diff options
Diffstat (limited to 'net')
97 files changed, 1978 insertions, 1094 deletions
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 97b42d3c4bef..a2b480a90872 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -87,22 +87,198 @@ static uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[]) return (uint8_t)(sum / count); } +/** + * batadv_iv_ogm_orig_free - free the private resources allocated for this + * orig_node + * @orig_node: the orig_node for which the resources have to be free'd + */ +static void batadv_iv_ogm_orig_free(struct batadv_orig_node *orig_node) +{ + kfree(orig_node->bat_iv.bcast_own); + kfree(orig_node->bat_iv.bcast_own_sum); +} + +/** + * batadv_iv_ogm_orig_add_if - change the private structures of the orig_node to + * include the new hard-interface + * @orig_node: the orig_node that has to be changed + * @max_if_num: the current amount of interfaces + * + * Returns 0 on success, a negative error code otherwise. + */ +static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node, + int max_if_num) +{ + void *data_ptr; + size_t data_size, old_size; + int ret = -ENOMEM; + + spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); + + data_size = max_if_num * sizeof(unsigned long) * BATADV_NUM_WORDS; + old_size = (max_if_num - 1) * sizeof(unsigned long) * BATADV_NUM_WORDS; + data_ptr = kmalloc(data_size, GFP_ATOMIC); + if (!data_ptr) + goto unlock; + + memcpy(data_ptr, orig_node->bat_iv.bcast_own, old_size); + kfree(orig_node->bat_iv.bcast_own); + orig_node->bat_iv.bcast_own = data_ptr; + + data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC); + if (!data_ptr) { + kfree(orig_node->bat_iv.bcast_own); + goto unlock; + } + + memcpy(data_ptr, orig_node->bat_iv.bcast_own_sum, + (max_if_num - 1) * sizeof(uint8_t)); + kfree(orig_node->bat_iv.bcast_own_sum); + orig_node->bat_iv.bcast_own_sum = data_ptr; + + ret = 0; + +unlock: + spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); + + return ret; +} + +/** + * batadv_iv_ogm_orig_del_if - change the private structures of the orig_node to + * exclude the removed interface + * @orig_node: the orig_node that has to be changed + * @max_if_num: the current amount of interfaces + * @del_if_num: the index of the interface being removed + * + * Returns 0 on success, a negative error code otherwise. + */ +static int batadv_iv_ogm_orig_del_if(struct batadv_orig_node *orig_node, + int max_if_num, int del_if_num) +{ + int chunk_size, ret = -ENOMEM, if_offset; + void *data_ptr = NULL; + + spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); + + /* last interface was removed */ + if (max_if_num == 0) + goto free_bcast_own; + + chunk_size = sizeof(unsigned long) * BATADV_NUM_WORDS; + data_ptr = kmalloc(max_if_num * chunk_size, GFP_ATOMIC); + if (!data_ptr) + goto unlock; + + /* copy first part */ + memcpy(data_ptr, orig_node->bat_iv.bcast_own, del_if_num * chunk_size); + + /* copy second part */ + memcpy((char *)data_ptr + del_if_num * chunk_size, + orig_node->bat_iv.bcast_own + ((del_if_num + 1) * chunk_size), + (max_if_num - del_if_num) * chunk_size); + +free_bcast_own: + kfree(orig_node->bat_iv.bcast_own); + orig_node->bat_iv.bcast_own = data_ptr; + + if (max_if_num == 0) + goto free_own_sum; + + data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC); + if (!data_ptr) { + kfree(orig_node->bat_iv.bcast_own); + goto unlock; + } + + memcpy(data_ptr, orig_node->bat_iv.bcast_own_sum, + del_if_num * sizeof(uint8_t)); + + if_offset = (del_if_num + 1) * sizeof(uint8_t); + memcpy((char *)data_ptr + del_if_num * sizeof(uint8_t), + orig_node->bat_iv.bcast_own_sum + if_offset, + (max_if_num - del_if_num) * sizeof(uint8_t)); + +free_own_sum: + kfree(orig_node->bat_iv.bcast_own_sum); + orig_node->bat_iv.bcast_own_sum = data_ptr; + + ret = 0; +unlock: + spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); + + return ret; +} + +/** + * batadv_iv_ogm_orig_get - retrieve or create (if does not exist) an originator + * @bat_priv: the bat priv with all the soft interface information + * @addr: mac address of the originator + * + * Returns the originator object corresponding to the passed mac address or NULL + * on failure. + * If the object does not exists it is created an initialised. + */ +static struct batadv_orig_node * +batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const uint8_t *addr) +{ + struct batadv_orig_node *orig_node; + int size, hash_added; + + orig_node = batadv_orig_hash_find(bat_priv, addr); + if (orig_node) + return orig_node; + + orig_node = batadv_orig_node_new(bat_priv, addr); + if (!orig_node) + return NULL; + + spin_lock_init(&orig_node->bat_iv.ogm_cnt_lock); + + size = bat_priv->num_ifaces * sizeof(unsigned long) * BATADV_NUM_WORDS; + orig_node->bat_iv.bcast_own = kzalloc(size, GFP_ATOMIC); + if (!orig_node->bat_iv.bcast_own) + goto free_orig_node; + + size = bat_priv->num_ifaces * sizeof(uint8_t); + orig_node->bat_iv.bcast_own_sum = kzalloc(size, GFP_ATOMIC); + if (!orig_node->bat_iv.bcast_own_sum) + goto free_bcast_own; + + hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig, + batadv_choose_orig, orig_node, + &orig_node->hash_entry); + if (hash_added != 0) + goto free_bcast_own; + + return orig_node; + +free_bcast_own: + kfree(orig_node->bat_iv.bcast_own); +free_orig_node: + batadv_orig_node_free_ref(orig_node); + + return NULL; +} + static struct batadv_neigh_node * batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, const uint8_t *neigh_addr, struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh) { + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_neigh_node *neigh_node; - neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr); + neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, orig_node); if (!neigh_node) goto out; - INIT_LIST_HEAD(&neigh_node->bonding_list); + spin_lock_init(&neigh_node->bat_iv.lq_update_lock); - neigh_node->orig_node = orig_neigh; - neigh_node->if_incoming = hard_iface; + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Creating new neighbor %pM for orig_node %pM on interface %s\n", + neigh_addr, orig_node->orig, hard_iface->net_dev->name); spin_lock_bh(&orig_node->neigh_list_lock); hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); @@ -661,20 +837,22 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) uint32_t i; size_t word_index; uint8_t *w; + int if_num; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) { - spin_lock_bh(&orig_node->ogm_cnt_lock); + spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); word_index = hard_iface->if_num * BATADV_NUM_WORDS; - word = &(orig_node->bcast_own[word_index]); + word = &(orig_node->bat_iv.bcast_own[word_index]); batadv_bit_get_packet(bat_priv, word, 1, 0); - w = &orig_node->bcast_own_sum[hard_iface->if_num]; + if_num = hard_iface->if_num; + w = &orig_node->bat_iv.bcast_own_sum[if_num]; *w = bitmap_weight(word, BATADV_TQ_LOCAL_WINDOW_SIZE); - spin_unlock_bh(&orig_node->ogm_cnt_lock); + spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); } rcu_read_unlock(); } @@ -755,18 +933,18 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, if (dup_status != BATADV_NO_DUP) continue; - spin_lock_bh(&tmp_neigh_node->lq_update_lock); - batadv_ring_buffer_set(tmp_neigh_node->tq_recv, - &tmp_neigh_node->tq_index, 0); - tq_avg = batadv_ring_buffer_avg(tmp_neigh_node->tq_recv); - tmp_neigh_node->tq_avg = tq_avg; - spin_unlock_bh(&tmp_neigh_node->lq_update_lock); + spin_lock_bh(&tmp_neigh_node->bat_iv.lq_update_lock); + batadv_ring_buffer_set(tmp_neigh_node->bat_iv.tq_recv, + &tmp_neigh_node->bat_iv.tq_index, 0); + tq_avg = batadv_ring_buffer_avg(tmp_neigh_node->bat_iv.tq_recv); + tmp_neigh_node->bat_iv.tq_avg = tq_avg; + spin_unlock_bh(&tmp_neigh_node->bat_iv.lq_update_lock); } if (!neigh_node) { struct batadv_orig_node *orig_tmp; - orig_tmp = batadv_get_orig_node(bat_priv, ethhdr->h_source); + orig_tmp = batadv_iv_ogm_orig_get(bat_priv, ethhdr->h_source); if (!orig_tmp) goto unlock; @@ -785,19 +963,20 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, neigh_node->last_seen = jiffies; - spin_lock_bh(&neigh_node->lq_update_lock); - batadv_ring_buffer_set(neigh_node->tq_recv, - &neigh_node->tq_index, + spin_lock_bh(&neigh_node->bat_iv.lq_update_lock); + batadv_ring_buffer_set(neigh_node->bat_iv.tq_recv, + &neigh_node->bat_iv.tq_index, batadv_ogm_packet->tq); - neigh_node->tq_avg = batadv_ring_buffer_avg(neigh_node->tq_recv); - spin_unlock_bh(&neigh_node->lq_update_lock); + tq_avg = batadv_ring_buffer_avg(neigh_node->bat_iv.tq_recv); + neigh_node->bat_iv.tq_avg = tq_avg; + spin_unlock_bh(&neigh_node->bat_iv.lq_update_lock); if (dup_status == BATADV_NO_DUP) { orig_node->last_ttl = batadv_ogm_packet->header.ttl; neigh_node->last_ttl = batadv_ogm_packet->header.ttl; } - batadv_bonding_candidate_add(orig_node, neigh_node); + batadv_bonding_candidate_add(bat_priv, orig_node, neigh_node); /* if this neighbor already is our next hop there is nothing * to change @@ -807,24 +986,24 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, goto out; /* if this neighbor does not offer a better TQ we won't consider it */ - if (router && (router->tq_avg > neigh_node->tq_avg)) + if (router && (router->bat_iv.tq_avg > neigh_node->bat_iv.tq_avg)) goto out; /* if the TQ is the same and the link not more symmetric we * won't consider it either */ - if (router && (neigh_node->tq_avg == router->tq_avg)) { + if (router && (neigh_node->bat_iv.tq_avg == router->bat_iv.tq_avg)) { orig_node_tmp = router->orig_node; - spin_lock_bh(&orig_node_tmp->ogm_cnt_lock); + spin_lock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); if_num = router->if_incoming->if_num; - sum_orig = orig_node_tmp->bcast_own_sum[if_num]; - spin_unlock_bh(&orig_node_tmp->ogm_cnt_lock); + sum_orig = orig_node_tmp->bat_iv.bcast_own_sum[if_num]; + spin_unlock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); orig_node_tmp = neigh_node->orig_node; - spin_lock_bh(&orig_node_tmp->ogm_cnt_lock); + spin_lock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); if_num = neigh_node->if_incoming->if_num; - sum_neigh = orig_node_tmp->bcast_own_sum[if_num]; - spin_unlock_bh(&orig_node_tmp->ogm_cnt_lock); + sum_neigh = orig_node_tmp->bat_iv.bcast_own_sum[if_num]; + spin_unlock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock); if (sum_orig >= sum_neigh) goto out; @@ -852,7 +1031,7 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, uint8_t total_count; uint8_t orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; - int tq_asym_penalty, inv_asym_penalty, ret = 0; + int tq_asym_penalty, inv_asym_penalty, if_num, ret = 0; unsigned int combined_tq; /* find corresponding one hop neighbor */ @@ -890,10 +1069,11 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, orig_node->last_seen = jiffies; /* find packet count of corresponding one hop neighbor */ - spin_lock_bh(&orig_node->ogm_cnt_lock); - orig_eq_count = orig_neigh_node->bcast_own_sum[if_incoming->if_num]; - neigh_rq_count = neigh_node->real_packet_count; - spin_unlock_bh(&orig_node->ogm_cnt_lock); + spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); + if_num = if_incoming->if_num; + orig_eq_count = orig_neigh_node->bat_iv.bcast_own_sum[if_num]; + neigh_rq_count = neigh_node->bat_iv.real_packet_count; + spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); /* pay attention to not get a value bigger than 100 % */ if (orig_eq_count > neigh_rq_count) @@ -975,12 +1155,13 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, uint32_t seqno = ntohl(batadv_ogm_packet->seqno); uint8_t *neigh_addr; uint8_t packet_count; + unsigned long *bitmap; - orig_node = batadv_get_orig_node(bat_priv, batadv_ogm_packet->orig); + orig_node = batadv_iv_ogm_orig_get(bat_priv, batadv_ogm_packet->orig); if (!orig_node) return BATADV_NO_DUP; - spin_lock_bh(&orig_node->ogm_cnt_lock); + spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); seq_diff = seqno - orig_node->last_real_seqno; /* signalize caller that the packet is to be dropped. */ @@ -995,7 +1176,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { neigh_addr = tmp_neigh_node->addr; - is_dup = batadv_test_bit(tmp_neigh_node->real_bits, + is_dup = batadv_test_bit(tmp_neigh_node->bat_iv.real_bits, orig_node->last_real_seqno, seqno); @@ -1011,13 +1192,13 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, } /* if the window moved, set the update flag. */ - need_update |= batadv_bit_get_packet(bat_priv, - tmp_neigh_node->real_bits, + bitmap = tmp_neigh_node->bat_iv.real_bits; + need_update |= batadv_bit_get_packet(bat_priv, bitmap, seq_diff, set_mark); - packet_count = bitmap_weight(tmp_neigh_node->real_bits, + packet_count = bitmap_weight(tmp_neigh_node->bat_iv.real_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); - tmp_neigh_node->real_packet_count = packet_count; + tmp_neigh_node->bat_iv.real_packet_count = packet_count; } rcu_read_unlock(); @@ -1029,7 +1210,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, } out: - spin_unlock_bh(&orig_node->ogm_cnt_lock); + spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock); batadv_orig_node_free_ref(orig_node); return ret; } @@ -1041,7 +1222,7 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_hard_iface *hard_iface; - struct batadv_orig_node *orig_neigh_node, *orig_node; + struct batadv_orig_node *orig_neigh_node, *orig_node, *orig_node_tmp; struct batadv_neigh_node *router = NULL, *router_router = NULL; struct batadv_neigh_node *orig_neigh_router = NULL; int has_directlink_flag; @@ -1125,8 +1306,8 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, int16_t if_num; uint8_t *weight; - orig_neigh_node = batadv_get_orig_node(bat_priv, - ethhdr->h_source); + orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, + ethhdr->h_source); if (!orig_neigh_node) return; @@ -1140,15 +1321,15 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, if_num = if_incoming->if_num; offset = if_num * BATADV_NUM_WORDS; - spin_lock_bh(&orig_neigh_node->ogm_cnt_lock); - word = &(orig_neigh_node->bcast_own[offset]); + spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); + word = &(orig_neigh_node->bat_iv.bcast_own[offset]); bit_pos = if_incoming_seqno - 2; bit_pos -= ntohl(batadv_ogm_packet->seqno); batadv_set_bit(word, bit_pos); - weight = &orig_neigh_node->bcast_own_sum[if_num]; + weight = &orig_neigh_node->bat_iv.bcast_own_sum[if_num]; *weight = bitmap_weight(word, BATADV_TQ_LOCAL_WINDOW_SIZE); - spin_unlock_bh(&orig_neigh_node->ogm_cnt_lock); + spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock); } batadv_dbg(BATADV_DBG_BATMAN, bat_priv, @@ -1171,7 +1352,7 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, return; } - orig_node = batadv_get_orig_node(bat_priv, batadv_ogm_packet->orig); + orig_node = batadv_iv_ogm_orig_get(bat_priv, batadv_ogm_packet->orig); if (!orig_node) return; @@ -1192,10 +1373,12 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, } router = batadv_orig_node_get_router(orig_node); - if (router) - router_router = batadv_orig_node_get_router(router->orig_node); + if (router) { + orig_node_tmp = router->orig_node; + router_router = batadv_orig_node_get_router(orig_node_tmp); + } - if ((router && router->tq_avg != 0) && + if ((router && router->bat_iv.tq_avg != 0) && (batadv_compare_eth(router->addr, ethhdr->h_source))) is_from_best_next_hop = true; @@ -1219,8 +1402,8 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, if (is_single_hop_neigh) orig_neigh_node = orig_node; else - orig_neigh_node = batadv_get_orig_node(bat_priv, - ethhdr->h_source); + orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, + ethhdr->h_source); if (!orig_neigh_node) goto out; @@ -1351,6 +1534,106 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, return NET_RX_SUCCESS; } +/** + * batadv_iv_ogm_orig_print - print the originator table + * @bat_priv: the bat priv with all the soft interface information + * @seq: debugfs table seq_file struct + */ +static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv, + struct seq_file *seq) +{ + struct batadv_neigh_node *neigh_node, *neigh_node_tmp; + struct batadv_hashtable *hash = bat_priv->orig_hash; + int last_seen_msecs, last_seen_secs; + struct batadv_orig_node *orig_node; + unsigned long last_seen_jiffies; + struct hlist_head *head; + int batman_count = 0; + uint32_t i; + + seq_printf(seq, " %-15s %s (%s/%i) %17s [%10s]: %20s ...\n", + "Originator", "last-seen", "#", BATADV_TQ_MAX_VALUE, + "Nexthop", "outgoingIF", "Potential nexthops"); + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { + neigh_node = batadv_orig_node_get_router(orig_node); + if (!neigh_node) + continue; + + if (neigh_node->bat_iv.tq_avg == 0) + goto next; + + last_seen_jiffies = jiffies - orig_node->last_seen; + last_seen_msecs = jiffies_to_msecs(last_seen_jiffies); + last_seen_secs = last_seen_msecs / 1000; + last_seen_msecs = last_seen_msecs % 1000; + + seq_printf(seq, "%pM %4i.%03is (%3i) %pM [%10s]:", + orig_node->orig, last_seen_secs, + last_seen_msecs, neigh_node->bat_iv.tq_avg, + neigh_node->addr, + neigh_node->if_incoming->net_dev->name); + + hlist_for_each_entry_rcu(neigh_node_tmp, + &orig_node->neigh_list, list) { + seq_printf(seq, " %pM (%3i)", + neigh_node_tmp->addr, + neigh_node_tmp->bat_iv.tq_avg); + } + + seq_puts(seq, "\n"); + batman_count++; + +next: + batadv_neigh_node_free_ref(neigh_node); + } + rcu_read_unlock(); + } + + if (batman_count == 0) + seq_puts(seq, "No batman nodes in range ...\n"); +} + +/** + * batadv_iv_ogm_neigh_cmp - compare the metrics of two neighbors + * @neigh1: the first neighbor object of the comparison + * @neigh2: the second neighbor object of the comparison + * + * Returns a value less, equal to or greater than 0 if the metric via neigh1 is + * lower, the same as or higher than the metric via neigh2 + */ +static int batadv_iv_ogm_neigh_cmp(struct batadv_neigh_node *neigh1, + struct batadv_neigh_node *neigh2) +{ + uint8_t tq1, tq2; + + tq1 = neigh1->bat_iv.tq_avg; + tq2 = neigh2->bat_iv.tq_avg; + + return tq1 - tq2; +} + +/** + * 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 + * @neigh2: the second neighbor object of the comparison + * + * Returns true if the metric via neigh1 is equally good or better than the + * metric via neigh2, false otherwise. + */ +static bool batadv_iv_ogm_neigh_is_eob(struct batadv_neigh_node *neigh1, + struct batadv_neigh_node *neigh2) +{ + int diff = batadv_iv_ogm_neigh_cmp(neigh1, neigh2); + + return diff > -BATADV_TQ_SIMILARITY_THRESHOLD; +} + static struct batadv_algo_ops batadv_batman_iv __read_mostly = { .name = "BATMAN_IV", .bat_iface_enable = batadv_iv_ogm_iface_enable, @@ -1359,6 +1642,12 @@ static struct batadv_algo_ops batadv_batman_iv __read_mostly = { .bat_primary_iface_set = batadv_iv_ogm_primary_iface_set, .bat_ogm_schedule = batadv_iv_ogm_schedule, .bat_ogm_emit = batadv_iv_ogm_emit, + .bat_neigh_cmp = batadv_iv_ogm_neigh_cmp, + .bat_neigh_is_equiv_or_better = batadv_iv_ogm_neigh_is_eob, + .bat_orig_print = batadv_iv_ogm_orig_print, + .bat_orig_free = batadv_iv_ogm_orig_free, + .bat_orig_add_if = batadv_iv_ogm_orig_add_if, + .bat_orig_del_if = batadv_iv_ogm_orig_del_if, }; int __init batadv_iv_init(void) diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 20fa053b7f57..2449afaa7638 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -137,7 +137,7 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) if (!atomic_inc_not_zero(&gw_node->refcount)) goto next; - tq_avg = router->tq_avg; + tq_avg = router->bat_iv.tq_avg; switch (atomic_read(&bat_priv->gw_sel_class)) { case 1: /* fast connection */ @@ -256,7 +256,7 @@ void batadv_gw_election(struct batadv_priv *bat_priv) next_gw->bandwidth_down / 10, next_gw->bandwidth_down % 10, next_gw->bandwidth_up / 10, - next_gw->bandwidth_up % 10, router->tq_avg); + next_gw->bandwidth_up % 10, router->bat_iv.tq_avg); batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_ADD, gw_addr); } else { @@ -266,7 +266,7 @@ void batadv_gw_election(struct batadv_priv *bat_priv) next_gw->bandwidth_down / 10, next_gw->bandwidth_down % 10, next_gw->bandwidth_up / 10, - next_gw->bandwidth_up % 10, router->tq_avg); + next_gw->bandwidth_up % 10, router->bat_iv.tq_avg); batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_CHANGE, gw_addr); } @@ -305,8 +305,8 @@ void batadv_gw_check_election(struct batadv_priv *bat_priv, if (!router_orig) goto out; - gw_tq_avg = router_gw->tq_avg; - orig_tq_avg = router_orig->tq_avg; + gw_tq_avg = router_gw->bat_iv.tq_avg; + orig_tq_avg = router_orig->bat_iv.tq_avg; /* the TQ value has to be better */ if (orig_tq_avg < gw_tq_avg) @@ -528,7 +528,7 @@ static int batadv_write_buffer_text(struct batadv_priv *bat_priv, ret = seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %u.%u/%u.%u MBit\n", (curr_gw == gw_node ? "=>" : " "), gw_node->orig_node->orig, - router->tq_avg, router->addr, + router->bat_iv.tq_avg, router->addr, router->if_incoming->net_dev->name, gw_node->bandwidth_down / 10, gw_node->bandwidth_down % 10, @@ -792,7 +792,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, if (!neigh_curr) goto out; - curr_tq_avg = neigh_curr->tq_avg; + curr_tq_avg = neigh_curr->bat_iv.tq_avg; break; case BATADV_GW_MODE_OFF: default: @@ -803,7 +803,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, if (!neigh_old) goto out; - if (curr_tq_avg - neigh_old->tq_avg > BATADV_GW_THRESHOLD) + if (curr_tq_avg - neigh_old->bat_iv.tq_avg > BATADV_GW_THRESHOLD) out_of_range = true; out: diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index c5f871f218c6..57c2a19dcb5c 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -28,6 +28,7 @@ #include "originator.h" #include "hash.h" #include "bridge_loop_avoidance.h" +#include "gateway_client.h" #include <linux/if_arp.h> #include <linux/if_ether.h> @@ -124,8 +125,11 @@ static int batadv_is_valid_iface(const struct net_device *net_dev) * * Returns true if the net device is a 802.11 wireless device, false otherwise. */ -static bool batadv_is_wifi_netdev(struct net_device *net_device) +bool batadv_is_wifi_netdev(struct net_device *net_device) { + if (!net_device) + return false; + #ifdef CONFIG_WIRELESS_EXT /* pre-cfg80211 drivers have to implement WEXT, so it is possible to * check for wireless_handlers != NULL @@ -141,34 +145,6 @@ static bool batadv_is_wifi_netdev(struct net_device *net_device) return false; } -/** - * batadv_is_wifi_iface - check if the given interface represented by ifindex - * is a wifi interface - * @ifindex: interface index to check - * - * Returns true if the interface represented by ifindex is a 802.11 wireless - * device, false otherwise. - */ -bool batadv_is_wifi_iface(int ifindex) -{ - struct net_device *net_device = NULL; - bool ret = false; - - if (ifindex == BATADV_NULL_IFINDEX) - goto out; - - net_device = dev_get_by_index(&init_net, ifindex); - if (!net_device) - goto out; - - ret = batadv_is_wifi_netdev(net_device); - -out: - if (net_device) - dev_put(net_device); - return ret; -} - static struct batadv_hard_iface * batadv_hardif_get_active(const struct net_device *soft_iface) { @@ -266,16 +242,9 @@ static void batadv_check_known_mac_addr(const struct net_device *net_dev) int batadv_hardif_min_mtu(struct net_device *soft_iface) { - const struct batadv_priv *bat_priv = netdev_priv(soft_iface); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); const struct batadv_hard_iface *hard_iface; - /* allow big frames if all devices are capable to do so - * (have MTU > 1500 + batadv_max_header_len()) - */ int min_mtu = ETH_DATA_LEN; - int max_header_len = batadv_max_header_len(); - - if (atomic_read(&bat_priv->fragmentation)) - goto out; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { @@ -286,22 +255,40 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) if (hard_iface->soft_iface != soft_iface) continue; - min_mtu = min_t(int, hard_iface->net_dev->mtu - max_header_len, - min_mtu); + min_mtu = min_t(int, hard_iface->net_dev->mtu, min_mtu); } rcu_read_unlock(); + + atomic_set(&bat_priv->packet_size_max, min_mtu); + + if (atomic_read(&bat_priv->fragmentation) == 0) + goto out; + + /* with fragmentation enabled the maximum size of internally generated + * packets such as translation table exchanges or tvlv containers, etc + * has to be calculated + */ + min_mtu = min_t(int, min_mtu, BATADV_FRAG_MAX_FRAG_SIZE); + min_mtu -= sizeof(struct batadv_frag_packet); + min_mtu *= BATADV_FRAG_MAX_FRAGMENTS; + atomic_set(&bat_priv->packet_size_max, min_mtu); + + /* with fragmentation enabled we can fragment external packets easily */ + min_mtu = min_t(int, min_mtu, ETH_DATA_LEN); + out: - return min_mtu; + return min_mtu - batadv_max_header_len(); } /* adjusts the MTU if a new interface with a smaller MTU appeared. */ void batadv_update_min_mtu(struct net_device *soft_iface) { - int min_mtu; + soft_iface->mtu = batadv_hardif_min_mtu(soft_iface); - min_mtu = batadv_hardif_min_mtu(soft_iface); - if (soft_iface->mtu != min_mtu) - soft_iface->mtu = min_mtu; + /* Check if the local translate table should be cleaned up to match a + * new (and smaller) MTU. + */ + batadv_tt_local_resize_to_mtu(soft_iface); } static void @@ -524,8 +511,12 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, dev_put(hard_iface->soft_iface); /* nobody uses this interface anymore */ - if (!bat_priv->num_ifaces && autodel == BATADV_IF_CLEANUP_AUTO) - batadv_softif_destroy_sysfs(hard_iface->soft_iface); + if (!bat_priv->num_ifaces) { + batadv_gw_check_client_stop(bat_priv); + + if (autodel == BATADV_IF_CLEANUP_AUTO) + batadv_softif_destroy_sysfs(hard_iface->soft_iface); + } netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->soft_iface); hard_iface->soft_iface = NULL; diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 49892881a7c5..df4c8bd45c40 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -41,6 +41,7 @@ enum batadv_hard_if_cleanup { extern struct notifier_block batadv_hard_if_notifier; +bool batadv_is_wifi_netdev(struct net_device *net_device); struct batadv_hard_iface* batadv_hardif_get_by_netdev(const struct net_device *net_dev); int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, @@ -51,7 +52,6 @@ void batadv_hardif_remove_interfaces(void); int batadv_hardif_min_mtu(struct net_device *soft_iface); void batadv_update_min_mtu(struct net_device *soft_iface); void batadv_hardif_free_rcu(struct rcu_head *rcu); -bool batadv_is_wifi_iface(int ifindex); static inline void batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface) diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 82ac6472fa6f..29ae4efe3543 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -29,7 +29,7 @@ static struct batadv_socket_client *batadv_socket_client_hash[256]; static void batadv_socket_add_packet(struct batadv_socket_client *socket_client, - struct batadv_icmp_packet_rr *icmp_packet, + struct batadv_icmp_header *icmph, size_t icmp_len); void batadv_socket_init(void) @@ -155,13 +155,13 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, struct batadv_priv *bat_priv = socket_client->bat_priv; struct batadv_hard_iface *primary_if = NULL; struct sk_buff *skb; - struct batadv_icmp_packet_rr *icmp_packet; - + struct batadv_icmp_packet_rr *icmp_packet_rr; + struct batadv_icmp_header *icmp_header; struct batadv_orig_node *orig_node = NULL; struct batadv_neigh_node *neigh_node = NULL; size_t packet_len = sizeof(struct batadv_icmp_packet); - if (len < sizeof(struct batadv_icmp_packet)) { + if (len < sizeof(struct batadv_icmp_header)) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Error - can't send packet from char device: invalid packet size\n"); return -EINVAL; @@ -174,8 +174,10 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, goto out; } - if (len >= sizeof(struct batadv_icmp_packet_rr)) - packet_len = sizeof(struct batadv_icmp_packet_rr); + if (len >= BATADV_ICMP_MAX_PACKET_SIZE) + packet_len = BATADV_ICMP_MAX_PACKET_SIZE; + else + packet_len = len; skb = netdev_alloc_skb_ip_align(NULL, packet_len + ETH_HLEN); if (!skb) { @@ -185,67 +187,78 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, ETH_HLEN); - icmp_packet = (struct batadv_icmp_packet_rr *)skb_put(skb, packet_len); + icmp_header = (struct batadv_icmp_header *)skb_put(skb, packet_len); - if (copy_from_user(icmp_packet, buff, packet_len)) { + if (copy_from_user(icmp_header, buff, packet_len)) { len = -EFAULT; goto free_skb; } - if (icmp_packet->icmph.header.packet_type != BATADV_ICMP) { + if (icmp_header->header.packet_type != BATADV_ICMP) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Error - can't send packet from char device: got bogus packet type (expected: BAT_ICMP)\n"); len = -EINVAL; goto free_skb; } - if (icmp_packet->icmph.msg_type != BATADV_ECHO_REQUEST) { + switch (icmp_header->msg_type) { + case BATADV_ECHO_REQUEST: + if (len < sizeof(struct batadv_icmp_packet)) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Error - can't send packet from char device: invalid packet size\n"); + len = -EINVAL; + goto free_skb; + } + + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) + goto dst_unreach; + + orig_node = batadv_orig_hash_find(bat_priv, icmp_header->dst); + if (!orig_node) + goto dst_unreach; + + neigh_node = batadv_orig_node_get_router(orig_node); + if (!neigh_node) + goto dst_unreach; + + if (!neigh_node->if_incoming) + goto dst_unreach; + + if (neigh_node->if_incoming->if_status != BATADV_IF_ACTIVE) + goto dst_unreach; + + icmp_packet_rr = (struct batadv_icmp_packet_rr *)icmp_header; + if (packet_len == sizeof(*icmp_packet_rr)) + memcpy(icmp_packet_rr->rr, + neigh_node->if_incoming->net_dev->dev_addr, + ETH_ALEN); + + break; + default: batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Error - can't send packet from char device: got bogus message type (expected: ECHO_REQUEST)\n"); + "Error - can't send packet from char device: got unknown message type\n"); len = -EINVAL; goto free_skb; } - icmp_packet->icmph.uid = socket_client->index; + icmp_header->uid = socket_client->index; - if (icmp_packet->icmph.header.version != BATADV_COMPAT_VERSION) { - icmp_packet->icmph.msg_type = BATADV_PARAMETER_PROBLEM; - icmp_packet->icmph.header.version = BATADV_COMPAT_VERSION; - batadv_socket_add_packet(socket_client, icmp_packet, + if (icmp_header->header.version != BATADV_COMPAT_VERSION) { + icmp_header->msg_type = BATADV_PARAMETER_PROBLEM; + icmp_header->header.version = BATADV_COMPAT_VERSION; + batadv_socket_add_packet(socket_client, icmp_header, packet_len); goto free_skb; } - if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) - goto dst_unreach; - - orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->icmph.dst); - if (!orig_node) - goto dst_unreach; - - neigh_node = batadv_orig_node_get_router(orig_node); - if (!neigh_node) - goto dst_unreach; - - if (!neigh_node->if_incoming) - goto dst_unreach; - - if (neigh_node->if_incoming->if_status != BATADV_IF_ACTIVE) - goto dst_unreach; - - memcpy(icmp_packet->icmph.orig, - primary_if->net_dev->dev_addr, ETH_ALEN); - - if (packet_len == sizeof(struct batadv_icmp_packet_rr)) - memcpy(icmp_packet->rr, - neigh_node->if_incoming->net_dev->dev_addr, ETH_ALEN); + memcpy(icmp_header->orig, primary_if->net_dev->dev_addr, ETH_ALEN); batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); goto out; dst_unreach: - icmp_packet->icmph.msg_type = BATADV_DESTINATION_UNREACHABLE; - batadv_socket_add_packet(socket_client, icmp_packet, packet_len); + icmp_header->msg_type = BATADV_DESTINATION_UNREACHABLE; + batadv_socket_add_packet(socket_client, icmp_header, packet_len); free_skb: kfree_skb(skb); out: @@ -298,27 +311,40 @@ err: return -ENOMEM; } +/** + * batadv_socket_receive_packet - schedule an icmp packet to be sent to userspace + * on an icmp socket. + * @socket_client: the socket this packet belongs to + * @icmph: pointer to the header of the icmp packet + * @icmp_len: total length of the icmp packet + */ static void batadv_socket_add_packet(struct batadv_socket_client *socket_client, - struct batadv_icmp_packet_rr *icmp_packet, + struct batadv_icmp_header *icmph, size_t icmp_len) { struct batadv_socket_packet *socket_packet; + size_t len; socket_packet = kmalloc(sizeof(*socket_packet), GFP_ATOMIC); if (!socket_packet) return; + len = icmp_len; + /* check the maximum length before filling the buffer */ + if (len > sizeof(socket_packet->icmp_packet)) + len = sizeof(socket_packet->icmp_packet); + INIT_LIST_HEAD(&socket_packet->list); - memcpy(&socket_packet->icmp_packet, icmp_packet, icmp_len); - socket_packet->icmp_len = icmp_len; + memcpy(&socket_packet->icmp_packet, icmph, len); + socket_packet->icmp_len = len; spin_lock_bh(&socket_client->lock); /* while waiting for the lock the socket_client could have been * deleted */ - if (!batadv_socket_client_hash[icmp_packet->icmph.uid]) { + if (!batadv_socket_client_hash[icmph->uid]) { spin_unlock_bh(&socket_client->lock); kfree(socket_packet); return; @@ -342,12 +368,18 @@ static void batadv_socket_add_packet(struct batadv_socket_client *socket_client, wake_up(&socket_client->queue_wait); } -void batadv_socket_receive_packet(struct batadv_icmp_packet_rr *icmp_packet, +/** + * batadv_socket_receive_packet - schedule an icmp packet to be received + * locally and sent to userspace. + * @icmph: pointer to the header of the icmp packet + * @icmp_len: total length of the icmp packet + */ +void batadv_socket_receive_packet(struct batadv_icmp_header *icmph, size_t icmp_len) { struct batadv_socket_client *hash; - hash = batadv_socket_client_hash[icmp_packet->icmph.uid]; + hash = batadv_socket_client_hash[icmph->uid]; if (hash) - batadv_socket_add_packet(hash, icmp_packet, icmp_len); + batadv_socket_add_packet(hash, icmph, icmp_len); } diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 1fcca37b6223..6665080dff79 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -24,7 +24,7 @@ void batadv_socket_init(void); int batadv_socket_setup(struct batadv_priv *bat_priv); -void batadv_socket_receive_packet(struct batadv_icmp_packet_rr *icmp_packet, +void batadv_socket_receive_packet(struct batadv_icmp_header *icmph, size_t icmp_len); #endif /* _NET_BATMAN_ADV_ICMP_SOCKET_H_ */ diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 3159a148c1ac..c51a5e568f0a 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -501,7 +501,9 @@ int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops) !bat_algo_ops->bat_iface_update_mac || !bat_algo_ops->bat_primary_iface_set || !bat_algo_ops->bat_ogm_schedule || - !bat_algo_ops->bat_ogm_emit) { + !bat_algo_ops->bat_ogm_emit || + !bat_algo_ops->bat_neigh_cmp || + !bat_algo_ops->bat_neigh_is_equiv_or_better) { pr_info("Routing algo '%s' does not implement required ops\n", bat_algo_ops->name); ret = -EINVAL; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index d7dfafe45f29..f94f287b8670 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -26,7 +26,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2013.4.0" +#define BATADV_SOURCE_VERSION "2013.5.0" #endif /* B.A.T.M.A.N. parameters */ @@ -86,6 +86,12 @@ /* 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 + */ +#define BATADV_TQ_SIMILARITY_THRESHOLD 50 + /* how much worse secondary interfaces may be to be considered as bonding * candidates */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 23f611bedb0f..351e199bc0af 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1003,7 +1003,7 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, struct batadv_nc_packet *nc_packet, struct batadv_neigh_node *neigh_node) { - uint8_t tq_weighted_neigh, tq_weighted_coding; + uint8_t tq_weighted_neigh, tq_weighted_coding, tq_tmp; struct sk_buff *skb_dest, *skb_src; struct batadv_unicast_packet *packet1; struct batadv_unicast_packet *packet2; @@ -1028,8 +1028,10 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, if (!router_coding) goto out; - tq_weighted_neigh = batadv_nc_random_weight_tq(router_neigh->tq_avg); - tq_weighted_coding = batadv_nc_random_weight_tq(router_coding->tq_avg); + tq_tmp = batadv_nc_random_weight_tq(router_neigh->bat_iv.tq_avg); + tq_weighted_neigh = tq_tmp; + tq_tmp = batadv_nc_random_weight_tq(router_coding->bat_iv.tq_avg); + tq_weighted_coding = tq_tmp; /* Select one destination for the MAC-header dst-field based on * weighted TQ-values. diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index ee1d84724205..8ab14340d10f 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -36,7 +36,7 @@ static struct lock_class_key batadv_orig_hash_lock_class_key; static void batadv_purge_orig(struct work_struct *work); /* returns 1 if they are the same originator */ -static int batadv_compare_orig(const struct hlist_node *node, const void *data2) +int batadv_compare_orig(const struct hlist_node *node, const void *data2) { const void *data1 = container_of(node, struct batadv_orig_node, hash_entry); @@ -172,11 +172,20 @@ batadv_orig_node_get_router(struct batadv_orig_node *orig_node) return router; } +/** + * batadv_neigh_node_new - create and init a new neigh_node object + * @hard_iface: the interface where the neighbour is connected to + * @neigh_addr: the mac address of the neighbour interface + * @orig_node: originator object representing the neighbour + * + * Allocates a new neigh_node object and initialises all the generic fields. + * Returns the new object or NULL on failure. + */ struct batadv_neigh_node * batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, - const uint8_t *neigh_addr) + const uint8_t *neigh_addr, + struct batadv_orig_node *orig_node) { - struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_neigh_node *neigh_node; neigh_node = kzalloc(sizeof(*neigh_node), GFP_ATOMIC); @@ -186,15 +195,14 @@ batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, INIT_HLIST_NODE(&neigh_node->list); memcpy(neigh_node->addr, neigh_addr, ETH_ALEN); - spin_lock_init(&neigh_node->lq_update_lock); + neigh_node->if_incoming = hard_iface; + neigh_node->orig_node = orig_node; + + INIT_LIST_HEAD(&neigh_node->bonding_list); /* extra reference for return */ atomic_set(&neigh_node->refcount, 2); - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Creating new neighbor %pM on interface %s\n", neigh_addr, - hard_iface->net_dev->name); - out: return neigh_node; } @@ -233,9 +241,10 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) 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); + kfree(orig_node->tt_buff); - kfree(orig_node->bcast_own); - kfree(orig_node->bcast_own_sum); kfree(orig_node); } @@ -293,21 +302,22 @@ void batadv_originator_free(struct batadv_priv *bat_priv) batadv_hash_destroy(hash); } -/* this function finds or creates an originator entry for the given - * address if it does not exits +/** + * batadv_orig_node_new - creates a new orig_node + * @bat_priv: the bat priv with all the soft interface information + * @addr: the mac address of the originator + * + * Creates a new originator object and initialise all the generic fields. + * The new object is not added to the originator list. + * Returns the newly created object or NULL on failure. */ -struct batadv_orig_node *batadv_get_orig_node(struct batadv_priv *bat_priv, +struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const uint8_t *addr) { struct batadv_orig_node *orig_node; struct batadv_orig_node_vlan *vlan; - int size, i; - int hash_added; unsigned long reset_time; - - orig_node = batadv_orig_hash_find(bat_priv, addr); - if (orig_node) - return orig_node; + int i; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Creating new originator: %pM\n", addr); @@ -319,7 +329,6 @@ struct batadv_orig_node *batadv_get_orig_node(struct batadv_priv *bat_priv, INIT_HLIST_HEAD(&orig_node->neigh_list); INIT_LIST_HEAD(&orig_node->bond_list); INIT_LIST_HEAD(&orig_node->vlan_list); - spin_lock_init(&orig_node->ogm_cnt_lock); spin_lock_init(&orig_node->bcast_seqno_lock); spin_lock_init(&orig_node->neigh_list_lock); spin_lock_init(&orig_node->tt_buff_lock); @@ -355,37 +364,13 @@ struct batadv_orig_node *batadv_get_orig_node(struct batadv_priv *bat_priv, */ batadv_orig_node_vlan_free_ref(vlan); - size = bat_priv->num_ifaces * sizeof(unsigned long) * BATADV_NUM_WORDS; - - orig_node->bcast_own = kzalloc(size, GFP_ATOMIC); - if (!orig_node->bcast_own) - goto free_vlan; - - size = bat_priv->num_ifaces * sizeof(uint8_t); - orig_node->bcast_own_sum = kzalloc(size, GFP_ATOMIC); - for (i = 0; i < BATADV_FRAG_BUFFER_COUNT; i++) { INIT_HLIST_HEAD(&orig_node->fragments[i].head); spin_lock_init(&orig_node->fragments[i].lock); orig_node->fragments[i].size = 0; } - if (!orig_node->bcast_own_sum) - goto free_bcast_own; - - hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig, - batadv_choose_orig, orig_node, - &orig_node->hash_entry); - if (hash_added != 0) - goto free_bcast_own_sum; - return orig_node; -free_bcast_own_sum: - kfree(orig_node->bcast_own_sum); -free_bcast_own: - kfree(orig_node->bcast_own); -free_vlan: - batadv_orig_node_vlan_free_ref(vlan); free_orig_node: kfree(orig_node); return NULL; @@ -394,15 +379,16 @@ free_orig_node: static bool batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, - struct batadv_neigh_node **best_neigh_node) + struct batadv_neigh_node **best_neigh) { + struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; bool neigh_purged = false; unsigned long last_seen; struct batadv_hard_iface *if_incoming; - *best_neigh_node = NULL; + *best_neigh = NULL; spin_lock_bh(&orig_node->neigh_list_lock); @@ -435,9 +421,12 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, batadv_bonding_candidate_del(orig_node, neigh_node); batadv_neigh_node_free_ref(neigh_node); } else { - if ((!*best_neigh_node) || - (neigh_node->tq_avg > (*best_neigh_node)->tq_avg)) - *best_neigh_node = neigh_node; + /* store the best_neighbour if this is the first + * iteration or if a better neighbor has been found + */ + if (!*best_neigh || + bao->bat_neigh_cmp(neigh_node, *best_neigh) > 0) + *best_neigh = neigh_node; } } @@ -526,100 +515,26 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; struct batadv_priv *bat_priv = netdev_priv(net_dev); - struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_head *head; struct batadv_hard_iface *primary_if; - struct batadv_orig_node *orig_node; - struct batadv_neigh_node *neigh_node, *neigh_node_tmp; - int batman_count = 0; - int last_seen_secs; - int last_seen_msecs; - unsigned long last_seen_jiffies; - uint32_t i; primary_if = batadv_seq_print_text_primary_if_get(seq); if (!primary_if) - goto out; + return 0; - seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n", + seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s %s)]\n", BATADV_SOURCE_VERSION, primary_if->net_dev->name, - primary_if->net_dev->dev_addr, net_dev->name); - seq_printf(seq, " %-15s %s (%s/%i) %17s [%10s]: %20s ...\n", - "Originator", "last-seen", "#", BATADV_TQ_MAX_VALUE, - "Nexthop", "outgoingIF", "Potential nexthops"); - - for (i = 0; i < hash->size; i++) { - head = &hash->table[i]; - - rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, head, hash_entry) { - neigh_node = batadv_orig_node_get_router(orig_node); - if (!neigh_node) - continue; - - if (neigh_node->tq_avg == 0) - goto next; - - last_seen_jiffies = jiffies - orig_node->last_seen; - last_seen_msecs = jiffies_to_msecs(last_seen_jiffies); - last_seen_secs = last_seen_msecs / 1000; - last_seen_msecs = last_seen_msecs % 1000; - - seq_printf(seq, "%pM %4i.%03is (%3i) %pM [%10s]:", - orig_node->orig, last_seen_secs, - last_seen_msecs, neigh_node->tq_avg, - neigh_node->addr, - neigh_node->if_incoming->net_dev->name); - - hlist_for_each_entry_rcu(neigh_node_tmp, - &orig_node->neigh_list, list) { - seq_printf(seq, " %pM (%3i)", - neigh_node_tmp->addr, - neigh_node_tmp->tq_avg); - } + primary_if->net_dev->dev_addr, net_dev->name, + bat_priv->bat_algo_ops->name); - seq_puts(seq, "\n"); - batman_count++; + batadv_hardif_free_ref(primary_if); -next: - batadv_neigh_node_free_ref(neigh_node); - } - rcu_read_unlock(); + if (!bat_priv->bat_algo_ops->bat_orig_print) { + seq_puts(seq, + "No printing function for this routing protocol\n"); + return 0; } - if (batman_count == 0) - seq_puts(seq, "No batman nodes in range ...\n"); - -out: - if (primary_if) - batadv_hardif_free_ref(primary_if); - return 0; -} - -static int batadv_orig_node_add_if(struct batadv_orig_node *orig_node, - int max_if_num) -{ - void *data_ptr; - size_t data_size, old_size; - - data_size = max_if_num * sizeof(unsigned long) * BATADV_NUM_WORDS; - old_size = (max_if_num - 1) * sizeof(unsigned long) * BATADV_NUM_WORDS; - data_ptr = kmalloc(data_size, GFP_ATOMIC); - if (!data_ptr) - return -ENOMEM; - - memcpy(data_ptr, orig_node->bcast_own, old_size); - kfree(orig_node->bcast_own); - orig_node->bcast_own = data_ptr; - - data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC); - if (!data_ptr) - return -ENOMEM; - - memcpy(data_ptr, orig_node->bcast_own_sum, - (max_if_num - 1) * sizeof(uint8_t)); - kfree(orig_node->bcast_own_sum); - orig_node->bcast_own_sum = data_ptr; + bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq); return 0; } @@ -628,6 +543,7 @@ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; struct batadv_orig_node *orig_node; @@ -642,10 +558,10 @@ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) { - spin_lock_bh(&orig_node->ogm_cnt_lock); - ret = batadv_orig_node_add_if(orig_node, max_if_num); - spin_unlock_bh(&orig_node->ogm_cnt_lock); - + ret = 0; + if (bao->bat_orig_add_if) + ret = bao->bat_orig_add_if(orig_node, + max_if_num); if (ret == -ENOMEM) goto err; } @@ -659,54 +575,6 @@ err: return -ENOMEM; } -static int batadv_orig_node_del_if(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) -{ - void *data_ptr = NULL; - int chunk_size; - - /* last interface was removed */ - if (max_if_num == 0) - goto free_bcast_own; - - chunk_size = sizeof(unsigned long) * BATADV_NUM_WORDS; - data_ptr = kmalloc(max_if_num * chunk_size, GFP_ATOMIC); - if (!data_ptr) - return -ENOMEM; - - /* copy first part */ - memcpy(data_ptr, orig_node->bcast_own, del_if_num * chunk_size); - - /* copy second part */ - memcpy((char *)data_ptr + del_if_num * chunk_size, - orig_node->bcast_own + ((del_if_num + 1) * chunk_size), - (max_if_num - del_if_num) * chunk_size); - -free_bcast_own: - kfree(orig_node->bcast_own); - orig_node->bcast_own = data_ptr; - - if (max_if_num == 0) - goto free_own_sum; - - data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC); - if (!data_ptr) - return -ENOMEM; - - memcpy(data_ptr, orig_node->bcast_own_sum, - del_if_num * sizeof(uint8_t)); - - memcpy((char *)data_ptr + del_if_num * sizeof(uint8_t), - orig_node->bcast_own_sum + ((del_if_num + 1) * sizeof(uint8_t)), - (max_if_num - del_if_num) * sizeof(uint8_t)); - -free_own_sum: - kfree(orig_node->bcast_own_sum); - orig_node->bcast_own_sum = data_ptr; - - return 0; -} - int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, int max_if_num) { @@ -715,6 +583,7 @@ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, struct hlist_head *head; struct batadv_hard_iface *hard_iface_tmp; struct batadv_orig_node *orig_node; + struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; uint32_t i; int ret; @@ -726,11 +595,11 @@ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) { - spin_lock_bh(&orig_node->ogm_cnt_lock); - ret = batadv_orig_node_del_if(orig_node, max_if_num, - hard_iface->if_num); - spin_unlock_bh(&orig_node->ogm_cnt_lock); - + ret = 0; + if (bao->bat_orig_del_if) + ret = bao->bat_orig_del_if(orig_node, + max_if_num, + hard_iface->if_num); if (ret == -ENOMEM) goto err; } diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index cc6d686cfe6d..6f77d808a916 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -22,16 +22,18 @@ #include "hash.h" +int batadv_compare_orig(const struct hlist_node *node, const void *data2); int batadv_originator_init(struct batadv_priv *bat_priv); void batadv_originator_free(struct batadv_priv *bat_priv); void batadv_purge_orig_ref(struct batadv_priv *bat_priv); void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node); void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node); -struct batadv_orig_node *batadv_get_orig_node(struct batadv_priv *bat_priv, +struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_neigh_node * batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, - const uint8_t *neigh_addr); + const uint8_t *neigh_addr, + struct batadv_orig_node *orig_node); void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node); struct batadv_neigh_node * batadv_orig_node_get_router(struct batadv_orig_node *orig_node); diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 9fbcaacc345a..207459b62966 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -110,12 +110,13 @@ enum batadv_tt_data_flags { /* BATADV_TT_CLIENT flags. * Flags from BIT(0) to BIT(7) are sent on the wire, while flags from BIT(8) to - * BIT(15) are used for local computation only + * BIT(15) are used for local computation only. + * Flags from BIT(4) to BIT(7) are kept in sync with the rest of the network. */ enum batadv_tt_client_flags { BATADV_TT_CLIENT_DEL = BIT(0), BATADV_TT_CLIENT_ROAM = BIT(1), - BATADV_TT_CLIENT_WIFI = BIT(2), + BATADV_TT_CLIENT_WIFI = BIT(4), BATADV_TT_CLIENT_NOPURGE = BIT(8), BATADV_TT_CLIENT_NEW = BIT(9), BATADV_TT_CLIENT_PENDING = BIT(10), @@ -238,6 +239,8 @@ struct batadv_icmp_packet_rr { uint8_t rr[BATADV_RR_LEN][ETH_ALEN]; }; +#define BATADV_ICMP_MAX_PACKET_SIZE sizeof(struct batadv_icmp_packet_rr) + /* All packet headers in front of an ethernet header have to be completely * divisible by 2 but not by 4 to make the payload after the ethernet * header again 4 bytes boundary aligned. diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 4bcf22129ffe..d4114d775ad6 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -115,9 +115,19 @@ out: return; } -void batadv_bonding_candidate_add(struct batadv_orig_node *orig_node, +/** + * batadv_bonding_candidate_add - consider a new link for bonding mode towards + * the given originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: the target node + * @neigh_node: the neighbor representing the new link to consider for bonding + * mode + */ +void batadv_bonding_candidate_add(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node) { + struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; struct batadv_neigh_node *tmp_neigh_node, *router = NULL; uint8_t interference_candidate = 0; @@ -132,8 +142,9 @@ void batadv_bonding_candidate_add(struct batadv_orig_node *orig_node, if (!router) goto candidate_del; + /* ... and is good enough to be considered */ - if (neigh_node->tq_avg < router->tq_avg - BATADV_BONDING_TQ_THRESHOLD) + if (bao->bat_neigh_is_equiv_or_better(neigh_node, router)) goto candidate_del; /* check if we have another candidate with the same mac address or @@ -249,47 +260,65 @@ bool batadv_check_management_packet(struct sk_buff *skb, return true; } +/** + * batadv_recv_my_icmp_packet - receive an icmp packet locally + * @bat_priv: the bat priv with all the soft interface information + * @skb: icmp packet to process + * + * Returns NET_RX_SUCCESS if the packet has been consumed or NET_RX_DROP + * otherwise. + */ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv, - struct sk_buff *skb, size_t icmp_len) + struct sk_buff *skb) { struct batadv_hard_iface *primary_if = NULL; struct batadv_orig_node *orig_node = NULL; - struct batadv_icmp_packet_rr *icmp_packet; - int ret = NET_RX_DROP; + struct batadv_icmp_header *icmph; + int res, ret = NET_RX_DROP; - icmp_packet = (struct batadv_icmp_packet_rr *)skb->data; + icmph = (struct batadv_icmp_header *)skb->data; - /* add data to device queue */ - if (icmp_packet->icmph.msg_type != BATADV_ECHO_REQUEST) { - batadv_socket_receive_packet(icmp_packet, icmp_len); - goto out; - } + switch (icmph->msg_type) { + case BATADV_ECHO_REPLY: + case BATADV_DESTINATION_UNREACHABLE: + case BATADV_TTL_EXCEEDED: + /* receive the packet */ + if (skb_linearize(skb) < 0) + break; - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) - goto out; + batadv_socket_receive_packet(icmph, skb->len); + break; + case BATADV_ECHO_REQUEST: + /* answer echo request (ping) */ + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; - /* answer echo request (ping) */ - /* get routing information */ - orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->icmph.orig); - if (!orig_node) - goto out; + /* get routing information */ + orig_node = batadv_orig_hash_find(bat_priv, icmph->orig); + if (!orig_node) + goto out; - /* create a copy of the skb, if needed, to modify it. */ - if (skb_cow(skb, ETH_HLEN) < 0) - goto out; + /* create a copy of the skb, if needed, to modify it. */ + if (skb_cow(skb, ETH_HLEN) < 0) + goto out; - icmp_packet = (struct batadv_icmp_packet_rr *)skb->data; + icmph = (struct batadv_icmp_header *)skb->data; - memcpy(icmp_packet->icmph.dst, icmp_packet->icmph.orig, ETH_ALEN); - memcpy(icmp_packet->icmph.orig, primary_if->net_dev->dev_addr, - ETH_ALEN); - icmp_packet->icmph.msg_type = BATADV_ECHO_REPLY; - icmp_packet->icmph.header.ttl = BATADV_TTL; + memcpy(icmph->dst, icmph->orig, ETH_ALEN); + memcpy(icmph->orig, primary_if->net_dev->dev_addr, ETH_ALEN); + icmph->msg_type = BATADV_ECHO_REPLY; + icmph->header.ttl = BATADV_TTL; - if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP) - ret = NET_RX_SUCCESS; + res = batadv_send_skb_to_orig(skb, orig_node, NULL); + if (res != NET_XMIT_DROP) + ret = NET_RX_SUCCESS; + break; + default: + /* drop unknown type */ + goto out; + } out: if (primary_if) batadv_hardif_free_ref(primary_if); @@ -352,16 +381,13 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if) { struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); - struct batadv_icmp_packet_rr *icmp_packet; + struct batadv_icmp_header *icmph; + struct batadv_icmp_packet_rr *icmp_packet_rr; struct ethhdr *ethhdr; struct batadv_orig_node *orig_node = NULL; - int hdr_size = sizeof(struct batadv_icmp_packet); + int hdr_size = sizeof(struct batadv_icmp_header); int ret = NET_RX_DROP; - /* we truncate all incoming icmp packets if they don't match our size */ - if (skb->len >= sizeof(struct batadv_icmp_packet_rr)) - hdr_size = sizeof(struct batadv_icmp_packet_rr); - /* drop packet if it has not necessary minimum size */ if (unlikely(!pskb_may_pull(skb, hdr_size))) goto out; @@ -380,28 +406,39 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest)) goto out; - icmp_packet = (struct batadv_icmp_packet_rr *)skb->data; + icmph = (struct batadv_icmp_header *)skb->data; /* add record route information if not full */ - if ((icmp_packet->icmph.msg_type == BATADV_ECHO_REPLY || - icmp_packet->icmph.msg_type == BATADV_ECHO_REQUEST) && - (hdr_size == sizeof(struct batadv_icmp_packet_rr)) && - (icmp_packet->rr_cur < BATADV_RR_LEN)) { - memcpy(&(icmp_packet->rr[icmp_packet->rr_cur]), + if ((icmph->msg_type == BATADV_ECHO_REPLY || + icmph->msg_type == BATADV_ECHO_REQUEST) && + (skb->len >= sizeof(struct batadv_icmp_packet_rr))) { + if (skb_linearize(skb) < 0) + goto out; + + /* create a copy of the skb, if needed, to modify it. */ + if (skb_cow(skb, ETH_HLEN) < 0) + goto out; + + icmph = (struct batadv_icmp_header *)skb->data; + icmp_packet_rr = (struct batadv_icmp_packet_rr *)icmph; + if (icmp_packet_rr->rr_cur >= BATADV_RR_LEN) + goto out; + + memcpy(&(icmp_packet_rr->rr[icmp_packet_rr->rr_cur]), ethhdr->h_dest, ETH_ALEN); - icmp_packet->rr_cur++; + icmp_packet_rr->rr_cur++; } /* packet for me */ - if (batadv_is_my_mac(bat_priv, icmp_packet->icmph.dst)) - return batadv_recv_my_icmp_packet(bat_priv, skb, hdr_size); + if (batadv_is_my_mac(bat_priv, icmph->dst)) + return batadv_recv_my_icmp_packet(bat_priv, skb); /* TTL exceeded */ - if (icmp_packet->icmph.header.ttl < 2) + if (icmph->header.ttl < 2) return batadv_recv_icmp_ttl_exceeded(bat_priv, skb); /* get routing information */ - orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->icmph.dst); + orig_node = batadv_orig_hash_find(bat_priv, icmph->dst); if (!orig_node) goto out; @@ -409,10 +446,10 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, if (skb_cow(skb, ETH_HLEN) < 0) goto out; - icmp_packet = (struct batadv_icmp_packet_rr *)skb->data; + icmph = (struct batadv_icmp_header *)skb->data; /* decrement ttl */ - icmp_packet->icmph.header.ttl--; + icmph->header.ttl--; /* route it */ if (batadv_send_skb_to_orig(skb, orig_node, recv_if) != NET_XMIT_DROP) @@ -479,18 +516,25 @@ out: return router; } -/* Interface Alternating: Use the best of the - * remaining candidates which are not using - * this interface. +/** + * batadv_find_ifalter_router - find the best of the remaining candidates which + * are not using this interface + * @bat_priv: the bat priv with all the soft interface information + * @primary_orig: the destination + * @recv_if: the interface that the router returned by this function has to not + * use * - * Increases the returned router's refcount + * Returns the best candidate towards primary_orig that is not using recv_if. + * Increases the returned neighbor's refcount */ static struct batadv_neigh_node * -batadv_find_ifalter_router(struct batadv_orig_node *primary_orig, +batadv_find_ifalter_router(struct batadv_priv *bat_priv, + struct batadv_orig_node *primary_orig, const struct batadv_hard_iface *recv_if) { - struct batadv_neigh_node *tmp_neigh_node; struct batadv_neigh_node *router = NULL, *first_candidate = NULL; + struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; + struct batadv_neigh_node *tmp_neigh_node; rcu_read_lock(); list_for_each_entry_rcu(tmp_neigh_node, &primary_orig->bond_list, @@ -502,7 +546,7 @@ batadv_find_ifalter_router(struct batadv_orig_node *primary_orig, if (tmp_neigh_node->if_incoming == recv_if) continue; - if (router && tmp_neigh_node->tq_avg <= router->tq_avg) + if (router && bao->bat_neigh_cmp(tmp_neigh_node, router)) continue; if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) @@ -636,7 +680,8 @@ batadv_find_router(struct batadv_priv *bat_priv, if (bonding_enabled) router = batadv_find_bond_router(primary_orig_node, recv_if); else - router = batadv_find_ifalter_router(primary_orig_node, recv_if); + router = batadv_find_ifalter_router(bat_priv, primary_orig_node, + recv_if); return_router: if (router && router->if_incoming->if_status != BATADV_IF_ACTIVE) diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 55d637a90621..19544ddb81b5 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -48,7 +48,8 @@ batadv_find_router(struct batadv_priv *bat_priv, const struct batadv_hard_iface *recv_if); void batadv_bonding_candidate_del(struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node); -void batadv_bonding_candidate_add(struct batadv_orig_node *orig_node, +void batadv_bonding_candidate_add(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node); void batadv_bonding_save_primary(const struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index e70f530d8568..36f050876f82 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -166,7 +166,7 @@ static int batadv_interface_tx(struct sk_buff *skb, unsigned int header_len = 0; int data_len = skb->len, ret; unsigned long brd_delay = 1; - bool do_bcast = false; + bool do_bcast = false, client_added; unsigned short vid; uint32_t seqno; @@ -196,9 +196,12 @@ static int batadv_interface_tx(struct sk_buff *skb, ethhdr = (struct ethhdr *)skb->data; /* Register the client MAC in the transtable */ - if (!is_multicast_ether_addr(ethhdr->h_source)) - batadv_tt_local_add(soft_iface, ethhdr->h_source, vid, - skb->skb_iif); + if (!is_multicast_ether_addr(ethhdr->h_source)) { + client_added = batadv_tt_local_add(soft_iface, ethhdr->h_source, + vid, skb->skb_iif); + if (!client_added) + goto dropped; + } /* don't accept stp packets. STP does not help in meshes. * better use the bridge loop avoidance ... @@ -674,6 +677,7 @@ static int batadv_softif_init_late(struct net_device *dev) atomic_set(&bat_priv->log_level, 0); #endif atomic_set(&bat_priv->fragmentation, 1); + atomic_set(&bat_priv->packet_size_max, ETH_DATA_LEN); atomic_set(&bat_priv->bcast_queue_left, BATADV_BCAST_QUEUE_LEN); atomic_set(&bat_priv->batman_queue_left, BATADV_BATMAN_QUEUE_LEN); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 7731eaed737d..4add57d4857f 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -358,6 +358,13 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv, goto del; if (del_op_requested && !del_op_entry) goto del; + + /* this is a second add in the same originator interval. It + * means that flags have been changed: update them! + */ + if (!del_op_requested && !del_op_entry) + entry->change.flags = flags; + continue; del: list_del(&entry->list); @@ -401,6 +408,35 @@ static uint16_t batadv_tt_entries(uint16_t tt_len) return tt_len / batadv_tt_len(1); } +/** + * batadv_tt_local_table_transmit_size - calculates the local translation table + * size when transmitted over the air + * @bat_priv: the bat priv with all the soft interface information + * + * Returns local translation table size in bytes. + */ +static int batadv_tt_local_table_transmit_size(struct batadv_priv *bat_priv) +{ + uint16_t num_vlan = 0, tt_local_entries = 0; + struct batadv_softif_vlan *vlan; + int hdr_size; + + rcu_read_lock(); + hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { + num_vlan++; + tt_local_entries += atomic_read(&vlan->tt.num_entries); + } + rcu_read_unlock(); + + /* header size of tvlv encapsulated tt response payload */ + hdr_size = sizeof(struct batadv_unicast_tvlv_packet); + hdr_size += sizeof(struct batadv_tvlv_hdr); + hdr_size += sizeof(struct batadv_tvlv_tt_data); + hdr_size += num_vlan * sizeof(struct batadv_tvlv_tt_vlan_data); + + return hdr_size + batadv_tt_len(tt_local_entries); +} + static int batadv_tt_local_init(struct batadv_priv *bat_priv) { if (bat_priv->tt.local_hash) @@ -439,17 +475,24 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv, * @vid: VLAN identifier * @ifindex: index of the interface where the client is connected to (useful to * identify wireless clients) + * + * Returns true if the client was successfully added, false otherwise. */ -void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, +bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, unsigned short vid, int ifindex) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); struct batadv_tt_local_entry *tt_local; struct batadv_tt_global_entry *tt_global; + struct net_device *in_dev = NULL; struct hlist_head *head; struct batadv_tt_orig_list_entry *orig_entry; - int hash_added; - bool roamed_back = false; + int hash_added, table_size, packet_size_max; + bool ret = false, roamed_back = false; + uint8_t remote_flags; + + if (ifindex != BATADV_NULL_IFINDEX) + in_dev = dev_get_by_index(&init_net, ifindex); tt_local = batadv_tt_local_hash_find(bat_priv, addr, vid); tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid); @@ -484,6 +527,17 @@ void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, goto check_roaming; } + /* Ignore the client if we cannot send it in a full table response. */ + table_size = batadv_tt_local_table_transmit_size(bat_priv); + table_size += batadv_tt_len(1); + packet_size_max = atomic_read(&bat_priv->packet_size_max); + if (table_size > packet_size_max) { + net_ratelimited_function(batadv_info, soft_iface, + "Local translation table size (%i) exceeds maximum packet size (%i); Ignoring new local tt entry: %pM\n", + table_size, packet_size_max, addr); + goto out; + } + tt_local = kmalloc(sizeof(*tt_local), GFP_ATOMIC); if (!tt_local) goto out; @@ -500,7 +554,7 @@ void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, */ tt_local->common.flags = BATADV_TT_CLIENT_NEW; tt_local->common.vid = vid; - if (batadv_is_wifi_iface(ifindex)) + if (batadv_is_wifi_netdev(in_dev)) tt_local->common.flags |= BATADV_TT_CLIENT_WIFI; atomic_set(&tt_local->common.refcount, 2); tt_local->last_seen = jiffies; @@ -550,11 +604,31 @@ check_roaming: } } + /* store the current remote flags before altering them. This helps + * understanding is flags are changing or not + */ + remote_flags = tt_local->common.flags & BATADV_TT_REMOTE_MASK; + + if (batadv_is_wifi_netdev(in_dev)) + tt_local->common.flags |= BATADV_TT_CLIENT_WIFI; + else + tt_local->common.flags &= ~BATADV_TT_CLIENT_WIFI; + + /* if any "dynamic" flag has been modified, resend an ADD event for this + * entry so that all the nodes can get the new flags + */ + if (remote_flags ^ (tt_local->common.flags & BATADV_TT_REMOTE_MASK)) + batadv_tt_local_event(bat_priv, tt_local, BATADV_NO_FLAGS); + + ret = true; out: + if (in_dev) + dev_put(in_dev); if (tt_local) batadv_tt_local_entry_free_ref(tt_local); if (tt_global) batadv_tt_global_entry_free_ref(tt_global); + return ret; } /** @@ -926,8 +1000,16 @@ out: return curr_flags; } +/** + * batadv_tt_local_purge_list - purge inactive tt local entries + * @bat_priv: the bat priv with all the soft interface information + * @head: pointer to the list containing the local tt entries + * @timeout: parameter deciding whether a given tt local entry is considered + * inactive or not + */ static void batadv_tt_local_purge_list(struct batadv_priv *bat_priv, - struct hlist_head *head) + struct hlist_head *head, + int timeout) { struct batadv_tt_local_entry *tt_local_entry; struct batadv_tt_common_entry *tt_common_entry; @@ -945,8 +1027,7 @@ static void batadv_tt_local_purge_list(struct batadv_priv *bat_priv, if (tt_local_entry->common.flags & BATADV_TT_CLIENT_PENDING) continue; - if (!batadv_has_timed_out(tt_local_entry->last_seen, - BATADV_TT_LOCAL_TIMEOUT)) + if (!batadv_has_timed_out(tt_local_entry->last_seen, timeout)) continue; batadv_tt_local_set_pending(bat_priv, tt_local_entry, @@ -954,7 +1035,14 @@ static void batadv_tt_local_purge_list(struct batadv_priv *bat_priv, } } -static void batadv_tt_local_purge(struct batadv_priv *bat_priv) +/** + * batadv_tt_local_purge - purge inactive tt local entries + * @bat_priv: the bat priv with all the soft interface information + * @timeout: parameter deciding whether a given tt local entry is considered + * inactive or not + */ +static void batadv_tt_local_purge(struct batadv_priv *bat_priv, + int timeout) { struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct hlist_head *head; @@ -966,7 +1054,7 @@ static void batadv_tt_local_purge(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - batadv_tt_local_purge_list(bat_priv, head); + batadv_tt_local_purge_list(bat_priv, head, timeout); spin_unlock_bh(list_lock); } } @@ -1280,18 +1368,20 @@ out: } /* batadv_transtable_best_orig - Get best originator list entry from tt entry + * @bat_priv: the bat priv with all the soft interface information * @tt_global_entry: global translation table entry to be analyzed * * This functon assumes the caller holds rcu_read_lock(). * Returns best originator list entry or NULL on errors. */ static struct batadv_tt_orig_list_entry * -batadv_transtable_best_orig(struct batadv_tt_global_entry *tt_global_entry) +batadv_transtable_best_orig(struct batadv_priv *bat_priv, + struct batadv_tt_global_entry *tt_global_entry) { - struct batadv_neigh_node *router = NULL; + struct batadv_neigh_node *router, *best_router = NULL; + struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; struct hlist_head *head; struct batadv_tt_orig_list_entry *orig_entry, *best_entry = NULL; - int best_tq = 0; head = &tt_global_entry->orig_list; hlist_for_each_entry_rcu(orig_entry, head, list) { @@ -1299,26 +1389,37 @@ batadv_transtable_best_orig(struct batadv_tt_global_entry *tt_global_entry) if (!router) continue; - if (router->tq_avg > best_tq) { - best_entry = orig_entry; - best_tq = router->tq_avg; + if (best_router && + bao->bat_neigh_cmp(router, best_router) <= 0) { + batadv_neigh_node_free_ref(router); + continue; } - batadv_neigh_node_free_ref(router); + /* release the refcount for the "old" best */ + if (best_router) + batadv_neigh_node_free_ref(best_router); + + best_entry = orig_entry; + best_router = router; } + if (best_router) + batadv_neigh_node_free_ref(best_router); + return best_entry; } /* batadv_tt_global_print_entry - print all orig nodes who announce the address * for this global entry + * @bat_priv: the bat priv with all the soft interface information * @tt_global_entry: global translation table entry to be printed * @seq: debugfs table seq_file struct * * This functon assumes the caller holds rcu_read_lock(). */ static void -batadv_tt_global_print_entry(struct batadv_tt_global_entry *tt_global_entry, +batadv_tt_global_print_entry(struct batadv_priv *bat_priv, + struct batadv_tt_global_entry *tt_global_entry, struct seq_file *seq) { struct batadv_tt_orig_list_entry *orig_entry, *best_entry; @@ -1331,7 +1432,7 @@ batadv_tt_global_print_entry(struct batadv_tt_global_entry *tt_global_entry, tt_common_entry = &tt_global_entry->common; flags = tt_common_entry->flags; - best_entry = batadv_transtable_best_orig(tt_global_entry); + best_entry = batadv_transtable_best_orig(bat_priv, tt_global_entry); if (best_entry) { vlan = batadv_orig_node_vlan_get(best_entry->orig_node, tt_common_entry->vid); @@ -1420,7 +1521,7 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset) tt_global = container_of(tt_common_entry, struct batadv_tt_global_entry, common); - batadv_tt_global_print_entry(tt_global, seq); + batadv_tt_global_print_entry(bat_priv, tt_global, seq); } rcu_read_unlock(); } @@ -1808,7 +1909,7 @@ struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, goto out; rcu_read_lock(); - best_entry = batadv_transtable_best_orig(tt_global_entry); + best_entry = batadv_transtable_best_orig(bat_priv, tt_global_entry); /* found anything? */ if (best_entry) orig_node = best_entry->orig_node; @@ -1858,6 +1959,7 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, struct batadv_tt_global_entry *tt_global; struct hlist_head *head; uint32_t i, crc_tmp, crc = 0; + uint8_t flags; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1896,6 +1998,13 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, crc_tmp = crc32c(0, &tt_common->vid, sizeof(tt_common->vid)); + + /* compute the CRC on flags that have to be kept in sync + * among nodes + */ + flags = tt_common->flags & BATADV_TT_SYNC_MASK; + crc_tmp = crc32c(crc_tmp, &flags, sizeof(flags)); + crc ^= crc32c(crc_tmp, tt_common->addr, ETH_ALEN); } rcu_read_unlock(); @@ -1921,6 +2030,7 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, struct batadv_tt_common_entry *tt_common; struct hlist_head *head; uint32_t i, crc_tmp, crc = 0; + uint8_t flags; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1941,6 +2051,13 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, crc_tmp = crc32c(0, &tt_common->vid, sizeof(tt_common->vid)); + + /* compute the CRC on flags that have to be kept in sync + * among nodes + */ + flags = tt_common->flags & BATADV_TT_SYNC_MASK; + crc_tmp = crc32c(crc_tmp, &flags, sizeof(flags)); + crc ^= crc32c(crc_tmp, tt_common->addr, ETH_ALEN); } rcu_read_unlock(); @@ -2370,6 +2487,15 @@ static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv, req_dst_orig_node); } + /* Don't send the response, if larger than fragmented packet. */ + tt_len = sizeof(struct batadv_unicast_tvlv_packet) + tvlv_len; + if (tt_len > atomic_read(&bat_priv->packet_size_max)) { + net_ratelimited_function(batadv_info, bat_priv->soft_iface, + "Ignoring TT_REQUEST from %pM; Response size exceeds max packet size.\n", + res_dst_orig_node->orig); + goto out; + } + tvlv_tt_data->flags = BATADV_TT_RESPONSE; tvlv_tt_data->ttvn = req_ttvn; @@ -2846,7 +2972,7 @@ static void batadv_tt_purge(struct work_struct *work) priv_tt = container_of(delayed_work, struct batadv_priv_tt, work); bat_priv = container_of(priv_tt, struct batadv_priv, tt); - batadv_tt_local_purge(bat_priv); + batadv_tt_local_purge(bat_priv, BATADV_TT_LOCAL_TIMEOUT); batadv_tt_global_purge(bat_priv); batadv_tt_req_purge(bat_priv); batadv_tt_roam_purge(bat_priv); @@ -2959,18 +3085,18 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) } /** - * batadv_tt_local_commit_changes - commit all pending local tt changes which - * have been queued in the time since the last commit + * batadv_tt_local_commit_changes_nolock - commit all pending local tt changes + * which have been queued in the time since the last commit * @bat_priv: the bat priv with all the soft interface information + * + * Caller must hold tt->commit_lock. */ -void batadv_tt_local_commit_changes(struct batadv_priv *bat_priv) +static void batadv_tt_local_commit_changes_nolock(struct batadv_priv *bat_priv) { - spin_lock_bh(&bat_priv->tt.commit_lock); - if (atomic_read(&bat_priv->tt.local_changes) < 1) { if (!batadv_atomic_dec_not_zero(&bat_priv->tt.ogm_append_cnt)) batadv_tt_tvlv_container_update(bat_priv); - goto out; + return; } batadv_tt_local_set_flags(bat_priv, BATADV_TT_CLIENT_NEW, false, true); @@ -2987,8 +3113,17 @@ void batadv_tt_local_commit_changes(struct batadv_priv *bat_priv) /* reset the sending counter */ atomic_set(&bat_priv->tt.ogm_append_cnt, BATADV_TT_OGM_APPEND_MAX); batadv_tt_tvlv_container_update(bat_priv); +} -out: +/** + * batadv_tt_local_commit_changes - commit all pending local tt changes which + * have been queued in the time since the last commit + * @bat_priv: the bat priv with all the soft interface information + */ +void batadv_tt_local_commit_changes(struct batadv_priv *bat_priv) +{ + spin_lock_bh(&bat_priv->tt.commit_lock); + batadv_tt_local_commit_changes_nolock(bat_priv); spin_unlock_bh(&bat_priv->tt.commit_lock); } @@ -3184,6 +3319,47 @@ out: } /** + * batadv_tt_local_resize_to_mtu - resize the local translation table fit the + * maximum packet size that can be transported through the mesh + * @soft_iface: netdev struct of the mesh interface + * + * Remove entries older than 'timeout' and half timeout if more entries need + * to be removed. + */ +void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface) +{ + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + int packet_size_max = atomic_read(&bat_priv->packet_size_max); + int table_size, timeout = BATADV_TT_LOCAL_TIMEOUT / 2; + bool reduced = false; + + spin_lock_bh(&bat_priv->tt.commit_lock); + + while (true) { + table_size = batadv_tt_local_table_transmit_size(bat_priv); + if (packet_size_max >= table_size) + break; + + batadv_tt_local_purge(bat_priv, timeout); + batadv_tt_local_purge_pending_clients(bat_priv); + + timeout /= 2; + reduced = true; + net_ratelimited_function(batadv_info, soft_iface, + "Forced to purge local tt entries to fit new maximum fragment MTU (%i)\n", + packet_size_max); + } + + /* commit these changes immediately, to avoid synchronization problem + * with the TTVN + */ + if (reduced) + batadv_tt_local_commit_changes_nolock(bat_priv); + + spin_unlock_bh(&bat_priv->tt.commit_lock); +} + +/** * batadv_tt_tvlv_ogm_handler_v1 - process incoming tt tvlv container * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node of the ogm @@ -3364,6 +3540,9 @@ int batadv_tt_init(struct batadv_priv *bat_priv) { int ret; + /* synchronized flags must be remote */ + BUILD_BUG_ON(!(BATADV_TT_SYNC_MASK & BATADV_TT_REMOTE_MASK)); + ret = batadv_tt_local_init(bat_priv); if (ret < 0) return ret; diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index dc6db4e00a43..026b1ffa6746 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -21,7 +21,7 @@ #define _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ int batadv_tt_init(struct batadv_priv *bat_priv); -void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, +bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, unsigned short vid, int ifindex); uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, const uint8_t *addr, unsigned short vid, @@ -45,6 +45,7 @@ bool batadv_tt_global_client_is_roaming(struct batadv_priv *bat_priv, uint8_t *addr, unsigned short vid); bool batadv_tt_local_client_is_roaming(struct batadv_priv *bat_priv, uint8_t *addr, unsigned short vid); +void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface); bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const unsigned char *addr, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ff53933b5a59..91dd369b0ff2 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -36,6 +36,18 @@ #endif /* CONFIG_BATMAN_ADV_DAT */ /** + * BATADV_TT_REMOTE_MASK - bitmask selecting the flags that are sent over the + * wire only + */ +#define BATADV_TT_REMOTE_MASK 0x00FF + +/** + * BATADV_TT_SYNC_MASK - bitmask of the flags that need to be kept in sync + * among the nodes. These flags are used to compute the global/local CRC + */ +#define BATADV_TT_SYNC_MASK 0x00F0 + +/** * struct batadv_hard_iface_bat_iv - per hard interface B.A.T.M.A.N. IV data * @ogm_buff: buffer holding the OGM packet * @ogm_buff_len: length of the OGM packet buffer @@ -133,14 +145,28 @@ struct batadv_orig_node_vlan { }; /** + * struct batadv_orig_bat_iv - B.A.T.M.A.N. IV private orig_node members + * @bcast_own: bitfield containing the number of our OGMs this orig_node + * rebroadcasted "back" to us (relative to last_real_seqno) + * @bcast_own_sum: counted result of bcast_own + * @ogm_cnt_lock: lock protecting bcast_own, bcast_own_sum, + * neigh_node->bat_iv.real_bits & neigh_node->bat_iv.real_packet_count + */ +struct batadv_orig_bat_iv { + unsigned long *bcast_own; + uint8_t *bcast_own_sum; + /* ogm_cnt_lock protects: bcast_own, bcast_own_sum, + * neigh_node->bat_iv.real_bits & neigh_node->bat_iv.real_packet_count + */ + spinlock_t ogm_cnt_lock; +}; + +/** * struct batadv_orig_node - structure for orig_list maintaining nodes of mesh * @orig: originator ethernet address * @primary_addr: hosts primary interface address * @router: router that should be used to reach this originator * @batadv_dat_addr_t: address of the orig node in the distributed hash - * @bcast_own: bitfield containing the number of our OGMs this orig_node - * rebroadcasted "back" to us (relative to last_real_seqno) - * @bcast_own_sum: counted result of bcast_own * @last_seen: time when last packet from this node was received * @bcast_seqno_reset: time when the broadcast seqno window was reset * @batman_seqno_reset: time when the batman seqno window was reset @@ -166,8 +192,6 @@ struct batadv_orig_node_vlan { * @neigh_list_lock: lock protecting neigh_list, router and bonding_list * @hash_entry: hlist node for batadv_priv::orig_hash * @bat_priv: pointer to soft_iface this orig node belongs to - * @ogm_cnt_lock: lock protecting bcast_own, bcast_own_sum, - * neigh_node->real_bits & neigh_node->real_packet_count * @bcast_seqno_lock: lock protecting bcast_bits & last_bcast_seqno * @bond_candidates: how many candidates are available * @bond_list: list of bonding candidates @@ -181,6 +205,7 @@ struct batadv_orig_node_vlan { * @vlan_list: a list of orig_node_vlan structs, one per VLAN served by the * originator represented by this object * @vlan_list_lock: lock protecting vlan_list + * @bat_iv: B.A.T.M.A.N. IV private structure */ struct batadv_orig_node { uint8_t orig[ETH_ALEN]; @@ -189,8 +214,6 @@ struct batadv_orig_node { #ifdef CONFIG_BATMAN_ADV_DAT batadv_dat_addr_t dat_addr; #endif - unsigned long *bcast_own; - uint8_t *bcast_own_sum; unsigned long last_seen; unsigned long bcast_seqno_reset; unsigned long batman_seqno_reset; @@ -211,10 +234,6 @@ struct batadv_orig_node { spinlock_t neigh_list_lock; struct hlist_node hash_entry; struct batadv_priv *bat_priv; - /* ogm_cnt_lock protects: bcast_own, bcast_own_sum, - * neigh_node->real_bits & neigh_node->real_packet_count - */ - spinlock_t ogm_cnt_lock; /* bcast_seqno_lock protects: bcast_bits & last_bcast_seqno */ spinlock_t bcast_seqno_lock; atomic_t bond_candidates; @@ -230,6 +249,7 @@ struct batadv_orig_node { struct batadv_frag_table_entry fragments[BATADV_FRAG_BUFFER_COUNT]; struct list_head vlan_list; spinlock_t vlan_list_lock; /* protects vlan_list */ + struct batadv_orig_bat_iv bat_iv; }; /** @@ -263,40 +283,49 @@ struct batadv_gw_node { }; /** - * struct batadv_neigh_node - structure for single hop neighbors - * @list: list node for batadv_orig_node::neigh_list - * @addr: mac address of neigh node + * struct batadv_neigh_bat_iv - B.A.T.M.A.N. IV specific structure for single + * hop neighbors * @tq_recv: ring buffer of received TQ values from this neigh node * @tq_index: ring buffer index * @tq_avg: averaged tq of all tq values in the ring buffer (tq_recv) - * @last_ttl: last received ttl from this neigh node - * @bonding_list: list node for batadv_orig_node::bond_list - * @last_seen: when last packet via this neighbor was received * @real_bits: bitfield containing the number of OGMs received from this neigh * node (relative to orig_node->last_real_seqno) * @real_packet_count: counted result of real_bits + * @lq_update_lock: lock protecting tq_recv & tq_index + */ +struct batadv_neigh_bat_iv { + uint8_t tq_recv[BATADV_TQ_GLOBAL_WINDOW_SIZE]; + uint8_t tq_index; + uint8_t tq_avg; + DECLARE_BITMAP(real_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); + uint8_t real_packet_count; + spinlock_t lq_update_lock; /* protects tq_recv & tq_index */ +}; + +/** + * struct batadv_neigh_node - structure for single hops neighbors + * @list: list node for batadv_orig_node::neigh_list * @orig_node: pointer to corresponding orig_node + * @addr: the MAC address of the neighboring interface * @if_incoming: pointer to incoming hard interface - * @lq_update_lock: lock protecting tq_recv & tq_index + * @last_seen: when last packet via this neighbor was received + * @last_ttl: last received ttl from this neigh node + * @bonding_list: list node for batadv_orig_node::bond_list * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner + * @bat_iv: B.A.T.M.A.N. IV private structure */ struct batadv_neigh_node { struct hlist_node list; + struct batadv_orig_node *orig_node; uint8_t addr[ETH_ALEN]; - uint8_t tq_recv[BATADV_TQ_GLOBAL_WINDOW_SIZE]; - uint8_t tq_index; - uint8_t tq_avg; + struct batadv_hard_iface *if_incoming; + unsigned long last_seen; uint8_t last_ttl; struct list_head bonding_list; - unsigned long last_seen; - DECLARE_BITMAP(real_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); - uint8_t real_packet_count; - struct batadv_orig_node *orig_node; - struct batadv_hard_iface *if_incoming; - spinlock_t lq_update_lock; /* protects tq_recv & tq_index */ atomic_t refcount; struct rcu_head rcu; + struct batadv_neigh_bat_iv bat_iv; }; /** @@ -595,6 +624,8 @@ struct batadv_softif_vlan { * @aggregated_ogms: bool indicating whether OGM aggregation is enabled * @bonding: bool indicating whether traffic bonding is enabled * @fragmentation: bool indicating whether traffic fragmentation is enabled + * @packet_size_max: max packet size that can be transmitted via + * multiple fragmented skbs or a single frame if fragmentation is disabled * @frag_seqno: incremental counter to identify chains of egress fragments * @bridge_loop_avoidance: bool indicating whether bridge loop avoidance is * enabled @@ -641,6 +672,7 @@ struct batadv_priv { atomic_t aggregated_ogms; atomic_t bonding; atomic_t fragmentation; + atomic_t packet_size_max; atomic_t frag_seqno; #ifdef CONFIG_BATMAN_ADV_BLA atomic_t bridge_loop_avoidance; @@ -717,7 +749,7 @@ struct batadv_socket_client { struct batadv_socket_packet { struct list_head list; size_t icmp_len; - struct batadv_icmp_packet_rr icmp_packet; + uint8_t icmp_packet[BATADV_ICMP_MAX_PACKET_SIZE]; }; /** @@ -975,6 +1007,16 @@ struct batadv_forw_packet { * @bat_primary_iface_set: called when primary interface is selected / changed * @bat_ogm_schedule: prepare a new outgoing OGM for the send queue * @bat_ogm_emit: send scheduled OGM + * @bat_neigh_cmp: compare the metrics of two neighbors + * @bat_neigh_is_equiv_or_better: check if neigh1 is equally good or + * better than neigh2 from the metric prospective + * @bat_orig_print: print the originator table (optional) + * @bat_orig_free: free the resources allocated by the routing algorithm for an + * orig_node object + * @bat_orig_add_if: ask the routing algorithm to apply the needed changes to + * the orig_node due to a new hard-interface being added into the mesh + * @bat_orig_del_if: ask the routing algorithm to apply the needed changes to + * the orig_node due to an hard-interface being removed from the mesh */ struct batadv_algo_ops { struct hlist_node list; @@ -985,6 +1027,17 @@ struct batadv_algo_ops { void (*bat_primary_iface_set)(struct batadv_hard_iface *hard_iface); void (*bat_ogm_schedule)(struct batadv_hard_iface *hard_iface); void (*bat_ogm_emit)(struct batadv_forw_packet *forw_packet); + int (*bat_neigh_cmp)(struct batadv_neigh_node *neigh1, + struct batadv_neigh_node *neigh2); + bool (*bat_neigh_is_equiv_or_better)(struct batadv_neigh_node *neigh1, + struct batadv_neigh_node *neigh2); + /* orig_node handling API */ + void (*bat_orig_print)(struct batadv_priv *priv, struct seq_file *seq); + void (*bat_orig_free)(struct batadv_orig_node *orig_node); + int (*bat_orig_add_if)(struct batadv_orig_node *orig_node, + int max_if_num); + int (*bat_orig_del_if)(struct batadv_orig_node *orig_node, + int max_if_num, int del_if_num); }; /** diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index ffd5874f2592..33e8f23acddd 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -700,7 +700,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], vid = nla_get_u16(tb[NDA_VLAN]); - if (vid >= VLAN_N_VID) { + if (!vid || vid >= VLAN_VID_MASK) { pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", vid); return -EINVAL; @@ -794,7 +794,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], vid = nla_get_u16(tb[NDA_VLAN]); - if (vid >= VLAN_N_VID) { + if (!vid || vid >= VLAN_VID_MASK) { pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", vid); return -EINVAL; diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 85a09bb5ca51..b7b1914dfa25 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -453,7 +453,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) call_rcu_bh(&p->rcu, br_multicast_free_pg); err = 0; - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); break; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 005d876dd86c..0513ef3ce667 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -272,7 +272,7 @@ static void br_multicast_del_pg(struct net_bridge *br, del_timer(&p->timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); @@ -620,7 +620,6 @@ rehash: mp->br = br; mp->addr = *group; - setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp); @@ -660,6 +659,7 @@ static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; + unsigned long now = jiffies; int err; spin_lock(&br->multicast_lock); @@ -674,6 +674,7 @@ static int br_multicast_add_group(struct net_bridge *br, if (!port) { mp->mglist = true; + mod_timer(&mp->timer, now + br->multicast_membership_interval); goto out; } @@ -681,7 +682,7 @@ static int br_multicast_add_group(struct net_bridge *br, (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->port == port) - goto out; + goto found; if ((unsigned long)p->port < (unsigned long)port) break; } @@ -692,6 +693,8 @@ static int br_multicast_add_group(struct net_bridge *br, rcu_assign_pointer(*pp, p); br_mdb_notify(br->dev, port, group, RTM_NEWMDB); +found: + mod_timer(&p->timer, now + br->multicast_membership_interval); out: err = 0; @@ -1191,9 +1194,6 @@ static int br_ip4_multicast_query(struct net_bridge *br, if (!mp) goto out; - mod_timer(&mp->timer, now + br->multicast_membership_interval); - mp->timer_armed = true; - max_delay *= br->multicast_last_member_count; if (mp->mglist && @@ -1270,9 +1270,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (!mp) goto out; - mod_timer(&mp->timer, now + br->multicast_membership_interval); - mp->timer_armed = true; - max_delay *= br->multicast_last_member_count; if (mp->mglist && (timer_pending(&mp->timer) ? @@ -1358,7 +1355,7 @@ static void br_multicast_leave_group(struct net_bridge *br, call_rcu_bh(&p->rcu, br_multicast_free_pg); br_mdb_notify(br->dev, port, group, RTM_DELMDB); - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); } @@ -1370,12 +1367,30 @@ static void br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval; if (!port) { - if (mp->mglist && mp->timer_armed && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { mod_timer(&mp->timer, time); } + + goto out; + } + + for (p = mlock_dereference(mp->ports, br); + p != NULL; + p = mlock_dereference(p->next, br)) { + if (p->port != port) + continue; + + if (!hlist_unhashed(&p->mglist) && + (timer_pending(&p->timer) ? + time_after(p->timer.expires, time) : + try_to_del_timer_sync(&p->timer) >= 0)) { + mod_timer(&p->timer, time); + } + + break; } out: spin_unlock(&br->multicast_lock); @@ -1798,7 +1813,6 @@ void br_multicast_stop(struct net_bridge *br) hlist_for_each_entry_safe(mp, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); - mp->timer_armed = false; call_rcu_bh(&mp->rcu, br_multicast_free_group); } } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e74ddc1c29a8..f75d92e4f96b 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -243,7 +243,7 @@ static int br_afspec(struct net_bridge *br, vinfo = nla_data(tb[IFLA_BRIDGE_VLAN_INFO]); - if (vinfo->vid >= VLAN_N_VID) + if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK) return -EINVAL; switch (cmd) { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 767c4dad8504..d1ca6d956633 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -126,7 +126,6 @@ struct net_bridge_mdb_entry struct timer_list timer; struct br_ip addr; bool mglist; - bool timer_armed; }; struct net_bridge_mdb_htable @@ -624,9 +623,7 @@ static inline u16 br_get_pvid(const struct net_port_vlans *v) * vid wasn't set */ smp_rmb(); - return (v->pvid & VLAN_TAG_PRESENT) ? - (v->pvid & ~VLAN_TAG_PRESENT) : - VLAN_N_VID; + return v->pvid ?: VLAN_N_VID; } #else diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 108084a04671..656a6f3e40de 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -134,7 +134,7 @@ static void br_stp_start(struct net_bridge *br) if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY) __br_set_forward_delay(br, BR_MIN_FORWARD_DELAY); - else if (br->bridge_forward_delay < BR_MAX_FORWARD_DELAY) + else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY) __br_set_forward_delay(br, BR_MAX_FORWARD_DELAY); if (r == 0) { diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 9a9ffe7e4019..53f0990eab58 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -45,37 +45,34 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags) return 0; } - if (vid) { - if (v->port_idx) { - p = v->parent.port; - br = p->br; - dev = p->dev; - } else { - br = v->parent.br; - dev = br->dev; - } - ops = dev->netdev_ops; - - if (p && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { - /* Add VLAN to the device filter if it is supported. - * Stricly speaking, this is not necessary now, since - * devices are made promiscuous by the bridge, but if - * that ever changes this code will allow tagged - * traffic to enter the bridge. - */ - err = ops->ndo_vlan_rx_add_vid(dev, htons(ETH_P_8021Q), - vid); - if (err) - return err; - } - - err = br_fdb_insert(br, p, dev->dev_addr, vid); - if (err) { - br_err(br, "failed insert local address into bridge " - "forwarding table\n"); - goto out_filt; - } + if (v->port_idx) { + p = v->parent.port; + br = p->br; + dev = p->dev; + } else { + br = v->parent.br; + dev = br->dev; + } + ops = dev->netdev_ops; + + if (p && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { + /* Add VLAN to the device filter if it is supported. + * Stricly speaking, this is not necessary now, since + * devices are made promiscuous by the bridge, but if + * that ever changes this code will allow tagged + * traffic to enter the bridge. + */ + err = ops->ndo_vlan_rx_add_vid(dev, htons(ETH_P_8021Q), + vid); + if (err) + return err; + } + err = br_fdb_insert(br, p, dev->dev_addr, vid); + if (err) { + br_err(br, "failed insert local address into bridge " + "forwarding table\n"); + goto out_filt; } set_bit(vid, v->vlan_bitmap); @@ -98,7 +95,7 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid) __vlan_delete_pvid(v, vid); clear_bit(vid, v->untagged_bitmap); - if (v->port_idx && vid) { + if (v->port_idx) { struct net_device *dev = v->parent.port->dev; const struct net_device_ops *ops = dev->netdev_ops; @@ -192,6 +189,8 @@ out: bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, struct sk_buff *skb, u16 *vid) { + int err; + /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ @@ -204,20 +203,32 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, if (!v) return false; - if (br_vlan_get_tag(skb, vid)) { + err = br_vlan_get_tag(skb, vid); + if (!*vid) { u16 pvid = br_get_pvid(v); - /* Frame did not have a tag. See if pvid is set - * on this port. That tells us which vlan untagged - * traffic belongs to. + /* Frame had a tag with VID 0 or did not have a tag. + * See if pvid is set on this port. That tells us which + * vlan untagged or priority-tagged traffic belongs to. */ if (pvid == VLAN_N_VID) return false; - /* PVID is set on this port. Any untagged ingress - * frame is considered to belong to this vlan. + /* PVID is set on this port. Any untagged or priority-tagged + * ingress frame is considered to belong to this vlan. */ - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), pvid); + *vid = pvid; + if (likely(err)) + /* Untagged Frame. */ + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), pvid); + else + /* Priority-tagged Frame. + * At this point, We know that skb->vlan_tci had + * VLAN_TAG_PRESENT bit and its VID field was 0x000. + * We update only VID field and preserve PCP field. + */ + skb->vlan_tci |= pvid; + return true; } @@ -248,7 +259,9 @@ bool br_allowed_egress(struct net_bridge *br, return false; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) { struct net_port_vlans *pv = NULL; @@ -278,7 +291,9 @@ out: return err; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int br_vlan_delete(struct net_bridge *br, u16 vid) { struct net_port_vlans *pv; @@ -289,14 +304,9 @@ int br_vlan_delete(struct net_bridge *br, u16 vid) if (!pv) return -EINVAL; - if (vid) { - /* If the VID !=0 remove fdb for this vid. VID 0 is special - * in that it's the default and is always there in the fdb. - */ - spin_lock_bh(&br->hash_lock); - fdb_delete_by_addr(br, br->dev->dev_addr, vid); - spin_unlock_bh(&br->hash_lock); - } + spin_lock_bh(&br->hash_lock); + fdb_delete_by_addr(br, br->dev->dev_addr, vid); + spin_unlock_bh(&br->hash_lock); __vlan_del(pv, vid); return 0; @@ -329,7 +339,9 @@ unlock: return 0; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) { struct net_port_vlans *pv = NULL; @@ -363,7 +375,9 @@ clean_up: return err; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) { struct net_port_vlans *pv; @@ -374,14 +388,9 @@ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) if (!pv) return -EINVAL; - if (vid) { - /* If the VID !=0 remove fdb for this vid. VID 0 is special - * in that it's the default and is always there in the fdb. - */ - spin_lock_bh(&port->br->hash_lock); - fdb_delete_by_addr(port->br, port->dev->dev_addr, vid); - spin_unlock_bh(&port->br->hash_lock); - } + spin_lock_bh(&port->br->hash_lock); + fdb_delete_by_addr(port->br, port->dev->dev_addr, vid); + spin_unlock_bh(&port->br->hash_lock); return __vlan_del(pv, vid); } diff --git a/net/core/datagram.c b/net/core/datagram.c index af814e764206..a16ed7bbe376 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -577,7 +577,7 @@ EXPORT_SYMBOL(skb_copy_datagram_from_iovec); /** * zerocopy_sg_from_iovec - Build a zerocopy datagram from an iovec * @skb: buffer to copy - * @from: io vector to copy to + * @from: io vector to copy from * @offset: offset in the io vector to start copying from * @count: amount of vectors to copy to buffer from * diff --git a/net/core/dev.c b/net/core/dev.c index 0918aadc20fd..0054c8c75f50 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1203,7 +1203,7 @@ void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { call_netdevice_notifiers(NETDEV_CHANGE, dev); - rtmsg_ifinfo(RTM_NEWLINK, dev, 0); + rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); } } EXPORT_SYMBOL(netdev_state_change); @@ -1293,7 +1293,7 @@ int dev_open(struct net_device *dev) if (ret < 0) return ret; - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); call_netdevice_notifiers(NETDEV_UP, dev); return ret; @@ -1371,7 +1371,7 @@ static int dev_close_many(struct list_head *head) __dev_close_many(head); list_for_each_entry_safe(dev, tmp, head, close_list) { - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); call_netdevice_notifiers(NETDEV_DOWN, dev); list_del_init(&dev->close_list); } @@ -4648,6 +4648,7 @@ remove_symlinks: free_adj: kfree(adj); + dev_put(adj_dev); return ret; } @@ -5257,7 +5258,7 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, unsigned int changes = dev->flags ^ old_flags; if (gchanges) - rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges); + rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC); if (changes & IFF_UP) { if (dev->flags & IFF_UP) @@ -5489,7 +5490,7 @@ static void rollback_registered_many(struct list_head *head) if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); /* * Flush the unicast and multicast chains @@ -5888,7 +5889,7 @@ int register_netdevice(struct net_device *dev) */ if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); out: return ret; @@ -6500,7 +6501,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); /* * Flush the unicast and multicast chains @@ -6539,7 +6540,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); synchronize_net(); err = 0; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 6cda4e2c2132..ec40a849fc42 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -752,7 +752,7 @@ int dev_mc_del_global(struct net_device *dev, const unsigned char *addr) EXPORT_SYMBOL(dev_mc_del_global); /** - * dev_mc_sync - Synchronize device's unicast list to another device + * dev_mc_sync - Synchronize device's multicast list to another device * @to: destination device * @from: source device * @@ -780,7 +780,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from) EXPORT_SYMBOL(dev_mc_sync); /** - * dev_mc_sync_multiple - Synchronize device's unicast list to another + * dev_mc_sync_multiple - Synchronize device's multicast list to another * device, but allow for multiple calls to sync to multiple devices. * @to: destination device * @from: source device diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 8cab7744790e..862989898f61 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -82,6 +82,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", [NETIF_F_GSO_IPIP_BIT] = "tx-ipip-segmentation", + [NETIF_F_GSO_SIT_BIT] = "tx-sit-segmentation", [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", [NETIF_F_GSO_MPLS_BIT] = "tx-mpls-segmentation", diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index f8e25ac41c6c..5cac36e6ccd1 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -184,6 +184,22 @@ ipv6: EXPORT_SYMBOL(skb_flow_dissect); static u32 hashrnd __read_mostly; +static __always_inline void __flow_hash_secret_init(void) +{ + net_get_random_once(&hashrnd, sizeof(hashrnd)); +} + +static __always_inline u32 __flow_hash_3words(u32 a, u32 b, u32 c) +{ + __flow_hash_secret_init(); + return jhash_3words(a, b, c, hashrnd); +} + +static __always_inline u32 __flow_hash_1word(u32 a) +{ + __flow_hash_secret_init(); + return jhash_1word(a, hashrnd); +} /* * __skb_get_rxhash: calculate a flow hash based on src/dst addresses @@ -210,9 +226,9 @@ void __skb_get_rxhash(struct sk_buff *skb) swap(keys.port16[0], keys.port16[1]); } - hash = jhash_3words((__force u32)keys.dst, - (__force u32)keys.src, - (__force u32)keys.ports, hashrnd); + hash = __flow_hash_3words((__force u32)keys.dst, + (__force u32)keys.src, + (__force u32)keys.ports); if (!hash) hash = 1; @@ -248,7 +264,7 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, hash = skb->sk->sk_hash; else hash = (__force u16) skb->protocol; - hash = jhash_1word(hash, hashrnd); + hash = __flow_hash_1word(hash); return (u16) (((u64) hash * qcount) >> 32) + qoffset; } @@ -340,7 +356,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) else hash = (__force u16) skb->protocol ^ skb->rxhash; - hash = jhash_1word(hash, hashrnd); + hash = __flow_hash_1word(hash); queue_index = map->queues[ ((u64)hash * map->len) >> 32]; } @@ -395,11 +411,3 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, skb_set_queue_mapping(skb, queue_index); return netdev_get_tx_queue(dev, queue_index); } - -static int __init initialize_hashrnd(void) -{ - get_random_bytes(&hashrnd, sizeof(hashrnd)); - return 0; -} - -late_initcall_sync(initialize_hashrnd); diff --git a/net/core/iovec.c b/net/core/iovec.c index b77eeecc0011..4cdb7c48dad6 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -100,7 +100,7 @@ int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata, EXPORT_SYMBOL(memcpy_toiovecend); /* - * Copy iovec from kernel. Returns -EFAULT on error. + * Copy iovec to kernel. Returns -EFAULT on error. */ int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 4aedf03da052..cf67144d3e3c 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1984,14 +1984,15 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change) +void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, + gfp_t flags) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; size_t if_info_size; - skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), GFP_KERNEL); + skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), flags); if (skb == NULL) goto errout; @@ -2002,7 +2003,7 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change) kfree_skb(skb); goto errout; } - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL); + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags); return; errout: if (err < 0) @@ -2716,7 +2717,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_JOIN: break; default: - rtmsg_ifinfo(RTM_NEWLINK, dev, 0); + rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); break; } return NOTIFY_DONE; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index b02fd16b8942..897da56f3aff 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -11,14 +11,16 @@ #include <net/secure_seq.h> +#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET) #define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4) static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned; -static void net_secret_init(void) +static __always_inline void net_secret_init(void) { net_get_random_once(net_secret, sizeof(net_secret)); } +#endif #ifdef CONFIG_INET static u32 seq_scale(u32 seq) diff --git a/net/core/sock.c b/net/core/sock.c index 440afdca1e8f..ab20ed9b0f31 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -475,12 +475,6 @@ discard_and_relse: } EXPORT_SYMBOL(sk_receive_skb); -void sk_reset_txq(struct sock *sk) -{ - sk_tx_queue_clear(sk); -} -EXPORT_SYMBOL(sk_reset_txq); - struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); diff --git a/net/core/utils.c b/net/core/utils.c index bf09371e19b1..2f737bf90b3f 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -370,16 +370,17 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done, struct static_key *done_key) { static DEFINE_SPINLOCK(lock); + unsigned long flags; - spin_lock_bh(&lock); + spin_lock_irqsave(&lock, flags); if (*done) { - spin_unlock_bh(&lock); + spin_unlock_irqrestore(&lock, flags); return false; } get_random_bytes(buf, nbytes); *done = true; - spin_unlock_bh(&lock); + spin_unlock_irqrestore(&lock, flags); __net_random_once_disable_jump(done_key); diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index ff41b4d60d30..9497c6f3276b 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -440,7 +440,6 @@ lowpan_uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh) default: pr_debug("ERROR: unknown UDP format\n"); goto err; - break; } pr_debug("uncompressed UDP ports: src = %d, dst = %d\n", @@ -655,7 +654,9 @@ static int lowpan_header_create(struct sk_buff *skb, head[1] = iphc1; skb_pull(skb, sizeof(struct ipv6hdr)); + skb_reset_transport_header(skb); memcpy(skb_push(skb, hc06_ptr - head), head, hc06_ptr - head); + skb_reset_network_header(skb); lowpan_raw_dump_table(__func__, "raw skb data dump", skb->data, skb->len); @@ -738,7 +739,6 @@ static int lowpan_skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr) return -ENOMEM; skb_push(new, sizeof(struct ipv6hdr)); - skb_reset_network_header(new); skb_copy_to_linear_data(new, hdr, sizeof(struct ipv6hdr)); new->protocol = htons(ETH_P_IPV6); @@ -785,7 +785,6 @@ lowpan_alloc_new_frame(struct sk_buff *skb, u16 len, u16 tag) goto skb_err; frame->skb->priority = skb->priority; - frame->skb->dev = skb->dev; /* reserve headroom for uncompressed ipv6 header */ skb_reserve(frame->skb, sizeof(struct ipv6hdr)); @@ -1061,7 +1060,6 @@ lowpan_process_data(struct sk_buff *skb) skb = new; skb_push(skb, sizeof(struct udphdr)); - skb_reset_transport_header(skb); skb_copy_to_linear_data(skb, &uh, sizeof(struct udphdr)); lowpan_raw_dump_table(__func__, "raw UDP header dump", @@ -1104,50 +1102,40 @@ static int lowpan_set_address(struct net_device *dev, void *p) return 0; } -static int lowpan_get_mac_header_length(struct sk_buff *skb) -{ - /* - * Currently long addressing mode is supported only, so the overall - * header size is 21: - * FC SeqNum DPAN DA SA Sec - * 2 + 1 + 2 + 8 + 8 + 0 = 21 - */ - return 21; -} - static int lowpan_fragment_xmit(struct sk_buff *skb, u8 *head, int mlen, int plen, int offset, int type) { struct sk_buff *frag; - int hlen, ret; + int hlen; hlen = (type == LOWPAN_DISPATCH_FRAG1) ? LOWPAN_FRAG1_HEAD_SIZE : LOWPAN_FRAGN_HEAD_SIZE; lowpan_raw_dump_inline(__func__, "6lowpan fragment header", head, hlen); - frag = dev_alloc_skb(hlen + mlen + plen + IEEE802154_MFR_SIZE); + frag = netdev_alloc_skb(skb->dev, + hlen + mlen + plen + IEEE802154_MFR_SIZE); if (!frag) return -ENOMEM; frag->priority = skb->priority; - frag->dev = skb->dev; /* copy header, MFR and payload */ - memcpy(skb_put(frag, mlen), skb->data, mlen); - memcpy(skb_put(frag, hlen), head, hlen); + skb_put(frag, mlen); + skb_copy_to_linear_data(frag, skb_mac_header(skb), mlen); - if (plen) - skb_copy_from_linear_data_offset(skb, offset + mlen, - skb_put(frag, plen), plen); + skb_put(frag, hlen); + skb_copy_to_linear_data_offset(frag, mlen, head, hlen); + + skb_put(frag, plen); + skb_copy_to_linear_data_offset(frag, mlen + hlen, + skb_network_header(skb) + offset, plen); lowpan_raw_dump_table(__func__, " raw fragment dump", frag->data, frag->len); - ret = dev_queue_xmit(frag); - - return ret; + return dev_queue_xmit(frag); } static int @@ -1156,7 +1144,7 @@ lowpan_skb_fragmentation(struct sk_buff *skb, struct net_device *dev) int err, header_length, payload_length, tag, offset = 0; u8 head[5]; - header_length = lowpan_get_mac_header_length(skb); + header_length = skb->mac_len; payload_length = skb->len - header_length; tag = lowpan_dev_info(dev)->fragment_tag++; @@ -1181,7 +1169,7 @@ lowpan_skb_fragmentation(struct sk_buff *skb, struct net_device *dev) head[0] &= ~LOWPAN_DISPATCH_FRAG1; head[0] |= LOWPAN_DISPATCH_FRAGN; - while ((payload_length - offset > 0) && (err >= 0)) { + while (payload_length - offset > 0) { int len = LOWPAN_FRAG_SIZE; head[4] = offset / 8; @@ -1327,8 +1315,6 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, /* Pull off the 1-byte of 6lowpan header. */ skb_pull(local_skb, 1); - skb_reset_network_header(local_skb); - skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); lowpan_give_skb_to_devices(local_skb); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9433a6186f54..09d78d4a3cff 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1251,8 +1251,8 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; unsigned int offset = 0; + bool udpfrag, encap; struct iphdr *iph; - bool tunnel; int proto; int nhoff; int ihl; @@ -1265,6 +1265,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_TCP_ECN | SKB_GSO_GRE | SKB_GSO_IPIP | + SKB_GSO_SIT | SKB_GSO_TCPV6 | SKB_GSO_UDP_TUNNEL | SKB_GSO_MPLS | @@ -1289,8 +1290,8 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, goto out; __skb_pull(skb, ihl); - tunnel = SKB_GSO_CB(skb)->encap_level > 0; - if (tunnel) + encap = SKB_GSO_CB(skb)->encap_level > 0; + if (encap) features = skb->dev->hw_enc_features & netif_skb_features(skb); SKB_GSO_CB(skb)->encap_level += ihl; @@ -1305,24 +1306,23 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (IS_ERR_OR_NULL(segs)) goto out; + udpfrag = !!skb->encapsulation && proto == IPPROTO_UDP; skb = segs; do { iph = (struct iphdr *)(skb_mac_header(skb) + nhoff); - if (!tunnel && proto == IPPROTO_UDP) { + if (udpfrag) { iph->id = htons(id); iph->frag_off = htons(offset >> 3); if (skb->next != NULL) iph->frag_off |= htons(IP_MF); offset += skb->len - nhoff - ihl; - } else { + } else { iph->id = htons(id++); } iph->tot_len = htons(skb->len - nhoff); ip_send_check(iph); - if (tunnel) { + if (encap) skb_reset_inner_headers(skb); - skb->encapsulation = 1; - } skb->network_header = (u8 *)iph - skb->head; } while ((skb = skb->next)); @@ -1697,8 +1697,6 @@ static int __init inet_init(void) ip_static_sysctl_init(); #endif - tcp_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem; - /* * Add all the base protocols. */ diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c5313a9c019b..bb075fc9a14f 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -93,9 +93,6 @@ void inet_frags_init(struct inet_frags *f) } rwlock_init(&f->lock); - f->rnd = (u32) ((totalram_pages ^ (totalram_pages >> 7)) ^ - (jiffies ^ (jiffies >> 6))); - setup_timer(&f->secret_timer, inet_frag_secret_rebuild, (unsigned long)f); f->secret_timer.expires = jiffies + f->secret_interval; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b66910aaef4d..2481993a4970 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -106,6 +106,7 @@ struct ip4_create_arg { static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot) { + net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd)); return jhash_3words((__force u32)id << 16 | prot, (__force u32)saddr, (__force u32)daddr, ip4_frags.rnd) & (INETFRAGS_HASHSZ - 1); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 7d8357bb2ba6..51be64e18e32 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -772,15 +772,20 @@ static inline int ip_ufo_append_data(struct sock *sk, /* initialize protocol header pointer */ skb->transport_header = skb->network_header + fragheaderlen; - skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - /* specify the length of each IP datagram fragment */ - skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + __skb_queue_tail(queue, skb); + } else if (skb_is_gso(skb)) { + goto append; } + skb->ip_summed = CHECKSUM_PARTIAL; + /* specify the length of each IP datagram fragment */ + skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + +append: return skb_append_datato_frags(sk, skb, getfrag, from, (length - transhdrlen)); } @@ -805,7 +810,7 @@ static int __ip_append_data(struct sock *sk, int copy; int err; int offset = 0; - unsigned int maxfraglen, fragheaderlen; + unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; @@ -818,8 +823,10 @@ static int __ip_append_data(struct sock *sk, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; + maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ? + mtu : 0xFFFF; - if (cork->length + length > 0xFFFF - fragheaderlen) { + if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu-exthdrlen); return -EMSGSIZE; @@ -1117,7 +1124,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, int mtu; int len; int err; - unsigned int maxfraglen, fragheaderlen, fraggap; + unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize; if (inet->hdrincl) return -EPERM; @@ -1141,8 +1148,10 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; + maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ? + mtu : 0xFFFF; - if (cork->length + size > 0xFFFF - fragheaderlen) { + if (cork->length + size > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu); return -EMSGSIZE; } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 91f69bc883fe..5d9c845d288a 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -61,8 +61,17 @@ static int vti_rcv(struct sk_buff *skb) iph->saddr, iph->daddr, 0); if (tunnel != NULL) { struct pcpu_tstats *tstats; + u32 oldmark = skb->mark; + int ret; - if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + + /* temporarily mark the skb with the tunnel o_key, to + * only match policies with this mark. + */ + skb->mark = be32_to_cpu(tunnel->parms.o_key); + ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb); + skb->mark = oldmark; + if (!ret) return -1; tstats = this_cpu_ptr(tunnel->dev->tstats); @@ -71,7 +80,6 @@ static int vti_rcv(struct sk_buff *skb) tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); - skb->mark = 0; secpath_reset(skb); skb->dev = tunnel->dev; return 1; @@ -103,7 +111,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&fl4, 0, sizeof(fl4)); flowi4_init_output(&fl4, tunnel->parms.link, - be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos), + be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPIP, 0, dst, tiph->saddr, 0, 0); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 4b161d5aba0b..d5b1390eebbe 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -200,49 +200,6 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl, return ret; } -static int ipv4_tcp_mem(struct ctl_table *ctl, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) -{ - int ret; - unsigned long vec[3]; - struct net *net = current->nsproxy->net_ns; -#ifdef CONFIG_MEMCG_KMEM - struct mem_cgroup *memcg; -#endif - - struct ctl_table tmp = { - .data = &vec, - .maxlen = sizeof(vec), - .mode = ctl->mode, - }; - - if (!write) { - ctl->data = &net->ipv4.sysctl_tcp_mem; - return proc_doulongvec_minmax(ctl, write, buffer, lenp, ppos); - } - - ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos); - if (ret) - return ret; - -#ifdef CONFIG_MEMCG_KMEM - rcu_read_lock(); - memcg = mem_cgroup_from_task(current); - - tcp_prot_mem(memcg, vec[0], 0); - tcp_prot_mem(memcg, vec[1], 1); - tcp_prot_mem(memcg, vec[2], 2); - rcu_read_unlock(); -#endif - - net->ipv4.sysctl_tcp_mem[0] = vec[0]; - net->ipv4.sysctl_tcp_mem[1] = vec[1]; - net->ipv4.sysctl_tcp_mem[2] = vec[2]; - - return 0; -} - static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -557,6 +514,13 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { + .procname = "tcp_mem", + .maxlen = sizeof(sysctl_tcp_mem), + .data = &sysctl_tcp_mem, + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { .procname = "tcp_wmem", .data = &sysctl_tcp_wmem, .maxlen = sizeof(sysctl_tcp_wmem), @@ -865,12 +829,6 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = ipv4_local_port_range, }, - { - .procname = "tcp_mem", - .maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem), - .mode = 0644, - .proc_handler = ipv4_tcp_mem, - }, { } }; @@ -880,32 +838,15 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) table = ipv4_net_table; if (!net_eq(net, &init_net)) { + int i; + table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL); if (table == NULL) goto err_alloc; - table[0].data = - &net->ipv4.sysctl_icmp_echo_ignore_all; - table[1].data = - &net->ipv4.sysctl_icmp_echo_ignore_broadcasts; - table[2].data = - &net->ipv4.sysctl_icmp_ignore_bogus_error_responses; - table[3].data = - &net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr; - table[4].data = - &net->ipv4.sysctl_icmp_ratelimit; - table[5].data = - &net->ipv4.sysctl_icmp_ratemask; - table[6].data = - &net->ipv4.sysctl_ping_group_range; - table[7].data = - &net->ipv4.sysctl_tcp_ecn; - table[8].data = - &net->ipv4.sysctl_local_ports.range; - - /* Don't export sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) - table[0].procname = NULL; + /* Update the variables to point into the current struct net */ + for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) + table[i].data += (void *)net - (void *)&init_net; } /* @@ -922,8 +863,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_local_ports.range[0] = 32768; net->ipv4.sysctl_local_ports.range[1] = 61000; - tcp_init_mem(net); - net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); if (net->ipv4.ipv4_hdr == NULL) goto err_reg; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index be4b161802e8..8e8529d3c8c9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -288,9 +288,11 @@ int sysctl_tcp_min_tso_segs __read_mostly = 2; struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); +long sysctl_tcp_mem[3] __read_mostly; int sysctl_tcp_wmem[3] __read_mostly; int sysctl_tcp_rmem[3] __read_mostly; +EXPORT_SYMBOL(sysctl_tcp_mem); EXPORT_SYMBOL(sysctl_tcp_rmem); EXPORT_SYMBOL(sysctl_tcp_wmem); @@ -3097,13 +3099,13 @@ static int __init set_thash_entries(char *str) } __setup("thash_entries=", set_thash_entries); -void tcp_init_mem(struct net *net) +static void tcp_init_mem(void) { unsigned long limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); - net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3; - net->ipv4.sysctl_tcp_mem[1] = limit; - net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2; + sysctl_tcp_mem[0] = limit / 4 * 3; + sysctl_tcp_mem[1] = limit; + sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; } void __init tcp_init(void) @@ -3165,7 +3167,7 @@ void __init tcp_init(void) sysctl_tcp_max_orphans = cnt / 2; sysctl_max_syn_backlog = max(128, cnt / 256); - tcp_init_mem(&init_net); + tcp_init_mem(); /* Set per-socket limits to no more than 1/128 the pressure threshold */ limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); max_wshare = min(4UL*1024*1024, limit); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eb651a069a6c..b935397c703c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3338,7 +3338,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) tcp_init_cwnd_reduction(sk, true); tcp_set_ca_state(sk, TCP_CA_CWR); tcp_end_cwnd_reduction(sk); - tcp_set_ca_state(sk, TCP_CA_Open); + tcp_try_keep_open(sk); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBERECOVERY); } @@ -5751,6 +5751,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } else tcp_init_metrics(sk); + tcp_update_pacing_rate(sk); + /* Prevent spurious tcp_cwnd_restart() on first data packet */ tp->lsndtime = tcp_time_stamp; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 114d1b748cbb..300ab2c93f29 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2749,6 +2749,7 @@ struct proto tcp_prot = { .orphan_count = &tcp_orphan_count, .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, + .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem = sysctl_tcp_wmem, .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 559d4ae6ebf4..03e9154f7e68 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -6,15 +6,10 @@ #include <linux/memcontrol.h> #include <linux/module.h> -static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto) -{ - return container_of(cg_proto, struct tcp_memcontrol, cg_proto); -} - static void memcg_tcp_enter_memory_pressure(struct sock *sk) { if (sk->sk_cgrp->memory_pressure) - *sk->sk_cgrp->memory_pressure = 1; + sk->sk_cgrp->memory_pressure = 1; } EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure); @@ -27,34 +22,24 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss) */ struct res_counter *res_parent = NULL; struct cg_proto *cg_proto, *parent_cg; - struct tcp_memcontrol *tcp; struct mem_cgroup *parent = parent_mem_cgroup(memcg); - struct net *net = current->nsproxy->net_ns; cg_proto = tcp_prot.proto_cgroup(memcg); if (!cg_proto) return 0; - tcp = tcp_from_cgproto(cg_proto); - - tcp->tcp_prot_mem[0] = net->ipv4.sysctl_tcp_mem[0]; - tcp->tcp_prot_mem[1] = net->ipv4.sysctl_tcp_mem[1]; - tcp->tcp_prot_mem[2] = net->ipv4.sysctl_tcp_mem[2]; - tcp->tcp_memory_pressure = 0; + cg_proto->sysctl_mem[0] = sysctl_tcp_mem[0]; + cg_proto->sysctl_mem[1] = sysctl_tcp_mem[1]; + cg_proto->sysctl_mem[2] = sysctl_tcp_mem[2]; + cg_proto->memory_pressure = 0; + cg_proto->memcg = memcg; parent_cg = tcp_prot.proto_cgroup(parent); if (parent_cg) - res_parent = parent_cg->memory_allocated; - - res_counter_init(&tcp->tcp_memory_allocated, res_parent); - percpu_counter_init(&tcp->tcp_sockets_allocated, 0); + res_parent = &parent_cg->memory_allocated; - cg_proto->enter_memory_pressure = memcg_tcp_enter_memory_pressure; - cg_proto->memory_pressure = &tcp->tcp_memory_pressure; - cg_proto->sysctl_mem = tcp->tcp_prot_mem; - cg_proto->memory_allocated = &tcp->tcp_memory_allocated; - cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated; - cg_proto->memcg = memcg; + res_counter_init(&cg_proto->memory_allocated, res_parent); + percpu_counter_init(&cg_proto->sockets_allocated, 0); return 0; } @@ -63,21 +48,17 @@ EXPORT_SYMBOL(tcp_init_cgroup); void tcp_destroy_cgroup(struct mem_cgroup *memcg) { struct cg_proto *cg_proto; - struct tcp_memcontrol *tcp; cg_proto = tcp_prot.proto_cgroup(memcg); if (!cg_proto) return; - tcp = tcp_from_cgproto(cg_proto); - percpu_counter_destroy(&tcp->tcp_sockets_allocated); + percpu_counter_destroy(&cg_proto->sockets_allocated); } EXPORT_SYMBOL(tcp_destroy_cgroup); static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) { - struct net *net = current->nsproxy->net_ns; - struct tcp_memcontrol *tcp; struct cg_proto *cg_proto; u64 old_lim; int i; @@ -90,16 +71,14 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) if (val > RES_COUNTER_MAX) val = RES_COUNTER_MAX; - tcp = tcp_from_cgproto(cg_proto); - - old_lim = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT); - ret = res_counter_set_limit(&tcp->tcp_memory_allocated, val); + old_lim = res_counter_read_u64(&cg_proto->memory_allocated, RES_LIMIT); + ret = res_counter_set_limit(&cg_proto->memory_allocated, val); if (ret) return ret; for (i = 0; i < 3; i++) - tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT, - net->ipv4.sysctl_tcp_mem[i]); + cg_proto->sysctl_mem[i] = min_t(long, val >> PAGE_SHIFT, + sysctl_tcp_mem[i]); if (val == RES_COUNTER_MAX) clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); @@ -156,28 +135,24 @@ static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val) { - struct tcp_memcontrol *tcp; struct cg_proto *cg_proto; cg_proto = tcp_prot.proto_cgroup(memcg); if (!cg_proto) return default_val; - tcp = tcp_from_cgproto(cg_proto); - return res_counter_read_u64(&tcp->tcp_memory_allocated, type); + return res_counter_read_u64(&cg_proto->memory_allocated, type); } static u64 tcp_read_usage(struct mem_cgroup *memcg) { - struct tcp_memcontrol *tcp; struct cg_proto *cg_proto; cg_proto = tcp_prot.proto_cgroup(memcg); if (!cg_proto) return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT; - tcp = tcp_from_cgproto(cg_proto); - return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE); + return res_counter_read_u64(&cg_proto->memory_allocated, RES_USAGE); } static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft) @@ -205,54 +180,25 @@ static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft) static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event) { struct mem_cgroup *memcg; - struct tcp_memcontrol *tcp; struct cg_proto *cg_proto; memcg = mem_cgroup_from_css(css); cg_proto = tcp_prot.proto_cgroup(memcg); if (!cg_proto) return 0; - tcp = tcp_from_cgproto(cg_proto); switch (event) { case RES_MAX_USAGE: - res_counter_reset_max(&tcp->tcp_memory_allocated); + res_counter_reset_max(&cg_proto->memory_allocated); break; case RES_FAILCNT: - res_counter_reset_failcnt(&tcp->tcp_memory_allocated); + res_counter_reset_failcnt(&cg_proto->memory_allocated); break; } return 0; } -unsigned long long tcp_max_memory(const struct mem_cgroup *memcg) -{ - struct tcp_memcontrol *tcp; - struct cg_proto *cg_proto; - - cg_proto = tcp_prot.proto_cgroup((struct mem_cgroup *)memcg); - if (!cg_proto) - return 0; - - tcp = tcp_from_cgproto(cg_proto); - return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT); -} - -void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx) -{ - struct tcp_memcontrol *tcp; - struct cg_proto *cg_proto; - - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) - return; - - tcp = tcp_from_cgproto(cg_proto); - - tcp->tcp_prot_mem[idx] = val; -} - static struct cftype tcp_files[] = { { .name = "kmem.tcp.limit_in_bytes", diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 4a2a84110dfb..2ab09cbae74d 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -671,8 +671,9 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen; write_seqlock_bh(&fastopen_seqlock); - tfom->mss = mss; - if (cookie->len > 0) + if (mss) + tfom->mss = mss; + if (cookie && cookie->len > 0) tfom->cookie = *cookie; if (syn_lost) { ++tfom->syn_loss; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index dfc96b00673e..a7a5583eab04 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -57,6 +57,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, SKB_GSO_TCPV6 | SKB_GSO_GRE | SKB_GSO_IPIP | + SKB_GSO_SIT | SKB_GSO_MPLS | SKB_GSO_UDP_TUNNEL | 0) || diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index ce7c4d9d9195..672854664ff5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -986,8 +986,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { - if (skb->len <= mss_now || !sk_can_gso(sk) || - skb->ip_summed == CHECKSUM_NONE) { + /* Make sure we own this skb before messing gso_size/gso_segs */ + WARN_ON_ONCE(skb_cloned(skb)); + + if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal * non-TSO case. */ @@ -1067,9 +1069,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, if (nsize < 0) nsize = 0; - if (skb_cloned(skb) && - skb_is_nonlinear(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; /* Get a new skb... force flag on. */ @@ -2344,6 +2344,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) int oldpcount = tcp_skb_pcount(skb); if (unlikely(oldpcount > 1)) { + if (skb_unclone(skb, GFP_ATOMIC)) + return -ENOMEM; tcp_init_tso_segs(sk, skb, cur_mss); tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb)); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index af07b5b23ebf..64f0354c84c7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -156,12 +156,16 @@ static bool retransmits_timed_out(struct sock *sk, static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); int retry_until; bool do_reset, syn_set = false; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { - if (icsk->icsk_retransmits) + if (icsk->icsk_retransmits) { dst_negative_advice(sk); + if (tp->syn_fastopen || tp->syn_data) + tcp_fastopen_cache_set(sk, 0, NULL, true); + } retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; syn_set = true; } else { diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 9a459be24af7..ccde54248c8c 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -107,6 +107,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; + fl4->flowi4_oif = skb_dst(skb)->dev->ifindex; if (!ip_is_fragment(iph)) { switch (iph->protocol) { diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index e1a8d903e366..d92e5586783e 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -21,24 +21,6 @@ menuconfig IPV6 if IPV6 -config IPV6_PRIVACY - bool "IPv6: Privacy Extensions (RFC 3041) support" - ---help--- - Privacy Extensions for Stateless Address Autoconfiguration in IPv6 - support. With this option, additional periodically-altered - pseudo-random global-scope unicast address(es) will be assigned to - your interface(s). - - We use our standard pseudo-random algorithm to generate the - randomized interface identifier, instead of one described in RFC 3041. - - By default the kernel does not generate temporary addresses. - To use temporary addresses, do - - echo 2 >/proc/sys/net/ipv6/conf/all/use_tempaddr - - See <file:Documentation/networking/ip-sysctl.txt> for details. - config IPV6_ROUTER_PREF bool "IPv6: Router Preference (RFC 4191) support" ---help--- diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index cd3fb301da38..542d09561ed6 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -83,11 +83,7 @@ #include <linux/if_tunnel.h> #include <linux/rtnetlink.h> #include <linux/netconf.h> - -#ifdef CONFIG_IPV6_PRIVACY #include <linux/random.h> -#endif - #include <linux/uaccess.h> #include <asm/unaligned.h> @@ -124,11 +120,9 @@ static inline void addrconf_sysctl_unregister(struct inet6_dev *idev) } #endif -#ifdef CONFIG_IPV6_PRIVACY static void __ipv6_regen_rndid(struct inet6_dev *idev); static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr); static void ipv6_regen_rndid(unsigned long data); -#endif static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); static int ipv6_count_addresses(struct inet6_dev *idev); @@ -183,13 +177,11 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, -#ifdef CONFIG_IPV6_PRIVACY .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, -#endif .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_pinfo = 1, @@ -221,13 +213,11 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, -#ifdef CONFIG_IPV6_PRIVACY .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, -#endif .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_pinfo = 1, @@ -371,7 +361,6 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) } #endif -#ifdef CONFIG_IPV6_PRIVACY INIT_LIST_HEAD(&ndev->tempaddr_list); setup_timer(&ndev->regen_timer, ipv6_regen_rndid, (unsigned long)ndev); if ((dev->flags&IFF_LOOPBACK) || @@ -384,7 +373,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) in6_dev_hold(ndev); ipv6_regen_rndid((unsigned long) ndev); } -#endif + ndev->token = in6addr_any; if (netif_running(dev) && addrconf_qdisc_ok(dev)) @@ -865,12 +854,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, /* Add to inet6_dev unicast addr list. */ ipv6_link_dev_addr(idev, ifa); -#ifdef CONFIG_IPV6_PRIVACY if (ifa->flags&IFA_F_TEMPORARY) { list_add(&ifa->tmp_list, &idev->tempaddr_list); in6_ifa_hold(ifa); } -#endif in6_ifa_hold(ifa); write_unlock(&idev->lock); @@ -913,7 +900,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) spin_unlock_bh(&addrconf_hash_lock); write_lock_bh(&idev->lock); -#ifdef CONFIG_IPV6_PRIVACY + if (ifp->flags&IFA_F_TEMPORARY) { list_del(&ifp->tmp_list); if (ifp->ifpub) { @@ -922,7 +909,6 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) } __in6_ifa_put(ifp); } -#endif list_for_each_entry_safe(ifa, ifn, &idev->addr_list, if_list) { if (ifa == ifp) { @@ -1013,7 +999,6 @@ out: in6_ifa_put(ifp); } -#ifdef CONFIG_IPV6_PRIVACY static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *ift) { struct inet6_dev *idev = ifp->idev; @@ -1116,7 +1101,6 @@ retry: out: return ret; } -#endif /* * Choose an appropriate source address (RFC3484) @@ -1131,9 +1115,7 @@ enum { #endif IPV6_SADDR_RULE_OIF, IPV6_SADDR_RULE_LABEL, -#ifdef CONFIG_IPV6_PRIVACY IPV6_SADDR_RULE_PRIVACY, -#endif IPV6_SADDR_RULE_ORCHID, IPV6_SADDR_RULE_PREFIX, IPV6_SADDR_RULE_MAX @@ -1247,7 +1229,6 @@ static int ipv6_get_saddr_eval(struct net *net, &score->ifa->addr, score->addr_type, score->ifa->idev->dev->ifindex) == dst->label; break; -#ifdef CONFIG_IPV6_PRIVACY case IPV6_SADDR_RULE_PRIVACY: { /* Rule 7: Prefer public address @@ -1259,7 +1240,6 @@ static int ipv6_get_saddr_eval(struct net *net, ret = (!(score->ifa->flags & IFA_F_TEMPORARY)) ^ preftmp; break; } -#endif case IPV6_SADDR_RULE_ORCHID: /* Rule 8-: Prefer ORCHID vs ORCHID or * non-ORCHID vs non-ORCHID @@ -1588,7 +1568,6 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) if (dad_failed) ipv6_ifa_notify(0, ifp); in6_ifa_put(ifp); -#ifdef CONFIG_IPV6_PRIVACY } else if (ifp->flags&IFA_F_TEMPORARY) { struct inet6_ifaddr *ifpub; spin_lock_bh(&ifp->lock); @@ -1602,7 +1581,6 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) spin_unlock_bh(&ifp->lock); } ipv6_del_addr(ifp); -#endif } else ipv6_del_addr(ifp); } @@ -1851,7 +1829,6 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) return err; } -#ifdef CONFIG_IPV6_PRIVACY /* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */ static void __ipv6_regen_rndid(struct inet6_dev *idev) { @@ -1919,7 +1896,6 @@ static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmp if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0) __ipv6_regen_rndid(idev); } -#endif /* * Add prefix route. @@ -2207,9 +2183,7 @@ ok: if (ifp) { int flags; unsigned long now; -#ifdef CONFIG_IPV6_PRIVACY struct inet6_ifaddr *ift; -#endif u32 stored_lft; /* update lifetime (RFC2462 5.5.3 e) */ @@ -2250,7 +2224,6 @@ ok: } else spin_unlock(&ifp->lock); -#ifdef CONFIG_IPV6_PRIVACY read_lock_bh(&in6_dev->lock); /* update all temporary addresses in the list */ list_for_each_entry(ift, &in6_dev->tempaddr_list, @@ -2315,7 +2288,7 @@ ok: } else { read_unlock_bh(&in6_dev->lock); } -#endif + in6_ifa_put(ifp); addrconf_verify(0); } @@ -2995,7 +2968,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) if (!how) idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY); -#ifdef CONFIG_IPV6_PRIVACY if (how && del_timer(&idev->regen_timer)) in6_dev_put(idev); @@ -3015,7 +2987,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) in6_ifa_put(ifa); write_lock_bh(&idev->lock); } -#endif while (!list_empty(&idev->addr_list)) { ifa = list_first_entry(&idev->addr_list, @@ -3528,7 +3499,6 @@ restart: in6_ifa_put(ifp); goto restart; } -#ifdef CONFIG_IPV6_PRIVACY } else if ((ifp->flags&IFA_F_TEMPORARY) && !(ifp->flags&IFA_F_TENTATIVE)) { unsigned long regen_advance = ifp->idev->cnf.regen_max_retry * @@ -3556,7 +3526,6 @@ restart: } else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next)) next = ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ; spin_unlock(&ifp->lock); -#endif } else { /* ifp->prefered_lft <= ifp->valid_lft */ if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) @@ -4128,13 +4097,11 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, jiffies_to_msecs(cnf->mldv1_unsolicited_report_interval); array[DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL] = jiffies_to_msecs(cnf->mldv2_unsolicited_report_interval); -#ifdef CONFIG_IPV6_PRIVACY array[DEVCONF_USE_TEMPADDR] = cnf->use_tempaddr; array[DEVCONF_TEMP_VALID_LFT] = cnf->temp_valid_lft; array[DEVCONF_TEMP_PREFERED_LFT] = cnf->temp_prefered_lft; array[DEVCONF_REGEN_MAX_RETRY] = cnf->regen_max_retry; array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; -#endif array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; @@ -4828,7 +4795,6 @@ static struct addrconf_sysctl_table .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, -#ifdef CONFIG_IPV6_PRIVACY { .procname = "use_tempaddr", .data = &ipv6_devconf.use_tempaddr, @@ -4864,7 +4830,6 @@ static struct addrconf_sysctl_table .mode = 0644, .proc_handler = proc_dointvec, }, -#endif { .procname = "max_addresses", .data = &ipv6_devconf.max_addresses, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 20af1fb81c83..6468bda1f2b9 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -865,8 +865,6 @@ static int __init inet6_init(void) if (err) goto out_sock_register_fail; - tcpv6_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem; - /* * ipngwg API draft makes clear that the correct semantics * for TCP and UDP is to consider one TCP and UDP instance diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 73784c3d4642..82e1da3a40b9 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -618,8 +618,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 87eb79e65e49..b8719df0366e 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -430,8 +430,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 1ef1fa2b22a6..bf4a9a084de5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -976,6 +976,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) if (t->parms.o_flags&GRE_SEQ) addend += 4; } + t->hlen = addend; if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & @@ -1002,8 +1003,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) } ip6_rt_put(rt); } - - t->hlen = addend; } static int ip6gre_tnl_change(struct ip6_tnl *t, diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 5c2fc1d04196..4b851692b1f6 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -90,6 +90,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, u8 *prevhdr; int offset = 0; bool tunnel; + int nhoff; if (unlikely(skb_shinfo(skb)->gso_type & ~(SKB_GSO_UDP | @@ -97,16 +98,23 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, SKB_GSO_TCP_ECN | SKB_GSO_GRE | SKB_GSO_IPIP | + SKB_GSO_SIT | SKB_GSO_UDP_TUNNEL | SKB_GSO_MPLS | SKB_GSO_TCPV6 | 0))) goto out; + skb_reset_network_header(skb); + nhoff = skb_network_header(skb) - skb_mac_header(skb); if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) goto out; - tunnel = skb->encapsulation; + tunnel = SKB_GSO_CB(skb)->encap_level > 0; + if (tunnel) + features = skb->dev->hw_enc_features & netif_skb_features(skb); + SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h); + ipv6h = ipv6_hdr(skb); __skb_pull(skb, sizeof(*ipv6h)); segs = ERR_PTR(-EPROTONOSUPPORT); @@ -123,13 +131,17 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, goto out; for (skb = segs; skb; skb = skb->next) { - ipv6h = ipv6_hdr(skb); - ipv6h->payload_len = htons(skb->len - skb->mac_len - - sizeof(*ipv6h)); + ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); + ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h)); + if (tunnel) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } + skb->network_header = (u8 *)ipv6h - skb->head; + if (!tunnel && proto == IPPROTO_UDP) { unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); - fptr = (struct frag_hdr *)(skb_network_header(skb) + - unfrag_ip6hlen); + fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); fptr->frag_off = htons(offset); if (skb->next != NULL) fptr->frag_off |= htons(IP6_MF); @@ -265,6 +277,13 @@ static struct packet_offload ipv6_packet_offload __read_mostly = { }, }; +static const struct net_offload sit_offload = { + .callbacks = { + .gso_send_check = ipv6_gso_send_check, + .gso_segment = ipv6_gso_segment, + }, +}; + static int __init ipv6_offload_init(void) { @@ -276,6 +295,9 @@ static int __init ipv6_offload_init(void) pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); dev_add_offload(&ipv6_packet_offload); + + inet_add_offload(&sit_offload, IPPROTO_IPV6); + return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a54c45ce4a48..91fb4e8212f5 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -105,7 +105,7 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_lock_bh(); - nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + nexthop = rt6_nexthop((struct rt6_info *)dst); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); @@ -874,7 +874,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, */ rt = (struct rt6_info *) *dst; rcu_read_lock_bh(); - n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt)); err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock_bh(); @@ -1008,6 +1008,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, { struct sk_buff *skb; + struct frag_hdr fhdr; int err; /* There is support for UDP large send offload by network @@ -1015,8 +1016,6 @@ static inline int ip6_ufo_append_data(struct sock *sk, * udp datagram */ if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) { - struct frag_hdr fhdr; - skb = sock_alloc_send_skb(sk, hh_len + fragheaderlen + transhdrlen + 20, (flags & MSG_DONTWAIT), &err); @@ -1036,20 +1035,24 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb->transport_header = skb->network_header + fragheaderlen; skb->protocol = htons(ETH_P_IPV6); - skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - /* Specify the length of each IPv6 datagram fragment. - * It has to be a multiple of 8. - */ - skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - - sizeof(struct frag_hdr)) & ~7; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(&fhdr, rt); - skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); + } else if (skb_is_gso(skb)) { + goto append; } + skb->ip_summed = CHECKSUM_PARTIAL; + /* Specify the length of each IPv6 datagram fragment. + * It has to be a multiple of 8. + */ + skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - + sizeof(struct frag_hdr)) & ~7; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + ipv6_select_ident(&fhdr, rt); + skb_shinfo(skb)->ip6_frag_id = fhdr.identification; + +append: return skb_append_datato_frags(sk, skb, getfrag, from, (length - transhdrlen)); } diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 5636a912074a..ce507d9e1c90 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -64,8 +64,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, (struct ip_comp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index dffdc1a389c5..4a258263d8ec 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -144,12 +144,24 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); } +static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr, + const struct in6_addr *daddr) +{ + u32 c; + + net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd)); + c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), + (__force u32)id, nf_frags.rnd); + return c & (INETFRAGS_HASHSZ - 1); +} + + static unsigned int nf_hashfn(struct inet_frag_queue *q) { const struct frag_queue *nq; nq = container_of(q, struct frag_queue, q); - return inet6_hash_frag(nq->id, &nq->saddr, &nq->daddr, nf_frags.rnd); + return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr); } static void nf_skb_free(struct sk_buff *skb) @@ -185,7 +197,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id, arg.ecn = ecn; read_lock_bh(&nf_frags.lock); - hash = inet6_hash_frag(id, src, dst, nf_frags.rnd); + hash = nf_hash_frag(id, src, dst); q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash); local_bh_enable(); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 1aeb473b2cc6..cc85a9ba5010 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -82,24 +82,24 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, * callers should be careful not to use the hash value outside the ipfrag_lock * as doing so could race with ipfrag_hash_rnd being recalculated. */ -unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr, - const struct in6_addr *daddr, u32 rnd) +static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr, + const struct in6_addr *daddr) { u32 c; + net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd)); c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), - (__force u32)id, rnd); + (__force u32)id, ip6_frags.rnd); return c & (INETFRAGS_HASHSZ - 1); } -EXPORT_SYMBOL_GPL(inet6_hash_frag); static unsigned int ip6_hashfn(struct inet_frag_queue *q) { struct frag_queue *fq; fq = container_of(q, struct frag_queue, q); - return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr, ip6_frags.rnd); + return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr); } bool ip6_frag_match(struct inet_frag_queue *q, void *a) @@ -193,7 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, arg.ecn = ecn; read_lock(&ip6_frags.lock); - hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd); + hash = inet6_hash_frag(id, src, dst); q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash); if (IS_ERR_OR_NULL(q)) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c3130ffc3bca..1ac0b6e17d95 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -476,6 +476,24 @@ out: } #ifdef CONFIG_IPV6_ROUTER_PREF +struct __rt6_probe_work { + struct work_struct work; + struct in6_addr target; + struct net_device *dev; +}; + +static void rt6_probe_deferred(struct work_struct *w) +{ + struct in6_addr mcaddr; + struct __rt6_probe_work *work = + container_of(w, struct __rt6_probe_work, work); + + addrconf_addr_solict_mult(&work->target, &mcaddr); + ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL); + dev_put(work->dev); + kfree(w); +} + static void rt6_probe(struct rt6_info *rt) { struct neighbour *neigh; @@ -499,17 +517,23 @@ static void rt6_probe(struct rt6_info *rt) if (!neigh || time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { - struct in6_addr mcaddr; - struct in6_addr *target; + struct __rt6_probe_work *work; - if (neigh) { + work = kmalloc(sizeof(*work), GFP_ATOMIC); + + if (neigh && work) neigh->updated = jiffies; + + if (neigh) write_unlock(&neigh->lock); - } - target = (struct in6_addr *)&rt->rt6i_gateway; - addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } } else { out: write_unlock(&neigh->lock); @@ -595,7 +619,7 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, goto out; m = rt6_score_route(rt, oif, strict); - if (m == RT6_NUD_FAIL_SOFT && !IS_ENABLED(CONFIG_IPV6_ROUTER_PREF)) { + if (m == RT6_NUD_FAIL_SOFT) { match_do_rr = true; m = 0; /* lowest valid score */ } else if (m < 0) { @@ -851,7 +875,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; - rt->rt6i_gateway = *daddr; } rt->rt6i_flags |= RTF_CACHE; @@ -1335,6 +1358,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; atomic_set(&rt->dst.__refcnt, 1); + rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; @@ -1870,7 +1894,10 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, in6_dev_hold(rt->rt6i_idev); rt->dst.lastuse = jiffies; - rt->rt6i_gateway = ort->rt6i_gateway; + if (ort->rt6i_flags & RTF_GATEWAY) + rt->rt6i_gateway = ort->rt6i_gateway; + else + rt->rt6i_gateway = *dest; rt->rt6i_flags = ort->rt6i_flags; if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == (RTF_DEFAULT | RTF_ADDRCONF)) @@ -2157,6 +2184,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, else rt->rt6i_flags |= RTF_LOCAL; + rt->rt6i_gateway = *addr; rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 19269453a8ea..3a9038dd818d 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -933,10 +933,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, ttl = iph6->hop_limit; tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); - if (likely(!skb->encapsulation)) { - skb_reset_inner_headers(skb); - skb->encapsulation = 1; - } + skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT); + if (IS_ERR(skb)) + goto out; err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, IPPROTO_IPV6, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); @@ -946,8 +945,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, tx_error_icmp: dst_link_failure(skb); tx_error: - dev->stats.tx_errors++; dev_kfree_skb(skb); +out: + dev->stats.tx_errors++; return NETDEV_TX_OK; } @@ -956,13 +956,15 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; - if (likely(!skb->encapsulation)) { - skb_reset_inner_headers(skb); - skb->encapsulation = 1; - } + skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP); + if (IS_ERR(skb)) + goto out; ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP); return NETDEV_TX_OK; +out: + dev->stats.tx_errors++; + return NETDEV_TX_OK; } static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, @@ -1292,6 +1294,12 @@ static void ipip6_dev_free(struct net_device *dev) free_netdev(dev); } +#define SIT_FEATURES (NETIF_F_SG | \ + NETIF_F_FRAGLIST | \ + NETIF_F_HIGHDMA | \ + NETIF_F_GSO_SOFTWARE | \ + NETIF_F_HW_CSUM) + static void ipip6_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip6_netdev_ops; @@ -1305,6 +1313,8 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_LLTX; + dev->features |= SIT_FEATURES; + dev->hw_features |= SIT_FEATURES; } static int ipip6_tunnel_init(struct net_device *dev) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b996ee2005a9..0740f93a114a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1929,6 +1929,7 @@ struct proto tcpv6_prot = { .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, + .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem = sysctl_tcp_wmem, .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 44fc4e3d661f..f3893e897f72 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1243,9 +1243,6 @@ do_udp_sendmsg: if (tclass < 0) tclass = np->tclass; - if (dontfrag < 0) - dontfrag = np->dontfrag; - if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: @@ -1264,6 +1261,8 @@ back_from_confirm: up->pending = AF_INET6; do_append_data: + if (dontfrag < 0) + dontfrag = np->dontfrag; up->len += ulen; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index f63780ff3732..08e23b0bf302 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -65,6 +65,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE | SKB_GSO_IPIP | + SKB_GSO_SIT | SKB_GSO_MPLS) || !(type & (SKB_GSO_UDP)))) goto out; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 23ed03d786c8..08ed2772b7aa 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -138,6 +138,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; + fl6->flowi6_oif = skb_dst(skb)->dev->ifindex; fl6->daddr = reverse ? hdr->saddr : hdr->daddr; fl6->saddr = reverse ? hdr->daddr : hdr->saddr; diff --git a/net/key/af_key.c b/net/key/af_key.c index 9d585370c5b4..911ef03bf8fb 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1098,7 +1098,8 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, x->id.proto = proto; x->id.spi = sa->sadb_sa_spi; - x->props.replay_window = sa->sadb_sa_replay; + x->props.replay_window = min_t(unsigned int, sa->sadb_sa_replay, + (sizeof(x->replay.bitmap) * 8)); if (sa->sadb_sa_flags & SADB_SAFLAGS_NOECN) x->props.flags |= XFRM_STATE_NOECN; if (sa->sadb_sa_flags & SADB_SAFLAGS_DECAP_DSCP) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index f0a7adaef2ea..ffda81ef1a70 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -353,7 +353,9 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh goto error_put_sess_tun; } + local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); + local_bh_enable(); sock_put(ps->tunnel_sock); sock_put(sk); @@ -422,7 +424,9 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) skb->data[0] = ppph[0]; skb->data[1] = ppph[1]; + local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); + local_bh_enable(); sock_put(sk_tun); sock_put(sk); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index ac28af74a414..b0a651cc389f 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -3564,7 +3564,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, return -EINVAL; } band = chanctx_conf->def.chan->band; - sta = sta_info_get(sdata, peer); + sta = sta_info_get_bss(sdata, peer); if (sta) { qos = test_sta_flag(sta, WLAN_STA_WME); } else { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 3a87c8976a32..e73cd0637f3b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -893,6 +893,8 @@ struct tpt_led_trigger { * that the scan completed. * @SCAN_ABORTED: Set for our scan work function when the driver reported * a scan complete for an aborted scan. + * @SCAN_HW_CANCELLED: Set for our scan work function when the scan is being + * cancelled. */ enum { SCAN_SW_SCANNING, @@ -900,6 +902,7 @@ enum { SCAN_ONCHANNEL_SCANNING, SCAN_COMPLETED, SCAN_ABORTED, + SCAN_HW_CANCELLED, }; /** diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index acd1f71adc03..0c2a29484c07 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -394,6 +394,8 @@ void ieee80211_sw_roc_work(struct work_struct *work) if (started) ieee80211_start_next_roc(local); + else if (list_empty(&local->roc_list)) + ieee80211_run_deferred_scan(local); } out_unlock: diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index ecb57b0bf74a..5ad66a83ef7f 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -238,6 +238,9 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) enum ieee80211_band band; int i, ielen, n_chans; + if (test_bit(SCAN_HW_CANCELLED, &local->scanning)) + return false; + do { if (local->hw_scan_band == IEEE80211_NUM_BANDS) return false; @@ -939,7 +942,23 @@ void ieee80211_scan_cancel(struct ieee80211_local *local) if (!local->scan_req) goto out; + /* + * We have a scan running and the driver already reported completion, + * but the worker hasn't run yet or is stuck on the mutex - mark it as + * cancelled. + */ + if (test_bit(SCAN_HW_SCANNING, &local->scanning) && + test_bit(SCAN_COMPLETED, &local->scanning)) { + set_bit(SCAN_HW_CANCELLED, &local->scanning); + goto out; + } + if (test_bit(SCAN_HW_SCANNING, &local->scanning)) { + /* + * Make sure that __ieee80211_scan_completed doesn't trigger a + * scan on another band. + */ + set_bit(SCAN_HW_CANCELLED, &local->scanning); if (local->ops->cancel_hw_scan) drv_cancel_hw_scan(local, rcu_dereference_protected(local->scan_sdata, diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 368837fe3b80..78dc2e99027e 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -180,6 +180,9 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; + if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) + sta->last_rx = jiffies; + if (ieee80211_is_data_qos(mgmt->frame_control)) { struct ieee80211_hdr *hdr = (void *) skb->data; u8 *qc = ieee80211_get_qos_ctl(hdr); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 4fcbf634b548..9993fcb19ecd 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1120,7 +1120,8 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, tx->sta = rcu_dereference(sdata->u.vlan.sta); if (!tx->sta && sdata->dev->ieee80211_ptr->use_4addr) return TX_DROP; - } else if (info->flags & IEEE80211_TX_CTL_INJECTED || + } else if (info->flags & (IEEE80211_TX_CTL_INJECTED | + IEEE80211_TX_INTFL_NL80211_FRAME_TX) || tx->sdata->control_port_protocol == tx->skb->protocol) { tx->sta = sta_info_get_bss(sdata, hdr->addr1); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1220f5afdb7e..aefb9d5b9620 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2236,6 +2236,10 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, } rate = cfg80211_calculate_bitrate(&ri); + if (WARN_ONCE(!rate, + "Invalid bitrate: flags=0x%x, idx=%d, vht_nss=%d\n", + status->flag, status->rate_idx, status->vht_nss)) + return 0; /* rewind from end of MPDU */ if (status->flag & RX_FLAG_MACTIME_END) diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c index b7c7f815deae..52ae6646a411 100644 --- a/net/mac802154/ieee802154_dev.c +++ b/net/mac802154/ieee802154_dev.c @@ -174,8 +174,7 @@ ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops) if (!ops || !ops->xmit || !ops->ed || !ops->start || !ops->stop || !ops->set_channel) { - printk(KERN_ERR - "undefined IEEE802.15.4 device operations\n"); + pr_err("undefined IEEE802.15.4 device operations\n"); return NULL; } @@ -201,8 +200,7 @@ ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops) phy = wpan_phy_alloc(priv_size); if (!phy) { - printk(KERN_ERR - "failure to allocate master IEEE802.15.4 device\n"); + pr_err("failure to allocate master IEEE802.15.4 device\n"); return NULL; } diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c index 2ca2f4dceab7..e24bcf977296 100644 --- a/net/mac802154/wpan.c +++ b/net/mac802154/wpan.c @@ -208,6 +208,8 @@ static int mac802154_header_create(struct sk_buff *skb, head[1] = fc >> 8; memcpy(skb_push(skb, pos), head, pos); + skb_reset_mac_header(skb); + skb->mac_len = pos; return pos; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index bdebd03bc8cd..70866d192efc 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -778,8 +778,8 @@ static int callforward_do_filter(const union nf_inet_addr *src, flowi6_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, flowi6_to_flowi(&fl2), false)) { - if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, - sizeof(rt1->rt6i_gateway)) && + if (ipv6_addr_equal(rt6_nexthop(rt1), + rt6_nexthop(rt2)) && rt1->dst.dev == rt2->dst.dev) ret = 1; dst_release(&rt2->dst); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index c03a32a0418e..ad1f1d819203 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -443,6 +443,16 @@ config NET_CLS_CGROUP To compile this code as a module, choose M here: the module will be called cls_cgroup. +config NET_CLS_BPF + tristate "BPF-based classifier" + select NET_CLS + ---help--- + If you say Y here, you will be able to classify packets based on + programmable BPF (JIT'ed) filters as an alternative to ematches. + + To compile this code as a module, choose M here: the module will + be called cls_bpf. + config NET_EMATCH bool "Extended Matches" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index e5f9abe9a5db..35fa47a494ab 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -50,6 +50,7 @@ obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o +obj-$(CONFIG_NET_CLS_BPF) += cls_bpf.o obj-$(CONFIG_NET_EMATCH) += ematch.o obj-$(CONFIG_NET_EMATCH_CMP) += em_cmp.o obj-$(CONFIG_NET_EMATCH_NBYTE) += em_nbyte.o diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c new file mode 100644 index 000000000000..1002a8226281 --- /dev/null +++ b/net/sched/cls_bpf.c @@ -0,0 +1,385 @@ +/* + * Berkeley Packet Filter based traffic classifier + * + * Might be used to classify traffic through flexible, user-defined and + * possibly JIT-ed BPF filters for traffic control as an alternative to + * ematches. + * + * (C) 2013 Daniel Borkmann <dborkman@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/filter.h> +#include <net/rtnetlink.h> +#include <net/pkt_cls.h> +#include <net/sock.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>"); +MODULE_DESCRIPTION("TC BPF based classifier"); + +struct cls_bpf_head { + struct list_head plist; + u32 hgen; +}; + +struct cls_bpf_prog { + struct sk_filter *filter; + struct sock_filter *bpf_ops; + struct tcf_exts exts; + struct tcf_result res; + struct list_head link; + u32 handle; + u16 bpf_len; +}; + +static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { + [TCA_BPF_CLASSID] = { .type = NLA_U32 }, + [TCA_BPF_OPS_LEN] = { .type = NLA_U16 }, + [TCA_BPF_OPS] = { .type = NLA_BINARY, + .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, +}; + +static const struct tcf_ext_map bpf_ext_map = { + .action = TCA_BPF_ACT, + .police = TCA_BPF_POLICE, +}; + +static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res) +{ + struct cls_bpf_head *head = tp->root; + struct cls_bpf_prog *prog; + int ret; + + list_for_each_entry(prog, &head->plist, link) { + int filter_res = SK_RUN_FILTER(prog->filter, skb); + + if (filter_res == 0) + continue; + + *res = prog->res; + if (filter_res != -1) + res->classid = filter_res; + + ret = tcf_exts_exec(skb, &prog->exts, res); + if (ret < 0) + continue; + + return ret; + } + + return -1; +} + +static int cls_bpf_init(struct tcf_proto *tp) +{ + struct cls_bpf_head *head; + + head = kzalloc(sizeof(*head), GFP_KERNEL); + if (head == NULL) + return -ENOBUFS; + + INIT_LIST_HEAD(&head->plist); + tp->root = head; + + return 0; +} + +static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog) +{ + tcf_unbind_filter(tp, &prog->res); + tcf_exts_destroy(tp, &prog->exts); + + sk_unattached_filter_destroy(prog->filter); + + kfree(prog->bpf_ops); + kfree(prog); +} + +static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg) +{ + struct cls_bpf_head *head = tp->root; + struct cls_bpf_prog *prog, *todel = (struct cls_bpf_prog *) arg; + + list_for_each_entry(prog, &head->plist, link) { + if (prog == todel) { + tcf_tree_lock(tp); + list_del(&prog->link); + tcf_tree_unlock(tp); + + cls_bpf_delete_prog(tp, prog); + return 0; + } + } + + return -ENOENT; +} + +static void cls_bpf_destroy(struct tcf_proto *tp) +{ + struct cls_bpf_head *head = tp->root; + struct cls_bpf_prog *prog, *tmp; + + list_for_each_entry_safe(prog, tmp, &head->plist, link) { + list_del(&prog->link); + cls_bpf_delete_prog(tp, prog); + } + + kfree(head); +} + +static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) +{ + struct cls_bpf_head *head = tp->root; + struct cls_bpf_prog *prog; + unsigned long ret = 0UL; + + if (head == NULL) + return 0UL; + + list_for_each_entry(prog, &head->plist, link) { + if (prog->handle == handle) { + ret = (unsigned long) prog; + break; + } + } + + return ret; +} + +static void cls_bpf_put(struct tcf_proto *tp, unsigned long f) +{ +} + +static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, + struct cls_bpf_prog *prog, + unsigned long base, struct nlattr **tb, + struct nlattr *est) +{ + struct sock_filter *bpf_ops, *bpf_old; + struct tcf_exts exts; + struct sock_fprog tmp; + struct sk_filter *fp, *fp_old; + u16 bpf_size, bpf_len; + u32 classid; + int ret; + + if (!tb[TCA_BPF_OPS_LEN] || !tb[TCA_BPF_OPS] || !tb[TCA_BPF_CLASSID]) + return -EINVAL; + + ret = tcf_exts_validate(net, tp, tb, est, &exts, &bpf_ext_map); + if (ret < 0) + 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) { + ret = -EINVAL; + goto errout; + } + + bpf_size = bpf_len * sizeof(*bpf_ops); + bpf_ops = kzalloc(bpf_size, GFP_KERNEL); + if (bpf_ops == NULL) { + ret = -ENOMEM; + goto errout; + } + + memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size); + + tmp.len = bpf_len; + tmp.filter = (struct sock_filter __user *) bpf_ops; + + ret = sk_unattached_filter_create(&fp, &tmp); + if (ret) + goto errout_free; + + tcf_tree_lock(tp); + fp_old = prog->filter; + bpf_old = prog->bpf_ops; + + prog->bpf_len = bpf_len; + prog->bpf_ops = bpf_ops; + prog->filter = fp; + prog->res.classid = classid; + tcf_tree_unlock(tp); + + tcf_bind_filter(tp, &prog->res, base); + tcf_exts_change(tp, &prog->exts, &exts); + + if (fp_old) + sk_unattached_filter_destroy(fp_old); + if (bpf_old) + kfree(bpf_old); + + return 0; + +errout_free: + kfree(bpf_ops); +errout: + tcf_exts_destroy(tp, &exts); + return ret; +} + +static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp, + struct cls_bpf_head *head) +{ + unsigned int i = 0x80000000; + + do { + if (++head->hgen == 0x7FFFFFFF) + head->hgen = 1; + } while (--i > 0 && cls_bpf_get(tp, head->hgen)); + if (i == 0) + pr_err("Insufficient number of handles\n"); + + return i; +} + +static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, + struct tcf_proto *tp, unsigned long base, + u32 handle, struct nlattr **tca, + unsigned long *arg) +{ + struct cls_bpf_head *head = tp->root; + struct cls_bpf_prog *prog = (struct cls_bpf_prog *) *arg; + struct nlattr *tb[TCA_BPF_MAX + 1]; + int ret; + + if (tca[TCA_OPTIONS] == NULL) + return -EINVAL; + + ret = nla_parse_nested(tb, TCA_BPF_MAX, tca[TCA_OPTIONS], bpf_policy); + if (ret < 0) + return ret; + + if (prog != NULL) { + if (handle && prog->handle != handle) + return -EINVAL; + return cls_bpf_modify_existing(net, tp, prog, base, tb, + tca[TCA_RATE]); + } + + prog = kzalloc(sizeof(*prog), GFP_KERNEL); + if (prog == NULL) + return -ENOBUFS; + + if (handle == 0) + prog->handle = cls_bpf_grab_new_handle(tp, head); + else + prog->handle = handle; + if (prog->handle == 0) { + ret = -EINVAL; + goto errout; + } + + ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE]); + if (ret < 0) + goto errout; + + tcf_tree_lock(tp); + list_add(&prog->link, &head->plist); + tcf_tree_unlock(tp); + + *arg = (unsigned long) prog; + + return 0; +errout: + if (*arg == 0UL && prog) + kfree(prog); + + return ret; +} + +static int cls_bpf_dump(struct tcf_proto *tp, unsigned long fh, + struct sk_buff *skb, struct tcmsg *tm) +{ + struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh; + struct nlattr *nest, *nla; + + if (prog == NULL) + return skb->len; + + tm->tcm_handle = prog->handle; + + nest = nla_nest_start(skb, TCA_OPTIONS); + if (nest == NULL) + goto nla_put_failure; + + 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)) + goto nla_put_failure; + + nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_len * + sizeof(struct sock_filter)); + if (nla == NULL) + goto nla_put_failure; + + memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); + + if (tcf_exts_dump(skb, &prog->exts, &bpf_ext_map) < 0) + goto nla_put_failure; + + nla_nest_end(skb, nest); + + if (tcf_exts_dump_stats(skb, &prog->exts, &bpf_ext_map) < 0) + goto nla_put_failure; + + return skb->len; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg) +{ + struct cls_bpf_head *head = tp->root; + struct cls_bpf_prog *prog; + + list_for_each_entry(prog, &head->plist, link) { + if (arg->count < arg->skip) + goto skip; + if (arg->fn(tp, (unsigned long) prog, arg) < 0) { + arg->stop = 1; + break; + } +skip: + arg->count++; + } +} + +static struct tcf_proto_ops cls_bpf_ops __read_mostly = { + .kind = "bpf", + .owner = THIS_MODULE, + .classify = cls_bpf_classify, + .init = cls_bpf_init, + .destroy = cls_bpf_destroy, + .get = cls_bpf_get, + .put = cls_bpf_put, + .change = cls_bpf_change, + .delete = cls_bpf_delete, + .walk = cls_bpf_walk, + .dump = cls_bpf_dump, +}; + +static int __init cls_bpf_init_mod(void) +{ + return register_tcf_proto_ops(&cls_bpf_ops); +} + +static void __exit cls_bpf_exit_mod(void) +{ + unregister_tcf_proto_ops(&cls_bpf_ops); +} + +module_init(cls_bpf_init_mod); +module_exit(cls_bpf_exit_mod); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index a6d788d45216..75c94e59a3bd 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -235,7 +235,6 @@ static bool loss_4state(struct netem_sched_data *q) clg->state = 2; else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) { clg->state = 1; - return true; } else if (clg->a2 + clg->a3 < rnd) { clg->state = 3; return true; @@ -358,6 +357,21 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche return PSCHED_NS2TICKS(ticks); } +static void tfifo_reset(struct Qdisc *sch) +{ + struct netem_sched_data *q = qdisc_priv(sch); + struct rb_node *p; + + while ((p = rb_first(&q->t_root))) { + struct sk_buff *skb = netem_rb_to_skb(p); + + rb_erase(p, &q->t_root); + skb->next = NULL; + skb->prev = NULL; + kfree_skb(skb); + } +} + static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); @@ -520,6 +534,7 @@ static unsigned int netem_drop(struct Qdisc *sch) skb->next = NULL; skb->prev = NULL; len = qdisc_pkt_len(skb); + sch->qstats.backlog -= len; kfree_skb(skb); } } @@ -609,6 +624,7 @@ static void netem_reset(struct Qdisc *sch) struct netem_sched_data *q = qdisc_priv(sch); qdisc_reset_queue(sch); + tfifo_reset(sch); if (q->qdisc) qdisc_reset(q->qdisc); qdisc_watchdog_cancel(&q->watchdog); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index cef509985192..c9b91cb1cb0d 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -602,7 +602,7 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, /* Start a T3 timer here in case it wasn't running so * that these migrated packets have a chance to get - * retrnasmitted. + * retransmitted. */ if (!timer_pending(&active->T3_rtx_timer)) if (!mod_timer(&active->T3_rtx_timer, @@ -665,7 +665,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, /* Set the path max_retrans. */ peer->pathmaxrxt = asoc->pathmaxrxt; - /* And the partial failure retrnas threshold */ + /* And the partial failure retrans threshold */ peer->pf_retrans = asoc->pf_retrans; /* Initialize the peer's SACK delay timeout based on the diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 8c4fa5dec824..46b5977978a1 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -539,18 +539,14 @@ struct sctp_hmac *sctp_auth_asoc_get_hmac(const struct sctp_association *asoc) for (i = 0; i < n_elt; i++) { id = ntohs(hmacs->hmac_ids[i]); - /* Check the id is in the supported range */ - if (id > SCTP_AUTH_HMAC_ID_MAX) { - id = 0; - continue; - } - - /* See is we support the id. Supported IDs have name and - * length fields set, so that we can allocated and use + /* Check the id is in the supported range. And + * see if we support the id. Supported IDs have name and + * length fields set, so that we can allocate and use * them. We can safely just check for name, for without the * name, we can't allocate the TFM. */ - if (!sctp_hmac_list[id].hmac_name) { + if (id > SCTP_AUTH_HMAC_ID_MAX || + !sctp_hmac_list[id].hmac_name) { id = 0; continue; } diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 7bd5ed4a8657..f2044fcb9dd1 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -201,7 +201,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, max = asoc->frag_point; /* If the the peer requested that we authenticate DATA chunks - * we need to accound for bundling of the AUTH chunks along with + * we need to account for bundling of the AUTH chunks along with * DATA. */ if (sctp_auth_send_cid(SCTP_CID_DATA, asoc)) { diff --git a/net/sctp/output.c b/net/sctp/output.c index 0ac3a65daccb..319137340d15 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -536,7 +536,8 @@ int sctp_packet_transmit(struct sctp_packet *packet) * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>. */ if (!sctp_checksum_disable) { - if (!(dst->dev->features & NETIF_F_SCTP_CSUM)) { + if (!(dst->dev->features & NETIF_F_SCTP_CSUM) || + (dst_xfrm(dst) != NULL) || packet->ipfragok) { __u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len); /* 3) Put the resultant value into the checksum field in the diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index d244a23ab8d3..fe690320b1e4 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1297,6 +1297,13 @@ struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc) /* Turn an skb into a chunk. * FIXME: Eventually move the structure directly inside the skb->cb[]. + * + * sctpimpguide-05.txt Section 2.8.2 + * M1) Each time a new DATA chunk is transmitted + * set the 'TSN.Missing.Report' count for that TSN to 0. The + * 'TSN.Missing.Report' count will be used to determine missing chunks + * and when to fast retransmit. + * */ struct sctp_chunk *sctp_chunkify(struct sk_buff *skb, const struct sctp_association *asoc, @@ -1314,29 +1321,9 @@ struct sctp_chunk *sctp_chunkify(struct sk_buff *skb, INIT_LIST_HEAD(&retval->list); retval->skb = skb; retval->asoc = (struct sctp_association *)asoc; - retval->has_tsn = 0; - retval->has_ssn = 0; - retval->rtt_in_progress = 0; - retval->sent_at = 0; retval->singleton = 1; - retval->end_of_packet = 0; - retval->ecn_ce_done = 0; - retval->pdiscard = 0; - - /* sctpimpguide-05.txt Section 2.8.2 - * M1) Each time a new DATA chunk is transmitted - * set the 'TSN.Missing.Report' count for that TSN to 0. The - * 'TSN.Missing.Report' count will be used to determine missing chunks - * and when to fast retransmit. - */ - retval->tsn_missing_report = 0; - retval->tsn_gap_acked = 0; - retval->fast_retransmit = SCTP_CAN_FRTX; - /* If this is a fragmented message, track all fragments - * of the message (for SEND_FAILED). - */ - retval->msg = NULL; + retval->fast_retransmit = SCTP_CAN_FRTX; /* Polish the bead hole. */ INIT_LIST_HEAD(&retval->transmitted_list); diff --git a/net/tipc/link.c b/net/tipc/link.c index e8153f64d2d6..54163f91b8ae 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1507,15 +1507,15 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) /* Ensure bearer is still enabled */ if (unlikely(!b_ptr->active)) - goto cont; + goto discard; /* Ensure message is well-formed */ if (unlikely(!link_recv_buf_validate(buf))) - goto cont; + goto discard; /* Ensure message data is a single contiguous unit */ if (unlikely(skb_linearize(buf))) - goto cont; + goto discard; /* Handle arrival of a non-unicast link message */ msg = buf_msg(buf); @@ -1531,20 +1531,18 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) /* Discard unicast link messages destined for another node */ if (unlikely(!msg_short(msg) && (msg_destnode(msg) != tipc_own_addr))) - goto cont; + goto discard; /* Locate neighboring node that sent message */ n_ptr = tipc_node_find(msg_prevnode(msg)); if (unlikely(!n_ptr)) - goto cont; + goto discard; tipc_node_lock(n_ptr); /* Locate unicast link endpoint that should handle message */ l_ptr = n_ptr->links[b_ptr->identity]; - if (unlikely(!l_ptr)) { - tipc_node_unlock(n_ptr); - goto cont; - } + if (unlikely(!l_ptr)) + goto unlock_discard; /* Verify that communication with node is currently allowed */ if ((n_ptr->block_setup & WAIT_PEER_DOWN) && @@ -1554,10 +1552,8 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) !msg_redundant_link(msg)) n_ptr->block_setup &= ~WAIT_PEER_DOWN; - if (n_ptr->block_setup) { - tipc_node_unlock(n_ptr); - goto cont; - } + if (n_ptr->block_setup) + goto unlock_discard; /* Validate message sequence number info */ seq_no = msg_seqno(msg); @@ -1593,98 +1589,97 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) /* Now (finally!) process the incoming message */ protocol_check: - if (likely(link_working_working(l_ptr))) { - if (likely(seq_no == mod(l_ptr->next_in_no))) { - l_ptr->next_in_no++; - if (unlikely(l_ptr->oldest_deferred_in)) - head = link_insert_deferred_queue(l_ptr, - head); -deliver: - if (likely(msg_isdata(msg))) { - tipc_node_unlock(n_ptr); - tipc_port_recv_msg(buf); - continue; - } - switch (msg_user(msg)) { - int ret; - case MSG_BUNDLER: - l_ptr->stats.recv_bundles++; - l_ptr->stats.recv_bundled += - msg_msgcnt(msg); - tipc_node_unlock(n_ptr); - tipc_link_recv_bundle(buf); - continue; - case NAME_DISTRIBUTOR: - n_ptr->bclink.recv_permitted = true; - tipc_node_unlock(n_ptr); - tipc_named_recv(buf); - continue; - case BCAST_PROTOCOL: - tipc_link_recv_sync(n_ptr, buf); - tipc_node_unlock(n_ptr); - continue; - case CONN_MANAGER: - tipc_node_unlock(n_ptr); - tipc_port_recv_proto_msg(buf); - continue; - case MSG_FRAGMENTER: - l_ptr->stats.recv_fragments++; - ret = tipc_link_recv_fragment( - &l_ptr->defragm_buf, - &buf, &msg); - if (ret == 1) { - l_ptr->stats.recv_fragmented++; - goto deliver; - } - if (ret == -1) - l_ptr->next_in_no--; - break; - case CHANGEOVER_PROTOCOL: - type = msg_type(msg); - if (link_recv_changeover_msg(&l_ptr, - &buf)) { - msg = buf_msg(buf); - seq_no = msg_seqno(msg); - if (type == ORIGINAL_MSG) - goto deliver; - goto protocol_check; - } - break; - default: - kfree_skb(buf); - buf = NULL; - break; - } + if (unlikely(!link_working_working(l_ptr))) { + if (msg_user(msg) == LINK_PROTOCOL) { + link_recv_proto_msg(l_ptr, buf); + head = link_insert_deferred_queue(l_ptr, head); + tipc_node_unlock(n_ptr); + continue; + } + + /* Traffic message. Conditionally activate link */ + link_state_event(l_ptr, TRAFFIC_MSG_EVT); + + if (link_working_working(l_ptr)) { + /* Re-insert buffer in front of queue */ + buf->next = head; + head = buf; tipc_node_unlock(n_ptr); - tipc_net_route_msg(buf); continue; } + goto unlock_discard; + } + + /* 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, buf); head = link_insert_deferred_queue(l_ptr, head); tipc_node_unlock(n_ptr); continue; } - - /* Link is not in state WORKING_WORKING */ - if (msg_user(msg) == LINK_PROTOCOL) { - link_recv_proto_msg(l_ptr, buf); + l_ptr->next_in_no++; + if (unlikely(l_ptr->oldest_deferred_in)) head = link_insert_deferred_queue(l_ptr, head); +deliver: + if (likely(msg_isdata(msg))) { tipc_node_unlock(n_ptr); + tipc_port_recv_msg(buf); continue; } - - /* Traffic message. Conditionally activate link */ - link_state_event(l_ptr, TRAFFIC_MSG_EVT); - - if (link_working_working(l_ptr)) { - /* Re-insert buffer in front of queue */ - buf->next = head; - head = buf; + switch (msg_user(msg)) { + int ret; + case MSG_BUNDLER: + l_ptr->stats.recv_bundles++; + l_ptr->stats.recv_bundled += msg_msgcnt(msg); + tipc_node_unlock(n_ptr); + tipc_link_recv_bundle(buf); + continue; + case NAME_DISTRIBUTOR: + n_ptr->bclink.recv_permitted = true; + tipc_node_unlock(n_ptr); + tipc_named_recv(buf); + continue; + case BCAST_PROTOCOL: + tipc_link_recv_sync(n_ptr, buf); tipc_node_unlock(n_ptr); continue; + case CONN_MANAGER: + tipc_node_unlock(n_ptr); + tipc_port_recv_proto_msg(buf); + continue; + case MSG_FRAGMENTER: + l_ptr->stats.recv_fragments++; + ret = tipc_link_recv_fragment(&l_ptr->defragm_buf, + &buf, &msg); + if (ret == 1) { + l_ptr->stats.recv_fragmented++; + goto deliver; + } + if (ret == -1) + l_ptr->next_in_no--; + break; + case CHANGEOVER_PROTOCOL: + type = msg_type(msg); + if (link_recv_changeover_msg(&l_ptr, &buf)) { + msg = buf_msg(buf); + seq_no = msg_seqno(msg); + if (type == ORIGINAL_MSG) + goto deliver; + goto protocol_check; + } + break; + default: + kfree_skb(buf); + buf = NULL; + break; } tipc_node_unlock(n_ptr); -cont: + tipc_net_route_msg(buf); + continue; +unlock_discard: + + tipc_node_unlock(n_ptr); +discard: kfree_skb(buf); } read_unlock_bh(&tipc_net_lock); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 86de99ad2976..c1f403bed683 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1246,6 +1246,15 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb) return 0; } +static void unix_sock_inherit_flags(const struct socket *old, + struct socket *new) +{ + if (test_bit(SOCK_PASSCRED, &old->flags)) + set_bit(SOCK_PASSCRED, &new->flags); + if (test_bit(SOCK_PASSSEC, &old->flags)) + set_bit(SOCK_PASSSEC, &new->flags); +} + static int unix_accept(struct socket *sock, struct socket *newsock, int flags) { struct sock *sk = sock->sk; @@ -1280,6 +1289,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags) /* attach accepted sock to socket */ unix_state_lock(tsk); newsock->state = SS_CONNECTED; + unix_sock_inherit_flags(sock, newsock); sock_graft(tsk, newsock); unix_state_unlock(tsk); return 0; diff --git a/net/wireless/core.c b/net/wireless/core.c index fe8d4f2be49b..aff959e5a1b3 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -958,8 +958,6 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, case NETDEV_PRE_UP: if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype))) return notifier_from_errno(-EOPNOTSUPP); - if (rfkill_blocked(rdev->rfkill)) - return notifier_from_errno(-ERFKILL); ret = cfg80211_can_add_interface(rdev, wdev->iftype); if (ret) return notifier_from_errno(ret); diff --git a/net/wireless/core.h b/net/wireless/core.h index 74beff1e926f..af10e59af2d8 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -402,6 +402,9 @@ static inline int cfg80211_can_add_interface(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype) { + if (rfkill_blocked(rdev->rfkill)) + return -ERFKILL; + return cfg80211_can_change_interface(rdev, NULL, iftype); } diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c index 7d604c06c3dc..a271c27fac77 100644 --- a/net/wireless/radiotap.c +++ b/net/wireless/radiotap.c @@ -97,6 +97,10 @@ int ieee80211_radiotap_iterator_init( struct ieee80211_radiotap_header *radiotap_header, int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns) { + /* check the radiotap header can actually be present */ + if (max_length < sizeof(struct ieee80211_radiotap_header)) + return -EINVAL; + /* Linux only supports version 0 radiotap format */ if (radiotap_header->it_version) return -EINVAL; @@ -131,7 +135,8 @@ int ieee80211_radiotap_iterator_init( */ if ((unsigned long)iterator->_arg - - (unsigned long)iterator->_rtheader > + (unsigned long)iterator->_rtheader + + sizeof(uint32_t) > (unsigned long)iterator->_max_length) return -EINVAL; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e09edfcf1b79..9a91f7431c41 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -334,7 +334,8 @@ static void xfrm_policy_kill(struct xfrm_policy *policy) atomic_inc(&policy->genid); - del_timer(&policy->polq.hold_timer); + if (del_timer(&policy->polq.hold_timer)) + xfrm_pol_put(policy); xfrm_queue_purge(&policy->polq.hold_queue); if (del_timer(&policy->timer)) @@ -589,7 +590,8 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice_init(&pq->hold_queue, &list); - del_timer(&pq->hold_timer); + if (del_timer(&pq->hold_timer)) + xfrm_pol_put(old); spin_unlock_bh(&pq->hold_queue.lock); if (skb_queue_empty(&list)) @@ -600,7 +602,8 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice(&list, &pq->hold_queue); pq->timeout = XFRM_QUEUE_TMO_MIN; - mod_timer(&pq->hold_timer, jiffies); + if (!mod_timer(&pq->hold_timer, jiffies)) + xfrm_pol_hold(new); spin_unlock_bh(&pq->hold_queue.lock); } @@ -1769,6 +1772,10 @@ static void xfrm_policy_queue_process(unsigned long arg) spin_lock(&pq->hold_queue.lock); skb = skb_peek(&pq->hold_queue); + if (!skb) { + spin_unlock(&pq->hold_queue.lock); + goto out; + } dst = skb_dst(skb); sk = skb->sk; xfrm_decode_session(skb, &fl, dst->ops->family); @@ -1787,8 +1794,9 @@ static void xfrm_policy_queue_process(unsigned long arg) goto purge_queue; pq->timeout = pq->timeout << 1; - mod_timer(&pq->hold_timer, jiffies + pq->timeout); - return; + if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout)) + xfrm_pol_hold(pol); + goto out; } dst_release(dst); @@ -1819,11 +1827,14 @@ static void xfrm_policy_queue_process(unsigned long arg) err = dst_output(skb); } +out: + xfrm_pol_put(pol); return; purge_queue: pq->timeout = 0; xfrm_queue_purge(&pq->hold_queue); + xfrm_pol_put(pol); } static int xdst_queue_output(struct sk_buff *skb) @@ -1831,7 +1842,8 @@ static int xdst_queue_output(struct sk_buff *skb) unsigned long sched_next; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *) dst; - struct xfrm_policy_queue *pq = &xdst->pols[0]->polq; + struct xfrm_policy *pol = xdst->pols[0]; + struct xfrm_policy_queue *pq = &pol->polq; const struct sk_buff *fclone = skb + 1; if (unlikely(skb->fclone == SKB_FCLONE_ORIG && @@ -1857,10 +1869,12 @@ static int xdst_queue_output(struct sk_buff *skb) if (del_timer(&pq->hold_timer)) { if (time_before(pq->hold_timer.expires, sched_next)) sched_next = pq->hold_timer.expires; + xfrm_pol_put(pol); } __skb_queue_tail(&pq->hold_queue, skb); - mod_timer(&pq->hold_timer, sched_next); + if (!mod_timer(&pq->hold_timer, sched_next)) + xfrm_pol_hold(pol); spin_unlock_bh(&pq->hold_queue.lock); diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 8dafe6d3c6e4..dab57daae408 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -61,9 +61,9 @@ static void xfrm_replay_notify(struct xfrm_state *x, int event) switch (event) { case XFRM_REPLAY_UPDATE: - if (x->replay_maxdiff && - (x->replay.seq - x->preplay.seq < x->replay_maxdiff) && - (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff)) { + if (!x->replay_maxdiff || + ((x->replay.seq - x->preplay.seq < x->replay_maxdiff) && + (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff))) { if (x->xflags & XFRM_TIME_DEFER) event = XFRM_REPLAY_TIMEOUT; else @@ -129,8 +129,7 @@ static int xfrm_replay_check(struct xfrm_state *x, return 0; diff = x->replay.seq - seq; - if (diff >= min_t(unsigned int, x->props.replay_window, - sizeof(x->replay.bitmap) * 8)) { + if (diff >= x->props.replay_window) { x->stats.replay_window++; goto err; } @@ -302,9 +301,10 @@ static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event) switch (event) { case XFRM_REPLAY_UPDATE: - if (x->replay_maxdiff && - (replay_esn->seq - preplay_esn->seq < x->replay_maxdiff) && - (replay_esn->oseq - preplay_esn->oseq < x->replay_maxdiff)) { + if (!x->replay_maxdiff || + ((replay_esn->seq - preplay_esn->seq < x->replay_maxdiff) && + (replay_esn->oseq - preplay_esn->oseq + < x->replay_maxdiff))) { if (x->xflags & XFRM_TIME_DEFER) event = XFRM_REPLAY_TIMEOUT; else @@ -353,28 +353,30 @@ static void xfrm_replay_notify_esn(struct xfrm_state *x, int event) switch (event) { case XFRM_REPLAY_UPDATE: - if (!x->replay_maxdiff) - break; - - if (replay_esn->seq_hi == preplay_esn->seq_hi) - seq_diff = replay_esn->seq - preplay_esn->seq; - else - seq_diff = ~preplay_esn->seq + replay_esn->seq + 1; - - if (replay_esn->oseq_hi == preplay_esn->oseq_hi) - oseq_diff = replay_esn->oseq - preplay_esn->oseq; - else - oseq_diff = ~preplay_esn->oseq + replay_esn->oseq + 1; - - if (seq_diff < x->replay_maxdiff && - oseq_diff < x->replay_maxdiff) { + if (x->replay_maxdiff) { + if (replay_esn->seq_hi == preplay_esn->seq_hi) + seq_diff = replay_esn->seq - preplay_esn->seq; + else + seq_diff = ~preplay_esn->seq + replay_esn->seq + + 1; - if (x->xflags & XFRM_TIME_DEFER) - event = XFRM_REPLAY_TIMEOUT; + if (replay_esn->oseq_hi == preplay_esn->oseq_hi) + oseq_diff = replay_esn->oseq + - preplay_esn->oseq; else - return; + oseq_diff = ~preplay_esn->oseq + + replay_esn->oseq + 1; + + if (seq_diff >= x->replay_maxdiff || + oseq_diff >= x->replay_maxdiff) + break; } + if (x->xflags & XFRM_TIME_DEFER) + event = XFRM_REPLAY_TIMEOUT; + else + return; + break; case XFRM_REPLAY_TIMEOUT: diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 3f565e495ac6..f964d4c00ffb 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -446,7 +446,8 @@ static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info * memcpy(&x->sel, &p->sel, sizeof(x->sel)); memcpy(&x->lft, &p->lft, sizeof(x->lft)); x->props.mode = p->mode; - x->props.replay_window = p->replay_window; + x->props.replay_window = min_t(unsigned int, p->replay_window, + sizeof(x->replay.bitmap) * 8); x->props.reqid = p->reqid; x->props.family = p->family; memcpy(&x->props.saddr, &p->saddr, sizeof(x->props.saddr)); @@ -1856,7 +1857,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, if (x->km.state != XFRM_STATE_VALID) goto out; - err = xfrm_replay_verify_len(x->replay_esn, rp); + err = xfrm_replay_verify_len(x->replay_esn, re); if (err) goto out; |