS_KEY_ATTR_IPV4] = { .len = sizeof(struct ovs_key_ipv4) }, + [OVS_KEY_ATTR_IPV6] = { .len = sizeof(struct ovs_key_ipv6) }, + [OVS_KEY_ATTR_TCP] = { .len = sizeof(struct ovs_key_tcp) }, + [OVS_KEY_ATTR_TCP_FLAGS] = { .len = sizeof(__be16) }, + [OVS_KEY_ATTR_UDP] = { .len = sizeof(struct ovs_key_udp) }, + [OVS_KEY_ATTR_SCTP] = { .len = sizeof(struct ovs_key_sctp) }, + [OVS_KEY_ATTR_ICMP] = { .len = sizeof(struct ovs_key_icmp) }, + [OVS_KEY_ATTR_ICMPV6] = { .len = sizeof(struct ovs_key_icmpv6) }, + [OVS_KEY_ATTR_ARP] = { .len = sizeof(struct ovs_key_arp) }, + [OVS_KEY_ATTR_ND] = { .len = sizeof(struct ovs_key_nd) }, + [OVS_KEY_ATTR_RECIRC_ID] = { .len = sizeof(u32) }, + [OVS_KEY_ATTR_DP_HASH] = { .len = sizeof(u32) }, + [OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED, + .next = ovs_tunnel_key_lens, }, + [OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) }, }; static bool is_all_zero(const u8 *fp, size_t size) @@ -352,8 +379,8 @@ static int __parse_flow_nlattrs(const struct nlattr *attr, return -EINVAL; } - expected_len = ovs_key_lens[type]; - if (nla_len(nla) != expected_len && expected_len != -1) { + expected_len = ovs_key_lens[type].len; + if (nla_len(nla) != expected_len && expected_len != OVS_ATTR_NESTED) { OVS_NLERR(log, "Key %d has unexpected len %d expected %d", type, nla_len(nla), expected_len); return -EINVAL; @@ -432,13 +459,47 @@ static int genev_tun_opt_from_nlattr(const struct nlattr *a, SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true); } - opt_key_offset = (unsigned long)GENEVE_OPTS((struct sw_flow_key *)0, - nla_len(a)); + opt_key_offset = TUN_METADATA_OFFSET(nla_len(a)); SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, nla_data(a), nla_len(a), is_mask); return 0; } +static const struct nla_policy vxlan_opt_policy[OVS_VXLAN_EXT_MAX + 1] = { + [OVS_VXLAN_EXT_GBP] = { .type = NLA_U32 }, +}; + +static int vxlan_tun_opt_from_nlattr(const struct nlattr *a, + struct sw_flow_match *match, bool is_mask, + bool log) +{ + struct nlattr *tb[OVS_VXLAN_EXT_MAX+1]; + unsigned long opt_key_offset; + struct ovs_vxlan_opts opts; + int err; + + BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); + + err = nla_parse_nested(tb, OVS_VXLAN_EXT_MAX, a, vxlan_opt_policy); + if (err < 0) + return err; + + memset(&opts, 0, sizeof(opts)); + + if (tb[OVS_VXLAN_EXT_GBP]) + opts.gbp = nla_get_u32(tb[OVS_VXLAN_EXT_GBP]); + + if (!is_mask) + SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false); + else + SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true); + + opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts)); + SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts), + is_mask); + return 0; +} + static int ipv4_tun_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) @@ -447,35 +508,22 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, int rem; bool ttl = false; __be16 tun_flags = 0; + int opts_type = 0; nla_for_each_nested(a, attr, rem) { int type = nla_type(a); int err; - static const u32 ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = { - [OVS_TUNNEL_KEY_ATTR_ID] = sizeof(u64), - [OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = sizeof(u32), - [OVS_TUNNEL_KEY_ATTR_IPV4_DST] = sizeof(u32), - [OVS_TUNNEL_KEY_ATTR_TOS] = 1, - [OVS_TUNNEL_KEY_ATTR_TTL] = 1, - [OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0, - [OVS_TUNNEL_KEY_ATTR_CSUM] = 0, - [OVS_TUNNEL_KEY_ATTR_TP_SRC] = sizeof(u16), - [OVS_TUNNEL_KEY_ATTR_TP_DST] = sizeof(u16), - [OVS_TUNNEL_KEY_ATTR_OAM] = 0, - [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = -1, - }; - if (type > OVS_TUNNEL_KEY_ATTR_MAX) { OVS_NLERR(log, "Tunnel attr %d out of range max %d", type, OVS_TUNNEL_KEY_ATTR_MAX); return -EINVAL; } - if (ovs_tunnel_key_lens[type] != nla_len(a) && - ovs_tunnel_key_lens[type] != -1) { + if (ovs_tunnel_key_lens[type].len != nla_len(a) && + ovs_tunnel_key_lens[type].len != OVS_ATTR_NESTED) { OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d", - type, nla_len(a), ovs_tunnel_key_lens[type]); + type, nla_len(a), ovs_tunnel_key_lens[type].len); return -EINVAL; } @@ -520,11 +568,30 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, tun_flags |= TUNNEL_OAM; break; case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS: + if (opts_type) { + OVS_NLERR(log, "Multiple metadata blocks provided"); + return -EINVAL; + } + err = genev_tun_opt_from_nlattr(a, match, is_mask, log); if (err) return err; - tun_flags |= TUNNEL_OPTIONS_PRESENT; + tun_flags |= TUNNEL_GENEVE_OPT; + opts_type = type; + break; + case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: + if (opts_type) { + OVS_NLERR(log, "Multiple metadata blocks provided"); + return -EINVAL; + } + + err = vxlan_tun_opt_from_nlattr(a, match, is_mask, log); + if (err) + return err; + + tun_flags |= TUNNEL_VXLAN_OPT; + opts_type = type; break; default: OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d", @@ -553,13 +620,29 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, } } + return opts_type; +} + +static int vxlan_opt_to_nlattr(struct sk_buff *skb, + const void *tun_opts, int swkey_tun_opts_len) +{ + const struct ovs_vxlan_opts *opts = tun_opts; + struct nlattr *nla; + + nla = nla_nest_start(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS); + if (!nla) + return -EMSGSIZE; + + if (nla_put_u32(skb, OVS_VXLAN_EXT_GBP, opts->gbp) < 0) + return -EMSGSIZE; + + nla_nest_end(skb, nla); return 0; } static int __ipv4_tun_to_nlattr(struct sk_buff *skb, const struct ovs_key_ipv4_tunnel *output, - const struct geneve_opt *tun_opts, - int swkey_tun_opts_len) + const void *tun_opts, int swkey_tun_opts_len) { if (output->tun_flags & TUNNEL_KEY && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id)) @@ -590,18 +673,22 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb, if ((output->tun_flags & TUNNEL_OAM) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; - if (tun_opts && - nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, - swkey_tun_opts_len, tun_opts)) - return -EMSGSIZE; + if (tun_opts) { + if (output->tun_flags & TUNNEL_GENEVE_OPT && + nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, + swkey_tun_opts_len, tun_opts)) + return -EMSGSIZE; + else if (output->tun_flags & TUNNEL_VXLAN_OPT && + vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) + return -EMSGSIZE; + } return 0; } static int ipv4_tun_to_nlattr(struct sk_buff *skb, const struct ovs_key_ipv4_tunnel *output, - const struct geneve_opt *tun_opts, - int swkey_tun_opts_len) + const void *tun_opts, int swkey_tun_opts_len) { struct nlattr *nla; int err; @@ -675,7 +762,7 @@ static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs, } if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) { if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match, - is_mask, log)) + is_mask, log) < 0) return -EINVAL; *attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL); } @@ -915,18 +1002,16 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, return 0; } -static void nlattr_set(struct nlattr *attr, u8 val, bool is_attr_mask_key) +static void nlattr_set(struct nlattr *attr, u8 val, + const struct ovs_len_tbl *tbl) { struct nlattr *nla; int rem; /* The nlattr stream should already have been validated */ nla_for_each_nested(nla, attr, rem) { - /* We assume that ovs_key_lens[type] == -1 means that type is a - * nested attribute - */ - if (is_attr_mask_key && ovs_key_lens[nla_type(nla)] == -1) - nlattr_set(nla, val, false); + if (tbl && tbl[nla_type(nla)].len == OVS_ATTR_NESTED) + nlattr_set(nla, val, tbl[nla_type(nla)].next); else memset(nla_data(nla), val, nla_len(nla)); } @@ -934,7 +1019,7 @@ static void nlattr_set(struct nlattr *attr, u8 val, bool is_attr_mask_key) static void mask_set_nlattr(struct nlattr *attr, u8 val) { - nlattr_set(attr, val, true); + nlattr_set(attr, val, ovs_key_lens); } /** @@ -1148,10 +1233,10 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, goto nla_put_failure; if ((swkey->tun_key.ipv4_dst || is_mask)) { - const struct geneve_opt *opts = NULL; + const void *opts = NULL; if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT) - opts = GENEVE_OPTS(output, swkey->tun_opts_len); + opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len); if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts, swkey->tun_opts_len)) @@ -1540,6 +1625,34 @@ void ovs_match_init(struct sw_flow_match *match, } } +static int validate_geneve_opts(struct sw_flow_key *key) +{ + struct geneve_opt *option; + int opts_len = key->tun_opts_len; + bool crit_opt = false; + + option = (struct geneve_opt *)TUN_METADATA_OPTS(key, key->tun_opts_len); + while (opts_len > 0) { + int len; + + if (opts_len < sizeof(*option)) + return -EINVAL; + + len = sizeof(*option) + option->length * 4; + if (len > opts_len) + return -EINVAL; + + crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE); + + option = (struct geneve_opt *)((u8 *)option + len); + opts_len -= len; + }; + + key->tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0; + + return 0; +} + static int validate_and_copy_set_tun(const struct nlattr *attr, struct sw_flow_actions **sfa, bool log) { @@ -1547,36 +1660,23 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, struct sw_flow_key key; struct ovs_tunnel_info *tun_info; struct nlattr *a; - int err, start; + int err, start, opts_type; ovs_match_init(&match, &key, NULL); - err = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log); - if (err) - return err; + opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log); + if (opts_type < 0) + return opts_type; if (key.tun_opts_len) { - struct geneve_opt *option = GENEVE_OPTS(&key, - key.tun_opts_len); - int opts_len = key.tun_opts_len; - bool crit_opt = false; - - while (opts_len > 0) { - int len; - - if (opts_len < sizeof(*option)) - return -EINVAL; - - len = sizeof(*option) + option->length * 4; - if (len > opts_len) - return -EINVAL; - - crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE); - - option = (struct geneve_opt *)((u8 *)option + len); - opts_len -= len; - }; - - key.tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0; + switch (opts_type) { + case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS: + err = validate_geneve_opts(&key); + if (err < 0) + return err; + break; + case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: + break; + } }; start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET, log); @@ -1597,9 +1697,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, * everything else will go away after flow setup. We can append * it to tun_info and then point there. */ - memcpy((tun_info + 1), GENEVE_OPTS(&key, key.tun_opts_len), - key.tun_opts_len); - tun_info->options = (struct geneve_opt *)(tun_info + 1); + memcpy((tun_info + 1), + TUN_METADATA_OPTS(&key, key.tun_opts_len), key.tun_opts_len); + tun_info->options = (tun_info + 1); } else { tun_info->options = NULL; } @@ -1622,8 +1722,8 @@ static int validate_set(const struct nlattr *a, return -EINVAL; if (key_type > OVS_KEY_ATTR_MAX || - (ovs_key_lens[key_type] != nla_len(ovs_key) && - ovs_key_lens[key_type] != -1)) + (ovs_key_lens[key_type].len != nla_len(ovs_key) && + ovs_key_lens[key_type].len != OVS_ATTR_NESTED)) return -EINVAL; switch (key_type) { diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 484864dd0e68..7ca3d454ff3b 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -9,8 +9,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/version.h> - #include <linux/in.h> #include <linux/ip.h> #include <linux/net.h> @@ -90,7 +88,7 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb) opts_len = geneveh->opt_len * 4; - flags = TUNNEL_KEY | TUNNEL_OPTIONS_PRESENT | + flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT | (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0) | (geneveh->oam ? TUNNEL_OAM : 0) | (geneveh->critical ? TUNNEL_CRIT_OPT : 0); @@ -172,7 +170,7 @@ error: static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) { - struct ovs_key_ipv4_tunnel *tun_key; + const struct ovs_key_ipv4_tunnel *tun_key; struct ovs_tunnel_info *tun_info; struct net *net = ovs_dp_get_net(vport->dp); struct geneve_port *geneve_port = geneve_vport(vport); @@ -180,7 +178,7 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) __be16 sport; struct rtable *rt; struct flowi4 fl; - u8 vni[3]; + u8 vni[3], opts_len, *opts; __be16 df; int err; @@ -191,16 +189,7 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) } tun_key = &tun_info->tunnel; - - /* Route lookup */ - memset(&fl, 0, sizeof(fl)); - fl.daddr = tun_key->ipv4_dst; - fl.saddr = tun_key->ipv4_src; - fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos); - fl.flowi4_mark = skb->mark; - fl.flowi4_proto = IPPROTO_UDP; - - rt = ip_route_output_key(net, &fl); + rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP); if (IS_ERR(rt)) { err = PTR_ERR(rt); goto error; @@ -211,11 +200,18 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) tunnel_id_to_vni(tun_key->tun_id, vni); skb->ignore_df = 1; + if (tun_key->tun_flags & TUNNEL_GENEVE_OPT) { + opts = (u8 *)tun_info->options; + opts_len = tun_info->options_len; + } else { + opts = NULL; + opts_len = 0; + } + err = geneve_xmit_skb(geneve_port->gs, rt, skb, fl.saddr, tun_key->ipv4_dst, tun_key->ipv4_tos, tun_key->ipv4_ttl, df, sport, dport, - tun_key->tun_flags, vni, - tun_info->options_len, (u8 *)tun_info->options, + tun_key->tun_flags, vni, opts_len, opts, false); if (err < 0) ip_rt_put(rt); diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index d4168c442db5..f17ac9642f4e 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -134,7 +134,7 @@ static int gre_err(struct sk_buff *skb, u32 info, static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) { struct net *net = ovs_dp_get_net(vport->dp); - struct ovs_key_ipv4_tunnel *tun_key; + const struct ovs_key_ipv4_tunnel *tun_key; struct flowi4 fl; struct rtable *rt; int min_headroom; @@ -148,15 +148,7 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) } tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; - /* Route lookup */ - memset(&fl, 0, sizeof(fl)); - fl.daddr = tun_key->ipv4_dst; - fl.saddr = tun_key->ipv4_src; - fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos); - fl.flowi4_mark = skb->mark; - fl.flowi4_proto = IPPROTO_GRE; - - rt = ip_route_output_key(net, &fl); + rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_GRE); if (IS_ERR(rt)) { err = PTR_ERR(rt); goto err_free_skb; @@ -166,7 +158,7 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + tunnel_hlen + sizeof(struct iphdr) - + (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0); + + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) { int head_delta = SKB_DATA_ALIGN(min_headroom - skb_headroom(skb) + diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index d7c46b301024..8a2d54cba9ba 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -40,6 +40,7 @@ #include "datapath.h" #include "vport.h" +#include "vport-vxlan.h" /** * struct vxlan_port - Keeps track of open UDP ports @@ -49,6 +50,7 @@ struct vxlan_port { struct vxlan_sock *vs; char name[IFNAMSIZ]; + u32 exts; /* VXLAN_F_* in <net/vxlan.h> */ }; static struct vport_ops ovs_vxlan_vport_ops; @@ -59,19 +61,30 @@ static inline struct vxlan_port *vxlan_vport(const struct vport *vport) } /* Called with rcu_read_lock and BH disabled. */ -static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni) +static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, + struct vxlan_metadata *md) { struct ovs_tunnel_info tun_info; + struct vxlan_port *vxlan_port; struct vport *vport = vs->data; struct iphdr *iph; + struct ovs_vxlan_opts opts = { + .gbp = md->gbp, + }; __be64 key; + __be16 flags; + + flags = TUNNEL_KEY; + vxlan_port = vxlan_vport(vport); + if (vxlan_port->exts & VXLAN_F_GBP) + flags |= TUNNEL_VXLAN_OPT; /* Save outer tunnel values */ iph = ip_hdr(skb); - key = cpu_to_be64(ntohl(vx_vni) >> 8); + key = cpu_to_be64(ntohl(md->vni) >> 8); ovs_flow_tun_info_init(&tun_info, iph, udp_hdr(skb)->source, udp_hdr(skb)->dest, - key, TUNNEL_KEY, NULL, 0); + key, flags, &opts, sizeof(opts)); ovs_vport_receive(vport, skb, &tun_info); } @@ -83,6 +96,21 @@ static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port))) return -EMSGSIZE; + + if (vxlan_port->exts) { + struct nlattr *exts; + + exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION); + if (!exts) + return -EMSGSIZE; + + if (vxlan_port->exts & VXLAN_F_GBP && + nla_put_flag(skb, OVS_VXLAN_EXT_GBP)) + return -EMSGSIZE; + + nla_nest_end(skb, exts); + } + return 0; } @@ -95,6 +123,31 @@ static void vxlan_tnl_destroy(struct vport *vport) ovs_vport_deferred_free(vport); } +static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX+1] = { + [OVS_VXLAN_EXT_GBP] = { .type = NLA_FLAG, }, +}; + +static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr) +{ + struct nlattr *exts[OVS_VXLAN_EXT_MAX+1]; + struct vxlan_port *vxlan_port; + int err; + + if (nla_len(attr) < sizeof(struct nlattr)) + return -EINVAL; + + err = nla_parse_nested(exts, OVS_VXLAN_EXT_MAX, attr, exts_policy); + if (err < 0) + return err; + + vxlan_port = vxlan_vport(vport); + + if (exts[OVS_VXLAN_EXT_GBP]) + vxlan_port->exts |= VXLAN_F_GBP; + + return 0; +} + static struct vport *vxlan_tnl_create(const struct vport_parms *parms) { struct net *net = ovs_dp_get_net(parms->dp); @@ -127,7 +180,17 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) vxlan_port = vxlan_vport(vport); strncpy(vxlan_port->name, parms->name, IFNAMSIZ); - vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, 0); + a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION); + if (a) { + err = vxlan_configure_exts(vport, a); + if (err) { + ovs_vport_free(vport); + goto error; + } + } + + vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, + vxlan_port->exts); if (IS_ERR(vs)) { ovs_vport_free(vport); return (void *)vs; @@ -140,12 +203,28 @@ error: return ERR_PTR(err); } +static int vxlan_ext_gbp(struct sk_buff *skb) +{ + const struct ovs_tunnel_info *tun_info; + const struct ovs_vxlan_opts *opts; + + tun_info = OVS_CB(skb)->egress_tun_info; + opts = tun_info->options; + + if (tun_info->tunnel.tun_flags & TUNNEL_VXLAN_OPT && + tun_info->options_len >= sizeof(*opts)) + return opts->gbp; + else + return 0; +} + static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) { struct net *net = ovs_dp_get_net(vport->dp); struct vxlan_port *vxlan_port = vxlan_vport(vport); __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport; - struct ovs_key_ipv4_tunnel *tun_key; + const struct ovs_key_ipv4_tunnel *tun_key; + struct vxlan_metadata md = {0}; struct rtable *rt; struct flowi4 fl; __be16 src_port; @@ -158,15 +237,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) } tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; - /* Route lookup */ - memset(&fl, 0, sizeof(fl)); - fl.daddr = tun_key->ipv4_dst; - fl.saddr = tun_key->ipv4_src; - fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos); - fl.flowi4_mark = skb->mark; - fl.flowi4_proto = IPPROTO_UDP; - - rt = ip_route_output_key(net, &fl); + rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP); if (IS_ERR(rt)) { err = PTR_ERR(rt); goto error; @@ -178,12 +249,14 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) skb->ignore_df = 1; src_port = udp_flow_src_port(net, skb, 0, 0, true); + md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8); + md.gbp = vxlan_ext_gbp(skb); err = vxlan_xmit_skb(vxlan_port->vs, rt, skb, fl.saddr, tun_key->ipv4_dst, tun_key->ipv4_tos, tun_key->ipv4_ttl, df, src_port, dst_port, - htonl(be64_to_cpu(tun_key->tun_id) << 8), + &md, false); if (err < 0) ip_rt_put(rt); diff --git a/net/openvswitch/vport-vxlan.h b/net/openvswitch/vport-vxlan.h new file mode 100644 index 000000000000..4b08233e73d5 --- /dev/null +++ b/net/openvswitch/vport-vxlan.h @@ -0,0 +1,11 @@ +#ifndef VPORT_VXLAN_H +#define VPORT_VXLAN_H 1 + +#include <linux/kernel.h> +#include <linux/types.h> + +struct ovs_vxlan_opts { + __u32 gbp; +}; + +#endif diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 53f3ebbfceab..ec2954ffc690 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -480,7 +480,8 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb, stats = this_cpu_ptr(vport->percpu_stats); u64_stats_update_begin(&stats->syncp); stats->rx_packets++; - stats->rx_bytes += skb->len; + stats->rx_bytes += skb->len + + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); u64_stats_update_end(&stats->syncp); OVS_CB(skb)->input_vport = vport; @@ -594,14 +595,7 @@ int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info, * The process may need to be changed if the corresponding process * in vports ops changed. */ - memset(&fl, 0, sizeof(fl)); - fl.daddr = tun_key->ipv4_dst; - fl.saddr = tun_key->ipv4_src; - fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos); - fl.flowi4_mark = skb_mark; - fl.flowi4_proto = ipproto; - - rt = ip_route_output_key(net, &fl); + rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto); if (IS_ERR(rt)) return PTR_ERR(rt); diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index 99c8e71d9e6c..f8ae295fb001 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -236,4 +236,22 @@ static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb, int ovs_vport_ops_register(struct vport_ops *ops); void ovs_vport_ops_unregister(struct vport_ops *ops); +static inline struct rtable *ovs_tunnel_route_lookup(struct net *net, + const struct ovs_key_ipv4_tunnel *key, + u32 mark, + struct flowi4 *fl, + u8 protocol) +{ + struct rtable *rt; + + memset(fl, 0, sizeof(*fl)); + fl->daddr = key->ipv4_dst; + fl->saddr = key->ipv4_src; + fl->flowi4_tos = RT_TOS(key->ipv4_tos); + fl->flowi4_mark = mark; + fl->flowi4_proto = protocol; + + rt = ip_route_output_key(net, fl); + return rt; +} #endif /* vport.h */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6880f34a529a..9c28cec1a083 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -986,8 +986,8 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { - if (vlan_tx_tag_present(pkc->skb)) { - ppd->hv1.tp_vlan_tci = vlan_tx_tag_get(pkc->skb); + if (skb_vlan_tag_present(pkc->skb)) { + ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { @@ -2000,8 +2000,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h2->tp_net = netoff; h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; - if (vlan_tx_tag_present(skb)) { - h.h2->tp_vlan_tci = vlan_tx_tag_get(skb); + if (skb_vlan_tag_present(skb)) { + h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { @@ -2102,7 +2102,7 @@ static bool ll_header_truncated(const struct net_device *dev, int len) { /* net device doesn't like empty head */ if (unlikely(len <= dev->hard_header_len)) { - net_warn_ratelimited("%s: packet size is too short (%d < %d)\n", + net_warn_ratelimited("%s: packet size is too short (%d <= %d)\n", current->comm, len, dev->hard_header_len); return true; } @@ -2517,7 +2517,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) err = -EINVAL; if (sock->type == SOCK_DGRAM) { offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); - if (unlikely(offset) < 0) + if (unlikely(offset < 0)) goto out_free; } else { if (ll_header_truncated(dev, len)) @@ -3010,8 +3010,8 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, aux.tp_snaplen = skb->len; aux.tp_mac = 0; aux.tp_net = skb_network_offset(skb); - if (vlan_tx_tag_present(skb)) { - aux.tp_vlan_tci = vlan_tx_tag_get(skb); + if (skb_vlan_tag_present(skb)) { + aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { diff --git a/net/sched/Kconfig b/net/sched/Kconfig index c54c9d9d1ffb..466943551581 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -698,6 +698,18 @@ config NET_ACT_VLAN To compile this code as a module, choose M here: the module will be called act_vlan. +config NET_ACT_BPF + tristate "BPF based action" + depends on NET_CLS_ACT + ---help--- + Say Y here to execute BPF code on packets. The BPF code will decide + if the packet should be dropped or not. + + If unsure, say N. + + To compile this code as a module, choose M here: the + module will be called act_bpf. + config NET_CLS_IND bool "Incoming device classification" depends on NET_CLS_U32 || NET_CLS_FW diff --git a/net/sched/Makefile b/net/sched/Makefile index 679f24ae7f93..7ca2b4e76312 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_NET_ACT_SIMP) += act_simple.o obj-$(CONFIG_NET_ACT_SKBEDIT) += act_skbedit.o obj-$(CONFIG_NET_ACT_CSUM) += act_csum.o obj-$(CONFIG_NET_ACT_VLAN) += act_vlan.o +obj-$(CONFIG_NET_ACT_BPF) += act_bpf.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c new file mode 100644 index 000000000000..1bd257e473a9 --- /dev/null +++ b/net/sched/act_bpf.c @@ -0,0 +1,205 @@ +/* + * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/rtnetlink.h> +#include <linux/filter.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> + +#include <linux/tc_act/tc_bpf.h> +#include <net/tc_act/tc_bpf.h> + +#define BPF_TAB_MASK 15 + +static int tcf_bpf(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_bpf *b = a->priv; + int action; + int filter_res; + + spin_lock(&b->tcf_lock); + b->tcf_tm.lastuse = jiffies; + bstats_update(&b->tcf_bstats, skb); + action = b->tcf_action; + + filter_res = BPF_PROG_RUN(b->filter, skb); + if (filter_res == 0) { + /* Return code 0 from the BPF program + * is being interpreted as a drop here. + */ + action = TC_ACT_SHOT; + b->tcf_qstats.drops++; + } + + spin_unlock(&b->tcf_lock); + return action; +} + +static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + unsigned char *tp = skb_tail_pointer(skb); + struct tcf_bpf *b = a->priv; + struct tc_act_bpf opt = { + .index = b->tcf_index, + .refcnt = b->tcf_refcnt - ref, + .bindcnt = b->tcf_bindcnt - bind, + .action = b->tcf_action, + }; + struct tcf_t t; + struct nlattr *nla; + + if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, b->bpf_num_ops)) + goto nla_put_failure; + + nla = nla_reserve(skb, TCA_ACT_BPF_OPS, b->bpf_num_ops * + sizeof(struct sock_filter)); + if (!nla) + goto nla_put_failure; + + memcpy(nla_data(nla), b->bpf_ops, nla_len(nla)); + + t.install = jiffies_to_clock_t(jiffies - b->tcf_tm.install); + t.lastuse = jiffies_to_clock_t(jiffies - b->tcf_tm.lastuse); + t.expires = jiffies_to_clock_t(b->tcf_tm.expires); + if (nla_put(skb, TCA_ACT_BPF_TM, sizeof(t), &t)) + goto nla_put_failure; + return skb->len; + +nla_put_failure: + nlmsg_trim(skb, tp); + return -1; +} + +static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = { + [TCA_ACT_BPF_PARMS] = { .len = sizeof(struct tc_act_bpf) }, + [TCA_ACT_BPF_OPS_LEN] = { .type = NLA_U16 }, + [TCA_ACT_BPF_OPS] = { .type = NLA_BINARY, + .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, +}; + +static int tcf_bpf_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) +{ + struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + struct tc_act_bpf *parm; + struct tcf_bpf *b; + u16 bpf_size, bpf_num_ops; + struct sock_filter *bpf_ops; + struct sock_fprog_kern tmp; + struct bpf_prog *fp; + int ret; + + if (!nla) + return -EINVAL; + + ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy); + if (ret < 0) + return ret; + + if (!tb[TCA_ACT_BPF_PARMS] || + !tb[TCA_ACT_BPF_OPS_LEN] || !tb[TCA_ACT_BPF_OPS]) + return -EINVAL; + parm = nla_data(tb[TCA_ACT_BPF_PARMS]); + + bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]); + if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) + return -EINVAL; + + bpf_size = bpf_num_ops * sizeof(*bpf_ops); + bpf_ops = kzalloc(bpf_size, GFP_KERNEL); + if (!bpf_ops) + return -ENOMEM; + + memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size); + + tmp.len = bpf_num_ops; + tmp.filter = bpf_ops; + + ret = bpf_prog_create(&fp, &tmp); + if (ret) + goto free_bpf_ops; + + if (!tcf_hash_check(parm->index, a, bind)) { + ret = tcf_hash_create(parm->index, est, a, sizeof(*b), bind); + if (ret) + goto destroy_fp; + + ret = ACT_P_CREATED; + } else { + if (bind) + goto destroy_fp; + tcf_hash_release(a, bind); + if (!ovr) { + ret = -EEXIST; + goto destroy_fp; + } + } + + b = to_bpf(a); + spin_lock_bh(&b->tcf_lock); + b->tcf_action = parm->action; + b->bpf_num_ops = bpf_num_ops; + b->bpf_ops = bpf_ops; + b->filter = fp; + spin_unlock_bh(&b->tcf_lock); + + if (ret == ACT_P_CREATED) + tcf_hash_insert(a); + return ret; + +destroy_fp: + bpf_prog_destroy(fp); +free_bpf_ops: + kfree(bpf_ops); + return ret; +} + +static void tcf_bpf_cleanup(struct tc_action *a, int bind) +{ + struct tcf_bpf *b = a->priv; + + bpf_prog_destroy(b->filter); +} + +static struct tc_action_ops act_bpf_ops = { + .kind = "bpf", + .type = TCA_ACT_BPF, + .owner = THIS_MODULE, + .act = tcf_bpf, + .dump = tcf_bpf_dump, + .cleanup = tcf_bpf_cleanup, + .init = tcf_bpf_init, +}; + +static int __init bpf_init_module(void) +{ + return tcf_register_action(&act_bpf_ops, BPF_TAB_MASK); +} + +static void __exit bpf_cleanup_module(void) +{ + tcf_unregister_action(&act_bpf_ops); +} + +module_init(bpf_init_module); +module_exit(bpf_cleanup_module); + +MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>"); +MODULE_DESCRIPTION("TC BPF based action"); +MODULE_LICENSE("GPL v2"); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index edbf40dac709..4cd5cf1aedf8 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -509,7 +509,7 @@ static int tcf_csum(struct sk_buff *skb, if (unlikely(action == TC_ACT_SHOT)) goto drop; - switch (skb->protocol) { + switch (tc_skb_protocol(skb)) { case cpu_to_be16(ETH_P_IP): if (!tcf_csum_ipv4(skb, update_flags)) goto drop; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 84c8219c3e1c..1029923f9e86 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -37,7 +37,7 @@ struct cls_bpf_prog { struct tcf_result res; struct list_head link; u32 handle; - u16 bpf_len; + u16 bpf_num_ops; struct tcf_proto *tp; struct rcu_head rcu; }; @@ -160,7 +160,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, struct tcf_exts exts; struct sock_fprog_kern tmp; struct bpf_prog *fp; - u16 bpf_size, bpf_len; + u16 bpf_size, bpf_num_ops; u32 classid; int ret; @@ -173,13 +173,13 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, return ret; classid = nla_get_u32(tb[TCA_BPF_CLASSID]); - bpf_len = nla_get_u16(tb[TCA_BPF_OPS_LEN]); - if (bpf_len > BPF_MAXINSNS || bpf_len == 0) { + bpf_num_ops = nla_get_u16(tb[TCA_BPF_OPS_LEN]); + if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) { ret = -EINVAL; goto errout; } - bpf_size = bpf_len * sizeof(*bpf_ops); + bpf_size = bpf_num_ops * sizeof(*bpf_ops); bpf_ops = kzalloc(bpf_size, GFP_KERNEL); if (bpf_ops == NULL) { ret = -ENOMEM; @@ -188,14 +188,14 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size); - tmp.len = bpf_len; + tmp.len = bpf_num_ops; tmp.filter = bpf_ops; ret = bpf_prog_create(&fp, &tmp); if (ret) goto errout_free; - prog->bpf_len = bpf_len; + prog->bpf_num_ops = bpf_num_ops; prog->bpf_ops = bpf_ops; prog->filter = fp; prog->res.classid = classid; @@ -303,10 +303,10 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid)) goto nla_put_failure; - if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_len)) + if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_num_ops)) goto nla_put_failure; - nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_len * + nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_num_ops * sizeof(struct sock_filter)); if (nla == NULL) goto nla_put_failure; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 15d68f24a521..461410394d08 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -77,7 +77,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow) { if (flow->dst) return ntohl(flow->dst); - return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol; + return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); } static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow) @@ -98,7 +98,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys if (flow->ports) return ntohs(flow->port16[1]); - return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol; + return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); } static u32 flow_get_iif(const struct sk_buff *skb) @@ -144,7 +144,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb) static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (skb->protocol) { + switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, src.u3.ip)); case htons(ETH_P_IPV6): @@ -156,7 +156,7 @@ fallback: static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (skb->protocol) { + switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, dst.u3.ip)); case htons(ETH_P_IPV6): diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c index 5b4a4efe468c..a3d79c8bf3b8 100644 --- a/net/sched/em_ipset.c +++ b/net/sched/em_ipset.c @@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, struct net_device *dev, *indev = NULL; int ret, network_offset; - switch (skb->protocol) { + switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): acpar.family = NFPROTO_IPV4; if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index c8f8c399b99a..b5294ce20cd4 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -176,7 +176,7 @@ META_COLLECTOR(int_vlan_tag) { unsigned short tag; - tag = vlan_tx_tag_get(skb); + tag = skb_vlan_tag_get(skb); if (!tag && __vlan_get_tag(skb, &tag)) *err = -1; else @@ -197,7 +197,7 @@ META_COLLECTOR(int_priority) META_COLLECTOR(int_protocol) { /* Let userspace take care of the byte ordering */ - dst->value = skb->protocol; + dst->value = tc_skb_protocol(skb); } META_COLLECTOR(int_pkttype) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 76f402e05bd6..243b7d169d61 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1807,7 +1807,7 @@ done: int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { - __be16 protocol = skb->protocol; + __be16 protocol = tc_skb_protocol(skb); int err; for (; tp; tp = rcu_dereference_bh(tp->next)) { diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 227114f27f94..66700a6116aa 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -203,7 +203,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p); if (p->set_tc_index) { - switch (skb->protocol) { + switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): if (skb_cow_head(skb, sizeof(struct iphdr))) goto drop; @@ -289,7 +289,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) index = skb->tc_index & (p->indices - 1); pr_debug("index %d->%d\n", skb->tc_index, index); - switch (skb->protocol) { + switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): ipv4_change_dsfield(ip_hdr(skb), p->mask[index], p->value[index]); @@ -306,7 +306,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) */ if (p->mask[index] != 0xff || p->value[index]) pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(skb->protocol)); + __func__, ntohs(tc_skb_protocol(skb))); break; } diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 6ada42396a24..e02687185a59 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -122,13 +122,6 @@ teql_peek(struct Qdisc *sch) return NULL; } -static inline void -teql_neigh_release(struct neighbour *n) -{ - if (n) - neigh_release(n); -} - static void teql_reset(struct Qdisc *sch) { @@ -249,8 +242,8 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, char haddr[MAX_ADDR_LEN]; neigh_ha_snapshot(haddr, n, dev); - err = dev_hard_header(skb, dev, ntohs(skb->protocol), haddr, - NULL, skb->len); + err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)), + haddr, NULL, skb->len); if (err < 0) err = -EINVAL; diff --git a/net/socket.c b/net/socket.c index a2c33a4dc7ba..9fcf15b61009 100644 --- a/net/socket.c +++ b/net/socket.c @@ -882,20 +882,15 @@ static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, unsigned long nr_segs) { struct socket *sock = file->private_data; - size_t size = 0; - int i; - - for (i = 0; i < nr_segs; i++) - size += iov[i].iov_len; msg->msg_name = NULL; msg->msg_namelen = 0; msg->msg_control = NULL; msg->msg_controllen = 0; - iov_iter_init(&msg->msg_iter, READ, iov, nr_segs, size); + iov_iter_init(&msg->msg_iter, READ, iov, nr_segs, iocb->ki_nbytes); msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; - return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags); + return __sock_recvmsg(iocb, sock, msg, iocb->ki_nbytes, msg->msg_flags); } static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov, @@ -921,22 +916,17 @@ static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, unsigned long nr_segs) { struct socket *sock = file->private_data; - size_t size = 0; - int i; - - for (i = 0; i < nr_segs; i++) - size += iov[i].iov_len; msg->msg_name = NULL; msg->msg_namelen = 0; msg->msg_control = NULL; msg->msg_controllen = 0; - iov_iter_init(&msg->msg_iter, WRITE, iov, nr_segs, size); + iov_iter_init(&msg->msg_iter, WRITE, iov, nr_segs, iocb->ki_nbytes); msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; if (sock->type == SOCK_SEQPACKET) msg->msg_flags |= MSG_EOR; - return __sock_sendmsg(iocb, sock, msg, size); + return __sock_sendmsg(iocb, sock, msg, iocb->ki_nbytes); } static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov, diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 1cb61242e55e..4439ac4c1b53 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -606,7 +606,7 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len) struct kvec *head = buf->head; struct kvec *tail = buf->tail; int fraglen; - int new, old; + int new; if (len > buf->len) { WARN_ON_ONCE(1); @@ -629,8 +629,8 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len) buf->len -= fraglen; new = buf->page_base + buf->page_len; - old = new + fraglen; - xdr->page_ptr -= (old >> PAGE_SHIFT) - (new >> PAGE_SHIFT); + + xdr->page_ptr = buf->pages + (new >> PAGE_SHIFT); if (buf->page_len) { xdr->p = page_address(*xdr->page_ptr); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index d162b21b14bd..22e02f4edd99 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -11,6 +11,8 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/init.h> +#include <linux/mutex.h> +#include <linux/notifier.h> #include <linux/netdevice.h> #include <net/switchdev.h> @@ -50,3 +52,66 @@ int netdev_switch_port_stp_update(struct net_device *dev, u8 state) return ops->ndo_switch_port_stp_update(dev, state); } EXPORT_SYMBOL(netdev_switch_port_stp_update); + +static DEFINE_MUTEX(netdev_switch_mutex); +static RAW_NOTIFIER_HEAD(netdev_switch_notif_chain); + +/** + * register_netdev_switch_notifier - Register nofifier + * @nb: notifier_block + * + * Register switch device notifier. This should be used by code + * which needs to monitor events happening in particular device. + * Return values are same as for atomic_notifier_chain_register(). + */ +int register_netdev_switch_notifier(struct notifier_block *nb) +{ + int err; + + mutex_lock(&netdev_switch_mutex); + err = raw_notifier_chain_register(&netdev_switch_notif_chain, nb); + mutex_unlock(&netdev_switch_mutex); + return err; +} +EXPORT_SYMBOL(register_netdev_switch_notifier); + +/** + * unregister_netdev_switch_notifier - Unregister nofifier + * @nb: notifier_block + * + * Unregister switch device notifier. + * Return values are same as for atomic_notifier_chain_unregister(). + */ +int unregister_netdev_switch_notifier(struct notifier_block *nb) +{ + int err; + + mutex_lock(&netdev_switch_mutex); + err = raw_notifier_chain_unregister(&netdev_switch_notif_chain, nb); + mutex_unlock(&netdev_switch_mutex); + return err; +} +EXPORT_SYMBOL(unregister_netdev_switch_notifier); + +/** + * call_netdev_switch_notifiers - Call nofifiers + * @val: value passed unmodified to notifier function + * @dev: port device + * @info: notifier information data + * + * Call all network notifier blocks. This should be called by driver + * when it needs to propagate hardware event. + * Return values are same as for atomic_notifier_call_chain(). + */ +int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, + struct netdev_switch_notifier_info *info) +{ + int err; + + info->dev = dev; + mutex_lock(&netdev_switch_mutex); + err = raw_notifier_call_chain(&netdev_switch_notif_chain, val, info); + mutex_unlock(&netdev_switch_mutex); + return err; +} +EXPORT_SYMBOL(call_netdev_switch_notifiers); diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index c890848f9d56..91c8a8e031db 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -20,18 +20,6 @@ menuconfig TIPC If in doubt, say N. -config TIPC_PORTS - int "Maximum number of ports in a node" - depends on TIPC - range 127 65535 - default "8191" - help - Specifies how many ports can be supported by a node. - Can range from 127 to 65535 ports; default is 8191. - - Setting this to a smaller value saves some memory, - setting it to higher allows for more ports. - config TIPC_MEDIA_IB bool "InfiniBand media type support" depends on TIPC && INFINIBAND_IPOIB diff --git a/net/tipc/addr.c b/net/tipc/addr.c index 357b74b26f9e..48fd3b5a73fb 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -34,8 +34,51 @@ * POSSIBILITY OF SUCH DAMAGE. */ -#include "core.h" +#include <linux/kernel.h> #include "addr.h" +#include "core.h" + +/** + * in_own_cluster - test for cluster inclusion; <0.0.0> always matches + */ +int in_own_cluster(struct net *net, u32 addr) +{ + return in_own_cluster_exact(net, addr) || !addr; +} + +int in_own_cluster_exact(struct net *net, u32 addr) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); + + return !((addr ^ tn->own_addr) >> 12); +} + +/** + * in_own_node - test for node inclusion; <0.0.0> always matches + */ +int in_own_node(struct net *net, u32 addr) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); + + return (addr == tn->own_addr) || !addr; +} + +/** + * addr_domain - convert 2-bit scope value to equivalent message lookup domain + * + * Needed when address of a named message must be looked up a second time + * after a network hop. + */ +u32 addr_domain(struct net *net, u32 sc) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); + + if (likely(sc == TIPC_NODE_SCOPE)) + return tn->own_addr; + if (sc == TIPC_CLUSTER_SCOPE) + return tipc_cluster_mask(tn->own_addr); + return tipc_zone_mask(tn->own_addr); +} /** * tipc_addr_domain_valid - validates a network domain address diff --git a/net/tipc/addr.h b/net/tipc/addr.h index a74acf9ee804..c700c2d28e09 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -37,7 +37,10 @@ #ifndef _TIPC_ADDR_H #define _TIPC_ADDR_H -#include "core.h" +#include <linux/types.h> +#include <linux/tipc.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> #define TIPC_ZONE_MASK 0xff000000u #define TIPC_CLUSTER_MASK 0xfffff000u @@ -52,42 +55,10 @@ static inline u32 tipc_cluster_mask(u32 addr) return addr & TIPC_CLUSTER_MASK; } -static inline int in_own_cluster_exact(u32 addr) -{ - return !((addr ^ tipc_own_addr) >> 12); -} - -/** - * in_own_node - test for node inclusion; <0.0.0> always matches - */ -static inline int in_own_node(u32 addr) -{ - return (addr == tipc_own_addr) || !addr; -} - -/** - * in_own_cluster - test for cluster inclusion; <0.0.0> always matches - */ -static inline int in_own_cluster(u32 addr) -{ - return in_own_cluster_exact(addr) || !addr; -} - -/** - * addr_domain - convert 2-bit scope value to equivalent message lookup domain - * - * Needed when address of a named message must be looked up a second time - * after a network hop. - */ -static inline u32 addr_domain(u32 sc) -{ - if (likely(sc == TIPC_NODE_SCOPE)) - return tipc_own_addr; - if (sc == TIPC_CLUSTER_SCOPE) - return tipc_cluster_mask(tipc_own_addr); - return tipc_zone_mask(tipc_own_addr); -} - +int in_own_cluster(struct net *net, u32 addr); +int in_own_cluster_exact(struct net *net, u32 addr); +int in_own_node(struct net *net, u32 addr); +u32 addr_domain(struct net *net, u32 sc); int tipc_addr_domain_valid(u32); int tipc_addr_node_valid(u32 addr); int tipc_in_scope(u32 domain, u32 addr); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 96ceefeb9daf..53f8bf059fec 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -35,77 +35,14 @@ * POSSIBILITY OF SUCH DAMAGE. */ -#include "core.h" -#include "link.h" #include "socket.h" #include "msg.h" #include "bcast.h" #include "name_distr.h" +#include "core.h" #define MAX_PKT_DEFAULT_MCAST 1500 /* bcast link max packet size (fixed) */ #define BCLINK_WIN_DEFAULT 20 /* bcast link window size (default) */ -#define BCBEARER MAX_BEARERS - -/** - * struct tipc_bcbearer_pair - a pair of bearers used by broadcast link - * @primary: pointer to primary bearer - * @secondary: pointer to secondary bearer - * - * Bearers must have same priority and same set of reachable destinations - * to be paired. - */ - -struct tipc_bcbearer_pair { - struct tipc_bearer *primary; - struct tipc_bearer *secondary; -}; - -/** - * struct tipc_bcbearer - bearer used by broadcast link - * @bearer: (non-standard) broadcast bearer structure - * @media: (non-standard) broadcast media structure - * @bpairs: array of bearer pairs - * @bpairs_temp: temporary array of bearer pairs used by tipc_bcbearer_sort() - * @remains: temporary node map used by tipc_bcbearer_send() - * @remains_new: temporary node map used tipc_bcbearer_send() - * - * Note: The fields labelled "temporary" are incorporated into the bearer - * to avoid consuming potentially limited stack space through the use of - * large local variables within multicast routines. Concurrent access is - * prevented through use of the spinlock "bclink_lock". - */ -struct tipc_bcbearer { - struct tipc_bearer bearer; - struct tipc_media media; - struct tipc_bcbearer_pair bpairs[MAX_BEARERS]; - struct tipc_bcbearer_pair bpairs_temp[TIPC_MAX_LINK_PRI + 1]; - struct tipc_node_map remains; - struct tipc_node_map remains_new; -}; - -/** - * struct tipc_bclink - link used for broadcast messages - * @lock: spinlock governing access to structure - * @link: (non-standard) broadcast link structure - * @node: (non-standard) node structure representing b'cast link's peer node - * @flags: represent bclink states - * @bcast_nodes: map of broadcast-capable nodes - * @retransmit_to: node that most recently requested a retransmit - * - * Handles sequence numbering, fragmentation, bundling, etc. - */ -struct tipc_bclink { - spinlock_t lock; - struct tipc_link link; - struct tipc_node node; - unsigned int flags; - struct tipc_node_map bcast_nodes; - struct tipc_node *retransmit_to; -}; - -static struct tipc_bcbearer *bcbearer; -static struct tipc_bclink *bclink; -static struct tipc_link *bcl; const char tipc_bclink_name[] = "broadcast-link"; @@ -115,25 +52,28 @@ static void tipc_nmap_diff(struct tipc_node_map *nm_a, static void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node); static void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node); -static void tipc_bclink_lock(void) +static void tipc_bclink_lock(struct net *net) { - spin_lock_bh(&bclink->lock); + struct tipc_net *tn = net_generic(net, tipc_net_id); + + spin_lock_bh(&tn->bclink->lock); } -static void tipc_bclink_unlock(void) +static void tipc_bclink_unlock(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *node = NULL; - if (likely(!bclink->flags)) { - spin_unlock_bh(&bclink->lock); + if (likely(!tn->bclink->flags)) { + spin_unlock_bh(&tn->bclink->lock); return; } - if (bclink->flags & TIPC_BCLINK_RESET) { - bclink->flags &= ~TIPC_BCLINK_RESET; - node = tipc_bclink_retransmit_to(); + if (tn->bclink->flags & TIPC_BCLINK_RESET) { + tn->bclink->flags &= ~TIPC_BCLINK_RESET; + node = tipc_bclink_retransmit_to(net); } - spin_unlock_bh(&bclink->lock); + spin_unlock_bh(&tn->bclink->lock); if (node) tipc_link_reset_all(node); @@ -144,9 +84,11 @@ uint tipc_bclink_get_mtu(void) return MAX_PKT_DEFAULT_MCAST; } -void tipc_bclink_set_flags(unsigned int flags) +void tipc_bclink_set_flags(struct net *net, unsigned int flags) { - bclink->flags |= flags; + struct tipc_net *tn = net_generic(net, tipc_net_id); + + tn->bclink->flags |= flags; } static u32 bcbuf_acks(struct sk_buff *buf) @@ -164,31 +106,40 @@ static void bcbuf_decr_acks(struct sk_buff *buf) bcbuf_set_acks(buf, bcbuf_acks(buf) - 1); } -void tipc_bclink_add_node(u32 addr) +void tipc_bclink_add_node(struct net *net, u32 addr) { - tipc_bclink_lock(); - tipc_nmap_add(&bclink->bcast_nodes, addr); - tipc_bclink_unlock(); + struct tipc_net *tn = net_generic(net, tipc_net_id); + + tipc_bclink_lock(net); + tipc_nmap_add(&tn->bclink->bcast_nodes, addr); + tipc_bclink_unlock(net); } -void tipc_bclink_remove_node(u32 addr) +void tipc_bclink_remove_node(struct net *net, u32 addr) { - tipc_bclink_lock(); - tipc_nmap_remove(&bclink->bcast_nodes, addr); - tipc_bclink_unlock(); + struct tipc_net *tn = net_generic(net, tipc_net_id); + + tipc_bclink_lock(net); + tipc_nmap_remove(&tn->bclink->bcast_nodes, addr); + tipc_bclink_unlock(net); } -static void bclink_set_last_sent(void) +static void bclink_set_last_sent(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_link *bcl = tn->bcl; + if (bcl->next_out) bcl->fsm_msg_cnt = mod(buf_seqno(bcl->next_out) - 1); else bcl->fsm_msg_cnt = mod(bcl->next_out_no - 1); } -u32 tipc_bclink_get_last_sent(void) +u32 tipc_bclink_get_last_sent(struct net *net) { - return bcl->fsm_msg_cnt; + struct tipc_net *tn = net_generic(net, tipc_net_id); + + return tn->bcl->fsm_msg_cnt; } static void bclink_update_last_sent(struct tipc_node *node, u32 seqno) @@ -203,9 +154,11 @@ static void bclink_update_last_sent(struct tipc_node *node, u32 seqno) * * Called with bclink_lock locked */ -struct tipc_node *tipc_bclink_retransmit_to(void) +struct tipc_node *tipc_bclink_retransmit_to(struct net *net) { - return bclink->retransmit_to; + struct tipc_net *tn = net_generic(net, tipc_net_id); + + return tn->bclink->retransmit_to; } /** @@ -215,15 +168,17 @@ struct tipc_node *tipc_bclink_retransmit_to(void) * * Called with bclink_lock locked */ -static void bclink_retransmit_pkt(u32 after, u32 to) +static void bclink_retransmit_pkt(struct tipc_net *tn, u32 after, u32 to) { struct sk_buff *skb; + struct tipc_link *bcl = tn->bcl; skb_queue_walk(&bcl->outqueue, skb) { - if (more(buf_seqno(skb), after)) + if (more(buf_seqno(skb), after)) { + tipc_link_retransmit(bcl, skb, mod(to - after)); break; + } } - tipc_link_retransmit(bcl, skb, mod(to - after)); } /** @@ -231,13 +186,13 @@ static void bclink_retransmit_pkt(u32 after, u32 to) * * Called with no locks taken */ -void tipc_bclink_wakeup_users(void) +void tipc_bclink_wakeup_users(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff *skb; - while ((skb = skb_dequeue(&bclink->link.waiting_sks))) - tipc_sk_rcv(skb); - + while ((skb = skb_dequeue(&tn->bclink->link.waiting_sks))) + tipc_sk_rcv(net, skb); } /** @@ -252,10 +207,12 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked) struct sk_buff *skb, *tmp; struct sk_buff *next; unsigned int released = 0; + struct net *net = n_ptr->net; + struct tipc_net *tn = net_generic(net, tipc_net_id); - tipc_bclink_lock(); + tipc_bclink_lock(net); /* Bail out if tx queue is empty (no clean up is required) */ - skb = skb_peek(&bcl->outqueue); + skb = skb_peek(&tn->bcl->outqueue); if (!skb) goto exit; @@ -266,43 +223,43 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked) * acknowledge sent messages only (if other nodes still exist) * or both sent and unsent messages (otherwise) */ - if (bclink->bcast_nodes.count) - acked = bcl->fsm_msg_cnt; + if (tn->bclink->bcast_nodes.count) + acked = tn->bcl->fsm_msg_cnt; else - acked = bcl->next_out_no; + acked = tn->bcl->next_out_no; } else { /* * Bail out if specified sequence number does not correspond * to a message that has been sent and not yet acknowledged */ if (less(acked, buf_seqno(skb)) || - less(bcl->fsm_msg_cnt, acked) || + less(tn->bcl->fsm_msg_cnt, acked) || less_eq(acked, n_ptr->bclink.acked)) goto exit; } /* Skip over packets that node has previously acknowledged */ - skb_queue_walk(&bcl->outqueue, skb) { + skb_queue_walk(&tn->bcl->outqueue, skb) { if (more(buf_seqno(skb), n_ptr->bclink.acked)) break; } /* Update packets that node is now acknowledging */ - skb_queue_walk_from_safe(&bcl->outqueue, skb, tmp) { + skb_queue_walk_from_safe(&tn->bcl->outqueue, skb, tmp) { if (more(buf_seqno(skb), acked)) break; - next = tipc_skb_queue_next(&bcl->outqueue, skb); - if (skb != bcl->next_out) { + next = tipc_skb_queue_next(&tn->bcl->outqueue, skb); + if (skb != tn->bcl->next_out) { bcbuf_decr_acks(skb); } else { bcbuf_set_acks(skb, 0); - bcl->next_out = next; - bclink_set_last_sent(); + tn->bcl->next_out = next; + bclink_set_last_sent(net); } if (bcbuf_acks(skb) == 0) { - __skb_unlink(skb, &bcl->outqueue); + __skb_unlink(skb, &tn->bcl->outqueue); kfree_skb(skb); released = 1; } @@ -310,15 +267,15 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked) n_ptr->bclink.acked = acked; /* Try resolving broadcast link congestion, if necessary */ - if (unlikely(bcl->next_out)) { - tipc_link_push_packets(bcl); - bclink_set_last_sent(); + if (unlikely(tn->bcl->next_out)) { + tipc_link_push_packets(tn->bcl); + bclink_set_last_sent(net); } - if (unlikely(released && !skb_queue_empty(&bcl->waiting_sks))) + if (unlikely(released && !skb_queue_empty(&tn->bcl->waiting_sks))) n_ptr->action_flags |= TIPC_WAKEUP_BCAST_USERS; exit: - tipc_bclink_unlock(); + tipc_bclink_unlock(net); } /** @@ -326,9 +283,11 @@ exit: * * RCU and node lock set */ -void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent) +void tipc_bclink_update_link_state(struct net *net, struct tipc_node *n_ptr, + u32 last_sent) { struct sk_buff *buf; + struct tipc_net *tn = net_generic(net, tipc_net_id); /* Ignore "stale" link state info */ if (less_eq(last_sent, n_ptr->bclink.last_in)) @@ -358,18 +317,18 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent) struct sk_buff *skb = skb_peek(&n_ptr->bclink.deferred_queue); u32 to = skb ? buf_seqno(skb) - 1 : n_ptr->bclink.last_sent; - tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG, + tipc_msg_init(net, msg, BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, n_ptr->addr); msg_set_non_seq(msg, 1); - msg_set_mc_netid(msg, tipc_net_id); + msg_set_mc_netid(msg, tn->net_id); msg_set_bcast_ack(msg, n_ptr->bclink.last_in); msg_set_bcgap_after(msg, n_ptr->bclink.last_in); msg_set_bcgap_to(msg, to); - tipc_bclink_lock(); - tipc_bearer_send(MAX_BEARERS, buf, NULL); - bcl->stats.sent_nacks++; - tipc_bclink_unlock(); + tipc_bclink_lock(net); + tipc_bearer_send(net, MAX_BEARERS, buf, NULL); + tn->bcl->stats.sent_nacks++; + tipc_bclink_unlock(net); kfree_skb(buf); n_ptr->bclink.oos_state++; @@ -382,9 +341,9 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent) * Delay any upcoming NACK by this node if another node has already * requested the first message this node is going to ask for. */ -static void bclink_peek_nack(struct tipc_msg *msg) +static void bclink_peek_nack(struct net *net, struct tipc_msg *msg) { - struct tipc_node *n_ptr = tipc_node_find(msg_destnode(msg)); + struct tipc_node *n_ptr = tipc_node_find(net, msg_destnode(msg)); if (unlikely(!n_ptr)) return; @@ -401,12 +360,16 @@ static void bclink_peek_nack(struct tipc_msg *msg) /* tipc_bclink_xmit - broadcast buffer chain to all nodes in cluster * and to identified node local sockets + * @net: the applicable net namespace * @list: chain of buffers containing message * Consumes the buffer chain, except when returning -ELINKCONG * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE */ -int tipc_bclink_xmit(struct sk_buff_head *list) +int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list) { + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_link *bcl = tn->bcl; + struct tipc_bclink *bclink = tn->bclink; int rc = 0; int bc = 0; struct sk_buff *skb; @@ -420,19 +383,19 @@ int tipc_bclink_xmit(struct sk_buff_head *list) /* Broadcast to all other nodes */ if (likely(bclink)) { - tipc_bclink_lock(); + tipc_bclink_lock(net); if (likely(bclink->bcast_nodes.count)) { - rc = __tipc_link_xmit(bcl, list); + rc = __tipc_link_xmit(net, bcl, list); if (likely(!rc)) { u32 len = skb_queue_len(&bcl->outqueue); - bclink_set_last_sent(); + bclink_set_last_sent(net); bcl->stats.queue_sz_counts++; bcl->stats.accu_queue_sz += len; } bc = 1; } - tipc_bclink_unlock(); + tipc_bclink_unlock(net); } if (unlikely(!bc)) @@ -440,7 +403,7 @@ int tipc_bclink_xmit(struct sk_buff_head *list) /* Deliver message clone */ if (likely(!rc)) - tipc_sk_mcast_rcv(skb); + tipc_sk_mcast_rcv(net, skb); else kfree_skb(skb); @@ -454,19 +417,21 @@ int tipc_bclink_xmit(struct sk_buff_head *list) */ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) { + struct tipc_net *tn = net_generic(node->net, tipc_net_id); + bclink_update_last_sent(node, seqno); node->bclink.last_in = seqno; node->bclink.oos_state = 0; - bcl->stats.recv_info++; + tn->bcl->stats.recv_info++; /* * Unicast an ACK periodically, ensuring that * all nodes in the cluster don't ACK at the same time */ - if (((seqno - tipc_own_addr) % TIPC_MIN_LINK_WIN) == 0) { + if (((seqno - tn->own_addr) % TIPC_MIN_LINK_WIN) == 0) { tipc_link_proto_xmit(node->active_links[node->addr & 1], STATE_MSG, 0, 0, 0, 0, 0); - bcl->stats.sent_acks++; + tn->bcl->stats.sent_acks++; } } @@ -475,8 +440,10 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) * * RCU is locked, no other locks set */ -void tipc_bclink_rcv(struct sk_buff *buf) +void tipc_bclink_rcv(struct net *net, struct sk_buff *buf) { + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_link *bcl = tn->bcl; struct tipc_msg *msg = buf_msg(buf); struct tipc_node *node; u32 next_in; @@ -484,10 +451,10 @@ void tipc_bclink_rcv(struct sk_buff *buf) int deferred = 0; /* Screen out unwanted broadcast messages */ - if (msg_mc_netid(msg) != tipc_net_id) + if (msg_mc_netid(msg) != tn->net_id) goto exit; - node = tipc_node_find(msg_prevnode(msg)); + node = tipc_node_find(net, msg_prevnode(msg)); if (unlikely(!node)) goto exit; @@ -499,18 +466,18 @@ void tipc_bclink_rcv(struct sk_buff *buf) if (unlikely(msg_user(msg) == BCAST_PROTOCOL)) { if (msg_type(msg) != STATE_MSG) goto unlock; - if (msg_destnode(msg) == tipc_own_addr) { + if (msg_destnode(msg) == tn->own_addr) { tipc_bclink_acknowledge(node, msg_bcast_ack(msg)); tipc_node_unlock(node); - tipc_bclink_lock(); + tipc_bclink_lock(net); bcl->stats.recv_nacks++; - bclink->retransmit_to = node; - bclink_retransmit_pkt(msg_bcgap_after(msg), + tn->bclink->retransmit_to = node; + bclink_retransmit_pkt(tn, msg_bcgap_after(msg), msg_bcgap_to(msg)); - tipc_bclink_unlock(); + tipc_bclink_unlock(net); } else { tipc_node_unlock(node); - bclink_peek_nack(msg); + bclink_peek_nack(net, msg); } goto exit; } @@ -523,47 +490,47 @@ void tipc_bclink_rcv(struct sk_buff *buf) receive: /* Deliver message to destination */ if (likely(msg_isdata(msg))) { - tipc_bclink_lock(); + tipc_bclink_lock(net); bclink_accept_pkt(node, seqno); - tipc_bclink_unlock(); + tipc_bclink_unlock(net); tipc_node_unlock(node); if (likely(msg_mcast(msg))) - tipc_sk_mcast_rcv(buf); + tipc_sk_mcast_rcv(net, buf); else kfree_skb(buf); } else if (msg_user(msg) == MSG_BUNDLER) { - tipc_bclink_lock(); + tipc_bclink_lock(net); bclink_accept_pkt(node, seqno); bcl->stats.recv_bundles++; bcl->stats.recv_bundled += msg_msgcnt(msg); - tipc_bclink_unlock(); + tipc_bclink_unlock(net); tipc_node_unlock(node); - tipc_link_bundle_rcv(buf); + tipc_link_bundle_rcv(net, buf); } else if (msg_user(msg) == MSG_FRAGMENTER) { tipc_buf_append(&node->bclink.reasm_buf, &buf); if (unlikely(!buf && !node->bclink.reasm_buf)) goto unlock; - tipc_bclink_lock(); + tipc_bclink_lock(net); bclink_accept_pkt(node, seqno); bcl->stats.recv_fragments++; if (buf) { bcl->stats.recv_fragmented++; msg = buf_msg(buf); - tipc_bclink_unlock(); + tipc_bclink_unlock(net); goto receive; } - tipc_bclink_unlock(); + tipc_bclink_unlock(net); tipc_node_unlock(node); } else if (msg_user(msg) == NAME_DISTRIBUTOR) { - tipc_bclink_lock(); + tipc_bclink_lock(net); bclink_accept_pkt(node, seqno); - tipc_bclink_unlock(); + tipc_bclink_unlock(net); tipc_node_unlock(node); - tipc_named_rcv(buf); + tipc_named_rcv(net, buf); } else { - tipc_bclink_lock(); + tipc_bclink_lock(net); bclink_accept_pkt(node, seqno); - tipc_bclink_unlock(); + tipc_bclink_unlock(net); tipc_node_unlock(node); kfree_skb(buf); } @@ -601,14 +568,14 @@ receive: buf = NULL; } - tipc_bclink_lock(); + tipc_bclink_lock(net); if (deferred) bcl->stats.deferred_recv++; else bcl->stats.duplicates++; - tipc_bclink_unlock(); + tipc_bclink_unlock(net); unlock: tipc_node_unlock(node); @@ -619,7 +586,7 @@ exit: u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr) { return (n_ptr->bclink.recv_permitted && - (tipc_bclink_get_last_sent() != n_ptr->bclink.acked)); + (tipc_bclink_get_last_sent(n_ptr->net) != n_ptr->bclink.acked)); } @@ -632,11 +599,15 @@ u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr) * Returns 0 (packet sent successfully) under all circumstances, * since the broadcast link's pseudo-bearer never blocks */ -static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1, +static int tipc_bcbearer_send(struct net *net, struct sk_buff *buf, + struct tipc_bearer *unused1, struct tipc_media_addr *unused2) { int bp_index; struct tipc_msg *msg = buf_msg(buf); + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_bcbearer *bcbearer = tn->bcbearer; + struct tipc_bclink *bclink = tn->bclink; /* Prepare broadcast link message for reliable transmission, * if first time trying to send it; @@ -646,8 +617,8 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1, if (likely(!msg_non_seq(buf_msg(buf)))) { bcbuf_set_acks(buf, bclink->bcast_nodes.count); msg_set_non_seq(msg, 1); - msg_set_mc_netid(msg, tipc_net_id); - bcl->stats.sent_info++; + msg_set_mc_netid(msg, tn->net_id); + tn->bcl->stats.sent_info++; if (WARN_ON(!bclink->bcast_nodes.count)) { dump_stack(); @@ -676,13 +647,14 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1, if (bp_index == 0) { /* Use original buffer for first bearer */ - tipc_bearer_send(b->identity, buf, &b->bcast_addr); + tipc_bearer_send(net, b->identity, buf, &b->bcast_addr); } else { /* Avoid concurrent buffer access */ tbuf = pskb_copy_for_clone(buf, GFP_ATOMIC); if (!tbuf) break; - tipc_bearer_send(b->identity, tbuf, &b->bcast_addr); + tipc_bearer_send(net, b->identity, tbuf, + &b->bcast_addr); kfree_skb(tbuf); /* Bearer keeps a clone */ } if (bcbearer->remains_new.count == 0) @@ -697,15 +669,18 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1, /** * tipc_bcbearer_sort - create sets of bearer pairs used by broadcast bearer */ -void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action) +void tipc_bcbearer_sort(struct net *net, struct tipc_node_map *nm_ptr, + u32 node, bool action) { + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_bcbearer *bcbearer = tn->bcbearer; struct tipc_bcbearer_pair *bp_temp = bcbearer->bpairs_temp; struct tipc_bcbearer_pair *bp_curr; struct tipc_bearer *b; int b_index; int pri; - tipc_bclink_lock(); + tipc_bclink_lock(net); if (action) tipc_nmap_add(nm_ptr, node); @@ -717,7 +692,7 @@ void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action) rcu_read_lock(); for (b_index = 0; b_index < MAX_BEARERS; b_index++) { - b = rcu_dereference_rtnl(bearer_list[b_index]); + b = rcu_dereference_rtnl(tn->bearer_list[b_index]); if (!b || !b->nodes.count) continue; @@ -752,7 +727,7 @@ void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action) bp_curr++; } - tipc_bclink_unlock(); + tipc_bclink_unlock(net); } static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb, @@ -806,17 +781,19 @@ msg_full: return -EMSGSIZE; } -int tipc_nl_add_bc_link(struct tipc_nl_msg *msg) +int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) { int err; void *hdr; struct nlattr *attrs; struct nlattr *prop; + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_link *bcl = tn->bcl; if (!bcl) return 0; - tipc_bclink_lock(); + tipc_bclink_lock(net); hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_v2_family, NLM_F_MULTI, TIPC_NL_LINK_GET); @@ -851,7 +828,7 @@ int tipc_nl_add_bc_link(struct tipc_nl_msg *msg) if (err) goto attr_msg_full; - tipc_bclink_unlock(); + tipc_bclink_unlock(net); nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); @@ -862,21 +839,23 @@ prop_msg_full: attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: - tipc_bclink_unlock(); + tipc_bclink_unlock(net); genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } -int tipc_bclink_stats(char *buf, const u32 buf_size) +int tipc_bclink_stats(struct net *net, char *buf, const u32 buf_size) { int ret; struct tipc_stats *s; + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_link *bcl = tn->bcl; if (!bcl) return 0; - tipc_bclink_lock(); + tipc_bclink_lock(net); s = &bcl->stats; @@ -905,36 +884,47 @@ int tipc_bclink_stats(char *buf, const u32 buf_size) s->queue_sz_counts ? (s->accu_queue_sz / s->queue_sz_counts) : 0); - tipc_bclink_unlock(); + tipc_bclink_unlock(net); return ret; } -int tipc_bclink_reset_stats(void) +int tipc_bclink_reset_stats(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_link *bcl = tn->bcl; + if (!bcl) return -ENOPROTOOPT; - tipc_bclink_lock(); + tipc_bclink_lock(net); memset(&bcl->stats, 0, sizeof(bcl->stats)); - tipc_bclink_unlock(); + tipc_bclink_unlock(net); return 0; } -int tipc_bclink_set_queue_limits(u32 limit) +int tipc_bclink_set_queue_limits(struct net *net, u32 limit) { + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_link *bcl = tn->bcl; + if (!bcl) return -ENOPROTOOPT; if ((limit < TIPC_MIN_LINK_WIN) || (limit > TIPC_MAX_LINK_WIN)) return -EINVAL; - tipc_bclink_lock(); + tipc_bclink_lock(net); tipc_link_set_queue_limits(bcl, limit); - tipc_bclink_unlock(); + tipc_bclink_unlock(net); return 0; } -int tipc_bclink_init(void) +int tipc_bclink_init(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_bcbearer *bcbearer; + struct tipc_bclink *bclink; + struct tipc_link *bcl; + bcbearer = kzalloc(sizeof(*bcbearer), GFP_ATOMIC); if (!bcbearer) return -ENOMEM; @@ -958,25 +948,31 @@ int tipc_bclink_init(void) spin_lock_init(&bclink->node.lock); __skb_queue_head_init(&bclink->node.waiting_sks); bcl->owner = &bclink->node; + bcl->owner->net = net; bcl->max_pkt = MAX_PKT_DEFAULT_MCAST; tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT); bcl->bearer_id = MAX_BEARERS; - rcu_assign_pointer(bearer_list[MAX_BEARERS], &bcbearer->bearer); + rcu_assign_pointer(tn->bearer_list[MAX_BEARERS], &bcbearer->bearer); bcl->state = WORKING_WORKING; strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME); + tn->bcbearer = bcbearer; + tn->bclink = bclink; + tn->bcl = bcl; return 0; } -void tipc_bclink_stop(void) +void tipc_bclink_stop(struct net *net) { - tipc_bclink_lock(); - tipc_link_purge_queues(bcl); - tipc_bclink_unlock(); + struct tipc_net *tn = net_generic(net, tipc_net_id); + + tipc_bclink_lock(net); + tipc_link_purge_queues(tn->bcl); + tipc_bclink_unlock(net); - RCU_INIT_POINTER(bearer_list[BCBEARER], NULL); + RCU_INIT_POINTER(tn->bearer_list[BCBEARER], NULL); synchronize_net(); - kfree(bcbearer); - kfree(bclink); + kfree(tn->bcbearer); + kfree(tn->bclink); } /** diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 644d79129fba..a4583a109486 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -37,23 +37,13 @@ #ifndef _TIPC_BCAST_H #define _TIPC_BCAST_H -#include "netlink.h" +#include <linux/tipc_config.h> +#include "link.h" +#include "node.h" -#define MAX_NODES 4096 -#define WSIZE 32 -#define TIPC_BCLINK_RESET 1 - -/** - * struct tipc_node_map - set of node identifiers - * @count: # of nodes in set - * @map: bitmap of node identifiers that are in the set - */ -struct tipc_node_map { - u32 count; - u32 map[MAX_NODES / WSIZE]; -}; - -#define PLSIZE 32 +#define TIPC_BCLINK_RESET 1 +#define PLSIZE 32 +#define BCBEARER MAX_BEARERS /** * struct tipc_port_list - set of node local destination ports @@ -67,9 +57,64 @@ struct tipc_port_list { u32 ports[PLSIZE]; }; +/** + * struct tipc_bcbearer_pair - a pair of bearers used by broadcast link + * @primary: pointer to primary bearer + * @secondary: pointer to secondary bearer + * + * Bearers must have same priority and same set of reachable destinations + * to be paired. + */ -struct tipc_node; +struct tipc_bcbearer_pair { + struct tipc_bearer *primary; + struct tipc_bearer *secondary; +}; +/** + * struct tipc_bcbearer - bearer used by broadcast link + * @bearer: (non-standard) broadcast bearer structure + * @media: (non-standard) broadcast media structure + * @bpairs: array of bearer pairs + * @bpairs_temp: temporary array of bearer pairs used by tipc_bcbearer_sort() + * @remains: temporary node map used by tipc_bcbearer_send() + * @remains_new: temporary node map used tipc_bcbearer_send() + * + * Note: The fields labelled "temporary" are incorporated into the bearer + * to avoid consuming potentially limited stack space through the use of + * large local variables within multicast routines. Concurrent access is + * prevented through use of the spinlock "bclink_lock". + */ +struct tipc_bcbearer { + struct tipc_bearer bearer; + struct tipc_media media; + struct tipc_bcbearer_pair bpairs[MAX_BEARERS]; + struct tipc_bcbearer_pair bpairs_temp[TIPC_MAX_LINK_PRI + 1]; + struct tipc_node_map remains; + struct tipc_node_map remains_new; +}; + +/** + * struct tipc_bclink - link used for broadcast messages + * @lock: spinlock governing access to structure + * @link: (non-standard) broadcast link structure + * @node: (non-standard) node structure representing b'cast link's peer node + * @flags: represent bclink states + * @bcast_nodes: map of broadcast-capable nodes + * @retransmit_to: node that most recently requested a retransmit + * + * Handles sequence numbering, fragmentation, bundling, etc. + */ +struct tipc_bclink { + spinlock_t lock; + struct tipc_link link; + struct tipc_node node; + unsigned int flags; + struct tipc_node_map bcast_nodes; + struct tipc_node *retransmit_to; +}; + +struct tipc_node; extern const char tipc_bclink_name[]; /** @@ -84,24 +129,26 @@ static inline int tipc_nmap_equal(struct tipc_node_map *nm_a, void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port); void tipc_port_list_free(struct tipc_port_list *pl_ptr); -int tipc_bclink_init(void); -void tipc_bclink_stop(void); -void tipc_bclink_set_flags(unsigned int flags); -void tipc_bclink_add_node(u32 addr); -void tipc_bclink_remove_node(u32 addr); -struct tipc_node *tipc_bclink_retransmit_to(void); +int tipc_bclink_init(struct net *net); +void tipc_bclink_stop(struct net *net); +void tipc_bclink_set_flags(struct net *tn, unsigned int flags); +void tipc_bclink_add_node(struct net *net, u32 addr); +void tipc_bclink_remove_node(struct net *net, u32 addr); +struct tipc_node *tipc_bclink_retransmit_to(struct net *tn); void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked); -void tipc_bclink_rcv(struct sk_buff *buf); -u32 tipc_bclink_get_last_sent(void); +void tipc_bclink_rcv(struct net *net, struct sk_buff *buf); +u32 tipc_bclink_get_last_sent(struct net *net); u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr); -void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent); -int tipc_bclink_stats(char *stats_buf, const u32 buf_size); -int tipc_bclink_reset_stats(void); -int tipc_bclink_set_queue_limits(u32 limit); -void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action); +void tipc_bclink_update_link_state(struct net *net, struct tipc_node *n_ptr, + u32 last_sent); +int tipc_bclink_stats(struct net *net, char *stats_buf, const u32 buf_size); +int tipc_bclink_reset_stats(struct net *net); +int tipc_bclink_set_queue_limits(struct net *net, u32 limit); +void tipc_bcbearer_sort(struct net *net, struct tipc_node_map *nm_ptr, + u32 node, bool action); uint tipc_bclink_get_mtu(void); -int tipc_bclink_xmit(struct sk_buff_head *list); -void tipc_bclink_wakeup_users(void); -int tipc_nl_add_bc_link(struct tipc_nl_msg *msg); +int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list); +void tipc_bclink_wakeup_users(struct net *net); +int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg); #endif diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 463db5b15b8b..33dc3486d16c 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -34,11 +34,13 @@ * POSSIBILITY OF SUCH DAMAGE. */ +#include <net/sock.h> #include "core.h" #include "config.h" #include "bearer.h" #include "link.h" #include "discover.h" +#include "bcast.h" #define MAX_ADDR_STR 60 @@ -67,9 +69,8 @@ static const struct nla_policy tipc_nl_media_policy[TIPC_NLA_MEDIA_MAX + 1] = { [TIPC_NLA_MEDIA_PROP] = { .type = NLA_NESTED } }; -struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1]; - -static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down); +static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr, + bool shutting_down); /** * tipc_media_find - locates specified media object by name @@ -190,13 +191,14 @@ static int bearer_name_validate(const char *name, /** * tipc_bearer_find - locates bearer object with matching bearer name */ -struct tipc_bearer *tipc_bearer_find(const char *name) +struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b_ptr; u32 i; for (i = 0; i < MAX_BEARERS; i++) { - b_ptr = rtnl_dereference(bearer_list[i]); + b_ptr = rtnl_dereference(tn->bearer_list[i]); if (b_ptr && (!strcmp(b_ptr->name, name))) return b_ptr; } @@ -206,8 +208,9 @@ struct tipc_bearer *tipc_bearer_find(const char *name) /** * tipc_bearer_get_names - record names of bearers in buffer */ -struct sk_buff *tipc_bearer_get_names(void) +struct sk_buff *tipc_bearer_get_names(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff *buf; struct tipc_bearer *b; int i, j; @@ -218,7 +221,7 @@ struct sk_buff *tipc_bearer_get_names(void) for (i = 0; media_info_array[i] != NULL; i++) { for (j = 0; j < MAX_BEARERS; j++) { - b = rtnl_dereference(bearer_list[j]); + b = rtnl_dereference(tn->bearer_list[j]); if (!b) continue; if (b->media == media_info_array[i]) { @@ -231,27 +234,29 @@ struct sk_buff *tipc_bearer_get_names(void) return buf; } -void tipc_bearer_add_dest(u32 bearer_id, u32 dest) +void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b_ptr; rcu_read_lock(); - b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]); + b_ptr = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); if (b_ptr) { - tipc_bcbearer_sort(&b_ptr->nodes, dest, true); + tipc_bcbearer_sort(net, &b_ptr->nodes, dest, true); tipc_disc_add_dest(b_ptr->link_req); } rcu_read_unlock(); } -void tipc_bearer_remove_dest(u32 bearer_id, u32 dest) +void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b_ptr; rcu_read_lock(); - b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]); + b_ptr = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); if (b_ptr) { - tipc_bcbearer_sort(&b_ptr->nodes, dest, false); + tipc_bcbearer_sort(net, &b_ptr->nodes, dest, false); tipc_disc_remove_dest(b_ptr->link_req); } rcu_read_unlock(); @@ -260,8 +265,10 @@ void tipc_bearer_remove_dest(u32 bearer_id, u32 dest) /** * tipc_enable_bearer - enable bearer with the given name */ -int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) +int tipc_enable_bearer(struct net *net, const char *name, u32 disc_domain, + u32 priority) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b_ptr; struct tipc_media *m_ptr; struct tipc_bearer_names b_names; @@ -271,7 +278,7 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) u32 i; int res = -EINVAL; - if (!tipc_own_addr) { + if (!tn->own_addr) { pr_warn("Bearer <%s> rejected, not supported in standalone mode\n", name); return -ENOPROTOOPT; @@ -281,11 +288,11 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) return -EINVAL; } if (tipc_addr_domain_valid(disc_domain) && - (disc_domain != tipc_own_addr)) { - if (tipc_in_scope(disc_domain, tipc_own_addr)) { - disc_domain = tipc_own_addr & TIPC_CLUSTER_MASK; + (disc_domain != tn->own_addr)) { + if (tipc_in_scope(disc_domain, tn->own_addr)) { + disc_domain = tn->own_addr & TIPC_CLUSTER_MASK; res = 0; /* accept any node in own cluster */ - } else if (in_own_cluster_exact(disc_domain)) + } else if (in_own_cluster_exact(net, disc_domain)) res = 0; /* accept specified node in own cluster */ } if (res) { @@ -313,7 +320,7 @@ restart: bearer_id = MAX_BEARERS; with_this_prio = 1; for (i = MAX_BEARERS; i-- != 0; ) { - b_ptr = rtnl_dereference(bearer_list[i]); + b_ptr = rtnl_dereference(tn->bearer_list[i]); if (!b_ptr) { bearer_id = i; continue; @@ -347,7 +354,7 @@ restart: strcpy(b_ptr->name, name); b_ptr->media = m_ptr; - res = m_ptr->enable_media(b_ptr); + res = m_ptr->enable_media(net, b_ptr); if (res) { pr_warn("Bearer <%s> rejected, enable failure (%d)\n", name, -res); @@ -361,15 +368,15 @@ restart: b_ptr->net_plane = bearer_id + 'A'; b_ptr->priority = priority; - res = tipc_disc_create(b_ptr, &b_ptr->bcast_addr); + res = tipc_disc_create(net, b_ptr, &b_ptr->bcast_addr); if (res) { - bearer_disable(b_ptr, false); + bearer_disable(net, b_ptr, false); pr_warn("Bearer <%s> rejected, discovery object creation failed\n", name); return -EINVAL; } - rcu_assign_pointer(bearer_list[bearer_id], b_ptr); + rcu_assign_pointer(tn->bearer_list[bearer_id], b_ptr); pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n", name, @@ -380,11 +387,11 @@ restart: /** * tipc_reset_bearer - Reset all links established over this bearer */ -static int tipc_reset_bearer(struct tipc_bearer *b_ptr) +static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b_ptr) { pr_info("Resetting bearer <%s>\n", b_ptr->name); - tipc_link_reset_list(b_ptr->identity); - tipc_disc_reset(b_ptr); + tipc_link_reset_list(net, b_ptr->identity); + tipc_disc_reset(net, b_ptr); return 0; } @@ -393,49 +400,51 @@ static int tipc_reset_bearer(struct tipc_bearer *b_ptr) * * Note: This routine assumes caller holds RTNL lock. */ -static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down) +static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr, + bool shutting_down) { + struct tipc_net *tn = net_generic(net, tipc_net_id); u32 i; pr_info("Disabling bearer <%s>\n", b_ptr->name); b_ptr->media->disable_media(b_ptr); - tipc_link_delete_list(b_ptr->identity, shutting_down); + tipc_link_delete_list(net, b_ptr->identity, shutting_down); if (b_ptr->link_req) tipc_disc_delete(b_ptr->link_req); for (i = 0; i < MAX_BEARERS; i++) { - if (b_ptr == rtnl_dereference(bearer_list[i])) { - RCU_INIT_POINTER(bearer_list[i], NULL); + if (b_ptr == rtnl_dereference(tn->bearer_list[i])) { + RCU_INIT_POINTER(tn->bearer_list[i], NULL); break; } } kfree_rcu(b_ptr, rcu); } -int tipc_disable_bearer(const char *name) +int tipc_disable_bearer(struct net *net, const char *name) { struct tipc_bearer *b_ptr; int res; - b_ptr = tipc_bearer_find(name); + b_ptr = tipc_bearer_find(net, name); if (b_ptr == NULL) { pr_warn("Attempt to disable unknown bearer <%s>\n", name); res = -EINVAL; } else { - bearer_disable(b_ptr, false); + bearer_disable(net, b_ptr, false); res = 0; } return res; } -int tipc_enable_l2_media(struct tipc_bearer *b) +int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b) { struct net_device *dev; char *driver_name = strchr((const char *)b->name, ':') + 1; /* Find device with specified name */ - dev = dev_get_by_name(&init_net, driver_name); + dev = dev_get_by_name(net, driver_name); if (!dev) return -ENODEV; @@ -474,8 +483,8 @@ void tipc_disable_l2_media(struct tipc_bearer *b) * @b_ptr: the bearer through which the packet is to be sent * @dest: peer destination address */ -int tipc_l2_send_msg(struct sk_buff *buf, struct tipc_bearer *b, - struct tipc_media_addr *dest) +int tipc_l2_send_msg(struct net *net, struct sk_buff *buf, + struct tipc_bearer *b, struct tipc_media_addr *dest) { struct sk_buff *clone; struct net_device *dev; @@ -511,15 +520,16 @@ int tipc_l2_send_msg(struct sk_buff *buf, struct tipc_bearer *b, * The media send routine must not alter the buffer being passed in * as it may be needed for later retransmission! */ -void tipc_bearer_send(u32 bearer_id, struct sk_buff *buf, +void tipc_bearer_send(struct net *net, u32 bearer_id, struct sk_buff *buf, struct tipc_media_addr *dest) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b_ptr; rcu_read_lock(); - b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]); + b_ptr = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); if (likely(b_ptr)) - b_ptr->media->send_msg(buf, b_ptr, dest); + b_ptr->media->send_msg(net, buf, b_ptr, dest); rcu_read_unlock(); } @@ -539,17 +549,12 @@ static int tipc_l2_rcv_msg(struct sk_buff *buf, struct net_device *dev, { struct tipc_bearer *b_ptr; - if (!net_eq(dev_net(dev), &init_net)) { - kfree_skb(buf); - return NET_RX_DROP; - } - rcu_read_lock(); b_ptr = rcu_dereference_rtnl(dev->tipc_ptr); if (likely(b_ptr)) { if (likely(buf->pkt_type <= PACKET_BROADCAST)) { buf->next = NULL; - tipc_rcv(buf, b_ptr); + tipc_rcv(dev_net(dev), buf, b_ptr); rcu_read_unlock(); return NET_RX_SUCCESS; } @@ -572,11 +577,9 @@ static int tipc_l2_rcv_msg(struct sk_buff *buf, struct net_device *dev, static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, void *ptr) { - struct tipc_bearer *b_ptr; struct net_device *dev = netdev_notifier_info_to_dev(ptr); - - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; + struct net *net = dev_net(dev); + struct tipc_bearer *b_ptr; b_ptr = rtnl_dereference(dev->tipc_ptr); if (!b_ptr) @@ -590,16 +593,16 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, break; case NETDEV_DOWN: case NETDEV_CHANGEMTU: - tipc_reset_bearer(b_ptr); + tipc_reset_bearer(net, b_ptr); break; case NETDEV_CHANGEADDR: b_ptr->media->raw2addr(b_ptr, &b_ptr->addr, (char *)dev->dev_addr); - tipc_reset_bearer(b_ptr); + tipc_reset_bearer(net, b_ptr); break; case NETDEV_UNREGISTER: case NETDEV_CHANGENAME: - bearer_disable(b_ptr, false); + bearer_disable(dev_net(dev), b_ptr, false); break; } return NOTIFY_OK; @@ -632,16 +635,17 @@ void tipc_bearer_cleanup(void) dev_remove_pack(&tipc_packet_type); } -void tipc_bearer_stop(void) +void tipc_bearer_stop(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b_ptr; u32 i; for (i = 0; i < MAX_BEARERS; i++) { - b_ptr = rtnl_dereference(bearer_list[i]); + b_ptr = rtnl_dereference(tn->bearer_list[i]); if (b_ptr) { - bearer_disable(b_ptr, true); - bearer_list[i] = NULL; + bearer_disable(net, b_ptr, true); + tn->bearer_list[i] = NULL; } } } @@ -698,6 +702,8 @@ int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb) int i = cb->args[0]; struct tipc_bearer *bearer; struct tipc_nl_msg msg; + struct net *net = sock_net(skb->sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); if (i == MAX_BEARERS) return 0; @@ -708,7 +714,7 @@ int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); for (i = 0; i < MAX_BEARERS; i++) { - bearer = rtnl_dereference(bearer_list[i]); + bearer = rtnl_dereference(tn->bearer_list[i]); if (!bearer) continue; @@ -730,6 +736,7 @@ int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info) struct tipc_bearer *bearer; struct tipc_nl_msg msg; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; + struct net *net = genl_info_net(info); if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; @@ -753,7 +760,7 @@ int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info) msg.seq = info->snd_seq; rtnl_lock(); - bearer = tipc_bearer_find(name); + bearer = tipc_bearer_find(net, name); if (!bearer) { err = -EINVAL; goto err_out; @@ -778,6 +785,7 @@ int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) char *name; struct tipc_bearer *bearer; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; + struct net *net = genl_info_net(info); if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; @@ -794,13 +802,13 @@ int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); rtnl_lock(); - bearer = tipc_bearer_find(name); + bearer = tipc_bearer_find(net, name); if (!bearer) { rtnl_unlock(); return -EINVAL; } - bearer_disable(bearer, false); + bearer_disable(net, bearer, false); rtnl_unlock(); return 0; @@ -808,6 +816,8 @@ int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) { + struct net *net = genl_info_net(info); + struct tipc_net *tn = net_generic(net, tipc_net_id); int err; char *bearer; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; @@ -815,7 +825,7 @@ int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) u32 prio; prio = TIPC_MEDIA_LINK_PRI; - domain = tipc_own_addr & TIPC_CLUSTER_MASK; + domain = tn->own_addr & TIPC_CLUSTER_MASK; if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; @@ -847,7 +857,7 @@ int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) } rtnl_lock(); - err = tipc_enable_bearer(bearer, domain, prio); + err = tipc_enable_bearer(net, bearer, domain, prio); if (err) { rtnl_unlock(); return err; @@ -863,6 +873,7 @@ int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) char *name; struct tipc_bearer *b; struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; + struct net *net = genl_info_net(info); if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; @@ -878,7 +889,7 @@ int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); rtnl_lock(); - b = tipc_bearer_find(name); + b = tipc_bearer_find(net, name); if (!b) { rtnl_unlock(); return -EINVAL; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 2c1230ac5dfe..c035e3e24764 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -37,12 +37,13 @@ #ifndef _TIPC_BEARER_H #define _TIPC_BEARER_H -#include "bcast.h" #include "netlink.h" #include <net/genetlink.h> #define MAX_BEARERS 2 #define MAX_MEDIA 2 +#define MAX_NODES 4096 +#define WSIZE 32 /* Identifiers associated with TIPC message header media address info * - address info field is 32 bytes long @@ -59,6 +60,16 @@ #define TIPC_MEDIA_TYPE_IB 2 /** + * struct tipc_node_map - set of node identifiers + * @count: # of nodes in set + * @map: bitmap of node identifiers that are in the set + */ +struct tipc_node_map { + u32 count; + u32 map[MAX_NODES / WSIZE]; +}; + +/** * struct tipc_media_addr - destination address used by TIPC bearers * @value: address info (format defined by media) * @media_id: TIPC media type identifier @@ -89,10 +100,10 @@ struct tipc_bearer; * @name: media name */ struct tipc_media { - int (*send_msg)(struct sk_buff *buf, + int (*send_msg)(struct net *net, struct sk_buff *buf, struct tipc_bearer *b_ptr, struct tipc_media_addr *dest); - int (*enable_media)(struct tipc_bearer *b_ptr); + int (*enable_media)(struct net *net, struct tipc_bearer *b_ptr); void (*disable_media)(struct tipc_bearer *b_ptr); int (*addr2str)(struct tipc_media_addr *addr, char *strbuf, @@ -157,17 +168,14 @@ struct tipc_bearer_names { char if_name[TIPC_MAX_IF_NAME]; }; -struct tipc_link; - -extern struct tipc_bearer __rcu *bearer_list[]; - /* * TIPC routines available to supported media types */ -void tipc_rcv(struct sk_buff *skb, struct tipc_bearer *tb_ptr); -int tipc_enable_bearer(const char *bearer_name, u32 disc_domain, u32 priority); -int tipc_disable_bearer(const char *name); +void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr); +int tipc_enable_bearer(struct net *net, const char *bearer_name, + u32 disc_domain, u32 priority); +int tipc_disable_bearer(struct net *net, const char *name); /* * Routines made available to TIPC by supported media types @@ -192,20 +200,20 @@ int tipc_media_set_priority(const char *name, u32 new_value); int tipc_media_set_window(const char *name, u32 new_value); void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a); struct sk_buff *tipc_media_get_names(void); -int tipc_enable_l2_media(struct tipc_bearer *b); +int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b); void tipc_disable_l2_media(struct tipc_bearer *b); -int tipc_l2_send_msg(struct sk_buff *buf, struct tipc_bearer *b, - struct tipc_media_addr *dest); +int tipc_l2_send_msg(struct net *net, struct sk_buff *buf, + struct tipc_bearer *b, struct tipc_media_addr *dest); -struct sk_buff *tipc_bearer_get_names(void); -void tipc_bearer_add_dest(u32 bearer_id, u32 dest); -void tipc_bearer_remove_dest(u32 bearer_id, u32 dest); -struct tipc_bearer *tipc_bearer_find(const char *name); +struct sk_buff *tipc_bearer_get_names(struct net *net); +void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest); +void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest); +struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name); struct tipc_media *tipc_media_find(const char *name); int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); -void tipc_bearer_stop(void); -void tipc_bearer_send(u32 bearer_id, struct sk_buff *buf, +void tipc_bearer_stop(struct net *net); +void tipc_bearer_send(struct net *net, u32 bearer_id, struct sk_buff *buf, struct tipc_media_addr *dest); #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/config.c b/net/tipc/config.c index 876f4c6a2631..6873360cda53 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -134,7 +134,7 @@ static struct sk_buff *tipc_show_stats(void) return buf; } -static struct sk_buff *cfg_enable_bearer(void) +static struct sk_buff *cfg_enable_bearer(struct net *net) { struct tipc_bearer_config *args; @@ -142,7 +142,7 @@ static struct sk_buff *cfg_enable_bearer(void) return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); args = (struct tipc_bearer_config *)TLV_DATA(req_tlv_area); - if (tipc_enable_bearer(args->name, + if (tipc_enable_bearer(net, args->name, ntohl(args->disc_domain), ntohl(args->priority))) return tipc_cfg_reply_error_string("unable to enable bearer"); @@ -150,78 +150,66 @@ static struct sk_buff *cfg_enable_bearer(void) return tipc_cfg_reply_none(); } -static struct sk_buff *cfg_disable_bearer(void) +static struct sk_buff *cfg_disable_bearer(struct net *net) { if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_BEARER_NAME)) return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - if (tipc_disable_bearer((char *)TLV_DATA(req_tlv_area))) + if (tipc_disable_bearer(net, (char *)TLV_DATA(req_tlv_area))) return tipc_cfg_reply_error_string("unable to disable bearer"); return tipc_cfg_reply_none(); } -static struct sk_buff *cfg_set_own_addr(void) +static struct sk_buff *cfg_set_own_addr(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); u32 addr; if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NET_ADDR)) return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); addr = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (addr == tipc_own_addr) + if (addr == tn->own_addr) return tipc_cfg_reply_none(); if (!tipc_addr_node_valid(addr)) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (node address)"); - if (tipc_own_addr) + if (tn->own_addr) return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (cannot change node address once assigned)"); - if (!tipc_net_start(addr)) + if (!tipc_net_start(net, addr)) return tipc_cfg_reply_none(); return tipc_cfg_reply_error_string("cannot change to network mode"); } -static struct sk_buff *cfg_set_max_ports(void) +static struct sk_buff *cfg_set_netid(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); u32 value; if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (value == tipc_max_ports) - return tipc_cfg_reply_none(); - if (value < 127 || value > 65535) - return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE - " (max ports must be 127-65535)"); - return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED - " (cannot change max ports while TIPC is active)"); -} - -static struct sk_buff *cfg_set_netid(void) -{ - u32 value; - - if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) - return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (value == tipc_net_id) + if (value == tn->net_id) return tipc_cfg_reply_none(); if (value < 1 || value > 9999) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (network id must be 1-9999)"); - if (tipc_own_addr) + if (tn->own_addr) return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (cannot change network id once TIPC has joined a network)"); - tipc_net_id = value; + tn->net_id = value; return tipc_cfg_reply_none(); } -struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area, - int request_space, int reply_headroom) +struct sk_buff *tipc_cfg_do_cmd(struct net *net, u32 orig_node, u16 cmd, + const void *request_area, int request_space, + int reply_headroom) { struct sk_buff *rep_tlv_buf; + struct tipc_net *tn = net_generic(net, tipc_net_id); rtnl_lock(); @@ -231,7 +219,7 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area rep_headroom = reply_headroom; /* Check command authorization */ - if (likely(in_own_node(orig_node))) { + if (likely(in_own_node(net, orig_node))) { /* command is permitted */ } else { rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED @@ -245,28 +233,33 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area rep_tlv_buf = tipc_cfg_reply_none(); break; case TIPC_CMD_GET_NODES: - rep_tlv_buf = tipc_node_get_nodes(req_tlv_area, req_tlv_space); + rep_tlv_buf = tipc_node_get_nodes(net, req_tlv_area, + req_tlv_space); break; case TIPC_CMD_GET_LINKS: - rep_tlv_buf = tipc_node_get_links(req_tlv_area, req_tlv_space); + rep_tlv_buf = tipc_node_get_links(net, req_tlv_area, + req_tlv_space); break; case TIPC_CMD_SHOW_LINK_STATS: - rep_tlv_buf = tipc_link_cmd_show_stats(req_tlv_area, req_tlv_space); + rep_tlv_buf = tipc_link_cmd_show_stats(net, req_tlv_area, + req_tlv_space); break; case TIPC_CMD_RESET_LINK_STATS: - rep_tlv_buf = tipc_link_cmd_reset_stats(req_tlv_area, req_tlv_space); + rep_tlv_buf = tipc_link_cmd_reset_stats(net, req_tlv_area, + req_tlv_space); break; case TIPC_CMD_SHOW_NAME_TABLE: - rep_tlv_buf = tipc_nametbl_get(req_tlv_area, req_tlv_space); + rep_tlv_buf = tipc_nametbl_get(net, req_tlv_area, + req_tlv_space); break; case TIPC_CMD_GET_BEARER_NAMES: - rep_tlv_buf = tipc_bearer_get_names(); + rep_tlv_buf = tipc_bearer_get_names(net); break; case TIPC_CMD_GET_MEDIA_NAMES: rep_tlv_buf = tipc_media_get_names(); break; case TIPC_CMD_SHOW_PORTS: - rep_tlv_buf = tipc_sk_socks_show(); + rep_tlv_buf = tipc_sk_socks_show(net); break; case TIPC_CMD_SHOW_STATS: rep_tlv_buf = tipc_show_stats(); @@ -274,28 +267,23 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SET_LINK_TOL: case TIPC_CMD_SET_LINK_PRI: case TIPC_CMD_SET_LINK_WINDOW: - rep_tlv_buf = tipc_link_cmd_config(req_tlv_area, req_tlv_space, cmd); + rep_tlv_buf = tipc_link_cmd_config(net, req_tlv_area, + req_tlv_space, cmd); break; case TIPC_CMD_ENABLE_BEARER: - rep_tlv_buf = cfg_enable_bearer(); + rep_tlv_buf = cfg_enable_bearer(net); break; case TIPC_CMD_DISABLE_BEARER: - rep_tlv_buf = cfg_disable_bearer(); + rep_tlv_buf = cfg_disable_bearer(net); break; case TIPC_CMD_SET_NODE_ADDR: - rep_tlv_buf = cfg_set_own_addr(); - break; - case TIPC_CMD_SET_MAX_PORTS: - rep_tlv_buf = cfg_set_max_ports(); + rep_tlv_buf = cfg_set_own_addr(net); break; case TIPC_CMD_SET_NETID: - rep_tlv_buf = cfg_set_netid(); - break; - case TIPC_CMD_GET_MAX_PORTS: - rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_ports); + rep_tlv_buf = cfg_set_netid(net); break; case TIPC_CMD_GET_NETID: - rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_net_id); + rep_tlv_buf = tipc_cfg_reply_unsigned(tn->net_id); break; case TIPC_CMD_NOT_NET_ADMIN: rep_tlv_buf = @@ -317,6 +305,8 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SET_REMOTE_MNG: case TIPC_CMD_GET_REMOTE_MNG: case TIPC_CMD_DUMP_LOG: + case TIPC_CMD_SET_MAX_PORTS: + case TIPC_CMD_GET_MAX_PORTS: rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (obsolete command)"); break; diff --git a/net/tipc/config.h b/net/tipc/config.h index 47b1bf181612..9e9b575fc429 100644 --- a/net/tipc/config.h +++ b/net/tipc/config.h @@ -37,10 +37,10 @@ #ifndef _TIPC_CONFIG_H #define _TIPC_CONFIG_H -/* ---------------------------------------------------------------------- */ - #include "link.h" +#define ULTRA_STRING_MAX_LEN 32768 + struct sk_buff *tipc_cfg_reply_alloc(int payload_size); int tipc_cfg_append_tlv(struct sk_buff *buf, int tlv_type, void *tlv_data, int tlv_data_size); @@ -61,7 +61,7 @@ static inline struct sk_buff *tipc_cfg_reply_ultra_string(char *string) return tipc_cfg_reply_string_type(TIPC_TLV_ULTRA_STRING, string); } -struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, +struct sk_buff *tipc_cfg_do_cmd(struct net *net, u32 orig_node, u16 cmd, const void *req_tlv_area, int req_tlv_space, int headroom); #endif diff --git a/net/tipc/core.c b/net/tipc/core.c index a5737b8407dd..674bd2698528 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -34,6 +34,8 @@ * POSSIBILITY OF SUCH DAMAGE. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include "core.h" #include "name_table.h" #include "subscr.h" @@ -42,69 +44,68 @@ #include <linux/module.h> -/* global variables used by multiple sub-systems within TIPC */ -int tipc_random __read_mostly; - /* configurable TIPC parameters */ -u32 tipc_own_addr __read_mostly; -int tipc_max_ports __read_mostly; int tipc_net_id __read_mostly; int sysctl_tipc_rmem[3] __read_mostly; /* min/default/max */ -/** - * tipc_buf_acquire - creates a TIPC message buffer - * @size: message size (including TIPC header) - * - * Returns a new buffer with data pointers set to the specified size. - * - * NOTE: Headroom is reserved to allow prepending of a data link header. - * There may also be unrequested tailroom present at the buffer's end. - */ -struct sk_buff *tipc_buf_acquire(u32 size) +static int __net_init tipc_init_net(struct net *net) { - struct sk_buff *skb; - unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u; - - skb = alloc_skb_fclone(buf_size, GFP_ATOMIC); - if (skb) { - skb_reserve(skb, BUF_HEADROOM); - skb_put(skb, size); - skb->next = NULL; - } - return skb; + struct tipc_net *tn = net_generic(net, tipc_net_id); + int err; + + tn->net_id = 4711; + tn->own_addr = 0; + get_random_bytes(&tn->random, sizeof(int)); + INIT_LIST_HEAD(&tn->node_list); + spin_lock_init(&tn->node_list_lock); + + err = tipc_sk_rht_init(net); + if (err) + goto out_sk_rht; + + err = tipc_nametbl_init(net); + if (err) + goto out_nametbl; + + err = tipc_subscr_start(net); + if (err) + goto out_subscr; + return 0; + +out_subscr: + tipc_nametbl_stop(net); +out_nametbl: + tipc_sk_rht_destroy(net); +out_sk_rht: + return err; } -/** - * tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode - */ -static void tipc_core_stop(void) +static void __net_exit tipc_exit_net(struct net *net) { - tipc_net_stop(); - tipc_bearer_cleanup(); - tipc_netlink_stop(); - tipc_subscr_stop(); - tipc_nametbl_stop(); - tipc_sk_ref_table_stop(); - tipc_socket_stop(); - tipc_unregister_sysctl(); + tipc_subscr_stop(net); + tipc_net_stop(net); + tipc_nametbl_stop(net); + tipc_sk_rht_destroy(net); } -/** - * tipc_core_start - switch TIPC from NOT RUNNING to SINGLE NODE mode - */ -static int tipc_core_start(void) +static struct pernet_operations tipc_net_ops = { + .init = tipc_init_net, + .exit = tipc_exit_net, + .id = &tipc_net_id, + .size = sizeof(struct tipc_net), +}; + +static int __init tipc_init(void) { int err; - get_random_bytes(&tipc_random, sizeof(tipc_random)); - - err = tipc_sk_ref_table_init(tipc_max_ports, tipc_random); - if (err) - goto out_reftbl; + pr_info("Activated (version " TIPC_MOD_VER ")\n"); - err = tipc_nametbl_init(); - if (err) - goto out_nametbl; + sysctl_tipc_rmem[0] = TIPC_CONN_OVERLOAD_LIMIT >> 4 << + TIPC_LOW_IMPORTANCE; + sysctl_tipc_rmem[1] = TIPC_CONN_OVERLOAD_LIMIT >> 4 << + TIPC_CRITICAL_IMPORTANCE; + sysctl_tipc_rmem[2] = TIPC_CONN_OVERLOAD_LIMIT; err = tipc_netlink_start(); if (err) @@ -118,58 +119,37 @@ static int tipc_core_start(void) if (err) goto out_sysctl; - err = tipc_subscr_start(); + err = register_pernet_subsys(&tipc_net_ops); if (err) - goto out_subscr; + goto out_pernet; err = tipc_bearer_setup(); if (err) goto out_bearer; + pr_info("Started in single node mode\n"); return 0; out_bearer: - tipc_subscr_stop(); -out_subscr: + unregister_pernet_subsys(&tipc_net_ops); +out_pernet: tipc_unregister_sysctl(); out_sysctl: tipc_socket_stop(); out_socket: tipc_netlink_stop(); out_netlink: - tipc_nametbl_stop(); -out_nametbl: - tipc_sk_ref_table_stop(); -out_reftbl: + pr_err("Unable to start in single node mode\n"); return err; } -static int __init tipc_init(void) -{ - int res; - - pr_info("Activated (version " TIPC_MOD_VER ")\n"); - - tipc_own_addr = 0; - tipc_max_ports = CONFIG_TIPC_PORTS; - tipc_net_id = 4711; - - sysctl_tipc_rmem[0] = TIPC_CONN_OVERLOAD_LIMIT >> 4 << - TIPC_LOW_IMPORTANCE; - sysctl_tipc_rmem[1] = TIPC_CONN_OVERLOAD_LIMIT >> 4 << - TIPC_CRITICAL_IMPORTANCE; - sysctl_tipc_rmem[2] = TIPC_CONN_OVERLOAD_LIMIT; - - res = tipc_core_start(); - if (res) - pr_err("Unable to start in single node mode\n"); - else - pr_info("Started in single node mode\n"); - return res; -} - static void __exit tipc_exit(void) { - tipc_core_stop(); + tipc_bearer_cleanup(); + tipc_netlink_stop(); + tipc_socket_stop(); + tipc_unregister_sysctl(); + unregister_pernet_subsys(&tipc_net_ops); + pr_info("Deactivated\n"); } diff --git a/net/tipc/core.h b/net/tipc/core.h index 84602137ce20..817b2e9d4227 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -37,8 +37,6 @@ #ifndef _TIPC_CORE_H #define _TIPC_CORE_H -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include <linux/tipc.h> #include <linux/tipc_config.h> #include <linux/tipc_netlink.h> @@ -59,47 +57,56 @@ #include <linux/vmalloc.h> #include <linux/rtnetlink.h> #include <linux/etherdevice.h> +#include <net/netns/generic.h> +#include <linux/rhashtable.h> -#define TIPC_MOD_VER "2.0.0" - -#define ULTRA_STRING_MAX_LEN 32768 -#define TIPC_MAX_SUBSCRIPTIONS 65535 -#define TIPC_MAX_PUBLICATIONS 65535 +#include "node.h" +#include "bearer.h" +#include "bcast.h" +#include "netlink.h" +#include "link.h" +#include "node.h" +#include "msg.h" -struct tipc_msg; /* msg.h */ +#define TIPC_MOD_VER "2.0.0" int tipc_snprintf(char *buf, int len, const char *fmt, ...); -/* - * TIPC-specific error codes - */ -#define ELINKCONG EAGAIN /* link congestion <=> resource unavailable */ - -/* - * Global configuration variables - */ -extern u32 tipc_own_addr __read_mostly; -extern int tipc_max_ports __read_mostly; extern int tipc_net_id __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; extern int sysctl_tipc_named_timeout __read_mostly; -/* - * Other global variables - */ -extern int tipc_random __read_mostly; +struct tipc_net { + u32 own_addr; + int net_id; + int random; -/* - * Routines available to privileged subsystems - */ -int tipc_netlink_start(void); -void tipc_netlink_stop(void); -int tipc_socket_init(void); -void tipc_socket_stop(void); -int tipc_sock_create_local(int type, struct socket **res); -void tipc_sock_release_local(struct socket *sock); -int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, - int flags); + /* Node table and node list */ + spinlock_t node_list_lock; + struct hlist_head node_htable[NODE_HTABLE_SIZE]; + struct list_head node_list; + u32 num_nodes; + u32 num_links; + + /* Bearer list */ + struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1]; + + /* Broadcast link */ + struct tipc_bcbearer *bcbearer; + struct tipc_bclink *bclink; + struct tipc_link *bcl; + + /* Socket hash table */ + struct rhashtable sk_rht; + + /* Name table */ + spinlock_t nametbl_lock; + struct name_table *nametbl; + + /* Topology subscription server */ + struct tipc_server *topsrv; + atomic_t subscription_count; +}; #ifdef CONFIG_SYSCTL int tipc_register_sysctl(void); @@ -109,101 +116,4 @@ void tipc_unregister_sysctl(void); #define tipc_unregister_sysctl() #endif -/* - * TIPC timer code - */ -typedef void (*Handler) (unsigned long); - -/** - * k_init_timer - initialize a timer - * @timer: pointer to timer structure - * @routine: pointer to routine to invoke when timer expires - * @argument: value to pass to routine when timer expires - * - * Timer must be initialized before use (and terminated when no longer needed). - */ -static inline void k_init_timer(struct timer_list *timer, Handler routine, - unsigned long argument) -{ - setup_timer(timer, routine, argument); -} - -/** - * k_start_timer - start a timer - * @timer: pointer to timer structure - * @msec: time to delay (in ms) - * - * Schedules a previously initialized timer for later execution. - * If timer is already running, the new timeout overrides the previous request. - * - * To ensure the timer doesn't expire before the specified delay elapses, - * the amount of delay is rounded up when converting to the jiffies - * then an additional jiffy is added to account for the fact that - * the starting time may be in the middle of the current jiffy. - */ -static inline void k_start_timer(struct timer_list *timer, unsigned long msec) -{ - mod_timer(timer, jiffies + msecs_to_jiffies(msec) + 1); -} - -/** - * k_cancel_timer - cancel a timer - * @timer: pointer to timer structure - * - * Cancels a previously initialized timer. - * Can be called safely even if the timer is already inactive. - * - * WARNING: Must not be called when holding locks required by the timer's - * timeout routine, otherwise deadlock can occur on SMP systems! - */ -static inline void k_cancel_timer(struct timer_list *timer) -{ - del_timer_sync(timer); -} - -/** - * k_term_timer - terminate a timer - * @timer: pointer to timer structure - * - * Prevents further use of a previously initialized timer. - * - * WARNING: Caller must ensure timer isn't currently running. - * - * (Do not "enhance" this routine to automatically cancel an active timer, - * otherwise deadlock can arise when a timeout routine calls k_term_timer.) - */ -static inline void k_term_timer(struct timer_list *timer) -{ -} - -/* - * TIPC message buffer code - * - * TIPC message buffer headroom reserves space for the worst-case - * link-level device header (in case the message is sent off-node). - * - * Note: Headroom should be a multiple of 4 to ensure the TIPC header fields - * are word aligned for quicker access - */ -#define BUF_HEADROOM LL_MAX_HEADER - -struct tipc_skb_cb { - void *handle; - struct sk_buff *tail; - bool deferred; - bool wakeup_pending; - bool bundling; - u16 chain_sz; - u16 chain_imp; -}; - -#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0])) - -static inline struct tipc_msg *buf_msg(struct sk_buff *skb) -{ - return (struct tipc_msg *)skb->data; -} - -struct sk_buff *tipc_buf_acquire(u32 size); - #endif diff --git a/net/tipc/discover.c b/net/tipc/discover.c index aa722a42ef8b..5b40cb89ff0a 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -38,15 +38,20 @@ #include "link.h" #include "discover.h" -#define TIPC_LINK_REQ_INIT 125 /* min delay during bearer start up */ -#define TIPC_LINK_REQ_FAST 1000 /* max delay if bearer has no links */ -#define TIPC_LINK_REQ_SLOW 60000 /* max delay if bearer has links */ -#define TIPC_LINK_REQ_INACTIVE 0xffffffff /* indicates no timer in use */ +/* min delay during bearer start up */ +#define TIPC_LINK_REQ_INIT msecs_to_jiffies(125) +/* max delay if bearer has no links */ +#define TIPC_LINK_REQ_FAST msecs_to_jiffies(1000) +/* max delay if bearer has links */ +#define TIPC_LINK_REQ_SLOW msecs_to_jiffies(60000) +/* indicates no timer in use */ +#define TIPC_LINK_REQ_INACTIVE 0xffffffff /** * struct tipc_link_req - information about an ongoing link setup request * @bearer_id: identity of bearer issuing requests + * @net: network namespace instance * @dest: destination address for request messages * @domain: network domain to which links can be established * @num_nodes: number of nodes currently discovered (i.e. with an active link) @@ -58,31 +63,34 @@ struct tipc_link_req { u32 bearer_id; struct tipc_media_addr dest; + struct net *net; u32 domain; int num_nodes; spinlock_t lock; struct sk_buff *buf; struct timer_list timer; - unsigned int timer_intv; + unsigned long timer_intv; }; /** * tipc_disc_init_msg - initialize a link setup message + * @net: the applicable net namespace * @type: message type (request or response) * @b_ptr: ptr to bearer issuing message */ -static void tipc_disc_init_msg(struct sk_buff *buf, u32 type, +static void tipc_disc_init_msg(struct net *net, struct sk_buff *buf, u32 type, struct tipc_bearer *b_ptr) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_msg *msg; u32 dest_domain = b_ptr->domain; msg = buf_msg(buf); - tipc_msg_init(msg, LINK_CONFIG, type, INT_H_SIZE, dest_domain); + tipc_msg_init(net, msg, LINK_CONFIG, type, INT_H_SIZE, dest_domain); msg_set_non_seq(msg, 1); - msg_set_node_sig(msg, tipc_random); + msg_set_node_sig(msg, tn->random); msg_set_dest_domain(msg, dest_domain); - msg_set_bc_netid(msg, tipc_net_id); + msg_set_bc_netid(msg, tn->net_id); b_ptr->media->addr2msg(msg_media_addr(msg), &b_ptr->addr); } @@ -107,11 +115,14 @@ static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr, /** * tipc_disc_rcv - handle incoming discovery message (request or response) + * @net: the applicable net namespace * @buf: buffer containing message * @bearer: bearer that message arrived on */ -void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *bearer) +void tipc_disc_rcv(struct net *net, struct sk_buff *buf, + struct tipc_bearer *bearer) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *node; struct tipc_link *link; struct tipc_media_addr maddr; @@ -133,7 +144,7 @@ void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *bearer) kfree_skb(buf); /* Ensure message from node is valid and communication is permitted */ - if (net_id != tipc_net_id) + if (net_id != tn->net_id) return; if (maddr.broadcast) return; @@ -142,20 +153,20 @@ void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *bearer) if (!tipc_addr_node_valid(onode)) return; - if (in_own_node(onode)) { + if (in_own_node(net, onode)) { if (memcmp(&maddr, &bearer->addr, sizeof(maddr))) - disc_dupl_alert(bearer, tipc_own_addr, &maddr); + disc_dupl_alert(bearer, tn->own_addr, &maddr); return; } - if (!tipc_in_scope(ddom, tipc_own_addr)) + if (!tipc_in_scope(ddom, tn->own_addr)) return; if (!tipc_in_scope(bearer->domain, onode)) return; /* Locate, or if necessary, create, node: */ - node = tipc_node_find(onode); + node = tipc_node_find(net, onode); if (!node) - node = tipc_node_create(onode); + node = tipc_node_create(net, onode); if (!node) return; @@ -244,8 +255,8 @@ void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *bearer) if (respond && (mtyp == DSC_REQ_MSG)) { rbuf = tipc_buf_acquire(INT_H_SIZE); if (rbuf) { - tipc_disc_init_msg(rbuf, DSC_RESP_MSG, bearer); - tipc_bearer_send(bearer->identity, rbuf, &maddr); + tipc_disc_init_msg(net, rbuf, DSC_RESP_MSG, bearer); + tipc_bearer_send(net, bearer->identity, rbuf, &maddr); kfree_skb(rbuf); } } @@ -265,7 +276,7 @@ static void disc_update(struct tipc_link_req *req) if ((req->timer_intv == TIPC_LINK_REQ_INACTIVE) || (req->timer_intv > TIPC_LINK_REQ_FAST)) { req->timer_intv = TIPC_LINK_REQ_INIT; - k_start_timer(&req->timer, req->timer_intv); + mod_timer(&req->timer, jiffies + req->timer_intv); } } } @@ -295,12 +306,13 @@ void tipc_disc_remove_dest(struct tipc_link_req *req) /** * disc_timeout - send a periodic link setup request - * @req: ptr to link request structure + * @data: ptr to link request structure * * Called whenever a link setup request timer associated with a bearer expires. */ -static void disc_timeout(struct tipc_link_req *req) +static void disc_timeout(unsigned long data) { + struct tipc_link_req *req = (struct tipc_link_req *)data; int max_delay; spin_lock_bh(&req->lock); @@ -318,7 +330,7 @@ static void disc_timeout(struct tipc_link_req *req) * hold at fast polling rate if don't have any associated nodes, * otherwise hold at slow polling rate */ - tipc_bearer_send(req->bearer_id, req->buf, &req->dest); + tipc_bearer_send(req->net, req->bearer_id, req->buf, &req->dest); req->timer_intv *= 2; @@ -329,20 +341,22 @@ static void disc_timeout(struct tipc_link_req *req) if (req->timer_intv > max_delay) req->timer_intv = max_delay; - k_start_timer(&req->timer, req->timer_intv); + mod_timer(&req->timer, jiffies + req->timer_intv); exit: spin_unlock_bh(&req->lock); } /** * tipc_disc_create - create object to send periodic link setup requests + * @net: the applicable net namespace * @b_ptr: ptr to bearer issuing requests * @dest: destination address for request messages * @dest_domain: network domain to which links can be established * * Returns 0 if successful, otherwise -errno. */ -int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest) +int tipc_disc_create(struct net *net, struct tipc_bearer *b_ptr, + struct tipc_media_addr *dest) { struct tipc_link_req *req; @@ -356,17 +370,18 @@ int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest) return -ENOMEM; } - tipc_disc_init_msg(req->buf, DSC_REQ_MSG, b_ptr); + tipc_disc_init_msg(net, req->buf, DSC_REQ_MSG, b_ptr); memcpy(&req->dest, dest, sizeof(*dest)); + req->net = net; req->bearer_id = b_ptr->identity; req->domain = b_ptr->domain; req->num_nodes = 0; req->timer_intv = TIPC_LINK_REQ_INIT; spin_lock_init(&req->lock); - k_init_timer(&req->timer, (Handler)disc_timeout, (unsigned long)req); - k_start_timer(&req->timer, req->timer_intv); + setup_timer(&req->timer, disc_timeout, (unsigned long)req); + mod_timer(&req->timer, jiffies + req->timer_intv); b_ptr->link_req = req; - tipc_bearer_send(req->bearer_id, req->buf, &req->dest); + tipc_bearer_send(net, req->bearer_id, req->buf, &req->dest); return 0; } @@ -376,28 +391,29 @@ int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest) */ void tipc_disc_delete(struct tipc_link_req *req) { - k_cancel_timer(&req->timer); - k_term_timer(&req->timer); + del_timer_sync(&req->timer); kfree_skb(req->buf); kfree(req); } /** * tipc_disc_reset - reset object to send periodic link setup requests + * @net: the applicable net namespace * @b_ptr: ptr to bearer issuing requests * @dest_domain: network domain to which links can be established */ -void tipc_disc_reset(struct tipc_bearer *b_ptr) +void tipc_disc_reset(struct net *net, struct tipc_bearer *b_ptr) { struct tipc_link_req *req = b_ptr->link_req; spin_lock_bh(&req->lock); - tipc_disc_init_msg(req->buf, DSC_REQ_MSG, b_ptr); + tipc_disc_init_msg(net, req->buf, DSC_REQ_MSG, b_ptr); + req->net = net; req->bearer_id = b_ptr->identity; req->domain = b_ptr->domain; req->num_nodes = 0; req->timer_intv = TIPC_LINK_REQ_INIT; - k_start_timer(&req->timer, req->timer_intv); - tipc_bearer_send(req->bearer_id, req->buf, &req->dest); + mod_timer(&req->timer, jiffies + req->timer_intv); + tipc_bearer_send(net, req->bearer_id, req->buf, &req->dest); spin_unlock_bh(&req->lock); } diff --git a/net/tipc/discover.h b/net/tipc/discover.h index 515b57392f4d..c9b12770c5ed 100644 --- a/net/tipc/discover.h +++ b/net/tipc/discover.h @@ -39,11 +39,13 @@ struct tipc_link_req; -int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest); +int tipc_disc_create(struct net *net, struct tipc_bearer *b_ptr, + struct tipc_media_addr *dest); void tipc_disc_delete(struct tipc_link_req *req); -void tipc_disc_reset(struct tipc_bearer *b_ptr); +void tipc_disc_reset(struct net *net, struct tipc_bearer *b_ptr); void tipc_disc_add_dest(struct tipc_link_req *req); void tipc_disc_remove_dest(struct tipc_link_req *req); -void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *b_ptr); +void tipc_disc_rcv(struct net *net, struct sk_buff *buf, + struct tipc_bearer *b_ptr); #endif diff --git a/net/tipc/link.c b/net/tipc/link.c index 082c3b5b32a1..193bc1560677 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -101,19 +101,23 @@ static const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { */ #define START_CHANGEOVER 100000u -static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, +static void link_handle_out_of_seq_msg(struct net *net, + struct tipc_link *l_ptr, struct sk_buff *buf); -static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf); -static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr, +static void tipc_link_proto_rcv(struct net *net, struct tipc_link *l_ptr, + struct sk_buff *buf); +static int tipc_link_tunnel_rcv(struct net *net, struct tipc_node *n_ptr, struct sk_buff **buf); -static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance); +static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol); static void link_state_event(struct tipc_link *l_ptr, u32 event); static void link_reset_statistics(struct tipc_link *l_ptr); static void link_print(struct tipc_link *l_ptr, const char *str); static void tipc_link_sync_xmit(struct tipc_link *l); static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf); -static int tipc_link_input(struct tipc_link *l, struct sk_buff *buf); -static int tipc_link_prepare_input(struct tipc_link *l, struct sk_buff **buf); +static int tipc_link_input(struct net *net, struct tipc_link *l, + struct sk_buff *buf); +static int tipc_link_prepare_input(struct net *net, struct tipc_link *l, + struct sk_buff **buf); /* * Simple link routines @@ -125,11 +129,13 @@ static unsigned int align(unsigned int i) static void link_init_max_pkt(struct tipc_link *l_ptr) { + struct tipc_node *node = l_ptr->owner; + struct tipc_net *tn = net_generic(node->net, tipc_net_id); struct tipc_bearer *b_ptr; u32 max_pkt; rcu_read_lock(); - b_ptr = rcu_dereference_rtnl(bearer_list[l_ptr->bearer_id]); + b_ptr = rcu_dereference_rtnl(tn->bearer_list[l_ptr->bearer_id]); if (!b_ptr) { rcu_read_unlock(); return; @@ -169,8 +175,9 @@ int tipc_link_is_active(struct tipc_link *l_ptr) * link_timeout - handle expiration of link timer * @l_ptr: pointer to link */ -static void link_timeout(struct tipc_link *l_ptr) +static void link_timeout(unsigned long data) { + struct tipc_link *l_ptr = (struct tipc_link *)data; struct sk_buff *skb; tipc_node_lock(l_ptr->owner); @@ -217,9 +224,9 @@ static void link_timeout(struct tipc_link *l_ptr) tipc_node_unlock(l_ptr->owner); } -static void link_set_timer(struct tipc_link *l_ptr, u32 time) +static void link_set_timer(struct tipc_link *link, unsigned long time) { - k_start_timer(&l_ptr->timer, time); + mod_timer(&link->timer, jiffies + time); } /** @@ -234,6 +241,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, struct tipc_bearer *b_ptr, const struct tipc_media_addr *media_addr) { + struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); struct tipc_link *l_ptr; struct tipc_msg *msg; char *if_name; @@ -263,8 +271,8 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, l_ptr->addr = peer; if_name = strchr(b_ptr->name, ':') + 1; sprintf(l_ptr->name, "%u.%u.%u:%s-%u.%u.%u:unknown", - tipc_zone(tipc_own_addr), tipc_cluster(tipc_own_addr), - tipc_node(tipc_own_addr), + tipc_zone(tn->own_addr), tipc_cluster(tn->own_addr), + tipc_node(tn->own_addr), if_name, tipc_zone(peer), tipc_cluster(peer), tipc_node(peer)); /* note: peer i/f name is updated by reset/activate message */ @@ -278,9 +286,10 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, l_ptr->pmsg = (struct tipc_msg *)&l_ptr->proto_msg; msg = l_ptr->pmsg; - tipc_msg_init(msg, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, l_ptr->addr); + tipc_msg_init(n_ptr->net, msg, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, + l_ptr->addr); msg_set_size(msg, sizeof(l_ptr->proto_msg)); - msg_set_session(msg, (tipc_random & 0xffff)); + msg_set_session(msg, (tn->random & 0xffff)); msg_set_bearer_id(msg, b_ptr->identity); strcpy((char *)msg_data(msg), if_name); @@ -299,21 +308,22 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, tipc_node_attach_link(n_ptr, l_ptr); - k_init_timer(&l_ptr->timer, (Handler)link_timeout, - (unsigned long)l_ptr); + setup_timer(&l_ptr->timer, link_timeout, (unsigned long)l_ptr); link_state_event(l_ptr, STARTING_EVT); return l_ptr; } -void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down) +void tipc_link_delete_list(struct net *net, unsigned int bearer_id, + bool shutting_down) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_link *l_ptr; struct tipc_node *n_ptr; rcu_read_lock(); - list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { + list_for_each_entry_rcu(n_ptr, &tn->node_list, list) { tipc_node_lock(n_ptr); l_ptr = n_ptr->links[bearer_id]; if (l_ptr) { @@ -350,10 +360,12 @@ void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down) static bool link_schedule_user(struct tipc_link *link, u32 oport, uint chain_sz, uint imp) { + struct net *net = link->owner->net; + struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff *buf; - buf = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, tipc_own_addr, - tipc_own_addr, oport, 0, 0); + buf = tipc_msg_create(net, SOCK_WAKEUP, 0, INT_H_SIZE, 0, tn->own_addr, + tn->own_addr, oport, 0, 0); if (!buf) return false; TIPC_SKB_CB(buf)->chain_sz = chain_sz; @@ -425,7 +437,7 @@ void tipc_link_reset(struct tipc_link *l_ptr) return; tipc_node_link_down(l_ptr->owner, l_ptr); - tipc_bearer_remove_dest(l_ptr->bearer_id, l_ptr->addr); + tipc_bearer_remove_dest(owner->net, l_ptr->bearer_id, l_ptr->addr); if (was_active_link && tipc_node_active_links(l_ptr->owner)) { l_ptr->reset_checkpoint = checkpoint; @@ -448,13 +460,14 @@ void tipc_link_reset(struct tipc_link *l_ptr) link_reset_statistics(l_ptr); } -void tipc_link_reset_list(unsigned int bearer_id) +void tipc_link_reset_list(struct net *net, unsigned int bearer_id) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_link *l_ptr; struct tipc_node *n_ptr; rcu_read_lock(); - list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { + list_for_each_entry_rcu(n_ptr, &tn->node_list, list) { tipc_node_lock(n_ptr); l_ptr = n_ptr->links[bearer_id]; if (l_ptr) @@ -464,11 +477,14 @@ void tipc_link_reset_list(unsigned int bearer_id) rcu_read_unlock(); } -static void link_activate(struct tipc_link *l_ptr) +static void link_activate(struct tipc_link *link) { - l_ptr->next_in_no = l_ptr->stats.recv_info = 1; - tipc_node_link_up(l_ptr->owner, l_ptr); - tipc_bearer_add_dest(l_ptr->bearer_id, l_ptr->addr); + struct tipc_node *node = link->owner; + + link->next_in_no = 1; + link->stats.recv_info = 1; + tipc_node_link_up(node, link); + tipc_bearer_add_dest(node->net, link->bearer_id, link->addr); } /** @@ -479,7 +495,7 @@ static void link_activate(struct tipc_link *l_ptr) static void link_state_event(struct tipc_link *l_ptr, unsigned int event) { struct tipc_link *other; - u32 cont_intv = l_ptr->continuity_interval; + unsigned long cont_intv = l_ptr->cont_intv; if (l_ptr->flags & LINK_STOPPED) return; @@ -700,7 +716,8 @@ drop: * Only the socket functions tipc_send_stream() and tipc_send_packet() need * to act on the return value, since they may need to do more send attempts. */ -int __tipc_link_xmit(struct tipc_link *link, struct sk_buff_head *list) +int __tipc_link_xmit(struct net *net, struct tipc_link *link, + struct sk_buff_head *list) { struct tipc_msg *msg = buf_msg(skb_peek(list)); uint psz = msg_size(msg); @@ -733,13 +750,14 @@ int __tipc_link_xmit(struct tipc_link *link, struct sk_buff_head *list) if (skb_queue_len(outqueue) < sndlim) { __skb_queue_tail(outqueue, skb); - tipc_bearer_send(link->bearer_id, skb, addr); + tipc_bearer_send(net, link->bearer_id, + skb, addr); link->next_out = NULL; link->unacked_window = 0; } else if (tipc_msg_bundle(outqueue, skb, mtu)) { link->stats.sent_bundled++; continue; - } else if (tipc_msg_make_bundle(outqueue, skb, mtu, + } else if (tipc_msg_make_bundle(net, outqueue, skb, mtu, link->addr)) { link->stats.sent_bundled++; link->stats.sent_bundles++; @@ -767,19 +785,21 @@ static int __tipc_link_xmit_skb(struct tipc_link *link, struct sk_buff *skb) struct sk_buff_head head; skb2list(skb, &head); - return __tipc_link_xmit(link, &head); + return __tipc_link_xmit(link->owner->net, link, &head); } -int tipc_link_xmit_skb(struct sk_buff *skb, u32 dnode, u32 selector) +int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, + u32 selector) { struct sk_buff_head head; skb2list(skb, &head); - return tipc_link_xmit(&head, dnode, selector); + return tipc_link_xmit(net, &head, dnode, selector); } /** * tipc_link_xmit() is the general link level function for message sending + * @net: the applicable net namespace * @list: chain of buffers containing message * @dsz: amount of user data to be sent * @dnode: address of destination node @@ -787,30 +807,31 @@ int tipc_link_xmit_skb(struct sk_buff *skb, u32 dnode, u32 selector) * Consumes the buffer chain, except when returning -ELINKCONG * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE */ -int tipc_link_xmit(struct sk_buff_head *list, u32 dnode, u32 selector) +int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, + u32 selector) { struct tipc_link *link = NULL; struct tipc_node *node; int rc = -EHOSTUNREACH; - node = tipc_node_find(dnode); + node = tipc_node_find(net, dnode); if (node) { tipc_node_lock(node); link = node->active_links[selector & 1]; if (link) - rc = __tipc_link_xmit(link, list); + rc = __tipc_link_xmit(net, link, list); tipc_node_unlock(node); } if (link) return rc; - if (likely(in_own_node(dnode))) { + if (likely(in_own_node(net, dnode))) { /* As a node local message chain never contains more than one * buffer, we just need to dequeue one SKB buffer from the * head list. */ - return tipc_sk_rcv(__skb_dequeue(list)); + return tipc_sk_rcv(net, __skb_dequeue(list)); } __skb_queue_purge(list); @@ -835,7 +856,8 @@ static void tipc_link_sync_xmit(struct tipc_link *link) return; msg = buf_msg(skb); - tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, link->addr); + tipc_msg_init(link->owner->net, msg, BCAST_PROTOCOL, STATE_MSG, + INT_H_SIZE, link->addr); msg_set_last_bcast(msg, link->owner->bclink.acked); __tipc_link_xmit_skb(link, skb); } @@ -890,7 +912,8 @@ void tipc_link_push_packets(struct tipc_link *l_ptr) msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); if (msg_user(msg) == MSG_BUNDLER) TIPC_SKB_CB(skb)->bundling = false; - tipc_bearer_send(l_ptr->bearer_id, skb, + tipc_bearer_send(l_ptr->owner->net, + l_ptr->bearer_id, skb, &l_ptr->media_addr); l_ptr->next_out = tipc_skb_queue_next(outqueue, skb); } else { @@ -923,6 +946,7 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); + struct net *net = l_ptr->owner->net; pr_warn("Retransmission failure on link <%s>\n", l_ptr->name); @@ -940,7 +964,7 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, pr_cont("Outstanding acks: %lu\n", (unsigned long) TIPC_SKB_CB(buf)->handle); - n_ptr = tipc_bclink_retransmit_to(); + n_ptr = tipc_bclink_retransmit_to(net); tipc_node_lock(n_ptr); tipc_addr_string_fill(addr_string, n_ptr->addr); @@ -955,7 +979,7 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, tipc_node_unlock(n_ptr); - tipc_bclink_set_flags(TIPC_BCLINK_RESET); + tipc_bclink_set_flags(net, TIPC_BCLINK_RESET); l_ptr->stale_count = 0; } } @@ -987,7 +1011,8 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *skb, msg = buf_msg(skb); msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); - tipc_bearer_send(l_ptr->bearer_id, skb, &l_ptr->media_addr); + tipc_bearer_send(l_ptr->owner->net, l_ptr->bearer_id, skb, + &l_ptr->media_addr); retransmits--; l_ptr->stats.retransmitted++; } @@ -1063,14 +1088,16 @@ static int link_recv_buf_validate(struct sk_buff *buf) /** * tipc_rcv - process TIPC packets/messages arriving from off-node + * @net: the applicable net namespace * @skb: TIPC packet * @b_ptr: pointer to bearer message arrived on * * Invoked with no locks held. Bearer pointer must point to a valid bearer * structure (i.e. cannot be NULL), but bearer can be inactive. */ -void tipc_rcv(struct sk_buff *skb, struct tipc_bearer *b_ptr) +void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff_head head; struct tipc_node *n_ptr; struct tipc_link *l_ptr; @@ -1096,19 +1123,19 @@ void tipc_rcv(struct sk_buff *skb, struct tipc_bearer *b_ptr) if (unlikely(msg_non_seq(msg))) { if (msg_user(msg) == LINK_CONFIG) - tipc_disc_rcv(skb, b_ptr); + tipc_disc_rcv(net, skb, b_ptr); else - tipc_bclink_rcv(skb); + tipc_bclink_rcv(net, skb); continue; } /* Discard unicast link messages destined for another node */ if (unlikely(!msg_short(msg) && - (msg_destnode(msg) != tipc_own_addr))) + (msg_destnode(msg) != tn->own_addr))) goto discard; /* Locate neighboring node that sent message */ - n_ptr = tipc_node_find(msg_prevnode(msg)); + n_ptr = tipc_node_find(net, msg_prevnode(msg)); if (unlikely(!n_ptr)) goto discard; tipc_node_lock(n_ptr); @@ -1159,7 +1186,7 @@ void tipc_rcv(struct sk_buff *skb, struct tipc_bearer *b_ptr) /* Process the incoming packet */ if (unlikely(!link_working_working(l_ptr))) { if (msg_user(msg) == LINK_PROTOCOL) { - tipc_link_proto_rcv(l_ptr, skb); + tipc_link_proto_rcv(net, l_ptr, skb); link_retrieve_defq(l_ptr, &head); tipc_node_unlock(n_ptr); continue; @@ -1179,7 +1206,7 @@ void tipc_rcv(struct sk_buff *skb, struct tipc_bearer *b_ptr) /* Link is now in state WORKING_WORKING */ if (unlikely(seq_no != mod(l_ptr->next_in_no))) { - link_handle_out_of_seq_msg(l_ptr, skb); + link_handle_out_of_seq_msg(net, l_ptr, skb); link_retrieve_defq(l_ptr, &head); tipc_node_unlock(n_ptr); continue; @@ -1193,13 +1220,13 @@ void tipc_rcv(struct sk_buff *skb, struct tipc_bearer *b_ptr) tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); } - if (tipc_link_prepare_input(l_ptr, &skb)) { + if (tipc_link_prepare_input(net, l_ptr, &skb)) { tipc_node_unlock(n_ptr); continue; } tipc_node_unlock(n_ptr); - if (tipc_link_input(l_ptr, skb) != 0) + if (tipc_link_input(net, l_ptr, skb) != 0) goto discard; continue; unlock_discard: @@ -1216,7 +1243,8 @@ discard: * * Node lock must be held */ -static int tipc_link_prepare_input(struct tipc_link *l, struct sk_buff **buf) +static int tipc_link_prepare_input(struct net *net, struct tipc_link *l, + struct sk_buff **buf) { struct tipc_node *n; struct tipc_msg *msg; @@ -1226,7 +1254,7 @@ static int tipc_link_prepare_input(struct tipc_link *l, struct sk_buff **buf) msg = buf_msg(*buf); switch (msg_user(msg)) { case CHANGEOVER_PROTOCOL: - if (tipc_link_tunnel_rcv(n, buf)) + if (tipc_link_tunnel_rcv(net, n, buf)) res = 0; break; case MSG_FRAGMENTER: @@ -1258,7 +1286,8 @@ static int tipc_link_prepare_input(struct tipc_link *l, struct sk_buff **buf) /** * tipc_link_input - Deliver message too higher layers */ -static int tipc_link_input(struct tipc_link *l, struct sk_buff *buf) +static int tipc_link_input(struct net *net, struct tipc_link *l, + struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); int res = 0; @@ -1269,13 +1298,13 @@ static int tipc_link_input(struct tipc_link *l, struct sk_buff *buf) case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: case CONN_MANAGER: - tipc_sk_rcv(buf); + tipc_sk_rcv(net, buf); break; case NAME_DISTRIBUTOR: - tipc_named_rcv(buf); + tipc_named_rcv(net, buf); break; case MSG_BUNDLER: - tipc_link_bundle_rcv(buf); + tipc_link_bundle_rcv(net, buf); break; default: res = -EINVAL; @@ -1325,13 +1354,14 @@ u32 tipc_link_defer_pkt(struct sk_buff_head *list, struct sk_buff *skb) /* * link_handle_out_of_seq_msg - handle arrival of out-of-sequence packet */ -static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, +static void link_handle_out_of_seq_msg(struct net *net, + struct tipc_link *l_ptr, struct sk_buff *buf) { u32 seq_no = buf_seqno(buf); if (likely(msg_user(buf_msg(buf)) == LINK_PROTOCOL)) { - tipc_link_proto_rcv(l_ptr, buf); + tipc_link_proto_rcv(net, l_ptr, buf); return; } @@ -1381,7 +1411,7 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, msg_set_type(msg, msg_typ); msg_set_net_plane(msg, l_ptr->net_plane); msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); - msg_set_last_bcast(msg, tipc_bclink_get_last_sent()); + msg_set_last_bcast(msg, tipc_bclink_get_last_sent(l_ptr->owner->net)); if (msg_typ == STATE_MSG) { u32 next_sent = mod(l_ptr->next_out_no); @@ -1445,7 +1475,8 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg)); buf->priority = TC_PRIO_CONTROL; - tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr); + tipc_bearer_send(l_ptr->owner->net, l_ptr->bearer_id, buf, + &l_ptr->media_addr); l_ptr->unacked_window = 0; kfree_skb(buf); } @@ -1455,8 +1486,10 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, * Note that network plane id propagates through the network, and may * change at any time. The node with lowest address rules */ -static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf) +static void tipc_link_proto_rcv(struct net *net, struct tipc_link *l_ptr, + struct sk_buff *buf) { + struct tipc_net *tn = net_generic(net, tipc_net_id); u32 rec_gap = 0; u32 max_pkt_info; u32 max_pkt_ack; @@ -1468,7 +1501,7 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf) goto exit; if (l_ptr->net_plane != msg_net_plane(msg)) - if (tipc_own_addr > msg_prevnode(msg)) + if (tn->own_addr > msg_prevnode(msg)) l_ptr->net_plane = msg_net_plane(msg); switch (msg_type(msg)) { @@ -1571,7 +1604,7 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf) /* Protocol message before retransmits, reduce loss risk */ if (l_ptr->owner->bclink.recv_permitted) - tipc_bclink_update_link_state(l_ptr->owner, + tipc_bclink_update_link_state(net, l_ptr->owner, msg_last_bcast(msg)); if (rec_gap || (msg_probe(msg))) { @@ -1636,8 +1669,8 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) if (!tunnel) return; - tipc_msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL, - ORIGINAL_MSG, INT_H_SIZE, l_ptr->addr); + tipc_msg_init(l_ptr->owner->net, &tunnel_hdr, CHANGEOVER_PROTOCOL, + ORIGINAL_MSG, INT_H_SIZE, l_ptr->addr); msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); msg_set_msgcnt(&tunnel_hdr, msgcount); @@ -1694,8 +1727,8 @@ void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct sk_buff *skb; struct tipc_msg tunnel_hdr; - tipc_msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL, - DUPLICATE_MSG, INT_H_SIZE, l_ptr->addr); + tipc_msg_init(l_ptr->owner->net, &tunnel_hdr, CHANGEOVER_PROTOCOL, + DUPLICATE_MSG, INT_H_SIZE, l_ptr->addr); msg_set_msgcnt(&tunnel_hdr, skb_queue_len(&l_ptr->outqueue)); msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); skb_queue_walk(&l_ptr->outqueue, skb) { @@ -1748,7 +1781,7 @@ static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos) /* tipc_link_dup_rcv(): Receive a tunnelled DUPLICATE_MSG packet. * Owner node is locked. */ -static void tipc_link_dup_rcv(struct tipc_link *l_ptr, +static void tipc_link_dup_rcv(struct net *net, struct tipc_link *l_ptr, struct sk_buff *t_buf) { struct sk_buff *buf; @@ -1763,7 +1796,7 @@ static void tipc_link_dup_rcv(struct tipc_link *l_ptr, } /* Add buffer to deferred queue, if applicable: */ - link_handle_out_of_seq_msg(l_ptr, buf); + link_handle_out_of_seq_msg(net, l_ptr, buf); } /* tipc_link_failover_rcv(): Receive a tunnelled ORIGINAL_MSG packet @@ -1817,7 +1850,7 @@ exit: * returned to the active link for delivery upwards. * Owner node is locked. */ -static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr, +static int tipc_link_tunnel_rcv(struct net *net, struct tipc_node *n_ptr, struct sk_buff **buf) { struct sk_buff *t_buf = *buf; @@ -1835,7 +1868,7 @@ static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr, goto exit; if (msg_type(t_msg) == DUPLICATE_MSG) - tipc_link_dup_rcv(l_ptr, t_buf); + tipc_link_dup_rcv(net, l_ptr, t_buf); else if (msg_type(t_msg) == ORIGINAL_MSG) *buf = tipc_link_failover_rcv(l_ptr, t_buf); else @@ -1848,7 +1881,7 @@ exit: /* * Bundler functionality: */ -void tipc_link_bundle_rcv(struct sk_buff *buf) +void tipc_link_bundle_rcv(struct net *net, struct sk_buff *buf) { u32 msgcount = msg_msgcnt(buf_msg(buf)); u32 pos = INT_H_SIZE; @@ -1865,13 +1898,13 @@ void tipc_link_bundle_rcv(struct sk_buff *buf) pos += align(msg_size(omsg)); if (msg_isdata(omsg)) { if (unlikely(msg_type(omsg) == TIPC_MCAST_MSG)) - tipc_sk_mcast_rcv(obuf); + tipc_sk_mcast_rcv(net, obuf); else - tipc_sk_rcv(obuf); + tipc_sk_rcv(net, obuf); } else if (msg_user(omsg) == CONN_MANAGER) { - tipc_sk_rcv(obuf); + tipc_sk_rcv(net, obuf); } else if (msg_user(omsg) == NAME_DISTRIBUTOR) { - tipc_named_rcv(obuf); + tipc_named_rcv(net, obuf); } else { pr_warn("Illegal bundled msg: %u\n", msg_user(omsg)); kfree_skb(obuf); @@ -1880,15 +1913,16 @@ void tipc_link_bundle_rcv(struct sk_buff *buf) kfree_skb(buf); } -static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance) +static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol) { - if ((tolerance < TIPC_MIN_LINK_TOL) || (tolerance > TIPC_MAX_LINK_TOL)) + unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4; + + if ((tol < TIPC_MIN_LINK_TOL) || (tol > TIPC_MAX_LINK_TOL)) return; - l_ptr->tolerance = tolerance; - l_ptr->continuity_interval = - ((tolerance / 4) > 500) ? 500 : tolerance / 4; - l_ptr->abort_limit = tolerance / (l_ptr->continuity_interval / 4); + l_ptr->tolerance = tol; + l_ptr->cont_intv = msecs_to_jiffies(intv); + l_ptr->abort_limit = tol / (jiffies_to_msecs(l_ptr->cont_intv) / 4); } void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window) @@ -1911,14 +1945,17 @@ void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window) } /* tipc_link_find_owner - locate owner node of link by link's name + * @net: the applicable net namespace * @name: pointer to link name string * @bearer_id: pointer to index in 'node->links' array where the link was found. * * Returns pointer to node owning the link, or 0 if no matching link is found. */ -static struct tipc_node *tipc_link_find_owner(const char *link_name, +static struct tipc_node *tipc_link_find_owner(struct net *net, + const char *link_name, unsigned int *bearer_id) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_link *l_ptr; struct tipc_node *n_ptr; struct tipc_node *found_node = NULL; @@ -1926,7 +1963,7 @@ static struct tipc_node *tipc_link_find_owner(const char *link_name, *bearer_id = 0; rcu_read_lock(); - list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { + list_for_each_entry_rcu(n_ptr, &tn->node_list, list) { tipc_node_lock(n_ptr); for (i = 0; i < MAX_BEARERS; i++) { l_ptr = n_ptr->links[i]; @@ -1970,6 +2007,7 @@ static int link_value_is_valid(u16 cmd, u32 new_value) /** * link_cmd_set_value - change priority/tolerance/window for link/bearer/media + * @net: the applicable net namespace * @name: ptr to link, bearer, or media name * @new_value: new value of link, bearer, or media setting * @cmd: which link, bearer, or media attribute to set (TIPC_CMD_SET_LINK_*) @@ -1978,7 +2016,8 @@ static int link_value_is_valid(u16 cmd, u32 new_value) * * Returns 0 if value updated and negative value on error. */ -static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd) +static int link_cmd_set_value(struct net *net, const char *name, u32 new_value, + u16 cmd) { struct tipc_node *node; struct tipc_link *l_ptr; @@ -1987,7 +2026,7 @@ static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd) int bearer_id; int res = 0; - node = tipc_link_find_owner(name, &bearer_id); + node = tipc_link_find_owner(net, name, &bearer_id); if (node) { tipc_node_lock(node); l_ptr = node->links[bearer_id]; @@ -2016,7 +2055,7 @@ static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd) return res; } - b_ptr = tipc_bearer_find(name); + b_ptr = tipc_bearer_find(net, name); if (b_ptr) { switch (cmd) { case TIPC_CMD_SET_LINK_TOL: @@ -2055,8 +2094,8 @@ static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd) return res; } -struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space, - u16 cmd) +struct sk_buff *tipc_link_cmd_config(struct net *net, const void *req_tlv_area, + int req_tlv_space, u16 cmd) { struct tipc_link_config *args; u32 new_value; @@ -2074,13 +2113,13 @@ struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space if (!strcmp(args->name, tipc_bclink_name)) { if ((cmd == TIPC_CMD_SET_LINK_WINDOW) && - (tipc_bclink_set_queue_limits(new_value) == 0)) + (tipc_bclink_set_queue_limits(net, new_value) == 0)) return tipc_cfg_reply_none(); return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (cannot change setting on broadcast link)"); } - res = link_cmd_set_value(args->name, new_value, cmd); + res = link_cmd_set_value(net, args->name, new_value, cmd); if (res) return tipc_cfg_reply_error_string("cannot change link setting"); @@ -2098,7 +2137,9 @@ static void link_reset_statistics(struct tipc_link *l_ptr) l_ptr->stats.recv_info = l_ptr->next_in_no; } -struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_space) +struct sk_buff *tipc_link_cmd_reset_stats(struct net *net, + const void *req_tlv_area, + int req_tlv_space) { char *link_name; struct tipc_link *l_ptr; @@ -2110,11 +2151,11 @@ struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_ link_name = (char *)TLV_DATA(req_tlv_area); if (!strcmp(link_name, tipc_bclink_name)) { - if (tipc_bclink_reset_stats()) + if (tipc_bclink_reset_stats(net)) return tipc_cfg_reply_error_string("link not found"); return tipc_cfg_reply_none(); } - node = tipc_link_find_owner(link_name, &bearer_id); + node = tipc_link_find_owner(net, link_name, &bearer_id); if (!node) return tipc_cfg_reply_error_string("link not found"); @@ -2139,13 +2180,15 @@ static u32 percent(u32 count, u32 total) /** * tipc_link_stats - print link statistics + * @net: the applicable net namespace * @name: link name * @buf: print buffer area * @buf_size: size of print buffer area * * Returns length of print buffer data string (or 0 if error) */ -static int tipc_link_stats(const char *name, char *buf, const u32 buf_size) +static int tipc_link_stats(struct net *net, const char *name, char *buf, + const u32 buf_size) { struct tipc_link *l; struct tipc_stats *s; @@ -2156,9 +2199,9 @@ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size) int ret; if (!strcmp(name, tipc_bclink_name)) - return tipc_bclink_stats(buf, buf_size); + return tipc_bclink_stats(net, buf, buf_size); - node = tipc_link_find_owner(name, &bearer_id); + node = tipc_link_find_owner(net, name, &bearer_id); if (!node) return 0; @@ -2235,7 +2278,9 @@ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size) return ret; } -struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_space) +struct sk_buff *tipc_link_cmd_show_stats(struct net *net, + const void *req_tlv_area, + int req_tlv_space) { struct sk_buff *buf; struct tlv_desc *rep_tlv; @@ -2253,7 +2298,7 @@ struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_s rep_tlv = (struct tlv_desc *)buf->data; pb = TLV_DATA(rep_tlv); pb_len = ULTRA_STRING_MAX_LEN; - str_len = tipc_link_stats((char *)TLV_DATA(req_tlv_area), + str_len = tipc_link_stats(net, (char *)TLV_DATA(req_tlv_area), pb, pb_len); if (!str_len) { kfree_skb(buf); @@ -2266,39 +2311,13 @@ struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_s return buf; } -/** - * tipc_link_get_max_pkt - get maximum packet size to use when sending to destination - * @dest: network address of destination node - * @selector: used to select from set of active links - * - * If no active link can be found, uses default maximum packet size. - */ -u32 tipc_link_get_max_pkt(u32 dest, u32 selector) -{ - struct tipc_node *n_ptr; - struct tipc_link *l_ptr; - u32 res = MAX_PKT_DEFAULT; - - if (dest == tipc_own_addr) - return MAX_MSG_SIZE; - - n_ptr = tipc_node_find(dest); - if (n_ptr) { - tipc_node_lock(n_ptr); - l_ptr = n_ptr->active_links[selector & 1]; - if (l_ptr) - res = l_ptr->max_pkt; - tipc_node_unlock(n_ptr); - } - return res; -} - static void link_print(struct tipc_link *l_ptr, const char *str) { + struct tipc_net *tn = net_generic(l_ptr->owner->net, tipc_net_id); struct tipc_bearer *b_ptr; rcu_read_lock(); - b_ptr = rcu_dereference_rtnl(bearer_list[l_ptr->bearer_id]); + b_ptr = rcu_dereference_rtnl(tn->bearer_list[l_ptr->bearer_id]); if (b_ptr) pr_info("%s Link %x<%s>:", str, l_ptr->addr, b_ptr->name); rcu_read_unlock(); @@ -2362,6 +2381,7 @@ int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info) struct tipc_link *link; struct tipc_node *node; struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1]; + struct net *net = genl_info_net(info); if (!info->attrs[TIPC_NLA_LINK]) return -EINVAL; @@ -2377,7 +2397,7 @@ int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info) name = nla_data(attrs[TIPC_NLA_LINK_NAME]); - node = tipc_link_find_owner(name, &bearer_id); + node = tipc_link_find_owner(net, name, &bearer_id); if (!node) return -EINVAL; @@ -2493,12 +2513,14 @@ msg_full: } /* Caller should hold appropriate locks to protect the link */ -static int __tipc_nl_add_link(struct tipc_nl_msg *msg, struct tipc_link *link) +static int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, + struct tipc_link *link) { int err; void *hdr; struct nlattr *attrs; struct nlattr *prop; + struct tipc_net *tn = net_generic(net, tipc_net_id); hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_v2_family, NLM_F_MULTI, TIPC_NL_LINK_GET); @@ -2512,7 +2534,7 @@ static int __tipc_nl_add_link(struct tipc_nl_msg *msg, struct tipc_link *link) if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, link->name)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_DEST, - tipc_cluster_mask(tipc_own_addr))) + tipc_cluster_mask(tn->own_addr))) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->max_pkt)) goto attr_msg_full; @@ -2562,9 +2584,8 @@ msg_full: } /* Caller should hold node lock */ -static int __tipc_nl_add_node_links(struct tipc_nl_msg *msg, - struct tipc_node *node, - u32 *prev_link) +static int __tipc_nl_add_node_links(struct net *net, struct tipc_nl_msg *msg, + struct tipc_node *node, u32 *prev_link) { u32 i; int err; @@ -2575,7 +2596,7 @@ static int __tipc_nl_add_node_links(struct tipc_nl_msg *msg, if (!node->links[i]) continue; - err = __tipc_nl_add_link(msg, node->links[i]); + err = __tipc_nl_add_link(net, msg, node->links[i]); if (err) return err; } @@ -2586,6 +2607,8 @@ static int __tipc_nl_add_node_links(struct tipc_nl_msg *msg, int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *node; struct tipc_nl_msg msg; u32 prev_node = cb->args[0]; @@ -2603,7 +2626,7 @@ int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); if (prev_node) { - node = tipc_node_find(prev_node); + node = tipc_node_find(net, prev_node); if (!node) { /* We never set seq or call nl_dump_check_consistent() * this means that setting prev_seq here will cause the @@ -2615,9 +2638,11 @@ int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb) goto out; } - list_for_each_entry_continue_rcu(node, &tipc_node_list, list) { + list_for_each_entry_continue_rcu(node, &tn->node_list, + list) { tipc_node_lock(node); - err = __tipc_nl_add_node_links(&msg, node, &prev_link); + err = __tipc_nl_add_node_links(net, &msg, node, + &prev_link); tipc_node_unlock(node); if (err) goto out; @@ -2625,13 +2650,14 @@ int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb) prev_node = node->addr; } } else { - err = tipc_nl_add_bc_link(&msg); + err = tipc_nl_add_bc_link(net, &msg); if (err) goto out; - list_for_each_entry_rcu(node, &tipc_node_list, list) { + list_for_each_entry_rcu(node, &tn->node_list, list) { tipc_node_lock(node); - err = __tipc_nl_add_node_links(&msg, node, &prev_link); + err = __tipc_nl_add_node_links(net, &msg, node, + &prev_link); tipc_node_unlock(node); if (err) goto out; @@ -2652,6 +2678,7 @@ out: int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info) { + struct net *net = genl_info_net(info); struct sk_buff *ans_skb; struct tipc_nl_msg msg; struct tipc_link *link; @@ -2664,7 +2691,7 @@ int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info) return -EINVAL; name = nla_data(info->attrs[TIPC_NLA_LINK_NAME]); - node = tipc_link_find_owner(name, &bearer_id); + node = tipc_link_find_owner(net, name, &bearer_id); if (!node) return -EINVAL; @@ -2683,7 +2710,7 @@ int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info) goto err_out; } - err = __tipc_nl_add_link(&msg, link); + err = __tipc_nl_add_link(net, &msg, link); if (err) goto err_out; @@ -2706,6 +2733,7 @@ int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info) struct tipc_link *link; struct tipc_node *node; struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1]; + struct net *net = genl_info_net(info); if (!info->attrs[TIPC_NLA_LINK]) return -EINVAL; @@ -2722,13 +2750,13 @@ int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info) link_name = nla_data(attrs[TIPC_NLA_LINK_NAME]); if (strcmp(link_name, tipc_bclink_name) == 0) { - err = tipc_bclink_reset_stats(); + err = tipc_bclink_reset_stats(net); if (err) return err; return 0; } - node = tipc_link_find_owner(link_name, &bearer_id); + node = tipc_link_find_owner(net, link_name, &bearer_id); if (!node) return -EINVAL; diff --git a/net/tipc/link.h b/net/tipc/link.h index 55812e87ca1e..9df7fa4d3bdd 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -41,6 +41,10 @@ #include "msg.h" #include "node.h" +/* TIPC-specific error codes +*/ +#define ELINKCONG EAGAIN /* link congestion <=> resource unavailable */ + /* Out-of-range value for link sequence numbers */ #define INVALID_LINK_SEQ 0x10000 @@ -105,7 +109,7 @@ struct tipc_stats { * @peer_bearer_id: bearer id used by link's peer endpoint * @bearer_id: local bearer id used by link * @tolerance: minimum link continuity loss needed to reset link [in ms] - * @continuity_interval: link continuity testing interval [in ms] + * @cont_intv: link continuity testing interval * @abort_limit: # of unacknowledged continuity probes needed to reset link * @state: current state of link FSM * @fsm_msg_cnt: # of protocol messages link FSM has sent in current state @@ -146,7 +150,7 @@ struct tipc_link { u32 peer_bearer_id; u32 bearer_id; u32 tolerance; - u32 continuity_interval; + unsigned long cont_intv; u32 abort_limit; int state; u32 fsm_msg_cnt; @@ -196,28 +200,32 @@ struct tipc_port; struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, struct tipc_bearer *b_ptr, const struct tipc_media_addr *media_addr); -void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down); +void tipc_link_delete_list(struct net *net, unsigned int bearer_id, + bool shutting_down); void tipc_link_failover_send_queue(struct tipc_link *l_ptr); void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct tipc_link *dest); void tipc_link_reset_fragments(struct tipc_link *l_ptr); int tipc_link_is_up(struct tipc_link *l_ptr); int tipc_link_is_active(struct tipc_link *l_ptr); void tipc_link_purge_queues(struct tipc_link *l_ptr); -struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, - int req_tlv_space, - u16 cmd); -struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, +struct sk_buff *tipc_link_cmd_config(struct net *net, const void *req_tlv_area, + int req_tlv_space, u16 cmd); +struct sk_buff *tipc_link_cmd_show_stats(struct net *net, + const void *req_tlv_area, int req_tlv_space); -struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, +struct sk_buff *tipc_link_cmd_reset_stats(struct net *net, + const void *req_tlv_area, int req_tlv_space); void tipc_link_reset_all(struct tipc_node *node); void tipc_link_reset(struct tipc_link *l_ptr); -void tipc_link_reset_list(unsigned int bearer_id); -int tipc_link_xmit_skb(struct sk_buff *skb, u32 dest, u32 selector); -int tipc_link_xmit(struct sk_buff_head *list, u32 dest, u32 selector); -int __tipc_link_xmit(struct tipc_link *link, struct sk_buff_head *list); -u32 tipc_link_get_max_pkt(u32 dest, u32 selector); -void tipc_link_bundle_rcv(struct sk_buff *buf); +void tipc_link_reset_list(struct net *net, unsigned int bearer_id); +int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, + u32 selector); +int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dest, + u32 selector); +int __tipc_link_xmit(struct net *net, struct tipc_link *link, + struct sk_buff_head *list); +void tipc_link_bundle_rcv(struct net *net, struct sk_buff *buf); void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob, u32 gap, u32 tolerance, u32 priority, u32 acked_mtu); void tipc_link_push_packets(struct tipc_link *l_ptr); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index a687b30a699c..18aba9e99345 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -34,6 +34,7 @@ * POSSIBILITY OF SUCH DAMAGE. */ +#include <net/sock.h> #include "core.h" #include "msg.h" #include "addr.h" @@ -46,25 +47,50 @@ static unsigned int align(unsigned int i) return (i + 3) & ~3u; } -void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize, - u32 destnode) +/** + * tipc_buf_acquire - creates a TIPC message buffer + * @size: message size (including TIPC header) + * + * Returns a new buffer with data pointers set to the specified size. + * + * NOTE: Headroom is reserved to allow prepending of a data link header. + * There may also be unrequested tailroom present at the buffer's end. + */ +struct sk_buff *tipc_buf_acquire(u32 size) { + struct sk_buff *skb; + unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u; + + skb = alloc_skb_fclone(buf_size, GFP_ATOMIC); + if (skb) { + skb_reserve(skb, BUF_HEADROOM); + skb_put(skb, size); + skb->next = NULL; + } + return skb; +} + +void tipc_msg_init(struct net *net, struct tipc_msg *m, u32 user, u32 type, + u32 hsize, u32 destnode) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); + memset(m, 0, hsize); msg_set_version(m); msg_set_user(m, user); msg_set_hdr_sz(m, hsize); msg_set_size(m, hsize); - msg_set_prevnode(m, tipc_own_addr); + msg_set_prevnode(m, tn->own_addr); msg_set_type(m, type); if (hsize > SHORT_H_SIZE) { - msg_set_orignode(m, tipc_own_addr); + msg_set_orignode(m, tn->own_addr); msg_set_destnode(m, destnode); } } -struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, - uint data_sz, u32 dnode, u32 onode, - u32 dport, u32 oport, int errcode) +struct sk_buff *tipc_msg_create(struct net *net, uint user, uint type, + uint hdr_sz, uint data_sz, u32 dnode, + u32 onode, u32 dport, u32 oport, int errcode) { struct tipc_msg *msg; struct sk_buff *buf; @@ -74,7 +100,7 @@ struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, return NULL; msg = buf_msg(buf); - tipc_msg_init(msg, user, type, hdr_sz, dnode); + tipc_msg_init(net, msg, user, type, hdr_sz, dnode); msg_set_size(msg, hdr_sz + data_sz); msg_set_prevnode(msg, onode); msg_set_origport(msg, oport); @@ -170,8 +196,8 @@ err: * * Returns message data size or errno: -ENOMEM, -EFAULT */ -int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, - int dsz, int pktmax, struct sk_buff_head *list) +int tipc_msg_build(struct net *net, struct tipc_msg *mhdr, struct msghdr *m, + int offset, int dsz, int pktmax, struct sk_buff_head *list) { int mhsz = msg_hdr_sz(mhdr); int msz = mhsz + dsz; @@ -191,6 +217,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, skb = tipc_buf_acquire(msz); if (unlikely(!skb)) return -ENOMEM; + skb_orphan(skb); __skb_queue_tail(list, skb); skb_copy_to_linear_data(skb, mhdr, mhsz); pktpos = skb->data + mhsz; @@ -202,8 +229,8 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, } /* Prepare reusable fragment header */ - tipc_msg_init(&pkthdr, MSG_FRAGMENTER, FIRST_FRAGMENT, - INT_H_SIZE, msg_destnode(mhdr)); + tipc_msg_init(net, &pkthdr, MSG_FRAGMENTER, FIRST_FRAGMENT, INT_H_SIZE, + msg_destnode(mhdr)); msg_set_size(&pkthdr, pktmax); msg_set_fragm_no(&pkthdr, pktno); @@ -211,6 +238,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, skb = tipc_buf_acquire(pktmax); if (!skb) return -ENOMEM; + skb_orphan(skb); __skb_queue_tail(list, skb); pktpos = skb->data; skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE); @@ -244,6 +272,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, rc = -ENOMEM; goto error; } + skb_orphan(skb); __skb_queue_tail(list, skb); msg_set_type(&pkthdr, FRAGMENT); msg_set_size(&pkthdr, pktsz); @@ -312,8 +341,8 @@ bool tipc_msg_bundle(struct sk_buff_head *list, struct sk_buff *skb, u32 mtu) * Replaces buffer if successful * Returns true if success, otherwise false */ -bool tipc_msg_make_bundle(struct sk_buff_head *list, struct sk_buff *skb, - u32 mtu, u32 dnode) +bool tipc_msg_make_bundle(struct net *net, struct sk_buff_head *list, + struct sk_buff *skb, u32 mtu, u32 dnode) { struct sk_buff *bskb; struct tipc_msg *bmsg; @@ -336,7 +365,7 @@ bool tipc_msg_make_bundle(struct sk_buff_head *list, struct sk_buff *skb, skb_trim(bskb, INT_H_SIZE); bmsg = buf_msg(bskb); - tipc_msg_init(bmsg, MSG_BUNDLER, 0, INT_H_SIZE, dnode); + tipc_msg_init(net, bmsg, MSG_BUNDLER, 0, INT_H_SIZE, dnode); msg_set_seqno(bmsg, msg_seqno(msg)); msg_set_ack(bmsg, msg_ack(msg)); msg_set_bcast_ack(bmsg, msg_bcast_ack(msg)); @@ -353,8 +382,10 @@ bool tipc_msg_make_bundle(struct sk_buff_head *list, struct sk_buff *skb, * Consumes buffer if failure * Returns true if success, otherwise false */ -bool tipc_msg_reverse(struct sk_buff *buf, u32 *dnode, int err) +bool tipc_msg_reverse(struct net *net, struct sk_buff *buf, u32 *dnode, + int err) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_msg *msg = buf_msg(buf); uint imp = msg_importance(msg); struct tipc_msg ohdr; @@ -374,7 +405,7 @@ bool tipc_msg_reverse(struct sk_buff *buf, u32 *dnode, int err) msg_set_errcode(msg, err); msg_set_origport(msg, msg_destport(&ohdr)); msg_set_destport(msg, msg_origport(&ohdr)); - msg_set_prevnode(msg, tipc_own_addr); + msg_set_prevnode(msg, tn->own_addr); if (!msg_short(msg)) { msg_set_orignode(msg, msg_destnode(&ohdr)); msg_set_destnode(msg, msg_orignode(&ohdr)); @@ -399,7 +430,7 @@ exit: * Returns 0 (TIPC_OK) if message ok and we can try again, -TIPC error * code if message to be rejected */ -int tipc_msg_eval(struct sk_buff *buf, u32 *dnode) +int tipc_msg_eval(struct net *net, struct sk_buff *buf, u32 *dnode) { struct tipc_msg *msg = buf_msg(buf); u32 dport; @@ -413,8 +444,8 @@ int tipc_msg_eval(struct sk_buff *buf, u32 *dnode) if (msg_reroute_cnt(msg) > 0) return -TIPC_ERR_NO_NAME; - *dnode = addr_domain(msg_lookup_scope(msg)); - dport = tipc_nametbl_translate(msg_nametype(msg), + *dnode = addr_domain(net, msg_lookup_scope(msg)); + dport = tipc_nametbl_translate(net, msg_nametype(msg), msg_nameinst(msg), dnode); if (!dport) diff --git a/net/tipc/msg.h b/net/tipc/msg.h index d5c83d7ecb47..526ef345b70e 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -37,7 +37,7 @@ #ifndef _TIPC_MSG_H #define _TIPC_MSG_H -#include "bearer.h" +#include <linux/tipc.h> /* * Constants and routines used to read and write TIPC payload message headers @@ -77,11 +77,37 @@ #define TIPC_MEDIA_ADDR_OFFSET 5 +/** + * TIPC message buffer code + * + * TIPC message buffer headroom reserves space for the worst-case + * link-level device header (in case the message is sent off-node). + * + * Note: Headroom should be a multiple of 4 to ensure the TIPC header fields + * are word aligned for quicker access + */ +#define BUF_HEADROOM LL_MAX_HEADER + +struct tipc_skb_cb { + void *handle; + struct sk_buff *tail; + bool deferred; + bool wakeup_pending; + bool bundling; + u16 chain_sz; + u16 chain_imp; +}; + +#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0])) struct tipc_msg { __be32 hdr[15]; }; +static inline struct tipc_msg *buf_msg(struct sk_buff *skb) +{ + return (struct tipc_msg *)skb->data; +} static inline u32 msg_word(struct tipc_msg *m, u32 pos) { @@ -721,27 +747,21 @@ static inline u32 msg_tot_origport(struct tipc_msg *m) return msg_origport(m); } -bool tipc_msg_reverse(struct sk_buff *buf, u32 *dnode, int err); - -int tipc_msg_eval(struct sk_buff *buf, u32 *dnode); - -void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize, - u32 destnode); - -struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, - uint data_sz, u32 dnode, u32 onode, - u32 dport, u32 oport, int errcode); - +struct sk_buff *tipc_buf_acquire(u32 size); +bool tipc_msg_reverse(struct net *net, struct sk_buff *buf, u32 *dnode, + int err); +int tipc_msg_eval(struct net *net, struct sk_buff *buf, u32 *dnode); +void tipc_msg_init(struct net *net, struct tipc_msg *m, u32 user, u32 type, + u32 hsize, u32 destnode); +struct sk_buff *tipc_msg_create(struct net *net, uint user, uint type, + uint hdr_sz, uint data_sz, u32 dnode, + u32 onode, u32 dport, u32 oport, int errcode); int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf); - bool tipc_msg_bundle(struct sk_buff_head *list, struct sk_buff *skb, u32 mtu); - -bool tipc_msg_make_bundle(struct sk_buff_head *list, struct sk_buff *skb, - u32 mtu, u32 dnode); - -int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, - int dsz, int mtu, struct sk_buff_head *list); - +bool tipc_msg_make_bundle(struct net *net, struct sk_buff_head *list, + struct sk_buff *skb, u32 mtu, u32 dnode); +int tipc_msg_build(struct net *net, struct tipc_msg *mhdr, struct msghdr *m, + int offset, int dsz, int mtu, struct sk_buff_head *list); struct sk_buff *tipc_msg_reassemble(struct sk_buff_head *list); #endif diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index ba6083dca95b..7f31cd4badc4 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -68,29 +68,32 @@ static void publ_to_item(struct distr_item *i, struct publication *p) /** * named_prepare_buf - allocate & initialize a publication message */ -static struct sk_buff *named_prepare_buf(u32 type, u32 size, u32 dest) +static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size, + u32 dest) { struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size); struct tipc_msg *msg; if (buf != NULL) { msg = buf_msg(buf); - tipc_msg_init(msg, NAME_DISTRIBUTOR, type, INT_H_SIZE, dest); + tipc_msg_init(net, msg, NAME_DISTRIBUTOR, type, INT_H_SIZE, + dest); msg_set_size(msg, INT_H_SIZE + size); } return buf; } -void named_cluster_distribute(struct sk_buff *skb) +void named_cluster_distribute(struct net *net, struct sk_buff *skb) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff *oskb; struct tipc_node *node; u32 dnode; rcu_read_lock(); - list_for_each_entry_rcu(node, &tipc_node_list, list) { + list_for_each_entry_rcu(node, &tn->node_list, list) { dnode = node->addr; - if (in_own_node(dnode)) + if (in_own_node(net, dnode)) continue; if (!tipc_node_active_links(node)) continue; @@ -98,7 +101,7 @@ void named_cluster_distribute(struct sk_buff *skb) if (!oskb) break; msg_set_destnode(buf_msg(oskb), dnode); - tipc_link_xmit_skb(oskb, dnode, dnode); + tipc_link_xmit_skb(net, oskb, dnode, dnode); } rcu_read_unlock(); @@ -108,18 +111,19 @@ void named_cluster_distribute(struct sk_buff *skb) /** * tipc_named_publish - tell other nodes about a new publication by this node */ -struct sk_buff *tipc_named_publish(struct publication *publ) +struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff *buf; struct distr_item *item; list_add_tail_rcu(&publ->local_list, - &tipc_nametbl->publ_list[publ->scope]); + &tn->nametbl->publ_list[publ->scope]); if (publ->scope == TIPC_NODE_SCOPE) return NULL; - buf = named_prepare_buf(PUBLICATION, ITEM_SIZE, 0); + buf = named_prepare_buf(net, PUBLICATION, ITEM_SIZE, 0); if (!buf) { pr_warn("Publication distribution failure\n"); return NULL; @@ -133,7 +137,7 @@ struct sk_buff *tipc_named_publish(struct publication *publ) /** * tipc_named_withdraw - tell other nodes about a withdrawn publication by this node */ -struct sk_buff *tipc_named_withdraw(struct publication *publ) +struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ) { struct sk_buff *buf; struct distr_item *item; @@ -143,7 +147,7 @@ struct sk_buff *tipc_named_withdraw(struct publication *publ) if (publ->scope == TIPC_NODE_SCOPE) return NULL; - buf = named_prepare_buf(WITHDRAWAL, ITEM_SIZE, 0); + buf = named_prepare_buf(net, WITHDRAWAL, ITEM_SIZE, 0); if (!buf) { pr_warn("Withdrawal distribution failure\n"); return NULL; @@ -160,19 +164,21 @@ struct sk_buff *tipc_named_withdraw(struct publication *publ) * @dnode: node to be updated * @pls: linked list of publication items to be packed into buffer chain */ -static void named_distribute(struct sk_buff_head *list, u32 dnode, - struct list_head *pls) +static void named_distribute(struct net *net, struct sk_buff_head *list, + u32 dnode, struct list_head *pls) { struct publication *publ; struct sk_buff *skb = NULL; struct distr_item *item = NULL; - uint msg_dsz = (tipc_node_get_mtu(dnode, 0) / ITEM_SIZE) * ITEM_SIZE; + uint msg_dsz = (tipc_node_get_mtu(net, dnode, 0) / ITEM_SIZE) * + ITEM_SIZE; uint msg_rem = msg_dsz; list_for_each_entry(publ, pls, local_list) { /* Prepare next buffer: */ if (!skb) { - skb = named_prepare_buf(PUBLICATION, msg_rem, dnode); + skb = named_prepare_buf(net, PUBLICATION, msg_rem, + dnode); if (!skb) { pr_warn("Bulk publication failure\n"); return; @@ -202,30 +208,32 @@ static void named_distribute(struct sk_buff_head *list, u32 dnode, /** * tipc_named_node_up - tell specified node about all publications by this node */ -void tipc_named_node_up(u32 dnode) +void tipc_named_node_up(struct net *net, u32 dnode) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff_head head; __skb_queue_head_init(&head); rcu_read_lock(); - named_distribute(&head, dnode, - &tipc_nametbl->publ_list[TIPC_CLUSTER_SCOPE]); - named_distribute(&head, dnode, - &tipc_nametbl->publ_list[TIPC_ZONE_SCOPE]); + named_distribute(net, &head, dnode, + &tn->nametbl->publ_list[TIPC_CLUSTER_SCOPE]); + named_distribute(net, &head, dnode, + &tn->nametbl->publ_list[TIPC_ZONE_SCOPE]); rcu_read_unlock(); - tipc_link_xmit(&head, dnode, dnode); + tipc_link_xmit(net, &head, dnode, dnode); } -static void tipc_publ_subscribe(struct publication *publ, u32 addr) +static void tipc_publ_subscribe(struct net *net, struct publication *publ, + u32 addr) { struct tipc_node *node; - if (in_own_node(addr)) + if (in_own_node(net, addr)) return; - node = tipc_node_find(addr); + node = tipc_node_find(net, addr); if (!node) { pr_warn("Node subscription rejected, unknown node 0x%x\n", addr); @@ -237,11 +245,12 @@ static void tipc_publ_subscribe(struct publication *publ, u32 addr) tipc_node_unlock(node); } -static void tipc_publ_unsubscribe(struct publication *publ, u32 addr) +static void tipc_publ_unsubscribe(struct net *net, struct publication *publ, + u32 addr) { struct tipc_node *node; - node = tipc_node_find(addr); + node = tipc_node_find(net, addr); if (!node) return; @@ -256,16 +265,17 @@ static void tipc_publ_unsubscribe(struct publication *publ, u32 addr) * Invoked for each publication issued by a newly failed node. * Removes publication structure from name table & deletes it. */ -static void tipc_publ_purge(struct publication *publ, u32 addr) +static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct publication *p; - spin_lock_bh(&tipc_nametbl_lock); - p = tipc_nametbl_remove_publ(publ->type, publ->lower, + spin_lock_bh(&tn->nametbl_lock); + p = tipc_nametbl_remove_publ(net, publ->type, publ->lower, publ->node, publ->ref, publ->key); if (p) - tipc_publ_unsubscribe(p, addr); - spin_unlock_bh(&tipc_nametbl_lock); + tipc_publ_unsubscribe(net, p, addr); + spin_unlock_bh(&tn->nametbl_lock); if (p != publ) { pr_err("Unable to remove publication from failed node\n" @@ -277,12 +287,12 @@ static void tipc_publ_purge(struct publication *publ, u32 addr) kfree_rcu(p, rcu); } -void tipc_publ_notify(struct list_head *nsub_list, u32 addr) +void tipc_publ_notify(struct net *net, struct list_head *nsub_list, u32 addr) { struct publication *publ, *tmp; list_for_each_entry_safe(publ, tmp, nsub_list, nodesub_list) - tipc_publ_purge(publ, addr); + tipc_publ_purge(net, publ, addr); } /** @@ -292,25 +302,28 @@ void tipc_publ_notify(struct list_head *nsub_list, u32 addr) * tipc_nametbl_lock must be held. * Returns the publication item if successful, otherwise NULL. */ -static bool tipc_update_nametbl(struct distr_item *i, u32 node, u32 dtype) +static bool tipc_update_nametbl(struct net *net, struct distr_item *i, + u32 node, u32 dtype) { struct publication *publ = NULL; if (dtype == PUBLICATION) { - publ = tipc_nametbl_insert_publ(ntohl(i->type), ntohl(i->lower), + publ = tipc_nametbl_insert_publ(net, ntohl(i->type), + ntohl(i->lower), ntohl(i->upper), TIPC_CLUSTER_SCOPE, node, ntohl(i->ref), ntohl(i->key)); if (publ) { - tipc_publ_subscribe(publ, node); + tipc_publ_subscribe(net, publ, node); return true; } } else if (dtype == WITHDRAWAL) { - publ = tipc_nametbl_remove_publ(ntohl(i->type), ntohl(i->lower), + publ = tipc_nametbl_remove_publ(net, ntohl(i->type), + ntohl(i->lower), node, ntohl(i->ref), ntohl(i->key)); if (publ) { - tipc_publ_unsubscribe(publ, node); + tipc_publ_unsubscribe(net, publ, node); kfree_rcu(publ, rcu); return true; } @@ -343,7 +356,7 @@ static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node) * tipc_named_process_backlog - try to process any pending name table updates * from the network. */ -void tipc_named_process_backlog(void) +void tipc_named_process_backlog(struct net *net) { struct distr_queue_item *e, *tmp; char addr[16]; @@ -351,7 +364,7 @@ void tipc_named_process_backlog(void) list_for_each_entry_safe(e, tmp, &tipc_dist_queue, next) { if (time_after(e->expires, now)) { - if (!tipc_update_nametbl(&e->i, e->node, e->dtype)) + if (!tipc_update_nametbl(net, &e->i, e->node, e->dtype)) continue; } else { tipc_addr_string_fill(addr, e->node); @@ -369,21 +382,22 @@ void tipc_named_process_backlog(void) /** * tipc_named_rcv - process name table update message sent by another node */ -void tipc_named_rcv(struct sk_buff *buf) +void tipc_named_rcv(struct net *net, struct sk_buff *buf) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_msg *msg = buf_msg(buf); struct distr_item *item = (struct distr_item *)msg_data(msg); u32 count = msg_data_sz(msg) / ITEM_SIZE; u32 node = msg_orignode(msg); - spin_lock_bh(&tipc_nametbl_lock); + spin_lock_bh(&tn->nametbl_lock); while (count--) { - if (!tipc_update_nametbl(item, node, msg_type(msg))) + if (!tipc_update_nametbl(net, item, node, msg_type(msg))) tipc_named_add_backlog(item, msg_type(msg), node); item++; } - tipc_named_process_backlog(); - spin_unlock_bh(&tipc_nametbl_lock); + tipc_named_process_backlog(net); + spin_unlock_bh(&tn->nametbl_lock); kfree_skb(buf); } @@ -394,17 +408,18 @@ void tipc_named_rcv(struct sk_buff *buf) * All name table entries published by this node are updated to reflect * the node's new network address. */ -void tipc_named_reinit(void) +void tipc_named_reinit(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct publication *publ; int scope; - spin_lock_bh(&tipc_nametbl_lock); + spin_lock_bh(&tn->nametbl_lock); for (scope = TIPC_ZONE_SCOPE; scope <= TIPC_NODE_SCOPE; scope++) - list_for_each_entry_rcu(publ, &tipc_nametbl->publ_list[scope], + list_for_each_entry_rcu(publ, &tn->nametbl->publ_list[scope], local_list) - publ->node = tipc_own_addr; + publ->node = tn->own_addr; - spin_unlock_bh(&tipc_nametbl_lock); + spin_unlock_bh(&tn->nametbl_lock); } diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h index cef55cedcfb2..5ec10b59527b 100644 --- a/net/tipc/name_distr.h +++ b/net/tipc/name_distr.h @@ -67,13 +67,13 @@ struct distr_item { __be32 key; }; -struct sk_buff *tipc_named_publish(struct publication *publ); -struct sk_buff *tipc_named_withdraw(struct publication *publ); -void named_cluster_distribute(struct sk_buff *buf); -void tipc_named_node_up(u32 dnode); -void tipc_named_rcv(struct sk_buff *buf); -void tipc_named_reinit(void); -void tipc_named_process_backlog(void); -void tipc_publ_notify(struct list_head *nsub_list, u32 addr); +struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ); +struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ); +void named_cluster_distribute(struct net *net, struct sk_buff *buf); +void tipc_named_node_up(struct net *net, u32 dnode); +void tipc_named_rcv(struct net *net, struct sk_buff *buf); +void tipc_named_reinit(struct net *net); +void tipc_named_process_backlog(struct net *net); +void tipc_publ_notify(struct net *net, struct list_head *nsub_list, u32 addr); #endif diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index c8df0223371a..ce09b863528c 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -34,11 +34,13 @@ * POSSIBILITY OF SUCH DAMAGE. */ +#include <net/sock.h> #include "core.h" #include "config.h" #include "name_table.h" #include "name_distr.h" #include "subscr.h" +#include "bcast.h" #define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */ @@ -105,9 +107,6 @@ struct name_seq { struct rcu_head rcu; }; -struct name_table *tipc_nametbl; -DEFINE_SPINLOCK(tipc_nametbl_lock); - static int hash(int x) { return x & (TIPC_NAMETBL_SIZE - 1); @@ -228,9 +227,11 @@ static u32 nameseq_locate_subseq(struct name_seq *nseq, u32 instance) /** * tipc_nameseq_insert_publ */ -static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, - u32 type, u32 lower, u32 upper, - u32 scope, u32 node, u32 port, u32 key) +static struct publication *tipc_nameseq_insert_publ(struct net *net, + struct name_seq *nseq, + u32 type, u32 lower, + u32 upper, u32 scope, + u32 node, u32 port, u32 key) { struct tipc_subscription *s; struct tipc_subscription *st; @@ -315,12 +316,12 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, list_add(&publ->zone_list, &info->zone_list); info->zone_list_size++; - if (in_own_cluster(node)) { + if (in_own_cluster(net, node)) { list_add(&publ->cluster_list, &info->cluster_list); info->cluster_list_size++; } - if (in_own_node(node)) { + if (in_own_node(net, node)) { list_add(&publ->node_list, &info->node_list); info->node_list_size++; } @@ -349,8 +350,10 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, * A failed withdraw request simply returns a failure indication and lets the * caller issue any error or warning messages associated with such a problem. */ -static struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 inst, - u32 node, u32 ref, u32 key) +static struct publication *tipc_nameseq_remove_publ(struct net *net, + struct name_seq *nseq, + u32 inst, u32 node, + u32 ref, u32 key) { struct publication *publ; struct sub_seq *sseq = nameseq_find_subseq(nseq, inst); @@ -378,13 +381,13 @@ found: info->zone_list_size--; /* Remove publication from cluster scope list, if present */ - if (in_own_cluster(node)) { + if (in_own_cluster(net, node)) { list_del(&publ->cluster_list); info->cluster_list_size--; } /* Remove publication from node scope list, if present */ - if (in_own_node(node)) { + if (in_own_node(net, node)) { list_del(&publ->node_list); info->node_list_size--; } @@ -447,12 +450,13 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq, } } -static struct name_seq *nametbl_find_seq(u32 type) +static struct name_seq *nametbl_find_seq(struct net *net, u32 type) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct hlist_head *seq_head; struct name_seq *ns; - seq_head = &tipc_nametbl->seq_hlist[hash(type)]; + seq_head = &tn->nametbl->seq_hlist[hash(type)]; hlist_for_each_entry_rcu(ns, seq_head, ns_list) { if (ns->type == type) return ns; @@ -461,11 +465,13 @@ static struct name_seq *nametbl_find_seq(u32 type) return NULL; }; -struct publication *tipc_nametbl_insert_publ(u32 type, u32 lower, u32 upper, - u32 scope, u32 node, u32 port, u32 key) +struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type, + u32 lower, u32 upper, u32 scope, + u32 node, u32 port, u32 key) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct publication *publ; - struct name_seq *seq = nametbl_find_seq(type); + struct name_seq *seq = nametbl_find_seq(net, type); int index = hash(type); if ((scope < TIPC_ZONE_SCOPE) || (scope > TIPC_NODE_SCOPE) || @@ -476,29 +482,29 @@ struct publication *tipc_nametbl_insert_publ(u32 type, u32 lower, u32 upper, } if (!seq) - seq = tipc_nameseq_create(type, - &tipc_nametbl->seq_hlist[index]); + seq = tipc_nameseq_create(type, &tn->nametbl->seq_hlist[index]); if (!seq) return NULL; spin_lock_bh(&seq->lock); - publ = tipc_nameseq_insert_publ(seq, type, lower, upper, + publ = tipc_nameseq_insert_publ(net, seq, type, lower, upper, scope, node, port, key); spin_unlock_bh(&seq->lock); return publ; } -struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, - u32 node, u32 ref, u32 key) +struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, + u32 lower, u32 node, u32 ref, + u32 key) { struct publication *publ; - struct name_seq *seq = nametbl_find_seq(type); + struct name_seq *seq = nametbl_find_seq(net, type); if (!seq) return NULL; spin_lock_bh(&seq->lock); - publ = tipc_nameseq_remove_publ(seq, lower, node, ref, key); + publ = tipc_nameseq_remove_publ(net, seq, lower, node, ref, key); if (!seq->first_free && list_empty(&seq->subscriptions)) { hlist_del_init_rcu(&seq->ns_list); kfree(seq->sseqs); @@ -523,8 +529,10 @@ struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, * - if name translation is attempted and fails, sets 'destnode' to 0 * and returns 0 */ -u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) +u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, + u32 *destnode) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct sub_seq *sseq; struct name_info *info; struct publication *publ; @@ -532,11 +540,11 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) u32 ref = 0; u32 node = 0; - if (!tipc_in_scope(*destnode, tipc_own_addr)) + if (!tipc_in_scope(*destnode, tn->own_addr)) return 0; rcu_read_lock(); - seq = nametbl_find_seq(type); + seq = nametbl_find_seq(net, type); if (unlikely(!seq)) goto not_found; spin_lock_bh(&seq->lock); @@ -569,13 +577,13 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) } /* Round-Robin Algorithm */ - else if (*destnode == tipc_own_addr) { + else if (*destnode == tn->own_addr) { if (list_empty(&info->node_list)) goto no_match; publ = list_first_entry(&info->node_list, struct publication, node_list); list_move_tail(&publ->node_list, &info->node_list); - } else if (in_own_cluster_exact(*destnode)) { + } else if (in_own_cluster_exact(net, *destnode)) { if (list_empty(&info->cluster_list)) goto no_match; publ = list_first_entry(&info->cluster_list, struct publication, @@ -609,8 +617,8 @@ not_found: * * Returns non-zero if any off-node ports overlap */ -int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit, - struct tipc_port_list *dports) +int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, + u32 limit, struct tipc_port_list *dports) { struct name_seq *seq; struct sub_seq *sseq; @@ -619,7 +627,7 @@ int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit, int res = 0; rcu_read_lock(); - seq = nametbl_find_seq(type); + seq = nametbl_find_seq(net, type); if (!seq) goto exit; @@ -650,50 +658,55 @@ exit: /* * tipc_nametbl_publish - add name publication to network name tables */ -struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper, - u32 scope, u32 port_ref, u32 key) +struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower, + u32 upper, u32 scope, u32 port_ref, + u32 key) { struct publication *publ; struct sk_buff *buf = NULL; + struct tipc_net *tn = net_generic(net, tipc_net_id); - spin_lock_bh(&tipc_nametbl_lock); - if (tipc_nametbl->local_publ_count >= TIPC_MAX_PUBLICATIONS) { + spin_lock_bh(&tn->nametbl_lock); + if (tn->nametbl->local_publ_count >= TIPC_MAX_PUBLICATIONS) { pr_warn("Publication failed, local publication limit reached (%u)\n", TIPC_MAX_PUBLICATIONS); - spin_unlock_bh(&tipc_nametbl_lock); + spin_unlock_bh(&tn->nametbl_lock); return NULL; } - publ = tipc_nametbl_insert_publ(type, lower, upper, scope, - tipc_own_addr, port_ref, key); + publ = tipc_nametbl_insert_publ(net, type, lower, upper, scope, + tn->own_addr, port_ref, key); if (likely(publ)) { - tipc_nametbl->local_publ_count++; - buf = tipc_named_publish(publ); + tn->nametbl->local_publ_count++; + buf = tipc_named_publish(net, publ); /* Any pending external events? */ - tipc_named_process_backlog(); + tipc_named_process_backlog(net); } - spin_unlock_bh(&tipc_nametbl_lock); + spin_unlock_bh(&tn->nametbl_lock); if (buf) - named_cluster_distribute(buf); + named_cluster_distribute(net, buf); return publ; } /** * tipc_nametbl_withdraw - withdraw name publication from network name tables */ -int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key) +int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 ref, + u32 key) { struct publication *publ; struct sk_buff *skb = NULL; + struct tipc_net *tn = net_generic(net, tipc_net_id); - spin_lock_bh(&tipc_nametbl_lock); - publ = tipc_nametbl_remove_publ(type, lower, tipc_own_addr, ref, key); + spin_lock_bh(&tn->nametbl_lock); + publ = tipc_nametbl_remove_publ(net, type, lower, tn->own_addr, + ref, key); if (likely(publ)) { - tipc_nametbl->local_publ_count--; - skb = tipc_named_withdraw(publ); + tn->nametbl->local_publ_count--; + skb = tipc_named_withdraw(net, publ); /* Any pending external events? */ - tipc_named_process_backlog(); + tipc_named_process_backlog(net); list_del_init(&publ->pport_list); kfree_rcu(publ, rcu); } else { @@ -701,10 +714,10 @@ int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key) "(type=%u, lower=%u, ref=%u, key=%u)\n", type, lower, ref, key); } - spin_unlock_bh(&tipc_nametbl_lock); + spin_unlock_bh(&tn->nametbl_lock); if (skb) { - named_cluster_distribute(skb); + named_cluster_distribute(net, skb); return 1; } return 0; @@ -715,15 +728,15 @@ int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key) */ void tipc_nametbl_subscribe(struct tipc_subscription *s) { + struct tipc_net *tn = net_generic(s->net, tipc_net_id); u32 type = s->seq.type; int index = hash(type); struct name_seq *seq; - spin_lock_bh(&tipc_nametbl_lock); - seq = nametbl_find_seq(type); + spin_lock_bh(&tn->nametbl_lock); + seq = nametbl_find_seq(s->net, type); if (!seq) - seq = tipc_nameseq_create(type, - &tipc_nametbl->seq_hlist[index]); + seq = tipc_nameseq_create(type, &tn->nametbl->seq_hlist[index]); if (seq) { spin_lock_bh(&seq->lock); tipc_nameseq_subscribe(seq, s); @@ -732,7 +745,7 @@ void tipc_nametbl_subscribe(struct tipc_subscription *s) pr_warn("Failed to create subscription for {%u,%u,%u}\n", s->seq.type, s->seq.lower, s->seq.upper); } - spin_unlock_bh(&tipc_nametbl_lock); + spin_unlock_bh(&tn->nametbl_lock); } /** @@ -740,10 +753,11 @@ void tipc_nametbl_subscribe(struct tipc_subscription *s) */ void tipc_nametbl_unsubscribe(struct tipc_subscription *s) { + struct tipc_net *tn = net_generic(s->net, tipc_net_id); struct name_seq *seq; - spin_lock_bh(&tipc_nametbl_lock); - seq = nametbl_find_seq(s->seq.type); + spin_lock_bh(&tn->nametbl_lock); + seq = nametbl_find_seq(s->net, s->seq.type); if (seq != NULL) { spin_lock_bh(&seq->lock); list_del_init(&s->nameseq_list); @@ -756,7 +770,7 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s) spin_unlock_bh(&seq->lock); } } - spin_unlock_bh(&tipc_nametbl_lock); + spin_unlock_bh(&tn->nametbl_lock); } /** @@ -858,9 +872,10 @@ static int nametbl_header(char *buf, int len, u32 depth) /** * nametbl_list - print specified name table contents into the given buffer */ -static int nametbl_list(char *buf, int len, u32 depth_info, +static int nametbl_list(struct net *net, char *buf, int len, u32 depth_info, u32 type, u32 lowbound, u32 upbound) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct hlist_head *seq_head; struct name_seq *seq; int all_types; @@ -880,7 +895,7 @@ static int nametbl_list(char *buf, int len, u32 depth_info, lowbound = 0; upbound = ~0; for (i = 0; i < TIPC_NAMETBL_SIZE; i++) { - seq_head = &tipc_nametbl->seq_hlist[i]; + seq_head = &tn->nametbl->seq_hlist[i]; hlist_for_each_entry_rcu(seq, seq_head, ns_list) { ret += nameseq_list(seq, buf + ret, len - ret, depth, seq->type, @@ -896,7 +911,7 @@ static int nametbl_list(char *buf, int len, u32 depth_info, } ret += nametbl_header(buf + ret, len - ret, depth); i = hash(type); - seq_head = &tipc_nametbl->seq_hlist[i]; + seq_head = &tn->nametbl->seq_hlist[i]; hlist_for_each_entry_rcu(seq, seq_head, ns_list) { if (seq->type == type) { ret += nameseq_list(seq, buf + ret, len - ret, @@ -909,7 +924,8 @@ static int nametbl_list(char *buf, int len, u32 depth_info, return ret; } -struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space) +struct sk_buff *tipc_nametbl_get(struct net *net, const void *req_tlv_area, + int req_tlv_space) { struct sk_buff *buf; struct tipc_name_table_query *argv; @@ -930,7 +946,7 @@ struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space) pb_len = ULTRA_STRING_MAX_LEN; argv = (struct tipc_name_table_query *)TLV_DATA(req_tlv_area); rcu_read_lock(); - str_len = nametbl_list(pb, pb_len, ntohl(argv->depth), + str_len = nametbl_list(net, pb, pb_len, ntohl(argv->depth), ntohl(argv->type), ntohl(argv->lowbound), ntohl(argv->upbound)); rcu_read_unlock(); @@ -941,8 +957,10 @@ struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space) return buf; } -int tipc_nametbl_init(void) +int tipc_nametbl_init(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct name_table *tipc_nametbl; int i; tipc_nametbl = kzalloc(sizeof(*tipc_nametbl), GFP_ATOMIC); @@ -955,6 +973,8 @@ int tipc_nametbl_init(void) INIT_LIST_HEAD(&tipc_nametbl->publ_list[TIPC_ZONE_SCOPE]); INIT_LIST_HEAD(&tipc_nametbl->publ_list[TIPC_CLUSTER_SCOPE]); INIT_LIST_HEAD(&tipc_nametbl->publ_list[TIPC_NODE_SCOPE]); + tn->nametbl = tipc_nametbl; + spin_lock_init(&tn->nametbl_lock); return 0; } @@ -963,7 +983,7 @@ int tipc_nametbl_init(void) * * tipc_nametbl_lock must be held when calling this function */ -static void tipc_purge_publications(struct name_seq *seq) +static void tipc_purge_publications(struct net *net, struct name_seq *seq) { struct publication *publ, *safe; struct sub_seq *sseq; @@ -973,8 +993,8 @@ static void tipc_purge_publications(struct name_seq *seq) sseq = seq->sseqs; info = sseq->info; list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) { - tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node, - publ->ref, publ->key); + tipc_nametbl_remove_publ(net, publ->type, publ->lower, + publ->node, publ->ref, publ->key); kfree_rcu(publ, rcu); } hlist_del_init_rcu(&seq->ns_list); @@ -984,25 +1004,27 @@ static void tipc_purge_publications(struct name_seq *seq) kfree_rcu(seq, rcu); } -void tipc_nametbl_stop(void) +void tipc_nametbl_stop(struct net *net) { u32 i; struct name_seq *seq; struct hlist_head *seq_head; + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct name_table *tipc_nametbl = tn->nametbl; /* Verify name table is empty and purge any lingering * publications, then release the name table */ - spin_lock_bh(&tipc_nametbl_lock); + spin_lock_bh(&tn->nametbl_lock); for (i = 0; i < TIPC_NAMETBL_SIZE; i++) { if (hlist_empty(&tipc_nametbl->seq_hlist[i])) continue; seq_head = &tipc_nametbl->seq_hlist[i]; hlist_for_each_entry_rcu(seq, seq_head, ns_list) { - tipc_purge_publications(seq); + tipc_purge_publications(net, seq); } } - spin_unlock_bh(&tipc_nametbl_lock); + spin_unlock_bh(&tn->nametbl_lock); synchronize_net(); kfree(tipc_nametbl); @@ -1106,9 +1128,10 @@ static int __tipc_nl_subseq_list(struct tipc_nl_msg *msg, struct name_seq *seq, return 0; } -static int __tipc_nl_seq_list(struct tipc_nl_msg *msg, u32 *last_type, - u32 *last_lower, u32 *last_publ) +static int tipc_nl_seq_list(struct net *net, struct tipc_nl_msg *msg, + u32 *last_type, u32 *last_lower, u32 *last_publ) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct hlist_head *seq_head; struct name_seq *seq = NULL; int err; @@ -1120,10 +1143,10 @@ static int __tipc_nl_seq_list(struct tipc_nl_msg *msg, u32 *last_type, i = 0; for (; i < TIPC_NAMETBL_SIZE; i++) { - seq_head = &tipc_nametbl->seq_hlist[i]; + seq_head = &tn->nametbl->seq_hlist[i]; if (*last_type) { - seq = nametbl_find_seq(*last_type); + seq = nametbl_find_seq(net, *last_type); if (!seq) return -EPIPE; } else { @@ -1157,6 +1180,7 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) u32 last_type = cb->args[0]; u32 last_lower = cb->args[1]; u32 last_publ = cb->args[2]; + struct net *net = sock_net(skb->sk); struct tipc_nl_msg msg; if (done) @@ -1167,7 +1191,7 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) msg.seq = cb->nlh->nlmsg_seq; rcu_read_lock(); - err = __tipc_nl_seq_list(&msg, &last_type, &last_lower, &last_publ); + err = tipc_nl_seq_list(net, &msg, &last_type, &last_lower, &last_publ); if (!err) { done = 1; } else if (err != -EMSGSIZE) { diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 5f0dee92010d..f67b3d8d4b2f 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -95,26 +95,27 @@ struct name_table { u32 local_publ_count; }; -extern spinlock_t tipc_nametbl_lock; -extern struct name_table *tipc_nametbl; - int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb); -struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space); -u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *node); -int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit, - struct tipc_port_list *dports); -struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper, - u32 scope, u32 port_ref, u32 key); -int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key); -struct publication *tipc_nametbl_insert_publ(u32 type, u32 lower, u32 upper, - u32 scope, u32 node, u32 ref, +struct sk_buff *tipc_nametbl_get(struct net *net, const void *req_tlv_area, + int req_tlv_space); +u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *node); +int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, + u32 limit, struct tipc_port_list *dports); +struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower, + u32 upper, u32 scope, u32 port_ref, + u32 key); +int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 ref, + u32 key); +struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type, + u32 lower, u32 upper, u32 scope, + u32 node, u32 ref, u32 key); +struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, + u32 lower, u32 node, u32 ref, u32 key); -struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, u32 node, - u32 ref, u32 key); void tipc_nametbl_subscribe(struct tipc_subscription *s); void tipc_nametbl_unsubscribe(struct tipc_subscription *s); -int tipc_nametbl_init(void); -void tipc_nametbl_stop(void); +int tipc_nametbl_init(struct net *net); +void tipc_nametbl_stop(struct net *net); #endif diff --git a/net/tipc/net.c b/net/tipc/net.c index cf13df3cde8f..263267e0e7fe 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -41,6 +41,7 @@ #include "socket.h" #include "node.h" #include "config.h" +#include "bcast.h" static const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = { [TIPC_NLA_NET_UNSPEC] = { .type = NLA_UNSPEC }, @@ -108,44 +109,50 @@ static const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = { * - A local spin_lock protecting the queue of subscriber events. */ -int tipc_net_start(u32 addr) +int tipc_net_start(struct net *net, u32 addr) { + struct tipc_net *tn = net_generic(net, tipc_net_id); char addr_string[16]; int res; - tipc_own_addr = addr; - tipc_named_reinit(); - tipc_sk_reinit(); - res = tipc_bclink_init(); + tn->own_addr = addr; + tipc_named_reinit(net); + tipc_sk_reinit(net); + res = tipc_bclink_init(net); if (res) return res; - tipc_nametbl_publish(TIPC_CFG_SRV, tipc_own_addr, tipc_own_addr, - TIPC_ZONE_SCOPE, 0, tipc_own_addr); + tipc_nametbl_publish(net, TIPC_CFG_SRV, tn->own_addr, tn->own_addr, + TIPC_ZONE_SCOPE, 0, tn->own_addr); pr_info("Started in network mode\n"); pr_info("Own node address %s, network identity %u\n", - tipc_addr_string_fill(addr_string, tipc_own_addr), tipc_net_id); + tipc_addr_string_fill(addr_string, tn->own_addr), + tn->net_id); return 0; } -void tipc_net_stop(void) +void tipc_net_stop(struct net *net) { - if (!tipc_own_addr) + struct tipc_net *tn = net_generic(net, tipc_net_id); + + if (!tn->own_addr) return; - tipc_nametbl_withdraw(TIPC_CFG_SRV, tipc_own_addr, 0, tipc_own_addr); + tipc_nametbl_withdraw(net, TIPC_CFG_SRV, tn->own_addr, 0, + tn->own_addr); rtnl_lock(); - tipc_bearer_stop(); - tipc_bclink_stop(); - tipc_node_stop(); + tipc_bearer_stop(net); + tipc_bclink_stop(net); + tipc_node_stop(net); rtnl_unlock(); pr_info("Left network mode\n"); } -static int __tipc_nl_add_net(struct tipc_nl_msg *msg) +static int __tipc_nl_add_net(struct net *net, struct tipc_nl_msg *msg) { + struct tipc_net *tn = net_generic(net, tipc_net_id); void *hdr; struct nlattr *attrs; @@ -158,7 +165,7 @@ static int __tipc_nl_add_net(struct tipc_nl_msg *msg) if (!attrs) goto msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_NET_ID, tipc_net_id)) + if (nla_put_u32(msg->skb, TIPC_NLA_NET_ID, tn->net_id)) goto attr_msg_full; nla_nest_end(msg->skb, attrs); @@ -176,6 +183,7 @@ msg_full: int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); int err; int done = cb->args[0]; struct tipc_nl_msg msg; @@ -187,7 +195,7 @@ int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb) msg.portid = NETLINK_CB(cb->skb).portid; msg.seq = cb->nlh->nlmsg_seq; - err = __tipc_nl_add_net(&msg); + err = __tipc_nl_add_net(net, &msg); if (err) goto out; @@ -200,8 +208,10 @@ out: int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) { - int err; + struct net *net = genl_info_net(info); + struct tipc_net *tn = net_generic(net, tipc_net_id); struct nlattr *attrs[TIPC_NLA_NET_MAX + 1]; + int err; if (!info->attrs[TIPC_NLA_NET]) return -EINVAL; @@ -216,21 +226,21 @@ int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) u32 val; /* Can't change net id once TIPC has joined a network */ - if (tipc_own_addr) + if (tn->own_addr) return -EPERM; val = nla_get_u32(attrs[TIPC_NLA_NET_ID]); if (val < 1 || val > 9999) return -EINVAL; - tipc_net_id = val; + tn->net_id = val; } if (attrs[TIPC_NLA_NET_ADDR]) { u32 addr; /* Can't change net addr once TIPC has joined a network */ - if (tipc_own_addr) + if (tn->own_addr) return -EPERM; addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]); @@ -238,7 +248,7 @@ int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) return -EINVAL; rtnl_lock(); - tipc_net_start(addr); + tipc_net_start(net, addr); rtnl_unlock(); } diff --git a/net/tipc/net.h b/net/tipc/net.h index a81c1b9eb150..77a7a118911d 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -39,9 +39,9 @@ #include <net/genetlink.h> -int tipc_net_start(u32 addr); +int tipc_net_start(struct net *net, u32 addr); -void tipc_net_stop(void); +void tipc_net_stop(struct net *net); int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info); diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index b891e3905bc4..fe0f5134ce15 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -46,6 +46,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info) { + struct net *net = genl_info_net(info); struct sk_buff *rep_buf; struct nlmsghdr *rep_nlh; struct nlmsghdr *req_nlh = info->nlhdr; @@ -53,22 +54,24 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info) int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN); u16 cmd; - if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN))) + if ((req_userhdr->cmd & 0xC000) && + (!netlink_net_capable(skb, CAP_NET_ADMIN))) cmd = TIPC_CMD_NOT_NET_ADMIN; else cmd = req_userhdr->cmd; - rep_buf = tipc_cfg_do_cmd(req_userhdr->dest, cmd, - nlmsg_data(req_nlh) + GENL_HDRLEN + TIPC_GENL_HDRLEN, - nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN), - hdr_space); + rep_buf = tipc_cfg_do_cmd(net, req_userhdr->dest, cmd, + nlmsg_data(req_nlh) + GENL_HDRLEN + + TIPC_GENL_HDRLEN, + nlmsg_attrlen(req_nlh, GENL_HDRLEN + + TIPC_GENL_HDRLEN), hdr_space); if (rep_buf) { skb_push(rep_buf, hdr_space); rep_nlh = nlmsg_hdr(rep_buf); memcpy(rep_nlh, req_nlh, hdr_space); rep_nlh->nlmsg_len = rep_buf->len; - genlmsg_unicast(&init_net, rep_buf, NETLINK_CB(skb).portid); + genlmsg_unicast(net, rep_buf, NETLINK_CB(skb).portid); } return 0; @@ -93,6 +96,7 @@ static struct genl_family tipc_genl_family = { .version = TIPC_GENL_VERSION, .hdrsize = TIPC_GENL_HDRLEN, .maxattr = 0, + .netnsok = true, }; /* Legacy ASCII API */ @@ -112,6 +116,7 @@ struct genl_family tipc_genl_v2_family = { .version = TIPC_GENL_V2_VERSION, .hdrsize = 0, .maxattr = TIPC_NLA_MAX, + .netnsok = true, }; static const struct genl_ops tipc_genl_v2_ops[] = { diff --git a/net/tipc/netlink.h b/net/tipc/netlink.h index 1425c6869de0..ae2f2d923a15 100644 --- a/net/tipc/netlink.h +++ b/net/tipc/netlink.h @@ -45,4 +45,7 @@ struct tipc_nl_msg { u32 seq; }; +int tipc_netlink_start(void); +void tipc_netlink_stop(void); + #endif diff --git a/net/tipc/node.c b/net/tipc/node.c index 8d353ec77a66..b1eb0927bac8 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -40,17 +40,9 @@ #include "name_distr.h" #include "socket.h" -#define NODE_HTABLE_SIZE 512 - static void node_lost_contact(struct tipc_node *n_ptr); static void node_established_contact(struct tipc_node *n_ptr); -static struct hlist_head node_htable[NODE_HTABLE_SIZE]; -LIST_HEAD(tipc_node_list); -static u32 tipc_num_nodes; -static u32 tipc_num_links; -static DEFINE_SPINLOCK(node_list_lock); - struct tipc_sock_conn { u32 port; u32 peer_port; @@ -78,15 +70,17 @@ static unsigned int tipc_hashfn(u32 addr) /* * tipc_node_find - locate specified node object, if it exists */ -struct tipc_node *tipc_node_find(u32 addr) +struct tipc_node *tipc_node_find(struct net *net, u32 addr) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *node; - if (unlikely(!in_own_cluster_exact(addr))) + if (unlikely(!in_own_cluster_exact(net, addr))) return NULL; rcu_read_lock(); - hlist_for_each_entry_rcu(node, &node_htable[tipc_hashfn(addr)], hash) { + hlist_for_each_entry_rcu(node, &tn->node_htable[tipc_hashfn(addr)], + hash) { if (node->addr == addr) { rcu_read_unlock(); return node; @@ -96,20 +90,22 @@ struct tipc_node *tipc_node_find(u32 addr) return NULL; } -struct tipc_node *tipc_node_create(u32 addr) +struct tipc_node *tipc_node_create(struct net *net, u32 addr) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *n_ptr, *temp_node; - spin_lock_bh(&node_list_lock); + spin_lock_bh(&tn->node_list_lock); n_ptr = kzalloc(sizeof(*n_ptr), GFP_ATOMIC); if (!n_ptr) { - spin_unlock_bh(&node_list_lock); + spin_unlock_bh(&tn->node_list_lock); pr_warn("Node creation failed, no memory\n"); return NULL; } n_ptr->addr = addr; + n_ptr->net = net; spin_lock_init(&n_ptr->lock); INIT_HLIST_NODE(&n_ptr->hash); INIT_LIST_HEAD(&n_ptr->list); @@ -118,9 +114,9 @@ struct tipc_node *tipc_node_create(u32 addr) skb_queue_head_init(&n_ptr->waiting_sks); __skb_queue_head_init(&n_ptr->bclink.deferred_queue); - hlist_add_head_rcu(&n_ptr->hash, &node_htable[tipc_hashfn(addr)]); + hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]); - list_for_each_entry_rcu(temp_node, &tipc_node_list, list) { + list_for_each_entry_rcu(temp_node, &tn->node_list, list) { if (n_ptr->addr < temp_node->addr) break; } @@ -128,40 +124,41 @@ struct tipc_node *tipc_node_create(u32 addr) n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN; n_ptr->signature = INVALID_NODE_SIG; - tipc_num_nodes++; + tn->num_nodes++; - spin_unlock_bh(&node_list_lock); + spin_unlock_bh(&tn->node_list_lock); return n_ptr; } -static void tipc_node_delete(struct tipc_node *n_ptr) +static void tipc_node_delete(struct tipc_net *tn, struct tipc_node *n_ptr) { list_del_rcu(&n_ptr->list); hlist_del_rcu(&n_ptr->hash); kfree_rcu(n_ptr, rcu); - tipc_num_nodes--; + tn->num_nodes--; } -void tipc_node_stop(void) +void tipc_node_stop(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *node, *t_node; - spin_lock_bh(&node_list_lock); - list_for_each_entry_safe(node, t_node, &tipc_node_list, list) - tipc_node_delete(node); - spin_unlock_bh(&node_list_lock); + spin_lock_bh(&tn->node_list_lock); + list_for_each_entry_safe(node, t_node, &tn->node_list, list) + tipc_node_delete(tn, node); + spin_unlock_bh(&tn->node_list_lock); } -int tipc_node_add_conn(u32 dnode, u32 port, u32 peer_port) +int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port) { struct tipc_node *node; struct tipc_sock_conn *conn; - if (in_own_node(dnode)) + if (in_own_node(net, dnode)) return 0; - node = tipc_node_find(dnode); + node = tipc_node_find(net, dnode); if (!node) { pr_warn("Connecting sock to node 0x%x failed\n", dnode); return -EHOSTUNREACH; @@ -179,15 +176,15 @@ int tipc_node_add_conn(u32 dnode, u32 port, u32 peer_port) return 0; } -void tipc_node_remove_conn(u32 dnode, u32 port) +void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) { struct tipc_node *node; struct tipc_sock_conn *conn, *safe; - if (in_own_node(dnode)) + if (in_own_node(net, dnode)) return; - node = tipc_node_find(dnode); + node = tipc_node_find(net, dnode); if (!node) return; @@ -201,18 +198,20 @@ void tipc_node_remove_conn(u32 dnode, u32 port) tipc_node_unlock(node); } -void tipc_node_abort_sock_conns(struct list_head *conns) +void tipc_node_abort_sock_conns(struct net *net, struct list_head *conns) { + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_sock_conn *conn, *safe; struct sk_buff *buf; list_for_each_entry_safe(conn, safe, conns, list) { - buf = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, - SHORT_H_SIZE, 0, tipc_own_addr, - conn->peer_node, conn->port, - conn->peer_port, TIPC_ERR_NO_NODE); + buf = tipc_msg_create(net, TIPC_CRITICAL_IMPORTANCE, + TIPC_CONN_MSG, SHORT_H_SIZE, 0, + tn->own_addr, conn->peer_node, + conn->port, conn->peer_port, + TIPC_ERR_NO_NODE); if (likely(buf)) - tipc_sk_rcv(buf); + tipc_sk_rcv(net, buf); list_del(&conn->list); kfree(conn); } @@ -290,6 +289,7 @@ static void node_select_active_links(struct tipc_node *n_ptr) */ void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr) { + struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); struct tipc_link **active; n_ptr->working_links--; @@ -324,7 +324,7 @@ void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr) } /* Loopback link went down? No fragmentation needed from now on. */ - if (n_ptr->addr == tipc_own_addr) { + if (n_ptr->addr == tn->own_addr) { n_ptr->act_mtus[0] = MAX_MSG_SIZE; n_ptr->act_mtus[1] = MAX_MSG_SIZE; } @@ -342,24 +342,27 @@ int tipc_node_is_up(struct tipc_node *n_ptr) void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) { + struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); + n_ptr->links[l_ptr->bearer_id] = l_ptr; - spin_lock_bh(&node_list_lock); - tipc_num_links++; - spin_unlock_bh(&node_list_lock); + spin_lock_bh(&tn->node_list_lock); + tn->num_links++; + spin_unlock_bh(&tn->node_list_lock); n_ptr->link_cnt++; } void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) { + struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); int i; for (i = 0; i < MAX_BEARERS; i++) { if (l_ptr != n_ptr->links[i]) continue; n_ptr->links[i] = NULL; - spin_lock_bh(&node_list_lock); - tipc_num_links--; - spin_unlock_bh(&node_list_lock); + spin_lock_bh(&tn->node_list_lock); + tn->num_links--; + spin_unlock_bh(&tn->node_list_lock); n_ptr->link_cnt--; } } @@ -368,8 +371,8 @@ static void node_established_contact(struct tipc_node *n_ptr) { n_ptr->action_flags |= TIPC_NOTIFY_NODE_UP; n_ptr->bclink.oos_state = 0; - n_ptr->bclink.acked = tipc_bclink_get_last_sent(); - tipc_bclink_add_node(n_ptr->addr); + n_ptr->bclink.acked = tipc_bclink_get_last_sent(n_ptr->net); + tipc_bclink_add_node(n_ptr->net, n_ptr->addr); } static void node_lost_contact(struct tipc_node *n_ptr) @@ -389,7 +392,7 @@ static void node_lost_contact(struct tipc_node *n_ptr) n_ptr->bclink.reasm_buf = NULL; } - tipc_bclink_remove_node(n_ptr->addr); + tipc_bclink_remove_node(n_ptr->net, n_ptr->addr); tipc_bclink_acknowledge(n_ptr, INVALID_LINK_SEQ); n_ptr->bclink.recv_permitted = false; @@ -414,8 +417,10 @@ static void node_lost_contact(struct tipc_node *n_ptr) TIPC_NOTIFY_NODE_DOWN; } -struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) +struct sk_buff *tipc_node_get_nodes(struct net *net, const void *req_tlv_area, + int req_tlv_space) { + struct tipc_net *tn = net_generic(net, tipc_net_id); u32 domain; struct sk_buff *buf; struct tipc_node *n_ptr; @@ -430,20 +435,20 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (network address)"); - spin_lock_bh(&node_list_lock); - if (!tipc_num_nodes) { - spin_unlock_bh(&node_list_lock); + spin_lock_bh(&tn->node_list_lock); + if (!tn->num_nodes) { + spin_unlock_bh(&tn->node_list_lock); return tipc_cfg_reply_none(); } /* For now, get space for all other nodes */ - payload_size = TLV_SPACE(sizeof(node_info)) * tipc_num_nodes; + payload_size = TLV_SPACE(sizeof(node_info)) * tn->num_nodes; if (payload_size > 32768u) { - spin_unlock_bh(&node_list_lock); + spin_unlock_bh(&tn->node_list_lock); return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (too many nodes)"); } - spin_unlock_bh(&node_list_lock); + spin_unlock_bh(&tn->node_list_lock); buf = tipc_cfg_reply_alloc(payload_size); if (!buf) @@ -451,7 +456,7 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) /* Add TLVs for all nodes in scope */ rcu_read_lock(); - list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { + list_for_each_entry_rcu(n_ptr, &tn->node_list, list) { if (!tipc_in_scope(domain, n_ptr->addr)) continue; node_info.addr = htonl(n_ptr->addr); @@ -463,8 +468,10 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) return buf; } -struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) +struct sk_buff *tipc_node_get_links(struct net *net, const void *req_tlv_area, + int req_tlv_space) { + struct tipc_net *tn = net_generic(net, tipc_net_id); u32 domain; struct sk_buff *buf; struct tipc_node *n_ptr; @@ -479,32 +486,32 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (network address)"); - if (!tipc_own_addr) + if (!tn->own_addr) return tipc_cfg_reply_none(); - spin_lock_bh(&node_list_lock); + spin_lock_bh(&tn->node_list_lock); /* Get space for all unicast links + broadcast link */ - payload_size = TLV_SPACE((sizeof(link_info)) * (tipc_num_links + 1)); + payload_size = TLV_SPACE((sizeof(link_info)) * (tn->num_links + 1)); if (payload_size > 32768u) { - spin_unlock_bh(&node_list_lock); + spin_unlock_bh(&tn->node_list_lock); return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (too many links)"); } - spin_unlock_bh(&node_list_lock); + spin_unlock_bh(&tn->node_list_lock); buf = tipc_cfg_reply_alloc(payload_size); if (!buf) return NULL; /* Add TLV for broadcast link */ - link_info.dest = htonl(tipc_cluster_mask(tipc_own_addr)); + link_info.dest = htonl(tipc_cluster_mask(tn->own_addr)); link_info.up = htonl(1); strlcpy(link_info.str, tipc_bclink_name, TIPC_MAX_LINK_NAME); tipc_cfg_append_tlv(buf, TIPC_TLV_LINK_INFO, &link_info, sizeof(link_info)); /* Add TLVs for any other links in scope */ rcu_read_lock(); - list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { + list_for_each_entry_rcu(n_ptr, &tn->node_list, list) { u32 i; if (!tipc_in_scope(domain, n_ptr->addr)) @@ -534,10 +541,11 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) * * Returns 0 on success */ -int tipc_node_get_linkname(u32 bearer_id, u32 addr, char *linkname, size_t len) +int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr, + char *linkname, size_t len) { struct tipc_link *link; - struct tipc_node *node = tipc_node_find(addr); + struct tipc_node *node = tipc_node_find(net, addr); if ((bearer_id >= MAX_BEARERS) || !node) return -EINVAL; @@ -554,6 +562,7 @@ int tipc_node_get_linkname(u32 bearer_id, u32 addr, char *linkname, size_t len) void tipc_node_unlock(struct tipc_node *node) { + struct net *net = node->net; LIST_HEAD(nsub_list); LIST_HEAD(conn_sks); struct sk_buff_head waiting_sks; @@ -585,26 +594,26 @@ void tipc_node_unlock(struct tipc_node *node) spin_unlock_bh(&node->lock); while (!skb_queue_empty(&waiting_sks)) - tipc_sk_rcv(__skb_dequeue(&waiting_sks)); + tipc_sk_rcv(net, __skb_dequeue(&waiting_sks)); if (!list_empty(&conn_sks)) - tipc_node_abort_sock_conns(&conn_sks); + tipc_node_abort_sock_conns(net, &conn_sks); if (!list_empty(&nsub_list)) - tipc_publ_notify(&nsub_list, addr); + tipc_publ_notify(net, &nsub_list, addr); if (flags & TIPC_WAKEUP_BCAST_USERS) - tipc_bclink_wakeup_users(); + tipc_bclink_wakeup_users(net); if (flags & TIPC_NOTIFY_NODE_UP) - tipc_named_node_up(addr); + tipc_named_node_up(net, addr); if (flags & TIPC_NOTIFY_LINK_UP) - tipc_nametbl_publish(TIPC_LINK_STATE, addr, addr, + tipc_nametbl_publish(net, TIPC_LINK_STATE, addr, addr, TIPC_NODE_SCOPE, link_id, addr); if (flags & TIPC_NOTIFY_LINK_DOWN) - tipc_nametbl_withdraw(TIPC_LINK_STATE, addr, + tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr, link_id, addr); } @@ -645,6 +654,8 @@ msg_full: int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; + struct net *net = sock_net(skb->sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); int done = cb->args[0]; int last_addr = cb->args[1]; struct tipc_node *node; @@ -659,7 +670,7 @@ int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); - if (last_addr && !tipc_node_find(last_addr)) { + if (last_addr && !tipc_node_find(net, last_addr)) { rcu_read_unlock(); /* We never set seq or call nl_dump_check_consistent() this * means that setting prev_seq here will cause the consistence @@ -671,7 +682,7 @@ int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb) return -EPIPE; } - list_for_each_entry_rcu(node, &tipc_node_list, list) { + list_for_each_entry_rcu(node, &tn->node_list, list) { if (last_addr) { if (node->addr == last_addr) last_addr = 0; diff --git a/net/tipc/node.h b/net/tipc/node.h index cbe0e950f1cc..43ef88ef3035 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -42,10 +42,10 @@ #include "bearer.h" #include "msg.h" -/* - * Out-of-range value for node signature - */ -#define INVALID_NODE_SIG 0x10000 +/* Out-of-range value for node signature */ +#define INVALID_NODE_SIG 0x10000 + +#define NODE_HTABLE_SIZE 512 /* Flags used to take different actions according to flag type * TIPC_WAIT_PEER_LINKS_DOWN: wait to see that peer's links are down @@ -90,6 +90,7 @@ struct tipc_node_bclink { * struct tipc_node - TIPC node structure * @addr: network address of node * @lock: spinlock governing access to structure + * @net: the applicable net namespace * @hash: links to adjacent nodes in unsorted hash chain * @active_links: pointers to active links to node * @links: pointers to all links to node @@ -106,6 +107,7 @@ struct tipc_node_bclink { struct tipc_node { u32 addr; spinlock_t lock; + struct net *net; struct hlist_node hash; struct tipc_link *active_links[2]; u32 act_mtus[2]; @@ -123,23 +125,24 @@ struct tipc_node { struct rcu_head rcu; }; -extern struct list_head tipc_node_list; - -struct tipc_node *tipc_node_find(u32 addr); -struct tipc_node *tipc_node_create(u32 addr); -void tipc_node_stop(void); +struct tipc_node *tipc_node_find(struct net *net, u32 addr); +struct tipc_node *tipc_node_create(struct net *net, u32 addr); +void tipc_node_stop(struct net *net); void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr); void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr); int tipc_node_active_links(struct tipc_node *n_ptr); int tipc_node_is_up(struct tipc_node *n_ptr); -struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space); -struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space); -int tipc_node_get_linkname(u32 bearer_id, u32 node, char *linkname, size_t len); +struct sk_buff *tipc_node_get_links(struct net *net, const void *req_tlv_area, + int req_tlv_space); +struct sk_buff *tipc_node_get_nodes(struct net *net, const void *req_tlv_area, + int req_tlv_space); +int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node, + char *linkname, size_t len); void tipc_node_unlock(struct tipc_node *node); -int tipc_node_add_conn(u32 dnode, u32 port, u32 peer_port); -void tipc_node_remove_conn(u32 dnode, u32 port); +int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port); +void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port); int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb); @@ -154,12 +157,12 @@ static inline bool tipc_node_blocked(struct tipc_node *node) TIPC_NOTIFY_NODE_DOWN | TIPC_WAIT_OWN_LINKS_DOWN)); } -static inline uint tipc_node_get_mtu(u32 addr, u32 selector) +static inline uint tipc_node_get_mtu(struct net *net, u32 addr, u32 selector) { struct tipc_node *node; u32 mtu; - node = tipc_node_find(addr); + node = tipc_node_find(net, addr); if (likely(node)) mtu = node->act_mtus[selector & 1]; diff --git a/net/tipc/server.c b/net/tipc/server.c index a538a02f869b..eadd4ed45905 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -35,6 +35,7 @@ #include "server.h" #include "core.h" +#include "socket.h" #include <net/sock.h> /* Number of messages to send before rescheduling */ @@ -255,7 +256,8 @@ static int tipc_receive_from_sock(struct tipc_conn *con) goto out_close; } - s->tipc_conn_recvmsg(con->conid, &addr, con->usr_data, buf, ret); + s->tipc_conn_recvmsg(sock_net(con->sock->sk), con->conid, &addr, + con->usr_data, buf, ret); kmem_cache_free(s->rcvbuf_cache, buf); @@ -307,7 +309,7 @@ static struct socket *tipc_create_listen_sock(struct tipc_conn *con) struct socket *sock = NULL; int ret; - ret = tipc_sock_create_local(s->type, &sock); + ret = tipc_sock_create_local(s->net, s->type, &sock); if (ret < 0) return NULL; ret = kernel_setsockopt(sock, SOL_TIPC, TIPC_IMPORTANCE, diff --git a/net/tipc/server.h b/net/tipc/server.h index be817b0b547e..9015faedb1b0 100644 --- a/net/tipc/server.h +++ b/net/tipc/server.h @@ -36,7 +36,9 @@ #ifndef _TIPC_SERVER_H #define _TIPC_SERVER_H -#include "core.h" +#include <linux/idr.h> +#include <linux/tipc.h> +#include <net/net_namespace.h> #define TIPC_SERVER_NAME_LEN 32 @@ -45,6 +47,7 @@ * @conn_idr: identifier set of connection * @idr_lock: protect the connection identifier set * @idr_in_use: amount of allocated identifier entry + * @net: network namspace instance * @rcvbuf_cache: memory cache of server receive buffer * @rcv_wq: receive workqueue * @send_wq: send workqueue @@ -61,16 +64,18 @@ struct tipc_server { struct idr conn_idr; spinlock_t idr_lock; int idr_in_use; + struct net *net; struct kmem_cache *rcvbuf_cache; struct workqueue_struct *rcv_wq; struct workqueue_struct *send_wq; int max_rcvbuf_size; - void *(*tipc_conn_new) (int conid); - void (*tipc_conn_shutdown) (int conid, void *usr_data); - void (*tipc_conn_recvmsg) (int conid, struct sockaddr_tipc *addr, - void *usr_data, void *buf, size_t len); + void *(*tipc_conn_new)(int conid); + void (*tipc_conn_shutdown)(int conid, void *usr_data); + void (*tipc_conn_recvmsg)(struct net *net, int conid, + struct sockaddr_tipc *addr, void *usr_data, + void *buf, size_t len); struct sockaddr_tipc *saddr; - const char name[TIPC_SERVER_NAME_LEN]; + char name[TIPC_SERVER_NAME_LEN]; int imp; int type; }; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 4731cad99d1c..720fda6cc2e6 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -34,22 +34,25 @@ * POSSIBILITY OF SUCH DAMAGE. */ +#include <linux/rhashtable.h> +#include <linux/jhash.h> #include "core.h" #include "name_table.h" #include "node.h" #include "link.h" -#include <linux/export.h> #include "config.h" #include "socket.h" -#define SS_LISTENING -1 /* socket is listening */ -#define SS_READY -2 /* socket is connectionless */ +#define SS_LISTENING -1 /* socket is listening */ +#define SS_READY -2 /* socket is connectionless */ -#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ -#define CONN_PROBING_INTERVAL 3600000 /* [ms] => 1 h */ -#define TIPC_FWD_MSG 1 -#define TIPC_CONN_OK 0 -#define TIPC_CONN_PROBING 1 +#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ +#define CONN_PROBING_INTERVAL msecs_to_jiffies(3600000) /* [ms] => 1 h */ +#define TIPC_FWD_MSG 1 +#define TIPC_CONN_OK 0 +#define TIPC_CONN_PROBING 1 +#define TIPC_MAX_PORT 0xffffffff +#define TIPC_MIN_PORT 1 /** * struct tipc_sock - TIPC socket structure @@ -59,14 +62,13 @@ * @conn_instance: TIPC instance used when connection was established * @published: non-zero if port has one or more associated names * @max_pkt: maximum packet size "hint" used when building messages sent by port - * @ref: unique reference to port in TIPC object registry + * @portid: unique port identity in TIPC socket hash table * @phdr: preformatted message header used when sending messages * @port_list: adjacent ports in TIPC's global list of ports * @publications: list of publications for port * @pub_count: total # of publications port has made during its lifetime * @probing_state: - * @probing_interval: - * @timer: + * @probing_intv: * @port: port - interacts with 'sk' and with the rest of the TIPC stack * @peer_name: the peer of the connection, if any * @conn_timeout: the time we can wait for an unresponded setup request @@ -74,6 +76,8 @@ * @link_cong: non-zero if owner must sleep because of link congestion * @sent_unacked: # messages sent by socket, and not yet acked by peer * @rcv_unacked: # messages read by user, but not yet acked back to peer + * @node: hash table node + * @rcu: rcu struct for tipc_sock */ struct tipc_sock { struct sock sk; @@ -82,19 +86,20 @@ struct tipc_sock { u32 conn_instance; int published; u32 max_pkt; - u32 ref; + u32 portid; struct tipc_msg phdr; struct list_head sock_list; struct list_head publications; u32 pub_count; u32 probing_state; - u32 probing_interval; - struct timer_list timer; + unsigned long probing_intv; uint conn_timeout; atomic_t dupl_rcvcnt; bool link_cong; uint sent_unacked; uint rcv_unacked; + struct rhash_head node; + struct rcu_head rcu; }; static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb); @@ -103,16 +108,14 @@ static void tipc_write_space(struct sock *sk); static int tipc_release(struct socket *sock); static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags); static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p); -static void tipc_sk_timeout(unsigned long ref); +static void tipc_sk_timeout(unsigned long data); static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); -static u32 tipc_sk_ref_acquire(struct tipc_sock *tsk); -static void tipc_sk_ref_discard(u32 ref); -static struct tipc_sock *tipc_sk_get(u32 ref); -static struct tipc_sock *tipc_sk_get_next(u32 *ref); -static void tipc_sk_put(struct tipc_sock *tsk); +static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid); +static int tipc_sk_insert(struct tipc_sock *tsk); +static void tipc_sk_remove(struct tipc_sock *tsk); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; @@ -246,10 +249,11 @@ static void tsk_rej_rx_queue(struct sock *sk) { struct sk_buff *skb; u32 dnode; + struct net *net = sock_net(sk); while ((skb = __skb_dequeue(&sk->sk_receive_queue))) { - if (tipc_msg_reverse(skb, &dnode, TIPC_ERR_NO_PORT)) - tipc_link_xmit_skb(skb, dnode, 0); + if (tipc_msg_reverse(net, skb, &dnode, TIPC_ERR_NO_PORT)) + tipc_link_xmit_skb(net, skb, dnode, 0); } } @@ -260,6 +264,7 @@ static void tsk_rej_rx_queue(struct sock *sk) */ static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg) { + struct tipc_net *tn = net_generic(sock_net(&tsk->sk), tipc_net_id); u32 peer_port = tsk_peer_port(tsk); u32 orig_node; u32 peer_node; @@ -276,10 +281,10 @@ static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg) if (likely(orig_node == peer_node)) return true; - if (!orig_node && (peer_node == tipc_own_addr)) + if (!orig_node && (peer_node == tn->own_addr)) return true; - if (!peer_node && (orig_node == tipc_own_addr)) + if (!peer_node && (orig_node == tn->own_addr)) return true; return false; @@ -305,7 +310,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock, struct sock *sk; struct tipc_sock *tsk; struct tipc_msg *msg; - u32 ref; /* Validate arguments */ if (unlikely(protocol != 0)) @@ -339,24 +343,22 @@ static int tipc_sk_create(struct net *net, struct socket *sock, return -ENOMEM; tsk = tipc_sk(sk); - ref = tipc_sk_ref_acquire(tsk); - if (!ref) { - pr_warn("Socket create failed; reference table exhausted\n"); - return -ENOMEM; - } tsk->max_pkt = MAX_PKT_DEFAULT; - tsk->ref = ref; INIT_LIST_HEAD(&tsk->publications); msg = &tsk->phdr; - tipc_msg_init(msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG, + tipc_msg_init(net, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG, NAMED_H_SIZE, 0); - msg_set_origport(msg, ref); /* Finish initializing socket data structures */ sock->ops = ops; sock->state = state; sock_init_data(sock, sk); - k_init_timer(&tsk->timer, (Handler)tipc_sk_timeout, ref); + if (tipc_sk_insert(tsk)) { + pr_warn("Socket create failed; port numbrer exhausted\n"); + return -EINVAL; + } + msg_set_origport(msg, tsk->portid); + setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk); sk->sk_backlog_rcv = tipc_backlog_rcv; sk->sk_rcvbuf = sysctl_tipc_rmem[1]; sk->sk_data_ready = tipc_data_ready; @@ -384,7 +386,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, * * Returns 0 on success, errno otherwise */ -int tipc_sock_create_local(int type, struct socket **res) +int tipc_sock_create_local(struct net *net, int type, struct socket **res) { int rc; @@ -393,7 +395,7 @@ int tipc_sock_create_local(int type, struct socket **res) pr_err("Failed to create kernel socket\n"); return rc; } - tipc_sk_create(&init_net, *res, 0, 1); + tipc_sk_create(net, *res, 0, 1); return 0; } @@ -442,6 +444,13 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, return ret; } +static void tipc_sk_callback(struct rcu_head *head) +{ + struct tipc_sock *tsk = container_of(head, struct tipc_sock, rcu); + + sock_put(&tsk->sk); +} + /** * tipc_release - destroy a TIPC socket * @sock: socket to destroy @@ -461,9 +470,11 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, static int tipc_release(struct socket *sock) { struct sock *sk = sock->sk; + struct net *net; + struct tipc_net *tn; struct tipc_sock *tsk; struct sk_buff *skb; - u32 dnode; + u32 dnode, probing_state; /* * Exit if socket isn't fully initialized (occurs when a failed accept() @@ -472,6 +483,9 @@ static int tipc_release(struct socket *sock) if (sk == NULL) return 0; + net = sock_net(sk); + tn = net_generic(net, tipc_net_id); + tsk = tipc_sk(sk); lock_sock(sk); @@ -491,26 +505,29 @@ static int tipc_release(struct socket *sock) (sock->state == SS_CONNECTED)) { sock->state = SS_DISCONNECTING; tsk->connected = 0; - tipc_node_remove_conn(dnode, tsk->ref); + tipc_node_remove_conn(net, dnode, tsk->portid); } - if (tipc_msg_reverse(skb, &dnode, TIPC_ERR_NO_PORT)) - tipc_link_xmit_skb(skb, dnode, 0); + if (tipc_msg_reverse(net, skb, &dnode, + TIPC_ERR_NO_PORT)) + tipc_link_xmit_skb(net, skb, dnode, 0); } } tipc_sk_withdraw(tsk, 0, NULL); - tipc_sk_ref_discard(tsk->ref); - k_cancel_timer(&tsk->timer); + probing_state = tsk->probing_state; + if (del_timer_sync(&sk->sk_timer) && + probing_state != TIPC_CONN_PROBING) + sock_put(sk); + tipc_sk_remove(tsk); if (tsk->connected) { - skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, - SHORT_H_SIZE, 0, dnode, tipc_own_addr, - tsk_peer_port(tsk), - tsk->ref, TIPC_ERR_NO_PORT); + skb = tipc_msg_create(net, TIPC_CRITICAL_IMPORTANCE, + TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode, + tn->own_addr, tsk_peer_port(tsk), + tsk->portid, TIPC_ERR_NO_PORT); if (skb) - tipc_link_xmit_skb(skb, dnode, tsk->ref); - tipc_node_remove_conn(dnode, tsk->ref); + tipc_link_xmit_skb(net, skb, dnode, tsk->portid); + tipc_node_remove_conn(net, dnode, tsk->portid); } - k_term_timer(&tsk->timer); /* Discard any remaining (connection-based) messages in receive queue */ __skb_queue_purge(&sk->sk_receive_queue); @@ -518,7 +535,8 @@ static int tipc_release(struct socket *sock) /* Reject any messages that accumulated in backlog queue */ sock->state = SS_DISCONNECTING; release_sock(sk); - sock_put(sk); + + call_rcu(&tsk->rcu, tipc_sk_callback); sock->sk = NULL; return 0; @@ -602,6 +620,7 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr, { struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; struct tipc_sock *tsk = tipc_sk(sock->sk); + struct tipc_net *tn = net_generic(sock_net(sock->sk), tipc_net_id); memset(addr, 0, sizeof(*addr)); if (peer) { @@ -611,8 +630,8 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr, addr->addr.id.ref = tsk_peer_port(tsk); addr->addr.id.node = tsk_peer_node(tsk); } else { - addr->addr.id.ref = tsk->ref; - addr->addr.id.node = tipc_own_addr; + addr->addr.id.ref = tsk->portid; + addr->addr.id.node = tn->own_addr; } *uaddr_len = sizeof(*addr); @@ -711,6 +730,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct msghdr *msg, size_t dsz, long timeo) { struct sock *sk = sock->sk; + struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tipc_sk(sk)->phdr; struct sk_buff_head head; uint mtu; @@ -728,12 +748,12 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, new_mtu: mtu = tipc_bclink_get_mtu(); __skb_queue_head_init(&head); - rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, &head); + rc = tipc_msg_build(net, mhdr, msg, 0, dsz, mtu, &head); if (unlikely(rc < 0)) return rc; do { - rc = tipc_bclink_xmit(&head); + rc = tipc_bclink_xmit(net, &head); if (likely(rc >= 0)) { rc = dsz; break; @@ -752,7 +772,7 @@ new_mtu: /* tipc_sk_mcast_rcv - Deliver multicast message to all destination sockets */ -void tipc_sk_mcast_rcv(struct sk_buff *buf) +void tipc_sk_mcast_rcv(struct net *net, struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); struct tipc_port_list dports = {0, NULL, }; @@ -761,15 +781,12 @@ void tipc_sk_mcast_rcv(struct sk_buff *buf) uint i, last, dst = 0; u32 scope = TIPC_CLUSTER_SCOPE; - if (in_own_node(msg_orignode(msg))) + if (in_own_node(net, msg_orignode(msg))) scope = TIPC_NODE_SCOPE; /* Create destination port list: */ - tipc_nametbl_mc_translate(msg_nametype(msg), - msg_namelower(msg), - msg_nameupper(msg), - scope, - &dports); + tipc_nametbl_mc_translate(net, msg_nametype(msg), msg_namelower(msg), + msg_nameupper(msg), scope, &dports); last = dports.count; if (!last) { kfree_skb(buf); @@ -784,7 +801,7 @@ void tipc_sk_mcast_rcv(struct sk_buff *buf) continue; } msg_set_destport(msg, item->ports[i]); - tipc_sk_rcv(b); + tipc_sk_rcv(net, b); } } tipc_port_list_free(&dports); @@ -816,7 +833,7 @@ static int tipc_sk_proto_rcv(struct tipc_sock *tsk, u32 *dnode, if (conn_cong) tsk->sk.sk_write_space(&tsk->sk); } else if (msg_type(msg) == CONN_PROBE) { - if (!tipc_msg_reverse(buf, dnode, TIPC_OK)) + if (!tipc_msg_reverse(sock_net(&tsk->sk), buf, dnode, TIPC_OK)) return TIPC_OK; msg_set_type(msg, CONN_PROBE_REPLY); return TIPC_FWD_MSG; @@ -872,6 +889,7 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); + struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; u32 dnode, dport; struct sk_buff_head head; @@ -929,7 +947,7 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, msg_set_nametype(mhdr, type); msg_set_nameinst(mhdr, inst); msg_set_lookup_scope(mhdr, tipc_addr_scope(domain)); - dport = tipc_nametbl_translate(type, inst, &dnode); + dport = tipc_nametbl_translate(net, type, inst, &dnode); msg_set_destnode(mhdr, dnode); msg_set_destport(mhdr, dport); if (unlikely(!dport && !dnode)) { @@ -946,16 +964,16 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, } new_mtu: - mtu = tipc_node_get_mtu(dnode, tsk->ref); + mtu = tipc_node_get_mtu(net, dnode, tsk->portid); __skb_queue_head_init(&head); - rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, &head); + rc = tipc_msg_build(net, mhdr, m, 0, dsz, mtu, &head); if (rc < 0) goto exit; do { skb = skb_peek(&head); TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; - rc = tipc_link_xmit(&head, dnode, tsk->ref); + rc = tipc_link_xmit(net, &head, dnode, tsk->portid); if (likely(rc >= 0)) { if (sock->state != SS_READY) sock->state = SS_CONNECTING; @@ -1024,11 +1042,12 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t dsz) { struct sock *sk = sock->sk; + struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *mhdr = &tsk->phdr; struct sk_buff_head head; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); - u32 ref = tsk->ref; + u32 portid = tsk->portid; int rc = -EINVAL; long timeo; u32 dnode; @@ -1062,12 +1081,12 @@ next: mtu = tsk->max_pkt; send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE); __skb_queue_head_init(&head); - rc = tipc_msg_build(mhdr, m, sent, send, mtu, &head); + rc = tipc_msg_build(net, mhdr, m, sent, send, mtu, &head); if (unlikely(rc < 0)) goto exit; do { if (likely(!tsk_conn_cong(tsk))) { - rc = tipc_link_xmit(&head, dnode, ref); + rc = tipc_link_xmit(net, &head, dnode, portid); if (likely(!rc)) { tsk->sent_unacked++; sent += send; @@ -1076,7 +1095,8 @@ next: goto next; } if (rc == -EMSGSIZE) { - tsk->max_pkt = tipc_node_get_mtu(dnode, ref); + tsk->max_pkt = tipc_node_get_mtu(net, dnode, + portid); goto next; } if (rc != -ELINKCONG) @@ -1118,6 +1138,8 @@ static int tipc_send_packet(struct kiocb *iocb, struct socket *sock, static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port, u32 peer_node) { + struct sock *sk = &tsk->sk; + struct net *net = sock_net(sk); struct tipc_msg *msg = &tsk->phdr; msg_set_destnode(msg, peer_node); @@ -1126,12 +1148,12 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port, msg_set_lookup_scope(msg, 0); msg_set_hdr_sz(msg, SHORT_H_SIZE); - tsk->probing_interval = CONN_PROBING_INTERVAL; + tsk->probing_intv = CONN_PROBING_INTERVAL; tsk->probing_state = TIPC_CONN_OK; tsk->connected = 1; - k_start_timer(&tsk->timer, tsk->probing_interval); - tipc_node_add_conn(peer_node, tsk->ref, peer_port); - tsk->max_pkt = tipc_node_get_mtu(peer_node, tsk->ref); + sk_reset_timer(sk, &sk->sk_timer, jiffies + tsk->probing_intv); + tipc_node_add_conn(net, peer_node, tsk->portid, peer_port); + tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid); } /** @@ -1230,6 +1252,8 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg, static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack) { + struct net *net = sock_net(&tsk->sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff *skb = NULL; struct tipc_msg *msg; u32 peer_port = tsk_peer_port(tsk); @@ -1237,13 +1261,14 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack) if (!tsk->connected) return; - skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0, dnode, - tipc_own_addr, peer_port, tsk->ref, TIPC_OK); + skb = tipc_msg_create(net, CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0, + dnode, tn->own_addr, peer_port, tsk->portid, + TIPC_OK); if (!skb) return; msg = buf_msg(skb); msg_set_msgcnt(msg, ack); - tipc_link_xmit_skb(skb, dnode, msg_link_selector(msg)); + tipc_link_xmit_skb(net, skb, dnode, msg_link_selector(msg)); } static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) @@ -1536,6 +1561,7 @@ static void tipc_data_ready(struct sock *sk) static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf) { struct sock *sk = &tsk->sk; + struct net *net = sock_net(sk); struct socket *sock = sk->sk_socket; struct tipc_msg *msg = buf_msg(*buf); int retval = -TIPC_ERR_NO_PORT; @@ -1551,8 +1577,8 @@ static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf) sock->state = SS_DISCONNECTING; tsk->connected = 0; /* let timer expire on it's own */ - tipc_node_remove_conn(tsk_peer_node(tsk), - tsk->ref); + tipc_node_remove_conn(net, tsk_peer_node(tsk), + tsk->portid); } retval = TIPC_OK; } @@ -1709,6 +1735,7 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) int rc; u32 onode; struct tipc_sock *tsk = tipc_sk(sk); + struct net *net = sock_net(sk); uint truesize = skb->truesize; rc = filter_rcv(sk, skb); @@ -1719,10 +1746,10 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) return 0; } - if ((rc < 0) && !tipc_msg_reverse(skb, &onode, -rc)) + if ((rc < 0) && !tipc_msg_reverse(net, skb, &onode, -rc)) return 0; - tipc_link_xmit_skb(skb, onode, 0); + tipc_link_xmit_skb(net, skb, onode, 0); return 0; } @@ -1733,7 +1760,7 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) * Consumes buffer * Returns 0 if success, or errno: -EHOSTUNREACH */ -int tipc_sk_rcv(struct sk_buff *skb) +int tipc_sk_rcv(struct net *net, struct sk_buff *skb) { struct tipc_sock *tsk; struct sock *sk; @@ -1743,9 +1770,9 @@ int tipc_sk_rcv(struct sk_buff *skb) u32 dnode; /* Validate destination and message */ - tsk = tipc_sk_get(dport); + tsk = tipc_sk_lookup(net, dport); if (unlikely(!tsk)) { - rc = tipc_msg_eval(skb, &dnode); + rc = tipc_msg_eval(net, skb, &dnode); goto exit; } sk = &tsk->sk; @@ -1763,14 +1790,14 @@ int tipc_sk_rcv(struct sk_buff *skb) rc = -TIPC_ERR_OVERLOAD; } spin_unlock_bh(&sk->sk_lock.slock); - tipc_sk_put(tsk); + sock_put(sk); if (likely(!rc)) return 0; exit: - if ((rc < 0) && !tipc_msg_reverse(skb, &dnode, -rc)) + if ((rc < 0) && !tipc_msg_reverse(net, skb, &dnode, -rc)) return -EHOSTUNREACH; - tipc_link_xmit_skb(skb, dnode, 0); + tipc_link_xmit_skb(net, skb, dnode, 0); return (rc < 0) ? -EHOSTUNREACH : 0; } @@ -2027,6 +2054,8 @@ exit: static int tipc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; + struct net *net = sock_net(sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_sock *tsk = tipc_sk(sk); struct sk_buff *skb; u32 dnode; @@ -2049,21 +2078,23 @@ restart: kfree_skb(skb); goto restart; } - if (tipc_msg_reverse(skb, &dnode, TIPC_CONN_SHUTDOWN)) - tipc_link_xmit_skb(skb, dnode, tsk->ref); - tipc_node_remove_conn(dnode, tsk->ref); + if (tipc_msg_reverse(net, skb, &dnode, + TIPC_CONN_SHUTDOWN)) + tipc_link_xmit_skb(net, skb, dnode, + tsk->portid); + tipc_node_remove_conn(net, dnode, tsk->portid); } else { dnode = tsk_peer_node(tsk); - skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, + skb = tipc_msg_create(net, TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, SHORT_H_SIZE, - 0, dnode, tipc_own_addr, + 0, dnode, tn->own_addr, tsk_peer_port(tsk), - tsk->ref, TIPC_CONN_SHUTDOWN); - tipc_link_xmit_skb(skb, dnode, tsk->ref); + tsk->portid, TIPC_CONN_SHUTDOWN); + tipc_link_xmit_skb(net, skb, dnode, tsk->portid); } tsk->connected = 0; sock->state = SS_DISCONNECTING; - tipc_node_remove_conn(dnode, tsk->ref); + tipc_node_remove_conn(net, dnode, tsk->portid); /* fall through */ case SS_DISCONNECTING: @@ -2084,18 +2115,15 @@ restart: return res; } -static void tipc_sk_timeout(unsigned long ref) +static void tipc_sk_timeout(unsigned long data) { - struct tipc_sock *tsk; - struct sock *sk; + struct tipc_sock *tsk = (struct tipc_sock *)data; + struct sock *sk = &tsk->sk; + struct net *net = sock_net(sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); struct sk_buff *skb = NULL; u32 peer_port, peer_node; - tsk = tipc_sk_get(ref); - if (!tsk) - return; - - sk = &tsk->sk; bh_lock_sock(sk); if (!tsk->connected) { bh_unlock_sock(sk); @@ -2106,38 +2134,39 @@ static void tipc_sk_timeout(unsigned long ref) if (tsk->probing_state == TIPC_CONN_PROBING) { /* Previous probe not answered -> self abort */ - skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, - SHORT_H_SIZE, 0, tipc_own_addr, - peer_node, ref, peer_port, - TIPC_ERR_NO_PORT); + skb = tipc_msg_create(net, TIPC_CRITICAL_IMPORTANCE, + TIPC_CONN_MSG, SHORT_H_SIZE, 0, + tn->own_addr, peer_node, tsk->portid, + peer_port, TIPC_ERR_NO_PORT); } else { - skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE, INT_H_SIZE, - 0, peer_node, tipc_own_addr, - peer_port, ref, TIPC_OK); + skb = tipc_msg_create(net, CONN_MANAGER, CONN_PROBE, INT_H_SIZE, + 0, peer_node, tn->own_addr, + peer_port, tsk->portid, TIPC_OK); tsk->probing_state = TIPC_CONN_PROBING; - k_start_timer(&tsk->timer, tsk->probing_interval); + sk_reset_timer(sk, &sk->sk_timer, jiffies + tsk->probing_intv); } bh_unlock_sock(sk); if (skb) - tipc_link_xmit_skb(skb, peer_node, ref); + tipc_link_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid); exit: - tipc_sk_put(tsk); + sock_put(sk); } static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq) { + struct net *net = sock_net(&tsk->sk); struct publication *publ; u32 key; if (tsk->connected) return -EINVAL; - key = tsk->ref + tsk->pub_count + 1; - if (key == tsk->ref) + key = tsk->portid + tsk->pub_count + 1; + if (key == tsk->portid) return -EADDRINUSE; - publ = tipc_nametbl_publish(seq->type, seq->lower, seq->upper, - scope, tsk->ref, key); + publ = tipc_nametbl_publish(net, seq->type, seq->lower, seq->upper, + scope, tsk->portid, key); if (unlikely(!publ)) return -EINVAL; @@ -2150,6 +2179,7 @@ static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq) { + struct net *net = sock_net(&tsk->sk); struct publication *publ; struct publication *safe; int rc = -EINVAL; @@ -2164,12 +2194,12 @@ static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, continue; if (publ->upper != seq->upper) break; - tipc_nametbl_withdraw(publ->type, publ->lower, + tipc_nametbl_withdraw(net, publ->type, publ->lower, publ->ref, publ->key); rc = 0; break; } - tipc_nametbl_withdraw(publ->type, publ->lower, + tipc_nametbl_withdraw(net, publ->type, publ->lower, publ->ref, publ->key); rc = 0; } @@ -2181,16 +2211,18 @@ static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, static int tipc_sk_show(struct tipc_sock *tsk, char *buf, int len, int full_id) { + struct net *net = sock_net(&tsk->sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); struct publication *publ; int ret; if (full_id) ret = tipc_snprintf(buf, len, "<%u.%u.%u:%u>:", - tipc_zone(tipc_own_addr), - tipc_cluster(tipc_own_addr), - tipc_node(tipc_own_addr), tsk->ref); + tipc_zone(tn->own_addr), + tipc_cluster(tn->own_addr), + tipc_node(tn->own_addr), tsk->portid); else - ret = tipc_snprintf(buf, len, "%-10u:", tsk->ref); + ret = tipc_snprintf(buf, len, "%-10u:", tsk->portid); if (tsk->connected) { u32 dport = tsk_peer_port(tsk); @@ -2222,15 +2254,18 @@ static int tipc_sk_show(struct tipc_sock *tsk, char *buf, return ret; } -struct sk_buff *tipc_sk_socks_show(void) +struct sk_buff *tipc_sk_socks_show(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); + const struct bucket_table *tbl; + struct rhash_head *pos; struct sk_buff *buf; struct tlv_desc *rep_tlv; char *pb; int pb_len; struct tipc_sock *tsk; int str_len = 0; - u32 ref = 0; + int i; buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN)); if (!buf) @@ -2239,14 +2274,18 @@ struct sk_buff *tipc_sk_socks_show(void) pb = TLV_DATA(rep_tlv); pb_len = ULTRA_STRING_MAX_LEN; - tsk = tipc_sk_get_next(&ref); - for (; tsk; tsk = tipc_sk_get_next(&ref)) { - lock_sock(&tsk->sk); - str_len += tipc_sk_show(tsk, pb + str_len, - pb_len - str_len, 0); - release_sock(&tsk->sk); - tipc_sk_put(tsk); + rcu_read_lock(); + tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht); + for (i = 0; i < tbl->size; i++) { + rht_for_each_entry_rcu(tsk, pos, tbl, i, node) { + spin_lock_bh(&tsk->sk.sk_lock.slock); + str_len += tipc_sk_show(tsk, pb + str_len, + pb_len - str_len, 0); + spin_unlock_bh(&tsk->sk.sk_lock.slock); + } } + rcu_read_unlock(); + str_len += 1; /* for "\0" */ skb_put(buf, TLV_SPACE(str_len)); TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); @@ -2257,257 +2296,102 @@ struct sk_buff *tipc_sk_socks_show(void) /* tipc_sk_reinit: set non-zero address in all existing sockets * when we go from standalone to network mode. */ -void tipc_sk_reinit(void) +void tipc_sk_reinit(struct net *net) { + struct tipc_net *tn = net_generic(net, tipc_net_id); + const struct bucket_table *tbl; + struct rhash_head *pos; + struct tipc_sock *tsk; struct tipc_msg *msg; - u32 ref = 0; - struct tipc_sock *tsk = tipc_sk_get_next(&ref); + int i; - for (; tsk; tsk = tipc_sk_get_next(&ref)) { - lock_sock(&tsk->sk); - msg = &tsk->phdr; - msg_set_prevnode(msg, tipc_own_addr); - msg_set_orignode(msg, tipc_own_addr); - release_sock(&tsk->sk); - tipc_sk_put(tsk); + rcu_read_lock(); + tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht); + for (i = 0; i < tbl->size; i++) { + rht_for_each_entry_rcu(tsk, pos, tbl, i, node) { + spin_lock_bh(&tsk->sk.sk_lock.slock); + msg = &tsk->phdr; + msg_set_prevnode(msg, tn->own_addr); + msg_set_orignode(msg, tn->own_addr); + spin_unlock_bh(&tsk->sk.sk_lock.slock); + } } + rcu_read_unlock(); } -/** - * struct reference - TIPC socket reference entry - * @tsk: pointer to socket associated with reference entry - * @ref: reference value for socket (combines instance & array index info) - */ -struct reference { - struct tipc_sock *tsk; - u32 ref; -}; - -/** - * struct tipc_ref_table - table of TIPC socket reference entries - * @entries: pointer to array of reference entries - * @capacity: array index of first unusable entry - * @init_point: array index of first uninitialized entry - * @first_free: array index of first unused socket reference entry - * @last_free: array index of last unused socket reference entry - * @index_mask: bitmask for array index portion of reference values - * @start_mask: initial value for instance value portion of reference values - */ -struct ref_table { - struct reference *entries; - u32 capacity; - u32 init_point; - u32 first_free; - u32 last_free; - u32 index_mask; - u32 start_mask; -}; - -/* Socket reference table consists of 2**N entries. - * - * State Socket ptr Reference - * ----- ---------- --------- - * In use non-NULL XXXX|own index - * (XXXX changes each time entry is acquired) - * Free NULL YYYY|next free index - * (YYYY is one more than last used XXXX) - * Uninitialized NULL 0 - * - * Entry 0 is not used; this allows index 0 to denote the end of the free list. - * - * Note that a reference value of 0 does not necessarily indicate that an - * entry is uninitialized, since the last entry in the free list could also - * have a reference value of 0 (although this is unlikely). - */ - -static struct ref_table tipc_ref_table; - -static DEFINE_RWLOCK(ref_table_lock); - -/** - * tipc_ref_table_init - create reference table for sockets - */ -int tipc_sk_ref_table_init(u32 req_sz, u32 start) +static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid) { - struct reference *table; - u32 actual_sz; - - /* account for unused entry, then round up size to a power of 2 */ - - req_sz++; - for (actual_sz = 16; actual_sz < req_sz; actual_sz <<= 1) { - /* do nothing */ - }; - - /* allocate table & mark all entries as uninitialized */ - table = vzalloc(actual_sz * sizeof(struct reference)); - if (table == NULL) - return -ENOMEM; - - tipc_ref_table.entries = table; - tipc_ref_table.capacity = req_sz; - tipc_ref_table.init_point = 1; - tipc_ref_table.first_free = 0; - tipc_ref_table.last_free = 0; - tipc_ref_table.index_mask = actual_sz - 1; - tipc_ref_table.start_mask = start & ~tipc_ref_table.index_mask; + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_sock *tsk; - return 0; -} + rcu_read_lock(); + tsk = rhashtable_lookup(&tn->sk_rht, &portid); + if (tsk) + sock_hold(&tsk->sk); + rcu_read_unlock(); -/** - * tipc_ref_table_stop - destroy reference table for sockets - */ -void tipc_sk_ref_table_stop(void) -{ - if (!tipc_ref_table.entries) - return; - vfree(tipc_ref_table.entries); - tipc_ref_table.entries = NULL; + return tsk; } -/* tipc_ref_acquire - create reference to a socket - * - * Register an socket pointer in the reference table. - * Returns a unique reference value that is used from then on to retrieve the - * socket pointer, or to determine if the socket has been deregistered. - */ -u32 tipc_sk_ref_acquire(struct tipc_sock *tsk) +static int tipc_sk_insert(struct tipc_sock *tsk) { - u32 index; - u32 index_mask; - u32 next_plus_upper; - u32 ref = 0; - struct reference *entry; - - if (unlikely(!tsk)) { - pr_err("Attempt to acquire ref. to non-existent obj\n"); - return 0; - } - if (unlikely(!tipc_ref_table.entries)) { - pr_err("Ref. table not found in acquisition attempt\n"); - return 0; - } - - /* Take a free entry, if available; otherwise initialize a new one */ - write_lock_bh(&ref_table_lock); - index = tipc_ref_table.first_free; - entry = &tipc_ref_table.entries[index]; - - if (likely(index)) { - index = tipc_ref_table.first_free; - entry = &tipc_ref_table.entries[index]; - index_mask = tipc_ref_table.index_mask; - next_plus_upper = entry->ref; - tipc_ref_table.first_free = next_plus_upper & index_mask; - ref = (next_plus_upper & ~index_mask) + index; - entry->tsk = tsk; - } else if (tipc_ref_table.init_point < tipc_ref_table.capacity) { - index = tipc_ref_table.init_point++; - entry = &tipc_ref_table.entries[index]; - ref = tipc_ref_table.start_mask + index; + struct sock *sk = &tsk->sk; + struct net *net = sock_net(sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); + u32 remaining = (TIPC_MAX_PORT - TIPC_MIN_PORT) + 1; + u32 portid = prandom_u32() % remaining + TIPC_MIN_PORT; + + while (remaining--) { + portid++; + if ((portid < TIPC_MIN_PORT) || (portid > TIPC_MAX_PORT)) + portid = TIPC_MIN_PORT; + tsk->portid = portid; + sock_hold(&tsk->sk); + if (rhashtable_lookup_insert(&tn->sk_rht, &tsk->node)) + return 0; + sock_put(&tsk->sk); } - if (ref) { - entry->ref = ref; - entry->tsk = tsk; - } - write_unlock_bh(&ref_table_lock); - return ref; + return -1; } -/* tipc_sk_ref_discard - invalidate reference to an socket - * - * Disallow future references to an socket and free up the entry for re-use. - */ -void tipc_sk_ref_discard(u32 ref) +static void tipc_sk_remove(struct tipc_sock *tsk) { - struct reference *entry; - u32 index; - u32 index_mask; - - if (unlikely(!tipc_ref_table.entries)) { - pr_err("Ref. table not found during discard attempt\n"); - return; - } - - index_mask = tipc_ref_table.index_mask; - index = ref & index_mask; - entry = &tipc_ref_table.entries[index]; - - write_lock_bh(&ref_table_lock); + struct sock *sk = &tsk->sk; + struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id); - if (unlikely(!entry->tsk)) { - pr_err("Attempt to discard ref. to non-existent socket\n"); - goto exit; - } - if (unlikely(entry->ref != ref)) { - pr_err("Attempt to discard non-existent reference\n"); - goto exit; + if (rhashtable_remove(&tn->sk_rht, &tsk->node)) { + WARN_ON(atomic_read(&sk->sk_refcnt) == 1); + __sock_put(sk); } - - /* Mark entry as unused; increment instance part of entry's - * reference to invalidate any subsequent references - */ - - entry->tsk = NULL; - entry->ref = (ref & ~index_mask) + (index_mask + 1); - - /* Append entry to free entry list */ - if (unlikely(tipc_ref_table.first_free == 0)) - tipc_ref_table.first_free = index; - else - tipc_ref_table.entries[tipc_ref_table.last_free].ref |= index; - tipc_ref_table.last_free = index; -exit: - write_unlock_bh(&ref_table_lock); } -/* tipc_sk_get - find referenced socket and return pointer to it - */ -struct tipc_sock *tipc_sk_get(u32 ref) +int tipc_sk_rht_init(struct net *net) { - struct reference *entry; - struct tipc_sock *tsk; + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct rhashtable_params rht_params = { + .nelem_hint = 192, + .head_offset = offsetof(struct tipc_sock, node), + .key_offset = offsetof(struct tipc_sock, portid), + .key_len = sizeof(u32), /* portid */ + .hashfn = jhash, + .max_shift = 20, /* 1M */ + .min_shift = 8, /* 256 */ + .grow_decision = rht_grow_above_75, + .shrink_decision = rht_shrink_below_30, + }; - if (unlikely(!tipc_ref_table.entries)) - return NULL; - read_lock_bh(&ref_table_lock); - entry = &tipc_ref_table.entries[ref & tipc_ref_table.index_mask]; - tsk = entry->tsk; - if (likely(tsk && (entry->ref == ref))) - sock_hold(&tsk->sk); - else - tsk = NULL; - read_unlock_bh(&ref_table_lock); - return tsk; + return rhashtable_init(&tn->sk_rht, &rht_params); } -/* tipc_sk_get_next - lock & return next socket after referenced one -*/ -struct tipc_sock *tipc_sk_get_next(u32 *ref) +void tipc_sk_rht_destroy(struct net *net) { - struct reference *entry; - struct tipc_sock *tsk = NULL; - uint index = *ref & tipc_ref_table.index_mask; + struct tipc_net *tn = net_generic(net, tipc_net_id); - read_lock_bh(&ref_table_lock); - while (++index < tipc_ref_table.capacity) { - entry = &tipc_ref_table.entries[index]; - if (!entry->tsk) - continue; - tsk = entry->tsk; - sock_hold(&tsk->sk); - *ref = entry->ref; - break; - } - read_unlock_bh(&ref_table_lock); - return tsk; -} + /* Wait for socket readers to complete */ + synchronize_net(); -static void tipc_sk_put(struct tipc_sock *tsk) -{ - sock_put(&tsk->sk); + rhashtable_destroy(&tn->sk_rht); } /** @@ -2639,8 +2523,9 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, return put_user(sizeof(value), ol); } -static int tipc_ioctl(struct socket *sk, unsigned int cmd, unsigned long arg) +static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { + struct sock *sk = sock->sk; struct tipc_sioc_ln_req lnr; void __user *argp = (void __user *)arg; @@ -2648,7 +2533,8 @@ static int tipc_ioctl(struct socket *sk, unsigned int cmd, unsigned long arg) case SIOCGETLINKNAME: if (copy_from_user(&lnr, argp, sizeof(lnr))) return -EFAULT; - if (!tipc_node_get_linkname(lnr.bearer_id & 0xffff, lnr.peer, + if (!tipc_node_get_linkname(sock_net(sk), + lnr.bearer_id & 0xffff, lnr.peer, lnr.linkname, TIPC_MAX_LINK_NAME)) { if (copy_to_user(argp, &lnr, sizeof(lnr))) return -EFAULT; @@ -2820,6 +2706,8 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb, int err; void *hdr; struct nlattr *attrs; + struct net *net = sock_net(skb->sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &tipc_genl_v2_family, NLM_F_MULTI, TIPC_NL_SOCK_GET); @@ -2829,9 +2717,9 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb, attrs = nla_nest_start(skb, TIPC_NLA_SOCK); if (!attrs) goto genlmsg_cancel; - if (nla_put_u32(skb, TIPC_NLA_SOCK_REF, tsk->ref)) + if (nla_put_u32(skb, TIPC_NLA_SOCK_REF, tsk->portid)) goto attr_msg_cancel; - if (nla_put_u32(skb, TIPC_NLA_SOCK_ADDR, tipc_own_addr)) + if (nla_put_u32(skb, TIPC_NLA_SOCK_ADDR, tn->own_addr)) goto attr_msg_cancel; if (tsk->connected) { @@ -2859,22 +2747,31 @@ int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; struct tipc_sock *tsk; - u32 prev_ref = cb->args[0]; - u32 ref = prev_ref; - - tsk = tipc_sk_get_next(&ref); - for (; tsk; tsk = tipc_sk_get_next(&ref)) { - lock_sock(&tsk->sk); - err = __tipc_nl_add_sk(skb, cb, tsk); - release_sock(&tsk->sk); - tipc_sk_put(tsk); - if (err) - break; + const struct bucket_table *tbl; + struct rhash_head *pos; + u32 prev_portid = cb->args[0]; + u32 portid = prev_portid; + struct net *net = sock_net(skb->sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); + int i; + + rcu_read_lock(); + tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht); + for (i = 0; i < tbl->size; i++) { + rht_for_each_entry_rcu(tsk, pos, tbl, i, node) { + spin_lock_bh(&tsk->sk.sk_lock.slock); + portid = tsk->portid; + err = __tipc_nl_add_sk(skb, cb, tsk); + spin_unlock_bh(&tsk->sk.sk_lock.slock); + if (err) + break; - prev_ref = ref; + prev_portid = portid; + } } + rcu_read_unlock(); - cb->args[0] = prev_ref; + cb->args[0] = prev_portid; return skb->len; } @@ -2962,12 +2859,13 @@ static int __tipc_nl_list_sk_publ(struct sk_buff *skb, int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; - u32 tsk_ref = cb->args[0]; + u32 tsk_portid = cb->args[0]; u32 last_publ = cb->args[1]; u32 done = cb->args[2]; + struct net *net = sock_net(skb->sk); struct tipc_sock *tsk; - if (!tsk_ref) { + if (!tsk_portid) { struct nlattr **attrs; struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1]; @@ -2984,13 +2882,13 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!sock[TIPC_NLA_SOCK_REF]) return -EINVAL; - tsk_ref = nla_get_u32(sock[TIPC_NLA_SOCK_REF]); + tsk_portid = nla_get_u32(sock[TIPC_NLA_SOCK_REF]); } if (done) return 0; - tsk = tipc_sk_get(tsk_ref); + tsk = tipc_sk_lookup(net, tsk_portid); if (!tsk) return -EINVAL; @@ -2999,9 +2897,9 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!err) done = 1; release_sock(&tsk->sk); - tipc_sk_put(tsk); + sock_put(&tsk->sk); - cb->args[0] = tsk_ref; + cb->args[0] = tsk_portid; cb->args[1] = last_publ; cb->args[2] = done; diff --git a/net/tipc/socket.h b/net/tipc/socket.h index d34089387006..f56c3fded51f 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -42,12 +42,19 @@ #define TIPC_FLOWCTRL_WIN (TIPC_CONNACK_INTV * 2) #define TIPC_CONN_OVERLOAD_LIMIT ((TIPC_FLOWCTRL_WIN * 2 + 1) * \ SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE)) -int tipc_sk_rcv(struct sk_buff *buf); -struct sk_buff *tipc_sk_socks_show(void); -void tipc_sk_mcast_rcv(struct sk_buff *buf); -void tipc_sk_reinit(void); -int tipc_sk_ref_table_init(u32 requested_size, u32 start); -void tipc_sk_ref_table_stop(void); + +int tipc_socket_init(void); +void tipc_socket_stop(void); +int tipc_sock_create_local(struct net *net, int type, struct socket **res); +void tipc_sock_release_local(struct socket *sock); +int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, + int flags); +int tipc_sk_rcv(struct net *net, struct sk_buff *buf); +struct sk_buff *tipc_sk_socks_show(struct net *net); +void tipc_sk_mcast_rcv(struct net *net, struct sk_buff *buf); +void tipc_sk_reinit(struct net *net); +int tipc_sk_rht_init(struct net *net); +void tipc_sk_rht_destroy(struct net *net); int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 0344206b984f..72c339e432aa 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -50,33 +50,6 @@ struct tipc_subscriber { struct list_head subscription_list; }; -static void subscr_conn_msg_event(int conid, struct sockaddr_tipc *addr, - void *usr_data, void *buf, size_t len); -static void *subscr_named_msg_event(int conid); -static void subscr_conn_shutdown_event(int conid, void *usr_data); - -static atomic_t subscription_count = ATOMIC_INIT(0); - -static struct sockaddr_tipc topsrv_addr __read_mostly = { - .family = AF_TIPC, - .addrtype = TIPC_ADDR_NAMESEQ, - .addr.nameseq.type = TIPC_TOP_SRV, - .addr.nameseq.lower = TIPC_TOP_SRV, - .addr.nameseq.upper = TIPC_TOP_SRV, - .scope = TIPC_NODE_SCOPE -}; - -static struct tipc_server topsrv __read_mostly = { - .saddr = &topsrv_addr, - .imp = TIPC_CRITICAL_IMPORTANCE, - .type = SOCK_SEQPACKET, - .max_rcvbuf_size = sizeof(struct tipc_subscr), - .name = "topology_server", - .tipc_conn_recvmsg = subscr_conn_msg_event, - .tipc_conn_new = subscr_named_msg_event, - .tipc_conn_shutdown = subscr_conn_shutdown_event, -}; - /** * htohl - convert value to endianness used by destination * @in: value to convert @@ -93,6 +66,7 @@ static void subscr_send_event(struct tipc_subscription *sub, u32 found_lower, u32 found_upper, u32 event, u32 port_ref, u32 node) { + struct tipc_net *tn = net_generic(sub->net, tipc_net_id); struct tipc_subscriber *subscriber = sub->subscriber; struct kvec msg_sect; @@ -103,8 +77,8 @@ static void subscr_send_event(struct tipc_subscription *sub, u32 found_lower, sub->evt.found_upper = htohl(found_upper, sub->swap); sub->evt.port.ref = htohl(port_ref, sub->swap); sub->evt.port.node = htohl(node, sub->swap); - tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, msg_sect.iov_base, - msg_sect.iov_len); + tipc_conn_sendmsg(tn->topsrv, subscriber->conid, NULL, + msg_sect.iov_base, msg_sect.iov_len); } /** @@ -141,9 +115,11 @@ void tipc_subscr_report_overlap(struct tipc_subscription *sub, u32 found_lower, subscr_send_event(sub, found_lower, found_upper, event, port_ref, node); } -static void subscr_timeout(struct tipc_subscription *sub) +static void subscr_timeout(unsigned long data) { + struct tipc_subscription *sub = (struct tipc_subscription *)data; struct tipc_subscriber *subscriber = sub->subscriber; + struct tipc_net *tn = net_generic(sub->net, tipc_net_id); /* The spin lock per subscriber is used to protect its members */ spin_lock_bh(&subscriber->lock); @@ -167,9 +143,8 @@ static void subscr_timeout(struct tipc_subscription *sub) TIPC_SUBSCR_TIMEOUT, 0, 0); /* Now destroy subscription */ - k_term_timer(&sub->timer); kfree(sub); - atomic_dec(&subscription_count); + atomic_dec(&tn->subscription_count); } /** @@ -179,10 +154,12 @@ static void subscr_timeout(struct tipc_subscription *sub) */ static void subscr_del(struct tipc_subscription *sub) { + struct tipc_net *tn = net_generic(sub->net, tipc_net_id); + tipc_nametbl_unsubscribe(sub); list_del(&sub->subscription_list); kfree(sub); - atomic_dec(&subscription_count); + atomic_dec(&tn->subscription_count); } /** @@ -190,9 +167,12 @@ static void subscr_del(struct tipc_subscription *sub) * * Note: Must call it in process context since it might sleep. */ -static void subscr_terminate(struct tipc_subscriber *subscriber) +static void subscr_terminate(struct tipc_subscription *sub) { - tipc_conn_terminate(&topsrv, subscriber->conid); + struct tipc_subscriber *subscriber = sub->subscriber; + struct tipc_net *tn = net_generic(sub->net, tipc_net_id); + + tipc_conn_terminate(tn->topsrv, subscriber->conid); } static void subscr_release(struct tipc_subscriber *subscriber) @@ -207,8 +187,7 @@ static void subscr_release(struct tipc_subscriber *subscriber) subscription_list) { if (sub->timeout != TIPC_WAIT_FOREVER) { spin_unlock_bh(&subscriber->lock); - k_cancel_timer(&sub->timer); - k_term_timer(&sub->timer); + del_timer_sync(&sub->timer); spin_lock_bh(&subscriber->lock); } subscr_del(sub); @@ -250,8 +229,7 @@ static void subscr_cancel(struct tipc_subscr *s, if (sub->timeout != TIPC_WAIT_FOREVER) { sub->timeout = TIPC_WAIT_FOREVER; spin_unlock_bh(&subscriber->lock); - k_cancel_timer(&sub->timer); - k_term_timer(&sub->timer); + del_timer_sync(&sub->timer); spin_lock_bh(&subscriber->lock); } subscr_del(sub); @@ -262,9 +240,11 @@ static void subscr_cancel(struct tipc_subscr *s, * * Called with subscriber lock held. */ -static int subscr_subscribe(struct tipc_subscr *s, +static int subscr_subscribe(struct net *net, struct tipc_subscr *s, struct tipc_subscriber *subscriber, - struct tipc_subscription **sub_p) { + struct tipc_subscription **sub_p) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_subscription *sub; int swap; @@ -279,7 +259,7 @@ static int subscr_subscribe(struct tipc_subscr *s, } /* Refuse subscription if global limit exceeded */ - if (atomic_read(&subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) { + if (atomic_read(&tn->subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) { pr_warn("Subscription rejected, limit reached (%u)\n", TIPC_MAX_SUBSCRIPTIONS); return -EINVAL; @@ -293,10 +273,11 @@ static int subscr_subscribe(struct tipc_subscr *s, } /* Initialize subscription object */ + sub->net = net; sub->seq.type = htohl(s->seq.type, swap); sub->seq.lower = htohl(s->seq.lower, swap); sub->seq.upper = htohl(s->seq.upper, swap); - sub->timeout = htohl(s->timeout, swap); + sub->timeout = msecs_to_jiffies(htohl(s->timeout, swap)); sub->filter = htohl(s->filter, swap); if ((!(sub->filter & TIPC_SUB_PORTS) == !(sub->filter & TIPC_SUB_SERVICE)) || @@ -309,11 +290,10 @@ static int subscr_subscribe(struct tipc_subscr *s, sub->subscriber = subscriber; sub->swap = swap; memcpy(&sub->evt.s, s, sizeof(struct tipc_subscr)); - atomic_inc(&subscription_count); + atomic_inc(&tn->subscription_count); if (sub->timeout != TIPC_WAIT_FOREVER) { - k_init_timer(&sub->timer, - (Handler)subscr_timeout, (unsigned long)sub); - k_start_timer(&sub->timer, sub->timeout); + setup_timer(&sub->timer, subscr_timeout, (unsigned long)sub); + mod_timer(&sub->timer, jiffies + sub->timeout); } *sub_p = sub; return 0; @@ -326,16 +306,18 @@ static void subscr_conn_shutdown_event(int conid, void *usr_data) } /* Handle one request to create a new subscription for the subscriber */ -static void subscr_conn_msg_event(int conid, struct sockaddr_tipc *addr, - void *usr_data, void *buf, size_t len) +static void subscr_conn_msg_event(struct net *net, int conid, + struct sockaddr_tipc *addr, void *usr_data, + void *buf, size_t len) { struct tipc_subscriber *subscriber = usr_data; struct tipc_subscription *sub = NULL; spin_lock_bh(&subscriber->lock); - if (subscr_subscribe((struct tipc_subscr *)buf, subscriber, &sub) < 0) { + if (subscr_subscribe(net, (struct tipc_subscr *)buf, subscriber, + &sub) < 0) { spin_unlock_bh(&subscriber->lock); - subscr_terminate(subscriber); + subscr_terminate(sub); return; } if (sub) @@ -343,7 +325,6 @@ static void subscr_conn_msg_event(int conid, struct sockaddr_tipc *addr, spin_unlock_bh(&subscriber->lock); } - /* Handle one request to establish a new subscriber */ static void *subscr_named_msg_event(int conid) { @@ -362,12 +343,50 @@ static void *subscr_named_msg_event(int conid) return (void *)subscriber; } -int tipc_subscr_start(void) +int tipc_subscr_start(struct net *net) { - return tipc_server_start(&topsrv); + struct tipc_net *tn = net_generic(net, tipc_net_id); + const char name[] = "topology_server"; + struct tipc_server *topsrv; + struct sockaddr_tipc *saddr; + + saddr = kzalloc(sizeof(*saddr), GFP_ATOMIC); + if (!saddr) + return -ENOMEM; + saddr->family = AF_TIPC; + saddr->addrtype = TIPC_ADDR_NAMESEQ; + saddr->addr.nameseq.type = TIPC_TOP_SRV; + saddr->addr.nameseq.lower = TIPC_TOP_SRV; + saddr->addr.nameseq.upper = TIPC_TOP_SRV; + saddr->scope = TIPC_NODE_SCOPE; + + topsrv = kzalloc(sizeof(*topsrv), GFP_ATOMIC); + if (!topsrv) { + kfree(saddr); + return -ENOMEM; + } + topsrv->net = net; + topsrv->saddr = saddr; + topsrv->imp = TIPC_CRITICAL_IMPORTANCE; + topsrv->type = SOCK_SEQPACKET; + topsrv->max_rcvbuf_size = sizeof(struct tipc_subscr); + topsrv->tipc_conn_recvmsg = subscr_conn_msg_event; + topsrv->tipc_conn_new = subscr_named_msg_event; + topsrv->tipc_conn_shutdown = subscr_conn_shutdown_event; + + strncpy(topsrv->name, name, strlen(name) + 1); + tn->topsrv = topsrv; + atomic_set(&tn->subscription_count, 0); + + return tipc_server_start(topsrv); } -void tipc_subscr_stop(void) +void tipc_subscr_stop(struct net *net) { - tipc_server_stop(&topsrv); + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_server *topsrv = tn->topsrv; + + tipc_server_stop(topsrv); + kfree(topsrv->saddr); + kfree(topsrv); } diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index 393e417bee3f..33488bd9fe3c 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -39,6 +39,9 @@ #include "server.h" +#define TIPC_MAX_SUBSCRIPTIONS 65535 +#define TIPC_MAX_PUBLICATIONS 65535 + struct tipc_subscription; struct tipc_subscriber; @@ -46,6 +49,7 @@ struct tipc_subscriber; * struct tipc_subscription - TIPC network topology subscription object * @subscriber: pointer to its subscriber * @seq: name sequence associated with subscription + * @net: point to network namespace * @timeout: duration of subscription (in ms) * @filter: event filtering to be done for subscription * @timer: timer governing subscription duration (optional) @@ -58,7 +62,8 @@ struct tipc_subscriber; struct tipc_subscription { struct tipc_subscriber *subscriber; struct tipc_name_seq seq; - u32 timeout; + struct net *net; + unsigned long timeout; u32 filter; struct timer_list timer; struct list_head nameseq_list; @@ -69,13 +74,10 @@ struct tipc_subscription { int tipc_subscr_overlap(struct tipc_subscription *sub, u32 found_lower, u32 found_upper); - void tipc_subscr_report_overlap(struct tipc_subscription *sub, u32 found_lower, u32 found_upper, u32 event, u32 port_ref, u32 node, int must); - -int tipc_subscr_start(void); - -void tipc_subscr_stop(void); +int tipc_subscr_start(struct net *net); +void tipc_subscr_stop(struct net *net); #endif diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 22ba971741e5..29c8675f9a11 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -175,7 +175,7 @@ config CFG80211_INTERNAL_REGDB Most distributions have a CRDA package. So if unsure, say N. config CFG80211_WEXT - bool + bool "cfg80211 wireless extensions compatibility" depends on CFG80211 select WEXT_CORE help diff --git a/net/wireless/core.c b/net/wireless/core.c index 53dda7728f86..456e4c38c279 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -21,6 +21,7 @@ #include <linux/sched.h> #include <net/genetlink.h> #include <net/cfg80211.h> +#include <net/rtnetlink.h> #include "nl80211.h" #include "core.h" #include "sysfs.h" @@ -320,6 +321,20 @@ static void cfg80211_destroy_iface_wk(struct work_struct *work) rtnl_unlock(); } +static void cfg80211_sched_scan_stop_wk(struct work_struct *work) +{ + struct cfg80211_registered_device *rdev; + + rdev = container_of(work, struct cfg80211_registered_device, + sched_scan_stop_wk); + + rtnl_lock(); + + __cfg80211_stop_sched_scan(rdev, false); + + rtnl_unlock(); +} + /* exported functions */ struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv, @@ -406,6 +421,7 @@ use_default_name: INIT_LIST_HEAD(&rdev->destroy_list); spin_lock_init(&rdev->destroy_list_lock); INIT_WORK(&rdev->destroy_work, cfg80211_destroy_iface_wk); + INIT_WORK(&rdev->sched_scan_stop_wk, cfg80211_sched_scan_stop_wk); #ifdef CONFIG_CFG80211_DEFAULT_PS rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT; @@ -560,6 +576,14 @@ int wiphy_register(struct wiphy *wiphy) BIT(NL80211_IFTYPE_MONITOR))) wiphy->regulatory_flags |= REGULATORY_IGNORE_STALE_KICKOFF; + if (WARN_ON((wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) && + (wiphy->regulatory_flags & + (REGULATORY_CUSTOM_REG | + REGULATORY_STRICT_REG | + REGULATORY_COUNTRY_IE_FOLLOW_POWER | + REGULATORY_COUNTRY_IE_IGNORE)))) + return -EINVAL; + if (WARN_ON(wiphy->coalesce && (!wiphy->coalesce->n_rules || !wiphy->coalesce->n_patterns) && @@ -778,6 +802,7 @@ void wiphy_unregister(struct wiphy *wiphy) flush_work(&rdev->event_work); cancel_delayed_work_sync(&rdev->dfs_update_channels_wk); flush_work(&rdev->destroy_work); + flush_work(&rdev->sched_scan_stop_wk); #ifdef CONFIG_PM if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup) @@ -858,6 +883,7 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { struct net_device *dev = wdev->netdev; + struct cfg80211_sched_scan_request *sched_scan_req; ASSERT_RTNL(); ASSERT_WDEV_LOCK(wdev); @@ -868,7 +894,8 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev, break; case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_STATION: - if (rdev->sched_scan_req && dev == rdev->sched_scan_req->dev) + sched_scan_req = rtnl_dereference(rdev->sched_scan_req); + if (sched_scan_req && dev == sched_scan_req->dev) __cfg80211_stop_sched_scan(rdev, false); #ifdef CONFIG_CFG80211_WEXT @@ -937,12 +964,17 @@ void cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev, } EXPORT_SYMBOL(cfg80211_stop_iface); +static const struct rtnl_link_ops wireless_link_ops = { + .kind = "wlan", +}; + static int cfg80211_netdev_notifier_call(struct notifier_block *nb, unsigned long state, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev; + struct cfg80211_sched_scan_request *sched_scan_req; if (!wdev) return NOTIFY_DONE; @@ -954,6 +986,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, switch (state) { case NETDEV_POST_INIT: SET_NETDEV_DEVTYPE(dev, &wiphy_type); + dev->rtnl_link_ops = &wireless_link_ops; break; case NETDEV_REGISTER: /* @@ -1007,8 +1040,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, ___cfg80211_scan_done(rdev, false); } - if (WARN_ON(rdev->sched_scan_req && - rdev->sched_scan_req->dev == wdev->netdev)) { + sched_scan_req = rtnl_dereference(rdev->sched_scan_req); + if (WARN_ON(sched_scan_req && + sched_scan_req->dev == wdev->netdev)) { __cfg80211_stop_sched_scan(rdev, false); } diff --git a/net/wireless/core.h b/net/wireless/core.h index faa5b1609aae..801cd49c5a0c 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -36,6 +36,13 @@ struct cfg80211_registered_device { * the country on the country IE changed. */ char country_ie_alpha2[2]; + /* + * the driver requests the regulatory core to set this regulatory + * domain as the wiphy's. Only used for %REGULATORY_WIPHY_SELF_MANAGED + * devices using the regulatory_set_wiphy_regd() API + */ + const struct ieee80211_regdomain *requested_regd; + /* If a Country IE has been received this tells us the environment * which its telling us its in. This defaults to ENVIRON_ANY */ enum environment_cap env; @@ -63,7 +70,7 @@ struct cfg80211_registered_device { u32 bss_generation; struct cfg80211_scan_request *scan_req; /* protected by RTNL */ struct sk_buff *scan_msg; - struct cfg80211_sched_scan_request *sched_scan_req; + struct cfg80211_sched_scan_request __rcu *sched_scan_req; unsigned long suspend_at; struct work_struct scan_done_wk; struct work_struct sched_scan_results_wk; @@ -84,6 +91,8 @@ struct cfg80211_registered_device { struct list_head destroy_list; struct work_struct destroy_work; + struct work_struct sched_scan_stop_wk; + /* must be last because of the way we do wiphy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ struct wiphy wiphy __aligned(NETDEV_ALIGN); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7ca4b5133123..380784378df8 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -59,13 +59,13 @@ enum nl80211_multicast_groups { }; static const struct genl_multicast_group nl80211_mcgrps[] = { - [NL80211_MCGRP_CONFIG] = { .name = "config", }, - [NL80211_MCGRP_SCAN] = { .name = "scan", }, - [NL80211_MCGRP_REGULATORY] = { .name = "regulatory", }, - [NL80211_MCGRP_MLME] = { .name = "mlme", }, - [NL80211_MCGRP_VENDOR] = { .name = "vendor", }, + [NL80211_MCGRP_CONFIG] = { .name = NL80211_MULTICAST_GROUP_CONFIG }, + [NL80211_MCGRP_SCAN] = { .name = NL80211_MULTICAST_GROUP_SCAN }, + [NL80211_MCGRP_REGULATORY] = { .name = NL80211_MULTICAST_GROUP_REG }, + [NL80211_MCGRP_MLME] = { .name = NL80211_MULTICAST_GROUP_MLME }, + [NL80211_MCGRP_VENDOR] = { .name = NL80211_MULTICAST_GROUP_VENDOR }, #ifdef CONFIG_NL80211_TESTMODE - [NL80211_MCGRP_TESTMODE] = { .name = "testmode", } + [NL80211_MCGRP_TESTMODE] = { .name = NL80211_MULTICAST_GROUP_TESTMODE } #endif }; @@ -396,6 +396,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 }, [NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 }, [NL80211_ATTR_MAC_MASK] = { .len = ETH_ALEN }, + [NL80211_ATTR_WIPHY_SELF_MANAGED_REG] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -1087,6 +1088,11 @@ static int nl80211_send_wowlan(struct sk_buff *msg, return -ENOBUFS; } + if ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_NET_DETECT) && + nla_put_u32(msg, NL80211_WOWLAN_TRIG_NET_DETECT, + rdev->wiphy.wowlan->max_nd_match_sets)) + return -ENOBUFS; + if (large && nl80211_send_wowlan_tcp_caps(rdev, msg)) return -ENOBUFS; @@ -1701,6 +1707,15 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.max_num_csa_counters)) goto nla_put_failure; + if (rdev->wiphy.regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED && + nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG)) + goto nla_put_failure; + + if (nla_put(msg, NL80211_ATTR_EXT_FEATURES, + sizeof(rdev->wiphy.ext_features), + rdev->wiphy.ext_features)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -3640,8 +3655,8 @@ static bool nl80211_put_signal(struct sk_buff *msg, u8 mask, s8 *signal, return true; } -static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq, - int flags, +static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, + u32 seq, int flags, struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *mac_addr, struct station_info *sinfo) @@ -3649,7 +3664,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq, void *hdr; struct nlattr *sinfoattr, *bss_param; - hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_STATION); + hdr = nl80211hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -1; @@ -3661,115 +3676,77 @@ static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq, sinfoattr = nla_nest_start(msg, NL80211_ATTR_STA_INFO); if (!sinfoattr) goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_CONNECTED_TIME) && - nla_put_u32(msg, NL80211_STA_INFO_CONNECTED_TIME, - sinfo->connected_time)) - goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_INACTIVE_TIME) && - nla_put_u32(msg, NL80211_STA_INFO_INACTIVE_TIME, - sinfo->inactive_time)) - goto nla_put_failure; - if ((sinfo->filled & (STATION_INFO_RX_BYTES | - STATION_INFO_RX_BYTES64)) && + +#define PUT_SINFO(attr, memb, type) do { \ + if (sinfo->filled & BIT(NL80211_STA_INFO_ ## attr) && \ + nla_put_ ## type(msg, NL80211_STA_INFO_ ## attr, \ + sinfo->memb)) \ + goto nla_put_failure; \ + } while (0) + + PUT_SINFO(CONNECTED_TIME, connected_time, u32); + PUT_SINFO(INACTIVE_TIME, inactive_time, u32); + + if (sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES) | + BIT(NL80211_STA_INFO_RX_BYTES64)) && nla_put_u32(msg, NL80211_STA_INFO_RX_BYTES, (u32)sinfo->rx_bytes)) goto nla_put_failure; - if ((sinfo->filled & (STATION_INFO_TX_BYTES | - STATION_INFO_TX_BYTES64)) && + + if (sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES) | + BIT(NL80211_STA_INFO_TX_BYTES64)) && nla_put_u32(msg, NL80211_STA_INFO_TX_BYTES, (u32)sinfo->tx_bytes)) goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_RX_BYTES64) && - nla_put_u64(msg, NL80211_STA_INFO_RX_BYTES64, - sinfo->rx_bytes)) - goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_TX_BYTES64) && - nla_put_u64(msg, NL80211_STA_INFO_TX_BYTES64, - sinfo->tx_bytes)) - goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_LLID) && - nla_put_u16(msg, NL80211_STA_INFO_LLID, sinfo->llid)) - goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_PLID) && - nla_put_u16(msg, NL80211_STA_INFO_PLID, sinfo->plid)) - goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_PLINK_STATE) && - nla_put_u8(msg, NL80211_STA_INFO_PLINK_STATE, - sinfo->plink_state)) - goto nla_put_failure; + + PUT_SINFO(RX_BYTES64, rx_bytes, u64); + PUT_SINFO(TX_BYTES64, tx_bytes, u64); + PUT_SINFO(LLID, llid, u16); + PUT_SINFO(PLID, plid, u16); + PUT_SINFO(PLINK_STATE, plink_state, u8); + switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: - if ((sinfo->filled & STATION_INFO_SIGNAL) && - nla_put_u8(msg, NL80211_STA_INFO_SIGNAL, - sinfo->signal)) - goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_SIGNAL_AVG) && - nla_put_u8(msg, NL80211_STA_INFO_SIGNAL_AVG, - sinfo->signal_avg)) - goto nla_put_failure; + PUT_SINFO(SIGNAL, signal, u8); + PUT_SINFO(SIGNAL_AVG, signal_avg, u8); break; default: break; } - if (sinfo->filled & STATION_INFO_CHAIN_SIGNAL) { + if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL)) { if (!nl80211_put_signal(msg, sinfo->chains, sinfo->chain_signal, NL80211_STA_INFO_CHAIN_SIGNAL)) goto nla_put_failure; } - if (sinfo->filled & STATION_INFO_CHAIN_SIGNAL_AVG) { + if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)) { if (!nl80211_put_signal(msg, sinfo->chains, sinfo->chain_signal_avg, NL80211_STA_INFO_CHAIN_SIGNAL_AVG)) goto nla_put_failure; } - if (sinfo->filled & STATION_INFO_TX_BITRATE) { + if (sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE)) { if (!nl80211_put_sta_rate(msg, &sinfo->txrate, NL80211_STA_INFO_TX_BITRATE)) goto nla_put_failure; } - if (sinfo->filled & STATION_INFO_RX_BITRATE) { + if (sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE)) { if (!nl80211_put_sta_rate(msg, &sinfo->rxrate, NL80211_STA_INFO_RX_BITRATE)) goto nla_put_failure; } - if ((sinfo->filled & STATION_INFO_RX_PACKETS) && - nla_put_u32(msg, NL80211_STA_INFO_RX_PACKETS, - sinfo->rx_packets)) - goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_TX_PACKETS) && - nla_put_u32(msg, NL80211_STA_INFO_TX_PACKETS, - sinfo->tx_packets)) - goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_TX_RETRIES) && - nla_put_u32(msg, NL80211_STA_INFO_TX_RETRIES, - sinfo->tx_retries)) - goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_TX_FAILED) && - nla_put_u32(msg, NL80211_STA_INFO_TX_FAILED, - sinfo->tx_failed)) - goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_EXPECTED_THROUGHPUT) && - nla_put_u32(msg, NL80211_STA_INFO_EXPECTED_THROUGHPUT, - sinfo->expected_throughput)) - goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_BEACON_LOSS_COUNT) && - 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) { + + PUT_SINFO(RX_PACKETS, rx_packets, u32); + PUT_SINFO(TX_PACKETS, tx_packets, u32); + PUT_SINFO(TX_RETRIES, tx_retries, u32); + PUT_SINFO(TX_FAILED, tx_failed, u32); + PUT_SINFO(EXPECTED_THROUGHPUT, expected_throughput, u32); + PUT_SINFO(BEACON_LOSS, beacon_loss_count, u32); + PUT_SINFO(LOCAL_PM, local_pm, u32); + PUT_SINFO(PEER_PM, peer_pm, u32); + PUT_SINFO(NONPEER_PM, nonpeer_pm, u32); + + if (sinfo->filled & BIT(NL80211_STA_INFO_BSS_PARAM)) { bss_param = nla_nest_start(msg, NL80211_STA_INFO_BSS_PARAM); if (!bss_param) goto nla_put_failure; @@ -3788,18 +3765,62 @@ static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq, nla_nest_end(msg, bss_param); } - if ((sinfo->filled & STATION_INFO_STA_FLAGS) && + if ((sinfo->filled & BIT(NL80211_STA_INFO_STA_FLAGS)) && nla_put(msg, NL80211_STA_INFO_STA_FLAGS, sizeof(struct nl80211_sta_flag_update), &sinfo->sta_flags)) goto nla_put_failure; - if ((sinfo->filled & STATION_INFO_T_OFFSET) && - nla_put_u64(msg, NL80211_STA_INFO_T_OFFSET, - sinfo->t_offset)) - goto nla_put_failure; + + PUT_SINFO(T_OFFSET, t_offset, u64); + PUT_SINFO(RX_DROP_MISC, rx_dropped_misc, u64); + PUT_SINFO(BEACON_RX, rx_beacon, u64); + PUT_SINFO(BEACON_SIGNAL_AVG, rx_beacon_signal_avg, u8); + +#undef PUT_SINFO + + if (sinfo->filled & BIT(NL80211_STA_INFO_TID_STATS)) { + struct nlattr *tidsattr; + int tid; + + tidsattr = nla_nest_start(msg, NL80211_STA_INFO_TID_STATS); + if (!tidsattr) + goto nla_put_failure; + + for (tid = 0; tid < IEEE80211_NUM_TIDS + 1; tid++) { + struct cfg80211_tid_stats *tidstats; + struct nlattr *tidattr; + + tidstats = &sinfo->pertid[tid]; + + if (!tidstats->filled) + continue; + + tidattr = nla_nest_start(msg, tid + 1); + if (!tidattr) + goto nla_put_failure; + +#define PUT_TIDVAL(attr, memb, type) do { \ + if (tidstats->filled & BIT(NL80211_TID_STATS_ ## attr) && \ + nla_put_ ## type(msg, NL80211_TID_STATS_ ## attr, \ + tidstats->memb)) \ + goto nla_put_failure; \ + } while (0) + + PUT_TIDVAL(RX_MSDU, rx_msdu, u64); + PUT_TIDVAL(TX_MSDU, tx_msdu, u64); + PUT_TIDVAL(TX_MSDU_RETRIES, tx_msdu_retries, u64); + PUT_TIDVAL(TX_MSDU_FAILED, tx_msdu_failed, u64); + +#undef PUT_TIDVAL + nla_nest_end(msg, tidattr); + } + + nla_nest_end(msg, tidsattr); + } + nla_nest_end(msg, sinfoattr); - if ((sinfo->filled & STATION_INFO_ASSOC_REQ_IES) && + if (sinfo->assoc_req_ies_len && nla_put(msg, NL80211_ATTR_IE, sinfo->assoc_req_ies_len, sinfo->assoc_req_ies)) goto nla_put_failure; @@ -3844,7 +3865,7 @@ static int nl80211_dump_station(struct sk_buff *skb, if (err) goto out_err; - if (nl80211_send_station(skb, + if (nl80211_send_station(skb, NL80211_CMD_NEW_STATION, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wdev->netdev, mac_addr, @@ -3891,7 +3912,8 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - if (nl80211_send_station(msg, info->snd_portid, info->snd_seq, 0, + if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, + info->snd_portid, info->snd_seq, 0, rdev, dev, mac_addr, &sinfo) < 0) { nlmsg_free(msg); return -ENOBUFS; @@ -5327,42 +5349,20 @@ static int nl80211_update_mesh_config(struct sk_buff *skb, return err; } -static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) +static int nl80211_put_regdom(const struct ieee80211_regdomain *regdom, + struct sk_buff *msg) { - const struct ieee80211_regdomain *regdom; - struct sk_buff *msg; - void *hdr = NULL; struct nlattr *nl_reg_rules; unsigned int i; - if (!cfg80211_regdomain) - return -EINVAL; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOBUFS; - - hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, - NL80211_CMD_GET_REG); - if (!hdr) - goto 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; + goto nla_put_failure; nl_reg_rules = nla_nest_start(msg, NL80211_ATTR_REG_RULES); if (!nl_reg_rules) - goto nla_put_failure_rcu; + goto nla_put_failure; for (i = 0; i < regdom->n_reg_rules; i++) { struct nlattr *nl_reg_rule; @@ -5377,7 +5377,7 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) nl_reg_rule = nla_nest_start(msg, i); if (!nl_reg_rule) - goto nla_put_failure_rcu; + goto nla_put_failure; max_bandwidth_khz = freq_range->max_bandwidth_khz; if (!max_bandwidth_khz) @@ -5398,13 +5398,74 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) power_rule->max_eirp) || nla_put_u32(msg, NL80211_ATTR_DFS_CAC_TIME, reg_rule->dfs_cac_ms)) - goto nla_put_failure_rcu; + goto nla_put_failure; nla_nest_end(msg, nl_reg_rule); } - rcu_read_unlock(); nla_nest_end(msg, nl_reg_rules); + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int nl80211_get_reg_do(struct sk_buff *skb, struct genl_info *info) +{ + const struct ieee80211_regdomain *regdom = NULL; + struct cfg80211_registered_device *rdev; + struct wiphy *wiphy = NULL; + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOBUFS; + + hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, + NL80211_CMD_GET_REG); + if (!hdr) + goto put_failure; + + if (info->attrs[NL80211_ATTR_WIPHY]) { + bool self_managed; + + rdev = cfg80211_get_dev_from_info(genl_info_net(info), info); + if (IS_ERR(rdev)) { + nlmsg_free(msg); + return PTR_ERR(rdev); + } + + wiphy = &rdev->wiphy; + self_managed = wiphy->regulatory_flags & + REGULATORY_WIPHY_SELF_MANAGED; + regdom = get_wiphy_regdom(wiphy); + + /* a self-managed-reg device must have a private regdom */ + if (WARN_ON(!regdom && self_managed)) { + nlmsg_free(msg); + return -EINVAL; + } + + if (regdom && + nla_put_u32(msg, NL80211_ATTR_WIPHY, get_wiphy_idx(wiphy))) + goto nla_put_failure; + } + + if (!wiphy && 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(); + + if (!regdom) + regdom = rcu_dereference(cfg80211_regdomain); + + if (nl80211_put_regdom(regdom, msg)) + goto nla_put_failure_rcu; + + rcu_read_unlock(); genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); @@ -5418,6 +5479,83 @@ put_failure: return -EMSGSIZE; } +static int nl80211_send_regdom(struct sk_buff *msg, struct netlink_callback *cb, + u32 seq, int flags, struct wiphy *wiphy, + const struct ieee80211_regdomain *regdom) +{ + void *hdr = nl80211hdr_put(msg, NETLINK_CB(cb->skb).portid, seq, flags, + NL80211_CMD_GET_REG); + + if (!hdr) + return -1; + + genl_dump_check_consistent(cb, hdr, &nl80211_fam); + + if (nl80211_put_regdom(regdom, msg)) + goto nla_put_failure; + + if (!wiphy && 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; + + if (wiphy && + nla_put_u32(msg, NL80211_ATTR_WIPHY, get_wiphy_idx(wiphy))) + goto nla_put_failure; + + if (wiphy && wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED && + nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG)) + goto nla_put_failure; + + return genlmsg_end(msg, hdr); + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int nl80211_get_reg_dump(struct sk_buff *skb, + struct netlink_callback *cb) +{ + const struct ieee80211_regdomain *regdom = NULL; + struct cfg80211_registered_device *rdev; + int err, reg_idx, start = cb->args[2]; + + rtnl_lock(); + + if (cfg80211_regdomain && start == 0) { + err = nl80211_send_regdom(skb, cb, cb->nlh->nlmsg_seq, + NLM_F_MULTI, NULL, + rtnl_dereference(cfg80211_regdomain)); + if (err < 0) + goto out_err; + } + + /* the global regdom is idx 0 */ + reg_idx = 1; + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + regdom = get_wiphy_regdom(&rdev->wiphy); + if (!regdom) + continue; + + if (++reg_idx <= start) + continue; + + err = nl80211_send_regdom(skb, cb, cb->nlh->nlmsg_seq, + NLM_F_MULTI, &rdev->wiphy, regdom); + if (err < 0) { + reg_idx--; + break; + } + } + + cb->args[2] = reg_idx; + err = skb->len; +out_err: + rtnl_unlock(); + return err; +} + static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[NL80211_REG_RULE_ATTR_MAX + 1]; @@ -6069,6 +6207,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_sched_scan_request *sched_scan_req; int err; if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) || @@ -6078,27 +6217,32 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, if (rdev->sched_scan_req) return -EINPROGRESS; - rdev->sched_scan_req = nl80211_parse_sched_scan(&rdev->wiphy, wdev, - info->attrs); - err = PTR_ERR_OR_ZERO(rdev->sched_scan_req); + sched_scan_req = nl80211_parse_sched_scan(&rdev->wiphy, wdev, + info->attrs); + + err = PTR_ERR_OR_ZERO(sched_scan_req); if (err) goto out_err; - err = rdev_sched_scan_start(rdev, dev, rdev->sched_scan_req); + err = rdev_sched_scan_start(rdev, dev, sched_scan_req); if (err) goto out_free; - rdev->sched_scan_req->dev = dev; - rdev->sched_scan_req->wiphy = &rdev->wiphy; + sched_scan_req->dev = dev; + sched_scan_req->wiphy = &rdev->wiphy; + + if (info->attrs[NL80211_ATTR_SOCKET_OWNER]) + sched_scan_req->owner_nlportid = info->snd_portid; + + rcu_assign_pointer(rdev->sched_scan_req, sched_scan_req); nl80211_send_sched_scan(rdev, dev, NL80211_CMD_START_SCHED_SCAN); return 0; out_free: - kfree(rdev->sched_scan_req); + kfree(sched_scan_req); out_err: - rdev->sched_scan_req = NULL; return err; } @@ -6481,12 +6625,17 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) } static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq, - int flags, struct net_device *dev, - struct survey_info *survey) + int flags, struct net_device *dev, + bool allow_radio_stats, + struct survey_info *survey) { void *hdr; struct nlattr *infoattr; + /* skip radio stats if userspace didn't request them */ + if (!survey->channel && !allow_radio_stats) + return 0; + hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_SURVEY_RESULTS); if (!hdr) @@ -6499,7 +6648,8 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq, if (!infoattr) goto nla_put_failure; - if (nla_put_u32(msg, NL80211_SURVEY_INFO_FREQUENCY, + if (survey->channel && + nla_put_u32(msg, NL80211_SURVEY_INFO_FREQUENCY, survey->channel->center_freq)) goto nla_put_failure; @@ -6509,25 +6659,29 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq, if ((survey->filled & SURVEY_INFO_IN_USE) && nla_put_flag(msg, NL80211_SURVEY_INFO_IN_USE)) goto nla_put_failure; - if ((survey->filled & SURVEY_INFO_CHANNEL_TIME) && - nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME, - survey->channel_time)) + if ((survey->filled & SURVEY_INFO_TIME) && + nla_put_u64(msg, NL80211_SURVEY_INFO_TIME, + survey->time)) goto nla_put_failure; - if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_BUSY) && - nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_BUSY, - survey->channel_time_busy)) + if ((survey->filled & SURVEY_INFO_TIME_BUSY) && + nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_BUSY, + survey->time_busy)) goto nla_put_failure; - if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY) && - nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_EXT_BUSY, - survey->channel_time_ext_busy)) + if ((survey->filled & SURVEY_INFO_TIME_EXT_BUSY) && + nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_EXT_BUSY, + survey->time_ext_busy)) goto nla_put_failure; - if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_RX) && - nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_RX, - survey->channel_time_rx)) + if ((survey->filled & SURVEY_INFO_TIME_RX) && + nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_RX, + survey->time_rx)) goto nla_put_failure; - if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_TX) && - nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_TX, - survey->channel_time_tx)) + if ((survey->filled & SURVEY_INFO_TIME_TX) && + nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_TX, + survey->time_tx)) + goto nla_put_failure; + if ((survey->filled & SURVEY_INFO_TIME_SCAN) && + nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_SCAN, + survey->time_scan)) goto nla_put_failure; nla_nest_end(msg, infoattr); @@ -6539,19 +6693,22 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq, return -EMSGSIZE; } -static int nl80211_dump_survey(struct sk_buff *skb, - struct netlink_callback *cb) +static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) { struct survey_info survey; struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; int survey_idx = cb->args[2]; int res; + bool radio_stats; res = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev); if (res) return res; + /* prepare_wdev_dump parsed the attributes */ + radio_stats = nl80211_fam.attrbuf[NL80211_ATTR_SURVEY_RADIO_STATS]; + if (!wdev->netdev) { res = -EINVAL; goto out_err; @@ -6569,13 +6726,9 @@ static int nl80211_dump_survey(struct sk_buff *skb, if (res) goto out_err; - /* Survey without a channel doesn't make sense */ - if (!survey.channel) { - res = -EINVAL; - goto out; - } - - if (survey.channel->flags & IEEE80211_CHAN_DISABLED) { + /* don't send disabled channels, but do send non-channel data */ + if (survey.channel && + survey.channel->flags & IEEE80211_CHAN_DISABLED) { survey_idx++; continue; } @@ -6583,7 +6736,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, if (nl80211_send_survey(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - wdev->netdev, &survey) < 0) + wdev->netdev, radio_stats, &survey) < 0) goto out; survey_idx++; } @@ -8599,6 +8752,48 @@ static int nl80211_send_wowlan_tcp(struct sk_buff *msg, return 0; } +static int nl80211_send_wowlan_nd(struct sk_buff *msg, + struct cfg80211_sched_scan_request *req) +{ + struct nlattr *nd, *freqs, *matches, *match; + int i; + + if (!req) + return 0; + + nd = nla_nest_start(msg, NL80211_WOWLAN_TRIG_NET_DETECT); + if (!nd) + return -ENOBUFS; + + if (nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_INTERVAL, req->interval)) + return -ENOBUFS; + + freqs = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQUENCIES); + if (!freqs) + return -ENOBUFS; + + for (i = 0; i < req->n_channels; i++) + nla_put_u32(msg, i, req->channels[i]->center_freq); + + nla_nest_end(msg, freqs); + + if (req->n_match_sets) { + matches = nla_nest_start(msg, NL80211_ATTR_SCHED_SCAN_MATCH); + for (i = 0; i < req->n_match_sets; i++) { + match = nla_nest_start(msg, i); + nla_put(msg, NL80211_SCHED_SCAN_MATCH_ATTR_SSID, + req->match_sets[i].ssid.ssid_len, + req->match_sets[i].ssid.ssid); + nla_nest_end(msg, match); + } + nla_nest_end(msg, matches); + } + + nla_nest_end(msg, nd); + + return 0; +} + static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -8656,6 +8851,11 @@ static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info) rdev->wiphy.wowlan_config->tcp)) goto nla_put_failure; + if (nl80211_send_wowlan_nd( + msg, + rdev->wiphy.wowlan_config->nd_config)) + goto nla_put_failure; + nla_nest_end(msg, nl_wowlan); } @@ -10225,7 +10425,8 @@ static const struct genl_ops nl80211_ops[] = { }, { .cmd = NL80211_CMD_GET_REG, - .doit = nl80211_get_reg, + .doit = nl80211_get_reg_do, + .dumpit = nl80211_get_reg_dump, .policy = nl80211_policy, .internal_flags = NL80211_FLAG_NEED_RTNL, /* can be retrieved by unprivileged users */ @@ -10939,25 +11140,9 @@ void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev, NL80211_MCGRP_SCAN, GFP_KERNEL); } -/* - * This can happen on global regulatory changes or device specific settings - * based on custom world regulatory domains. - */ -void nl80211_send_reg_change_event(struct regulatory_request *request) +static bool nl80211_reg_change_event_fill(struct sk_buff *msg, + struct regulatory_request *request) { - struct sk_buff *msg; - void *hdr; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_REG_CHANGE); - if (!hdr) { - nlmsg_free(msg); - return; - } - /* Userspace can always count this one always being set */ if (nla_put_u8(msg, NL80211_ATTR_REG_INITIATOR, request->initiator)) goto nla_put_failure; @@ -10983,8 +11168,46 @@ void nl80211_send_reg_change_event(struct regulatory_request *request) goto nla_put_failure; } - if (request->wiphy_idx != WIPHY_IDX_INVALID && - nla_put_u32(msg, NL80211_ATTR_WIPHY, request->wiphy_idx)) + if (request->wiphy_idx != WIPHY_IDX_INVALID) { + struct wiphy *wiphy = wiphy_idx_to_wiphy(request->wiphy_idx); + + if (wiphy && + nla_put_u32(msg, NL80211_ATTR_WIPHY, request->wiphy_idx)) + goto nla_put_failure; + + if (wiphy && + wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED && + nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG)) + goto nla_put_failure; + } + + return true; + +nla_put_failure: + return false; +} + +/* + * This can happen on global regulatory changes or device specific settings + * based on custom regulatory domains. + */ +void nl80211_common_reg_change_event(enum nl80211_commands cmd_id, + struct regulatory_request *request) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, cmd_id); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nl80211_reg_change_event_fill(msg, request) == false) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -11523,7 +11746,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr, if (!msg) return; - if (nl80211_send_station(msg, 0, 0, 0, + if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, 0, 0, 0, rdev, dev, mac_addr, sinfo) < 0) { nlmsg_free(msg); return; @@ -11534,12 +11757,16 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr, } EXPORT_SYMBOL(cfg80211_new_sta); -void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp) +void cfg80211_del_sta_sinfo(struct net_device *dev, const u8 *mac_addr, + struct station_info *sinfo, gfp_t gfp) { struct wiphy *wiphy = dev->ieee80211_ptr->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct sk_buff *msg; - void *hdr; + struct station_info empty_sinfo = {}; + + if (!sinfo) + sinfo = &empty_sinfo; trace_cfg80211_del_sta(dev, mac_addr); @@ -11547,27 +11774,16 @@ void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp) if (!msg) return; - hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_DEL_STATION); - if (!hdr) { + if (nl80211_send_station(msg, NL80211_CMD_DEL_STATION, 0, 0, 0, + rdev, dev, mac_addr, sinfo)) { nlmsg_free(msg); return; } - if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || - nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr)) - goto nla_put_failure; - - genlmsg_end(msg, hdr); - genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, NL80211_MCGRP_MLME, gfp); - return; - - nla_put_failure: - genlmsg_cancel(msg, hdr); - nlmsg_free(msg); } -EXPORT_SYMBOL(cfg80211_del_sta); +EXPORT_SYMBOL(cfg80211_del_sta_sinfo); void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr, enum nl80211_connect_failed_reason reason, @@ -12471,6 +12687,13 @@ static int nl80211_netlink_notify(struct notifier_block * nb, list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) { bool schedule_destroy_work = false; + bool schedule_scan_stop = false; + struct cfg80211_sched_scan_request *sched_scan_req = + rcu_dereference(rdev->sched_scan_req); + + if (sched_scan_req && notify->portid && + sched_scan_req->owner_nlportid == notify->portid) + schedule_scan_stop = true; list_for_each_entry_rcu(wdev, &rdev->wdev_list, list) { cfg80211_mlme_unregister_socket(wdev, notify->portid); @@ -12501,6 +12724,12 @@ static int nl80211_netlink_notify(struct notifier_block * nb, spin_unlock(&rdev->destroy_list_lock); schedule_work(&rdev->destroy_work); } + } else if (schedule_scan_stop) { + sched_scan_req->owner_nlportid = 0; + + if (rdev->ops->sched_scan_stop && + rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) + schedule_work(&rdev->sched_scan_stop_wk); } } diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 7ad70d6f0cc6..84d4edf1d545 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -17,7 +17,21 @@ void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev, struct net_device *netdev, u32 cmd); void nl80211_send_sched_scan_results(struct cfg80211_registered_device *rdev, struct net_device *netdev); -void nl80211_send_reg_change_event(struct regulatory_request *request); +void nl80211_common_reg_change_event(enum nl80211_commands cmd_id, + struct regulatory_request *request); + +static inline void +nl80211_send_reg_change_event(struct regulatory_request *request) +{ + nl80211_common_reg_change_event(NL80211_CMD_REG_CHANGE, request); +} + +static inline void +nl80211_send_wiphy_reg_change_event(struct regulatory_request *request) +{ + nl80211_common_reg_change_event(NL80211_CMD_WIPHY_REG_CHANGE, request); +} + void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, size_t len, gfp_t gfp); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 7b8309840d4e..886cc7cb5566 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -109,7 +109,7 @@ static struct regulatory_request core_request_world = { * protected by RTNL (and can be accessed with RCU protection) */ static struct regulatory_request __rcu *last_request = - (void __rcu *)&core_request_world; + (void __force __rcu *)&core_request_world; /* To trigger userspace events */ static struct platform_device *reg_pdev; @@ -142,7 +142,7 @@ static const struct ieee80211_regdomain *get_cfg80211_regdom(void) return rtnl_dereference(cfg80211_regdomain); } -static const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy) +const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy) { return rtnl_dereference(wiphy->regd); } @@ -1307,6 +1307,9 @@ static bool ignore_reg_update(struct wiphy *wiphy, { struct regulatory_request *lr = get_last_request(); + if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) + return true; + if (!lr) { REG_DBG_PRINT("Ignoring regulatory request set by %s " "since last_request is not set\n", @@ -1683,8 +1686,12 @@ static void handle_channel_custom(struct wiphy *wiphy, if (IS_ERR(reg_rule)) { REG_DBG_PRINT("Disabling freq %d MHz as custom regd has no rule that fits it\n", chan->center_freq); - chan->orig_flags |= IEEE80211_CHAN_DISABLED; - chan->flags = chan->orig_flags; + if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) { + chan->flags |= IEEE80211_CHAN_DISABLED; + } else { + chan->orig_flags |= IEEE80211_CHAN_DISABLED; + chan->flags = chan->orig_flags; + } return; } @@ -1709,7 +1716,13 @@ static void handle_channel_custom(struct wiphy *wiphy, chan->dfs_state = NL80211_DFS_USABLE; chan->beacon_found = false; - chan->flags |= map_regdom_flags(reg_rule->flags) | bw_flags; + + if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) + chan->flags = chan->orig_flags | bw_flags | + map_regdom_flags(reg_rule->flags); + else + chan->flags |= map_regdom_flags(reg_rule->flags) | bw_flags; + chan->max_antenna_gain = (int) MBI_TO_DBI(power_rule->max_antenna_gain); chan->max_reg_power = chan->max_power = (int) MBM_TO_DBM(power_rule->max_eirp); @@ -2095,6 +2108,26 @@ out_free: reg_free_request(reg_request); } +static bool reg_only_self_managed_wiphys(void) +{ + struct cfg80211_registered_device *rdev; + struct wiphy *wiphy; + bool self_managed_found = false; + + ASSERT_RTNL(); + + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + wiphy = &rdev->wiphy; + if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) + self_managed_found = true; + else + return false; + } + + /* make sure at least one self-managed wiphy exists */ + return self_managed_found; +} + /* * Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_* * Regulatory hints come on a first come first serve basis and we @@ -2126,6 +2159,11 @@ static void reg_process_pending_hints(void) spin_unlock(®_requests_lock); + if (reg_only_self_managed_wiphys()) { + reg_free_request(reg_request); + return; + } + reg_process_hint(reg_request); } @@ -2153,11 +2191,52 @@ static void reg_process_pending_beacon_hints(void) spin_unlock_bh(®_pending_beacons_lock); } +static void reg_process_self_managed_hints(void) +{ + struct cfg80211_registered_device *rdev; + struct wiphy *wiphy; + const struct ieee80211_regdomain *tmp; + const struct ieee80211_regdomain *regd; + enum ieee80211_band band; + struct regulatory_request request = {}; + + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + wiphy = &rdev->wiphy; + + spin_lock(®_requests_lock); + regd = rdev->requested_regd; + rdev->requested_regd = NULL; + spin_unlock(®_requests_lock); + + if (regd == NULL) + continue; + + tmp = get_wiphy_regdom(wiphy); + rcu_assign_pointer(wiphy->regd, regd); + rcu_free_regdom(tmp); + + for (band = 0; band < IEEE80211_NUM_BANDS; band++) + handle_band_custom(wiphy, wiphy->bands[band], regd); + + reg_process_ht_flags(wiphy); + + request.wiphy_idx = get_wiphy_idx(wiphy); + request.alpha2[0] = regd->alpha2[0]; + request.alpha2[1] = regd->alpha2[1]; + request.initiator = NL80211_REGDOM_SET_BY_DRIVER; + + nl80211_send_wiphy_reg_change_event(&request); + } + + reg_check_channels(); +} + static void reg_todo(struct work_struct *work) { rtnl_lock(); reg_process_pending_hints(); reg_process_pending_beacon_hints(); + reg_process_self_managed_hints(); rtnl_unlock(); } @@ -2438,6 +2517,8 @@ static void restore_regulatory_settings(bool reset_user) world_alpha2[1] = cfg80211_world_regdom->alpha2[1]; list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + if (rdev->wiphy.regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) + continue; if (rdev->wiphy.regulatory_flags & REGULATORY_CUSTOM_REG) restore_custom_reg_settings(&rdev->wiphy); } @@ -2841,10 +2922,79 @@ int set_regdom(const struct ieee80211_regdomain *rd) return 0; } +static int __regulatory_set_wiphy_regd(struct wiphy *wiphy, + struct ieee80211_regdomain *rd) +{ + const struct ieee80211_regdomain *regd; + const struct ieee80211_regdomain *prev_regd; + struct cfg80211_registered_device *rdev; + + if (WARN_ON(!wiphy || !rd)) + return -EINVAL; + + if (WARN(!(wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED), + "wiphy should have REGULATORY_WIPHY_SELF_MANAGED\n")) + return -EPERM; + + if (WARN(!is_valid_rd(rd), "Invalid regulatory domain detected\n")) { + print_regdomain_info(rd); + return -EINVAL; + } + + regd = reg_copy_regd(rd); + if (IS_ERR(regd)) + return PTR_ERR(regd); + + rdev = wiphy_to_rdev(wiphy); + + spin_lock(®_requests_lock); + prev_regd = rdev->requested_regd; + rdev->requested_regd = regd; + spin_unlock(®_requests_lock); + + kfree(prev_regd); + return 0; +} + +int regulatory_set_wiphy_regd(struct wiphy *wiphy, + struct ieee80211_regdomain *rd) +{ + int ret = __regulatory_set_wiphy_regd(wiphy, rd); + + if (ret) + return ret; + + schedule_work(®_work); + return 0; +} +EXPORT_SYMBOL(regulatory_set_wiphy_regd); + +int regulatory_set_wiphy_regd_sync_rtnl(struct wiphy *wiphy, + struct ieee80211_regdomain *rd) +{ + int ret; + + ASSERT_RTNL(); + + ret = __regulatory_set_wiphy_regd(wiphy, rd); + if (ret) + return ret; + + /* process the request immediately */ + reg_process_self_managed_hints(); + return 0; +} +EXPORT_SYMBOL(regulatory_set_wiphy_regd_sync_rtnl); + void wiphy_regulatory_register(struct wiphy *wiphy) { struct regulatory_request *lr; + /* self-managed devices ignore external hints */ + if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) + wiphy->regulatory_flags |= REGULATORY_DISABLE_BEACON_HINTS | + REGULATORY_COUNTRY_IE_IGNORE; + if (!reg_dev_ignore_cell_hint(wiphy)) reg_num_devs_support_basehint++; diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 5e48031ccb9a..4b45d6e61d24 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -38,6 +38,7 @@ unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd, const struct ieee80211_reg_rule *rule); bool reg_last_request_cell_base(void); +const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy); /** * regulatory_hint_found_beacon - hints a beacon was found on a channel diff --git a/net/wireless/scan.c b/net/wireless/scan.c index bda39f149810..c705c3e2b751 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -257,7 +257,7 @@ void __cfg80211_sched_scan_results(struct work_struct *wk) rtnl_lock(); - request = rdev->sched_scan_req; + request = rtnl_dereference(rdev->sched_scan_req); /* we don't have sched_scan_req anymore if the scan is stopping */ if (request) { @@ -279,7 +279,8 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy) { trace_cfg80211_sched_scan_results(wiphy); /* ignore if we're not scanning */ - if (wiphy_to_rdev(wiphy)->sched_scan_req) + + if (rcu_access_pointer(wiphy_to_rdev(wiphy)->sched_scan_req)) queue_work(cfg80211_wq, &wiphy_to_rdev(wiphy)->sched_scan_results_wk); } @@ -308,6 +309,7 @@ EXPORT_SYMBOL(cfg80211_sched_scan_stopped); int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev, bool driver_initiated) { + struct cfg80211_sched_scan_request *sched_scan_req; struct net_device *dev; ASSERT_RTNL(); @@ -315,7 +317,8 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev, if (!rdev->sched_scan_req) return -ENOENT; - dev = rdev->sched_scan_req->dev; + sched_scan_req = rtnl_dereference(rdev->sched_scan_req); + dev = sched_scan_req->dev; if (!driver_initiated) { int err = rdev_sched_scan_stop(rdev, dev); @@ -325,8 +328,8 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev, nl80211_send_sched_scan(rdev, dev, NL80211_CMD_SCHED_SCAN_STOPPED); - kfree(rdev->sched_scan_req); - rdev->sched_scan_req = NULL; + RCU_INIT_POINTER(rdev->sched_scan_req, NULL); + kfree_rcu(sched_scan_req, rcu_head); return 0; } diff --git a/net/wireless/trace.h b/net/wireless/trace.h index ad38910f7036..b17b3692f8c2 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1604,11 +1604,12 @@ TRACE_EVENT(rdev_return_int_survey_info, WIPHY_ENTRY CHAN_ENTRY __field(int, ret) - __field(u64, channel_time) - __field(u64, channel_time_busy) - __field(u64, channel_time_ext_busy) - __field(u64, channel_time_rx) - __field(u64, channel_time_tx) + __field(u64, time) + __field(u64, time_busy) + __field(u64, time_ext_busy) + __field(u64, time_rx) + __field(u64, time_tx) + __field(u64, time_scan) __field(u32, filled) __field(s8, noise) ), @@ -1616,22 +1617,24 @@ TRACE_EVENT(rdev_return_int_survey_info, WIPHY_ASSIGN; CHAN_ASSIGN(info->channel); __entry->ret = ret; - __entry->channel_time = info->channel_time; - __entry->channel_time_busy = info->channel_time_busy; - __entry->channel_time_ext_busy = info->channel_time_ext_busy; - __entry->channel_time_rx = info->channel_time_rx; - __entry->channel_time_tx = info->channel_time_tx; + __entry->time = info->time; + __entry->time_busy = info->time_busy; + __entry->time_ext_busy = info->time_ext_busy; + __entry->time_rx = info->time_rx; + __entry->time_tx = info->time_tx; + __entry->time_scan = info->time_scan; __entry->filled = info->filled; __entry->noise = info->noise; ), TP_printk(WIPHY_PR_FMT ", returned: %d, " CHAN_PR_FMT ", channel time: %llu, channel time busy: %llu, " "channel time extension busy: %llu, channel time rx: %llu, " - "channel time tx: %llu, filled: %u, noise: %d", + "channel time tx: %llu, scan time: %llu, filled: %u, noise: %d", WIPHY_PR_ARG, __entry->ret, CHAN_PR_ARG, - __entry->channel_time, __entry->channel_time_busy, - __entry->channel_time_ext_busy, __entry->channel_time_rx, - __entry->channel_time_tx, __entry->filled, __entry->noise) + __entry->time, __entry->time_busy, + __entry->time_ext_busy, __entry->time_rx, + __entry->time_tx, __entry->time_scan, + __entry->filled, __entry->noise) ); TRACE_EVENT(rdev_tdls_oper, diff --git a/net/wireless/util.c b/net/wireless/util.c index d0ac795445b7..1d2fcfad06cc 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -708,8 +708,8 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, if (skb->priority >= 256 && skb->priority <= 263) return skb->priority - 256; - if (vlan_tx_tag_present(skb)) { - vlan_priority = (vlan_tx_tag_get(skb) & VLAN_PRIO_MASK) + if (skb_vlan_tag_present(skb)) { + vlan_priority = (skb_vlan_tag_get(skb) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; if (vlan_priority > 0) return vlan_priority; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 0f47948c572f..5b24d39d7903 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -1300,7 +1300,7 @@ static int cfg80211_wext_giwrate(struct net_device *dev, if (err) return err; - if (!(sinfo.filled & STATION_INFO_TX_BITRATE)) + if (!(sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE))) return -EOPNOTSUPP; rate->value = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate); @@ -1340,7 +1340,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: - if (sinfo.filled & STATION_INFO_SIGNAL) { + if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) { int sig = sinfo.signal; wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; @@ -1354,7 +1354,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) break; } case CFG80211_SIGNAL_TYPE_UNSPEC: - if (sinfo.filled & STATION_INFO_SIGNAL) { + if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) { wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; wstats.qual.level = sinfo.signal; @@ -1367,9 +1367,9 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) } wstats.qual.updated |= IW_QUAL_NOISE_INVALID; - if (sinfo.filled & STATION_INFO_RX_DROP_MISC) + if (sinfo.filled & BIT(NL80211_STA_INFO_RX_DROP_MISC)) wstats.discard.misc = sinfo.rx_dropped_misc; - if (sinfo.filled & STATION_INFO_TX_FAILED) + if (sinfo.filled & BIT(NL80211_STA_INFO_TX_FAILED)) wstats.discard.retries = sinfo.tx_failed; return &wstats; diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index debe733386f8..12e82a5e4ad5 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -561,11 +561,6 @@ static struct xfrm_algo_desc calg_list[] = { }, }; -static inline int aead_entries(void) -{ - return ARRAY_SIZE(aead_list); -} - static inline int aalg_entries(void) { return ARRAY_SIZE(aalg_list); |