diff options
Diffstat (limited to 'net')
118 files changed, 925 insertions, 625 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 64aa9f7..45c9bf5 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -48,8 +48,8 @@ bool vlan_do_receive(struct sk_buff **skbp) * original position later */ skb_push(skb, offset); - skb = *skbp = vlan_insert_tag(skb, skb->vlan_proto, - skb->vlan_tci); + skb = *skbp = vlan_insert_inner_tag(skb, skb->vlan_proto, + skb->vlan_tci, skb->mac_len); if (!skb) return false; skb_pull(skb, offset + VLAN_HLEN); diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 79e3263..99abead 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -157,7 +157,7 @@ static void batadv_iv_ogm_orig_free(struct batadv_orig_node *orig_node) * Return: 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) + unsigned int max_if_num) { void *data_ptr; size_t old_size; @@ -201,7 +201,8 @@ unlock: */ static void batadv_iv_ogm_drop_bcast_own_entry(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { size_t chunk_size; size_t if_offset; @@ -239,7 +240,8 @@ batadv_iv_ogm_drop_bcast_own_entry(struct batadv_orig_node *orig_node, */ static void batadv_iv_ogm_drop_bcast_own_sum_entry(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { size_t if_offset; void *data_ptr; @@ -276,7 +278,8 @@ batadv_iv_ogm_drop_bcast_own_sum_entry(struct batadv_orig_node *orig_node, * Return: 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) + unsigned int max_if_num, + unsigned int del_if_num) { spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); @@ -311,7 +314,8 @@ static struct batadv_orig_node * batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) { struct batadv_orig_node *orig_node; - int size, hash_added; + int hash_added; + size_t size; orig_node = batadv_orig_hash_find(bat_priv, addr); if (orig_node) @@ -893,7 +897,7 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) u32 i; size_t word_index; u8 *w; - int if_num; + unsigned int if_num; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1023,7 +1027,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, struct batadv_neigh_node *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; - int if_num; + unsigned int if_num; u8 sum_orig, sum_neigh; u8 *neigh_addr; u8 tq_avg; @@ -1182,7 +1186,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, u8 total_count; u8 orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; - int if_num; + unsigned int if_num; unsigned int tq_asym_penalty, inv_asym_penalty; unsigned int combined_tq; unsigned int tq_iface_penalty; @@ -1702,9 +1706,9 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset, if (is_my_orig) { unsigned long *word; - int offset; + size_t offset; s32 bit_pos; - s16 if_num; + unsigned int if_num; u8 *weight; orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, @@ -2729,7 +2733,7 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; struct batadv_gw_node *curr_gw; - int ret = -EINVAL; + int ret = 0; void *hdr; router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 27e165a..c74f813 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -928,7 +928,7 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; struct batadv_gw_node *curr_gw; - int ret = -EINVAL; + int ret = 0; void *hdr; router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index fad4785..b1a0837 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -2161,22 +2161,25 @@ batadv_bla_claim_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_bla_claim *claim; int idx = 0; + int ret = 0; rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { if (idx++ < *idx_skip) continue; - if (batadv_bla_claim_dump_entry(msg, portid, seq, - primary_if, claim)) { + + ret = batadv_bla_claim_dump_entry(msg, portid, seq, + primary_if, claim); + if (ret) { *idx_skip = idx - 1; goto unlock; } } - *idx_skip = idx; + *idx_skip = 0; unlock: rcu_read_unlock(); - return 0; + return ret; } /** @@ -2391,22 +2394,25 @@ batadv_bla_backbone_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_bla_backbone_gw *backbone_gw; int idx = 0; + int ret = 0; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (idx++ < *idx_skip) continue; - if (batadv_bla_backbone_dump_entry(msg, portid, seq, - primary_if, backbone_gw)) { + + ret = batadv_bla_backbone_dump_entry(msg, portid, seq, + primary_if, backbone_gw); + if (ret) { *idx_skip = idx - 1; goto unlock; } } - *idx_skip = idx; + *idx_skip = 0; unlock: rcu_read_unlock(); - return 0; + return ret; } /** diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 9703c79..87cd962 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -393,7 +393,7 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, batadv_arp_hw_src(skb, hdr_size), &ip_src, batadv_arp_hw_dst(skb, hdr_size), &ip_dst); - if (hdr_size == 0) + if (hdr_size < sizeof(struct batadv_unicast_packet)) return; unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 22dde42..5afe641 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -288,7 +288,8 @@ batadv_frag_merge_packets(struct hlist_head *chain) /* Move the existing MAC header to just before the payload. (Override * the fragment header.) */ - skb_pull_rcsum(skb_out, hdr_size); + skb_pull(skb_out, hdr_size); + skb_out->ip_summed = CHECKSUM_NONE; memmove(skb_out->data - ETH_HLEN, skb_mac_header(skb_out), ETH_HLEN); skb_set_mac_header(skb_out, -ETH_HLEN); skb_reset_network_header(skb_out); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 5f186bf..68b54a3 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -763,6 +763,11 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); + if (bat_priv->num_ifaces >= UINT_MAX) { + ret = -ENOSPC; + goto err_dev; + } + ret = netdev_master_upper_dev_link(hard_iface->net_dev, soft_iface, NULL, NULL, NULL); if (ret) @@ -876,7 +881,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface); /* nobody uses this interface anymore */ - if (!bat_priv->num_ifaces) { + if (bat_priv->num_ifaces == 0) { batadv_gw_check_client_stop(bat_priv); if (autodel == BATADV_IF_CLEANUP_AUTO) @@ -912,7 +917,7 @@ batadv_hardif_add_interface(struct net_device *net_dev) if (ret) goto free_if; - hard_iface->if_num = -1; + hard_iface->if_num = 0; hard_iface->net_dev = net_dev; hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index e91f29c..5daa3d5 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -24,6 +24,7 @@ #include <linux/debugfs.h> #include <linux/errno.h> #include <linux/etherdevice.h> +#include <linux/eventpoll.h> #include <linux/export.h> #include <linux/fcntl.h> #include <linux/fs.h> diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index dc9fa37..cdbe0e5 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -22,6 +22,7 @@ #include <linux/compiler.h> #include <linux/debugfs.h> #include <linux/errno.h> +#include <linux/eventpoll.h> #include <linux/export.h> #include <linux/fcntl.h> #include <linux/fs.h> diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index cbdeb47..d706401 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -543,8 +543,8 @@ update: bat_priv->mcast.enabled = true; } - return !(mcast_data.flags & - (BATADV_MCAST_WANT_ALL_IPV4 | BATADV_MCAST_WANT_ALL_IPV6)); + return !(mcast_data.flags & BATADV_MCAST_WANT_ALL_IPV4 && + mcast_data.flags & BATADV_MCAST_WANT_ALL_IPV6); } /** diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 58a7d92..7478242 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1569,7 +1569,7 @@ int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) * Return: 0 on success or negative error number in case of failure */ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_algo_ops *bao = bat_priv->algo_ops; @@ -1611,7 +1611,7 @@ err: * Return: 0 on success or negative error number in case of failure */ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 8e543a3..15d896b 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -73,9 +73,9 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); struct batadv_orig_node_vlan * batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, unsigned short vid); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index b6891e8..e61dc12 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -759,6 +759,7 @@ free_skb: /** * batadv_reroute_unicast_packet() - update the unicast header for re-routing * @bat_priv: the bat priv with all the soft interface information + * @skb: unicast packet to process * @unicast_packet: the unicast header to be updated * @dst_addr: the payload destination * @vid: VLAN identifier @@ -770,7 +771,7 @@ free_skb: * Return: true if the packet header has been updated, false otherwise */ static bool -batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, +batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_unicast_packet *unicast_packet, u8 *dst_addr, unsigned short vid) { @@ -799,8 +800,10 @@ batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, } /* update the packet header */ + skb_postpull_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ether_addr_copy(unicast_packet->dest, orig_addr); unicast_packet->ttvn = orig_ttvn; + skb_postpush_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ret = true; out: @@ -841,7 +844,7 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, * the packet to */ if (batadv_tt_local_client_is_roaming(bat_priv, ethhdr->h_dest, vid)) { - if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + if (batadv_reroute_unicast_packet(bat_priv, skb, unicast_packet, ethhdr->h_dest, vid)) batadv_dbg_ratelimited(BATADV_DBG_TT, bat_priv, @@ -887,7 +890,7 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, * destination can possibly be updated and forwarded towards the new * target host */ - if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + if (batadv_reroute_unicast_packet(bat_priv, skb, unicast_packet, ethhdr->h_dest, vid)) { batadv_dbg_ratelimited(BATADV_DBG_TT, bat_priv, "Rerouting unicast packet to %pM (dst=%pM): TTVN mismatch old_ttvn=%u new_ttvn=%u\n", @@ -910,12 +913,14 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, if (!primary_if) return false; + /* update the packet header */ + skb_postpull_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ether_addr_copy(unicast_packet->dest, primary_if->net_dev->dev_addr); + unicast_packet->ttvn = curr_ttvn; + skb_postpush_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); batadv_hardif_put(primary_if); - unicast_packet->ttvn = curr_ttvn; - return true; } @@ -968,14 +973,10 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, struct batadv_orig_node *orig_node = NULL, *orig_node_gw = NULL; int check, hdr_size = sizeof(*unicast_packet); enum batadv_subtype subtype; - struct ethhdr *ethhdr; int ret = NET_RX_DROP; bool is4addr, is_gw; unicast_packet = (struct batadv_unicast_packet *)skb->data; - unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; - ethhdr = eth_hdr(skb); - is4addr = unicast_packet->packet_type == BATADV_UNICAST_4ADDR; /* the caller function should have already pulled 2 bytes */ if (is4addr) @@ -995,12 +996,14 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, if (!batadv_check_unicast_ttvn(bat_priv, skb, hdr_size)) goto free_skb; + unicast_packet = (struct batadv_unicast_packet *)skb->data; + /* packet for me */ if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { /* If this is a unicast packet from another backgone gw, * drop it. */ - orig_addr_gw = ethhdr->h_source; + orig_addr_gw = eth_hdr(skb)->h_source; orig_node_gw = batadv_orig_hash_find(bat_priv, orig_addr_gw); if (orig_node_gw) { is_gw = batadv_bla_is_backbone_gw(skb, orig_node_gw, @@ -1015,6 +1018,8 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, } if (is4addr) { + unicast_4addr_packet = + (struct batadv_unicast_4addr_packet *)skb->data; subtype = unicast_4addr_packet->subtype; batadv_dat_inc_counter(bat_priv, subtype); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 900c5ce..367a81f 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -459,13 +459,7 @@ void batadv_interface_rx(struct net_device *soft_iface, /* skb->dev & skb->pkt_type are set here */ skb->protocol = eth_type_trans(skb, soft_iface); - - /* should not be necessary anymore as we use skb_pull_rcsum() - * TODO: please verify this and remove this TODO - * -- Dec 21st 2009, Simon Wunderlich - */ - - /* skb->ip_summed = CHECKSUM_UNNECESSARY; */ + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); batadv_inc_counter(bat_priv, BATADV_CNT_RX); batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index bb15784..a5aa6d6 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -167,7 +167,7 @@ struct batadv_hard_iface { struct list_head list; /** @if_num: identificator of the interface */ - s16 if_num; + unsigned int if_num; /** @if_status: status of the interface for batman-adv */ char if_status; @@ -1596,7 +1596,7 @@ struct batadv_priv { atomic_t batman_queue_left; /** @num_ifaces: number of interfaces assigned to this mesh interface */ - char num_ifaces; + unsigned int num_ifaces; /** @mesh_obj: kobject for sysfs mesh subdirectory */ struct kobject *mesh_obj; @@ -2186,15 +2186,16 @@ struct batadv_algo_orig_ops { * orig_node due to a new hard-interface being added into the mesh * (optional) */ - int (*add_if)(struct batadv_orig_node *orig_node, int max_if_num); + int (*add_if)(struct batadv_orig_node *orig_node, + unsigned int max_if_num); /** * @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 * (optional) */ - int (*del_if)(struct batadv_orig_node *orig_node, int max_if_num, - int del_if_num); + int (*del_if)(struct batadv_orig_node *orig_node, + unsigned int max_if_num, unsigned int del_if_num); #ifdef CONFIG_BATMAN_ADV_DEBUGFS /** @print: print the originator table (optional) */ diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 01117ae..a2ddae2 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2296,8 +2296,14 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) else sec_level = authreq_to_seclevel(auth); - if (smp_sufficient_security(hcon, sec_level, SMP_USE_LTK)) + if (smp_sufficient_security(hcon, sec_level, SMP_USE_LTK)) { + /* If link is already encrypted with sufficient security we + * still need refresh encryption as per Core Spec 5.0 Vol 3, + * Part H 2.4.6 + */ + smp_ltk_encrypt(conn, hcon->sec_level); return 0; + } if (sec_level > hcon->pending_sec_level) hcon->pending_sec_level = sec_level; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 27f1d4f..9b16eaf 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -214,7 +214,7 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb) iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) - goto inhdr_error; + goto csum_error; len = ntohs(iph->tot_len); if (skb->len < len) { @@ -236,6 +236,8 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb) */ return 0; +csum_error: + __IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS); inhdr_error: __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); drop: diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 5193527..9896f49 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -168,6 +168,8 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) return NULL; + refcount_set(&masterv->refcnt, 1); + return masterv; } refcount_inc(&masterv->refcnt); diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c index ce7152a..620e54f 100644 --- a/net/bridge/netfilter/ebt_among.c +++ b/net/bridge/netfilter/ebt_among.c @@ -172,18 +172,69 @@ ebt_among_mt(const struct sk_buff *skb, struct xt_action_param *par) return true; } +static bool poolsize_invalid(const struct ebt_mac_wormhash *w) +{ + return w && w->poolsize >= (INT_MAX / sizeof(struct ebt_mac_wormhash_tuple)); +} + +static bool wormhash_offset_invalid(int off, unsigned int len) +{ + if (off == 0) /* not present */ + return false; + + if (off < (int)sizeof(struct ebt_among_info) || + off % __alignof__(struct ebt_mac_wormhash)) + return true; + + off += sizeof(struct ebt_mac_wormhash); + + return off > len; +} + +static bool wormhash_sizes_valid(const struct ebt_mac_wormhash *wh, int a, int b) +{ + if (a == 0) + a = sizeof(struct ebt_among_info); + + return ebt_mac_wormhash_size(wh) + a == b; +} + static int ebt_among_mt_check(const struct xt_mtchk_param *par) { const struct ebt_among_info *info = par->matchinfo; const struct ebt_entry_match *em = container_of(par->matchinfo, const struct ebt_entry_match, data); - int expected_length = sizeof(struct ebt_among_info); + unsigned int expected_length = sizeof(struct ebt_among_info); const struct ebt_mac_wormhash *wh_dst, *wh_src; int err; + if (expected_length > em->match_size) + return -EINVAL; + + if (wormhash_offset_invalid(info->wh_dst_ofs, em->match_size) || + wormhash_offset_invalid(info->wh_src_ofs, em->match_size)) + return -EINVAL; + wh_dst = ebt_among_wh_dst(info); - wh_src = ebt_among_wh_src(info); + if (poolsize_invalid(wh_dst)) + return -EINVAL; + expected_length += ebt_mac_wormhash_size(wh_dst); + if (expected_length > em->match_size) + return -EINVAL; + + wh_src = ebt_among_wh_src(info); + if (poolsize_invalid(wh_src)) + return -EINVAL; + + if (info->wh_src_ofs < info->wh_dst_ofs) { + if (!wormhash_sizes_valid(wh_src, info->wh_src_ofs, info->wh_dst_ofs)) + return -EINVAL; + } else { + if (!wormhash_sizes_valid(wh_dst, info->wh_dst_ofs, info->wh_src_ofs)) + return -EINVAL; + } + expected_length += ebt_mac_wormhash_size(wh_src); if (em->match_size != EBT_ALIGN(expected_length)) { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 02c4b40..a94d23b 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1641,7 +1641,8 @@ static int compat_match_to_user(struct ebt_entry_match *m, void __user **dstptr, int off = ebt_compat_match_offset(match, m->match_size); compat_uint_t msize = m->match_size - off; - BUG_ON(off >= m->match_size); + if (WARN_ON(off >= m->match_size)) + return -EINVAL; if (copy_to_user(cm->u.name, match->name, strlen(match->name) + 1) || put_user(msize, &cm->match_size)) @@ -1671,7 +1672,8 @@ static int compat_target_to_user(struct ebt_entry_target *t, int off = xt_compat_target_offset(target); compat_uint_t tsize = t->target_size - off; - BUG_ON(off >= t->target_size); + if (WARN_ON(off >= t->target_size)) + return -EINVAL; if (copy_to_user(cm->u.name, target->name, strlen(target->name) + 1) || put_user(tsize, &cm->match_size)) @@ -1902,7 +1904,8 @@ static int ebt_buf_add(struct ebt_entries_buf_state *state, if (state->buf_kern_start == NULL) goto count_only; - BUG_ON(state->buf_kern_offset + sz > state->buf_kern_len); + if (WARN_ON(state->buf_kern_offset + sz > state->buf_kern_len)) + return -EINVAL; memcpy(state->buf_kern_start + state->buf_kern_offset, data, sz); @@ -1915,7 +1918,8 @@ static int ebt_buf_add_pad(struct ebt_entries_buf_state *state, unsigned int sz) { char *b = state->buf_kern_start; - BUG_ON(b && state->buf_kern_offset > state->buf_kern_len); + if (WARN_ON(b && state->buf_kern_offset > state->buf_kern_len)) + return -EINVAL; if (b != NULL && sz > 0) memset(b + state->buf_kern_offset, 0, sz); @@ -1992,8 +1996,10 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, pad = XT_ALIGN(size_kern) - size_kern; if (pad > 0 && dst) { - BUG_ON(state->buf_kern_len <= pad); - BUG_ON(state->buf_kern_offset - (match_size + off) + size_kern > state->buf_kern_len - pad); + if (WARN_ON(state->buf_kern_len <= pad)) + return -EINVAL; + if (WARN_ON(state->buf_kern_offset - (match_size + off) + size_kern > state->buf_kern_len - pad)) + return -EINVAL; memset(dst + size_kern, 0, pad); } return off + match_size; @@ -2043,7 +2049,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (ret < 0) return ret; - BUG_ON(ret < match32->match_size); + if (WARN_ON(ret < match32->match_size)) + return -EINVAL; growth += ret - match32->match_size; growth += ebt_compat_entry_padsize(); @@ -2053,7 +2060,9 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - WARN_ON(type == EBT_COMPAT_TARGET && size_left); + if (WARN_ON(type == EBT_COMPAT_TARGET && size_left)) + return -EINVAL; + match32 = (struct compat_ebt_entry_mwt *) buf; } @@ -2109,6 +2118,19 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, * * offsets are relative to beginning of struct ebt_entry (i.e., 0). */ + for (i = 0; i < 4 ; ++i) { + if (offsets[i] > *total) + return -EINVAL; + + if (i < 3 && offsets[i] == *total) + return -EINVAL; + + if (i == 0) + continue; + if (offsets[i-1] > offsets[i]) + return -EINVAL; + } + for (i = 0, j = 1 ; j < 4 ; j++, i++) { struct compat_ebt_entry_mwt *match32; unsigned int size; @@ -2140,7 +2162,8 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, startoff = state->buf_user_offset - startoff; - BUG_ON(*total < startoff); + if (WARN_ON(*total < startoff)) + return -EINVAL; *total -= startoff; return 0; } @@ -2267,7 +2290,8 @@ static int compat_do_replace(struct net *net, void __user *user, state.buf_kern_len = size64; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); - BUG_ON(ret < 0); /* parses same data again */ + if (WARN_ON(ret < 0)) + goto out_unlock; vfree(entries_tmp); tmp.entries_size = size64; diff --git a/net/core/dev.c b/net/core/dev.c index d4362be..12be205 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3278,15 +3278,23 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { - struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); + const struct netprio_map *map; + const struct sock *sk; + unsigned int prioidx; - if (!skb->priority && skb->sk && map) { - unsigned int prioidx = - sock_cgroup_prioidx(&skb->sk->sk_cgrp_data); + if (skb->priority) + return; + map = rcu_dereference_bh(skb->dev->priomap); + if (!map) + return; + sk = skb_to_full_sk(skb); + if (!sk) + return; - if (prioidx < map->priomap_len) - skb->priority = map->priomap[prioidx]; - } + prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data); + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; } #else #define skb_update_prio(skb) @@ -6396,6 +6404,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, .linking = true, .upper_info = upper_info, }; + struct net_device *master_dev; int ret = 0; ASSERT_RTNL(); @@ -6407,11 +6416,14 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; - if (netdev_has_upper_dev(dev, upper_dev)) - return -EEXIST; - - if (master && netdev_master_upper_dev_get(dev)) - return -EBUSY; + if (!master) { + if (netdev_has_upper_dev(dev, upper_dev)) + return -EEXIST; + } else { + master_dev = netdev_master_upper_dev_get(dev); + if (master_dev) + return master_dev == upper_dev ? -EEXIST : -EBUSY; + } ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 0ab1af0..a04e1e8 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -402,8 +402,6 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c if (colon) *colon = 0; - dev_load(net, ifr->ifr_name); - /* * See which interface the caller is talking about. */ @@ -423,6 +421,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCGIFMAP: case SIOCGIFINDEX: case SIOCGIFTXQLEN: + dev_load(net, ifr->ifr_name); rcu_read_lock(); ret = dev_ifsioc_locked(net, ifr, cmd); rcu_read_unlock(); @@ -431,6 +430,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c return ret; case SIOCETHTOOL: + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ethtool(net, ifr); rtnl_unlock(); @@ -447,6 +447,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSIFNAME: + dev_load(net, ifr->ifr_name); if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_lock(); @@ -494,6 +495,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c /* fall through */ case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ifsioc(net, ifr, cmd); rtnl_unlock(); @@ -518,6 +520,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c cmd == SIOCGHWTSTAMP || (cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15)) { + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ifsioc(net, ifr, cmd); rtnl_unlock(); diff --git a/net/core/devlink.c b/net/core/devlink.c index 18d385e..effd484 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1695,10 +1695,11 @@ static int devlink_dpipe_table_put(struct sk_buff *skb, goto nla_put_failure; if (table->resource_valid) { - nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, - table->resource_id, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS, - table->resource_units, DEVLINK_ATTR_PAD); + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, + table->resource_id, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS, + table->resource_units, DEVLINK_ATTR_PAD)) + goto nla_put_failure; } if (devlink_dpipe_matches_put(table, skb)) goto nla_put_failure; @@ -1797,7 +1798,7 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } @@ -1806,7 +1807,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: -err_skb_send_alloc: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; @@ -2072,7 +2072,7 @@ static int devlink_dpipe_entries_fill(struct genl_info *info, table->counters_enabled, &dump_ctx); if (err) - goto err_entries_dump; + return err; send_done: nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq, @@ -2080,16 +2080,10 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(dump_ctx.skb, info); - -err_entries_dump: -err_skb_send_alloc: - genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr); - nlmsg_free(dump_ctx.skb); - return err; } static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, @@ -2228,7 +2222,7 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(skb, info); @@ -2236,7 +2230,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: -err_skb_send_alloc: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; @@ -2332,7 +2325,7 @@ devlink_resource_validate_children(struct devlink_resource *resource) list_for_each_entry(child_resource, &resource->resource_list, list) parts_size += child_resource->size_new; - if (parts_size > resource->size) + if (parts_size > resource->size_new) size_valid = false; out: resource->size_valid = size_valid; @@ -2372,20 +2365,22 @@ static int devlink_nl_cmd_resource_set(struct sk_buff *skb, return 0; } -static void +static int devlink_resource_size_params_put(struct devlink_resource *resource, struct sk_buff *skb) { struct devlink_resource_size_params *size_params; - size_params = resource->size_params; - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN, - size_params->size_granularity, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX, - size_params->size_max, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN, - size_params->size_min, DEVLINK_ATTR_PAD); - nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit); + size_params = &resource->size_params; + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN, + size_params->size_granularity, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX, + size_params->size_max, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN, + size_params->size_min, DEVLINK_ATTR_PAD) || + nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit)) + return -EMSGSIZE; + return 0; } static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, @@ -2409,10 +2404,12 @@ static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_NEW, resource->size_new, DEVLINK_ATTR_PAD); if (resource->resource_ops && resource->resource_ops->occ_get) - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, - resource->resource_ops->occ_get(devlink), - DEVLINK_ATTR_PAD); - devlink_resource_size_params_put(resource, skb); + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, + resource->resource_ops->occ_get(devlink), + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (devlink_resource_size_params_put(resource, skb)) + goto nla_put_failure; if (list_empty(&resource->resource_list)) goto out; @@ -3151,7 +3148,7 @@ int devlink_resource_register(struct devlink *devlink, u64 resource_size, u64 resource_id, u64 parent_resource_id, - struct devlink_resource_size_params *size_params, + const struct devlink_resource_size_params *size_params, const struct devlink_resource_ops *resource_ops) { struct devlink_resource *resource; @@ -3194,7 +3191,8 @@ int devlink_resource_register(struct devlink *devlink, resource->id = resource_id; resource->resource_ops = resource_ops; resource->size_valid = true; - resource->size_params = size_params; + memcpy(&resource->size_params, size_params, + sizeof(resource->size_params)); INIT_LIST_HEAD(&resource->resource_list); list_add_tail(&resource->list, resource_list); out: diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 494e6a5..3f89c76 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -2520,11 +2520,14 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr) static int ethtool_get_fecparam(struct net_device *dev, void __user *useraddr) { struct ethtool_fecparam fecparam = { ETHTOOL_GFECPARAM }; + int rc; if (!dev->ethtool_ops->get_fecparam) return -EOPNOTSUPP; - dev->ethtool_ops->get_fecparam(dev, &fecparam); + rc = dev->ethtool_ops->get_fecparam(dev, &fecparam); + if (rc) + return rc; if (copy_to_user(useraddr, &fecparam, sizeof(fecparam))) return -EFAULT; diff --git a/net/core/filter.c b/net/core/filter.c index 0c121ad..48aa7c7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2087,6 +2087,10 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@ -2096,19 +2100,21 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* SKB_GSO_TCPV4 needs to be changed into * SKB_GSO_TCPV6. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { - skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV4; - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; + if (shinfo->gso_type & SKB_GSO_TCPV4) { + shinfo->gso_type &= ~SKB_GSO_TCPV4; + shinfo->gso_type |= SKB_GSO_TCPV6; } /* Due to IPv6 header, MSS needs to be downgraded. */ - skb_shinfo(skb)->gso_size -= len_diff; + skb_decrease_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IPV6); @@ -2123,6 +2129,10 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@ -2132,19 +2142,21 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* SKB_GSO_TCPV6 needs to be changed into * SKB_GSO_TCPV4. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) { - skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV6; - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; + if (shinfo->gso_type & SKB_GSO_TCPV6) { + shinfo->gso_type &= ~SKB_GSO_TCPV6; + shinfo->gso_type |= SKB_GSO_TCPV4; } /* Due to IPv4 header, MSS can be upgraded. */ - skb_shinfo(skb)->gso_size += len_diff; + skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IP); @@ -2243,6 +2255,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@ -2252,11 +2268,13 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* Due to header grow, MSS needs to be downgraded. */ - skb_shinfo(skb)->gso_size -= len_diff; + skb_decrease_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } return 0; @@ -2267,6 +2285,10 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@ -2276,11 +2298,13 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* Due to header shrink, MSS can be upgraded. */ - skb_shinfo(skb)->gso_size += len_diff; + skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } return 0; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 09bd89c..1e7acdc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4179,7 +4179,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + sk->sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); @@ -4891,7 +4891,7 @@ EXPORT_SYMBOL_GPL(skb_scrub_packet); * * The MAC/L2 or network (IP, IPv6) headers are not accounted for. */ -unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) +static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int thlen = 0; @@ -4904,7 +4904,7 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) thlen += inner_tcp_hdrlen(skb); } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { thlen = tcp_hdrlen(skb); - } else if (unlikely(shinfo->gso_type & SKB_GSO_SCTP)) { + } else if (unlikely(skb_is_gso_sctp(skb))) { thlen = sizeof(struct sctphdr); } /* UFO sets gso_size to the size of the fragmentation @@ -4913,7 +4913,40 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) */ return thlen + shinfo->gso_size; } -EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); + +/** + * skb_gso_network_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_network_seglen is used to determine the real size of the + * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). + * + * The MAC/L2 header is not accounted for. + */ +static unsigned int skb_gso_network_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - + skb_network_header(skb); + + return hdr_len + skb_gso_transport_seglen(skb); +} + +/** + * skb_gso_mac_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_mac_seglen is used to determine the real size of the + * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4 + * headers (TCP/UDP). + */ +static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); + + return hdr_len + skb_gso_transport_seglen(skb); +} /** * skb_gso_size_check - check the skb size, considering GSO_BY_FRAGS @@ -4955,19 +4988,20 @@ static inline bool skb_gso_size_check(const struct sk_buff *skb, } /** - * skb_gso_validate_mtu - Return in case such skb fits a given MTU + * skb_gso_validate_network_len - Will a split GSO skb fit into a given MTU? * * @skb: GSO skb * @mtu: MTU to validate against * - * skb_gso_validate_mtu validates if a given skb will fit a wanted MTU - * once split. + * skb_gso_validate_network_len validates if a given skb will fit a + * wanted MTU once split. It considers L3 headers, L4 headers, and the + * payload. */ -bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu) +bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu) { return skb_gso_size_check(skb, skb_gso_network_seglen(skb), mtu); } -EXPORT_SYMBOL_GPL(skb_gso_validate_mtu); +EXPORT_SYMBOL_GPL(skb_gso_validate_network_len); /** * skb_gso_validate_mac_len - Will a split GSO skb fit in a given length? @@ -4986,13 +5020,16 @@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { + int mac_len; + if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); return NULL; } - memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN, - 2 * ETH_ALEN); + mac_len = skb->data - skb_mac_header(skb); + memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), + mac_len - VLAN_HLEN - ETH_TLEN); skb->mac_header += VLAN_HLEN; return skb; } diff --git a/net/core/sock.c b/net/core/sock.c index c501499..85b0b64 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3261,6 +3261,27 @@ void proto_unregister(struct proto *prot) } EXPORT_SYMBOL(proto_unregister); +int sock_load_diag_module(int family, int protocol) +{ + if (!protocol) { + if (!sock_is_registered(family)) + return -ENOENT; + + return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family); + } + +#ifdef CONFIG_INET + if (family == AF_INET && + !rcu_access_pointer(inet_protos[protocol])) + return -ENOENT; +#endif + + return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family, protocol); +} +EXPORT_SYMBOL(sock_load_diag_module); + #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) __acquires(proto_list_mutex) diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 146b50e..c37b5be 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -220,8 +220,7 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; if (sock_diag_handlers[req->sdiag_family] == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, req->sdiag_family); + sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[req->sdiag_family]; @@ -247,8 +246,7 @@ static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: if (inet_rcv_compat == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); mutex_lock(&sock_diag_table_mutex); if (inet_rcv_compat != NULL) @@ -281,14 +279,12 @@ static int sock_diag_bind(struct net *net, int group) case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: if (!sock_diag_handlers[AF_INET]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: if (!sock_diag_handlers[AF_INET6]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET6); + sock_load_diag_module(AF_INET6, 0); break; } return 0; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 15bdc00..84cd4e3 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -794,6 +794,11 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (skb == NULL) goto out_release; + if (sk->sk_state == DCCP_CLOSED) { + rc = -ENOTCONN; + goto out_discard; + } + skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index cb54b81..42a7b85 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -194,7 +194,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, ds->ports[i].dn = cd->port_dn[i]; ds->ports[i].cpu_dp = dst->cpu_dp; - if (dsa_is_user_port(ds, i)) + if (!dsa_is_user_port(ds, i)) continue; ret = dsa_slave_create(&ds->ports[i]); diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 974765b..e9f0489 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -206,9 +206,13 @@ static inline void lowpan_netlink_fini(void) static int lowpan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *wdev = netdev_notifier_info_to_dev(ptr); + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); + struct wpan_dev *wpan_dev; - if (wdev->type != ARPHRD_IEEE802154) + if (ndev->type != ARPHRD_IEEE802154) + return NOTIFY_DONE; + wpan_dev = ndev->ieee802154_ptr; + if (!wpan_dev) return NOTIFY_DONE; switch (event) { @@ -217,8 +221,8 @@ static int lowpan_device_event(struct notifier_block *unused, * also delete possible lowpan interfaces which belongs * to the wpan interface. */ - if (wdev->ieee802154_ptr->lowpan_dev) - lowpan_dellink(wdev->ieee802154_ptr->lowpan_dev, NULL); + if (wpan_dev->lowpan_dev) + lowpan_dellink(wpan_dev->lowpan_dev, NULL); break; default: return NOTIFY_DONE; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index a383f29..4e5bc4b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -53,8 +53,7 @@ static DEFINE_MUTEX(inet_diag_table_mutex); static const struct inet_diag_handler *inet_diag_lock_handler(int proto) { if (!inet_diag_table[proto]) - request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET, proto); + sock_load_diag_module(AF_INET, proto); mutex_lock(&inet_diag_table_mutex); if (!inet_diag_table[proto]) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 26a3d03..e8ec289 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -119,6 +119,9 @@ out: static bool inet_fragq_should_evict(const struct inet_frag_queue *q) { + if (!hlist_unhashed(&q->list_evictor)) + return false; + return q->net->low_thresh == 0 || frag_mem_limit(q->net) >= q->net->low_thresh; } diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 2dd21c3..b54b948 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -55,7 +55,7 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if (skb->ignore_df) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 45d97e9..0901de4 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -970,9 +970,6 @@ static void __gre_tunnel_init(struct net_device *dev) t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; - dev->mtu = ETH_DATA_LEN - t_hlen - 4; - dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; @@ -1290,8 +1287,6 @@ static int erspan_tunnel_init(struct net_device *dev) erspan_hdr_len(tunnel->erspan_ver); t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; - dev->mtu = ETH_DATA_LEN - t_hlen - 4; dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e8e675b..66340ab 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -248,7 +248,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, /* common case: seglen is <= mtu */ - if (skb_gso_validate_mtu(skb, mtu)) + if (skb_gso_validate_network_len(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length exceeds the egress MTU. diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 9c41a0c..74c962b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -258,7 +258,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) return -EINVAL; - ipc->oif = src_info->ipi6_ifindex; + if (src_info->ipi6_ifindex) + ipc->oif = src_info->ipi6_ifindex; ipc->addr = src_info->ipi6_addr.s6_addr32[3]; continue; } @@ -288,7 +289,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo))) return -EINVAL; info = (struct in_pktinfo *)CMSG_DATA(cmsg); - ipc->oif = info->ipi_ifindex; + if (info->ipi_ifindex) + ipc->oif = info->ipi_ifindex; ipc->addr = info->ipi_spec_dst.s_addr; break; } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index d786a84..6d21068 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -710,16 +710,9 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } } - if (tunnel->fwmark) { - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - tunnel->fwmark); - } - else { - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - skb->mark); - } + init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, + tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, + tunnel->fwmark); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 4b02ab3..8a8ae61 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -232,7 +232,6 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, c->hash_mode = i->hash_mode; c->hash_initval = i->hash_initval; refcount_set(&c->refcount, 1); - refcount_set(&c->entries, 1); spin_lock_bh(&cn->lock); if (__clusterip_config_find(net, ip)) { @@ -263,8 +262,10 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, c->notifier.notifier_call = clusterip_netdev_event; err = register_netdevice_notifier(&c->notifier); - if (!err) + if (!err) { + refcount_set(&c->entries, 1); return c; + } #ifdef CONFIG_PROC_FS proc_remove(c->pde); @@ -273,7 +274,7 @@ err: spin_lock_bh(&cn->lock); list_del_rcu(&c->list); spin_unlock_bh(&cn->lock); - kfree(c); + clusterip_config_put(c); return ERR_PTR(err); } @@ -496,12 +497,15 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) return PTR_ERR(config); } } - cipinfo->config = config; ret = nf_ct_netns_get(par->net, par->family); - if (ret < 0) + if (ret < 0) { pr_info("cannot load conntrack support for proto=%u\n", par->family); + clusterip_config_entry_put(par->net, config); + clusterip_config_put(config); + return ret; + } if (!par->net->xt.clusterip_deprecated_warning) { pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, " @@ -509,6 +513,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) par->net->xt.clusterip_deprecated_warning = true; } + cipinfo->config = config; return ret; } diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index 25d2975..0cd46bf 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -111,6 +111,7 @@ static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, default: return -1; } + csum_replace4(&iph->check, addr, new_addr); return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); } @@ -185,7 +186,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a4f44d8..299e247 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -128,10 +128,11 @@ static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; -static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; +static u32 ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; + /* * Interface to generic destination cache. */ @@ -633,6 +634,7 @@ static inline u32 fnhe_hashfun(__be32 daddr) static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; + rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { @@ -643,7 +645,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh } static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, - u32 pmtu, unsigned long expires) + u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; @@ -680,8 +682,10 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; - if (pmtu) + if (pmtu) { fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; + } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); @@ -705,6 +709,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = expires; /* Exception created; mark the cached routes for the nexthop @@ -786,7 +791,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, jiffies + ip_rt_gc_timeout); + 0, false, + jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -930,14 +936,23 @@ out_put_peer: static int ip_error(struct sk_buff *skb) { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); struct rtable *rt = skb_rtable(skb); + struct net_device *dev = skb->dev; + struct in_device *in_dev; struct inet_peer *peer; unsigned long now; struct net *net; bool send; int code; + if (netif_is_l3_master(skb->dev)) { + dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); + if (!dev) + goto out; + } + + in_dev = __in_dev_get_rcu(dev); + /* IP on this device is disabled. */ if (!in_dev) goto out; @@ -999,15 +1014,18 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct fib_result res; + bool lock = false; - if (dst_metric_locked(dst, RTAX_MTU)) + if (ip_mtu_locked(dst)) return; if (ipv4_mtu(dst) < mtu) return; - if (mtu < ip_rt_min_pmtu) + if (mtu < ip_rt_min_pmtu) { + lock = true; mtu = ip_rt_min_pmtu; + } if (rt->rt_pmtu == mtu && time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) @@ -1017,7 +1035,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); - update_or_create_fnhe(nh, fl4->daddr, 0, mtu, + update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } rcu_read_unlock(); @@ -1270,7 +1288,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = READ_ONCE(dst->dev->mtu); - if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { + if (unlikely(ip_mtu_locked(dst))) { if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } @@ -1383,7 +1401,7 @@ struct uncached_list { static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); -static void rt_add_uncached_list(struct rtable *rt) +void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); @@ -1394,14 +1412,8 @@ static void rt_add_uncached_list(struct rtable *rt) spin_unlock_bh(&ul->lock); } -static void ipv4_dst_destroy(struct dst_entry *dst) +void rt_del_uncached_list(struct rtable *rt) { - struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); - struct rtable *rt = (struct rtable *) dst; - - if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) - kfree(p); - if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; @@ -1411,6 +1423,17 @@ static void ipv4_dst_destroy(struct dst_entry *dst) } } +static void ipv4_dst_destroy(struct dst_entry *dst) +{ + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); + struct rtable *rt = (struct rtable *)dst; + + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) + kfree(p); + + rt_del_uncached_list(rt); +} + void rt_flush_dev(struct net_device *dev) { struct net *net = dev_net(dev); @@ -1506,6 +1529,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; + rt->rt_mtu_locked = 0; rt->rt_gateway = 0; rt->rt_uses_gateway = 0; rt->rt_table_id = 0; @@ -2531,6 +2555,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; + rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; @@ -2633,6 +2658,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; + if (rt->rt_mtu_locked && expires) + metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; @@ -2818,6 +2845,7 @@ void ip_rt_multicast_event(struct in_device *in_dev) static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; +static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write, void __user *buffer, @@ -2933,7 +2961,8 @@ static struct ctl_table ipv4_route_table[] = { .data = &ip_rt_min_pmtu, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &ip_min_valid_pmtu, }, { .procname = "min_adv_mss", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 48636ae..8b8059b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3566,6 +3566,7 @@ int tcp_abort(struct sock *sk, int err) bh_unlock_sock(sk); local_bh_enable(); + tcp_write_queue_purge(sk); release_sock(sk); return 0; } diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 7c84357..faddf4f 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -6,7 +6,7 @@ * The algorithm is described in: * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm * for High-Speed Networks" - * http://www.ifp.illinois.edu/~srikant/Papers/liubassri06perf.pdf + * http://tamerbasar.csl.illinois.edu/LiuBasarSrikantPerfEvalArtJun2008.pdf * * Implemented from description in paper and ns-2 simulation. * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 575d3c1..9a1b3c1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1971,11 +1971,6 @@ void tcp_enter_loss(struct sock *sk) /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous * loss recovery is underway except recurring timeout(s) on * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing - * - * In theory F-RTO can be used repeatedly during loss recovery. - * In practice this interacts badly with broken middle-boxes that - * falsely raise the receive window, which results in repeated - * timeouts and stop-and-go behavior. */ tp->frto = net->ipv4.sysctl_tcp_frto && (new_recovery || icsk->icsk_retransmits) && @@ -2631,18 +2626,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack, tcp_try_undo_loss(sk, false)) return; - /* The ACK (s)acks some never-retransmitted data meaning not all - * the data packets before the timeout were lost. Therefore we - * undo the congestion window and state. This is essentially - * the operation in F-RTO (RFC5682 section 3.1 step 3.b). Since - * a retransmitted skb is permantly marked, we can apply such an - * operation even if F-RTO was not used. - */ - if ((flag & FLAG_ORIG_SACK_ACKED) && - tcp_try_undo_loss(sk, tp->undo_marker)) - return; - if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ + /* Step 3.b. A timeout is spurious if not all data are + * lost, i.e., never-retransmitted data are (s)acked. + */ + if ((flag & FLAG_ORIG_SACK_ACKED) && + tcp_try_undo_loss(sk, true)) + return; + if (after(tp->snd_nxt, tp->high_seq)) { if (flag & FLAG_DATA_SACKED || is_dupack) tp->frto = 0; /* Step 3.a. loss was real */ @@ -4001,6 +3992,7 @@ void tcp_reset(struct sock *sk) /* This barrier is coupled with smp_rmb() in tcp_poll() */ smp_wmb(); + tcp_write_queue_purge(sk); tcp_done(sk); if (!sock_flag(sk, SOCK_DEAD)) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 71fc60f..f7d9448 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -34,6 +34,7 @@ static void tcp_write_err(struct sock *sk) sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; sk->sk_error_report(sk); + tcp_write_queue_purge(sk); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT); } diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 63faeee..2a9764b 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -92,7 +92,8 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) skb_reset_network_header(skb); skb_mac_header_rebuild(skb); - eth_hdr(skb)->h_proto = skb->protocol; + if (skb->mac_len) + eth_hdr(skb)->h_proto = skb->protocol; err = 0; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 94b8702..be980c1 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -30,7 +30,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) mtu = dst_mtu(skb_dst(skb)); if ((!skb_is_gso(skb) && skb->len > mtu) || - (skb_is_gso(skb) && skb_gso_network_seglen(skb) > ip_skb_dst_mtu(skb->sk, skb))) { + (skb_is_gso(skb) && + !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) { skb->protocol = htons(ETH_P_IP); if (skb->sk) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 05017e2..fbebda6 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,8 +100,10 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; + xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; xdst->u.rt.rt_table_id = rt->rt_table_id; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); + rt_add_uncached_list(&xdst->u.rt); return 0; } @@ -241,7 +243,8 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) struct xfrm_dst *xdst = (struct xfrm_dst *)dst; dst_destroy_metrics_generic(dst); - + if (xdst->u.rt.rt_uncached_list) + rt_del_uncached_list(&xdst->u.rt); xfrm_dst_destroy(xdst); } diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index fbf08ce..a9f7eca 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -146,10 +146,12 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct in6_addr *daddr; + struct in6_addr *daddr, old_daddr; + __be32 fl6_flowlabel = 0; + __be32 old_fl6_flowlabel; + __be16 old_dport; int addr_type; int err; - __be32 fl6_flowlabel = 0; if (usin->sin6_family == AF_INET) { if (__ipv6_only_sock(sk)) @@ -238,9 +240,13 @@ ipv4_connected: } } + /* save the current peer information before updating it */ + old_daddr = sk->sk_v6_daddr; + old_fl6_flowlabel = np->flow_label; + old_dport = inet->inet_dport; + sk->sk_v6_daddr = *daddr; np->flow_label = fl6_flowlabel; - inet->inet_dport = usin->sin6_port; /* @@ -250,11 +256,12 @@ ipv4_connected: err = ip6_datagram_dst_update(sk, true); if (err) { - /* Reset daddr and dport so that udp_v6_early_demux() - * fails to find this socket + /* Restore the socket peer info, to keep it consistent with + * the old socket state */ - memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr)); - inet->inet_dport = 0; + sk->sk_v6_daddr = old_daddr; + np->flow_label = old_fl6_flowlabel; + inet->inet_dport = old_dport; goto out; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3c35312..1bbd093 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -126,7 +126,8 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, struct ip6_tnl *t, *cand = NULL; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); int dev_type = (gre_proto == htons(ETH_P_TEB) || - gre_proto == htons(ETH_P_ERSPAN)) ? + gre_proto == htons(ETH_P_ERSPAN) || + gre_proto == htons(ETH_P_ERSPAN2)) ? ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; @@ -902,6 +903,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, truncate = true; } + if (skb_cow_head(skb, dev->needed_headroom)) + goto tx_err; + t->parms.o_flags &= ~TUNNEL_KEY; IPCB(skb)->flags = 0; @@ -944,6 +948,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); + } else { + goto tx_err; } } else { switch (skb->protocol) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 997c7f1..a8a9195 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -412,7 +412,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) if (skb->ignore_df) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 4b15fe9..6e0f21e 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1982,14 +1982,14 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - struct ip6_tnl *nt, *t; struct ip_tunnel_encap ipencap; + struct ip6_tnl *nt, *t; + int err; nt = netdev_priv(dev); if (ip6_tnl_netlink_encap_parms(data, &ipencap)) { - int err = ip6_tnl_encap_setup(nt, &ipencap); - + err = ip6_tnl_encap_setup(nt, &ipencap); if (err < 0) return err; } @@ -2005,7 +2005,11 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, return -EEXIST; } - return ip6_tnl_create2(dev); + err = ip6_tnl_create2(dev); + if (!err && tb[IFLA_MTU]) + ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + + return err; } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f61a5b6..ba5e04c 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1554,7 +1554,8 @@ static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, *(opt++) = (rd_len >> 3); opt += 6; - memcpy(opt, ipv6_hdr(orig_skb), rd_len - 8); + skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt, + rd_len - 8); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index d95ceca..531d695 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -21,18 +21,19 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); + struct sock *sk = sk_to_full_sk(skb->sk); unsigned int hh_len; struct dst_entry *dst; struct flowi6 fl6 = { - .flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, + .flowi6_oif = sk ? sk->sk_bound_dev_if : 0, .flowi6_mark = skb->mark, - .flowi6_uid = sock_net_uid(net, skb->sk), + .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, .saddr = iph->saddr, }; int err; - dst = ip6_route_output(net, skb->sk, &fl6); + dst = ip6_route_output(net, sk, &fl6); err = dst->error; if (err) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -50,7 +51,7 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) { skb_dst_set(skb, NULL); - dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0); + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); skb_dst_set(skb, dst); diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 94deb69..91ed25a 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -48,10 +48,6 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, } fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - if ((flags & XT_RPFILTER_LOOSE) == 0) { - fl6.flowi6_oif = dev->ifindex; - lookup_flags |= RT6_LOOKUP_F_IFACE; - } rt = (void *) ip6_route_lookup(net, &fl6, lookup_flags); if (rt->dst.error) diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index d346705..207cb35 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -178,7 +178,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if (skb->len <= mtu) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index bed57ee..6b7f075 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -99,6 +99,10 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff, target, maniptype)) return false; + + /* must reload, offset might have changed */ + ipv6h = (void *)skb->data + iphdroff; + manip_addr: if (maniptype == NF_NAT_MANIP_SRC) ipv6h->saddr = target->src.u3.in6; diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index cc5174c..62fc84d 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -180,7 +180,6 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, } *dest = 0; - again: rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, lookup_flags); if (rt->dst.error) goto put_rt_err; @@ -189,15 +188,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) goto put_rt_err; - if (oif && oif != rt->rt6i_idev->dev) { - /* multipath route? Try again with F_IFACE */ - if ((lookup_flags & RT6_LOOKUP_F_IFACE) == 0) { - lookup_flags |= RT6_LOOKUP_F_IFACE; - fl6.flowi6_oif = oif->ifindex; - ip6_rt_put(rt); - goto again; - } - } + if (oif && oif != rt->rt6i_idev->dev) + goto put_rt_err; switch (priv->result) { case NFT_FIB_RESULT_OIF: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9dcfadd..b0d5c64 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -128,7 +128,7 @@ struct uncached_list { static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); -static void rt6_uncached_list_add(struct rt6_info *rt) +void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); @@ -139,7 +139,7 @@ static void rt6_uncached_list_add(struct rt6_info *rt) spin_unlock_bh(&ul->lock); } -static void rt6_uncached_list_del(struct rt6_info *rt) +void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; @@ -1509,7 +1509,30 @@ static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) } } -static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) +static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) +{ + /* If the new MTU is lower than the route PMTU, this new MTU will be the + * lowest MTU in the path: always allow updating the route PMTU to + * reflect PMTU decreases. + * + * If the new MTU is higher, and the route PMTU is equal to the local + * MTU, this means the old MTU is the lowest in the path, so allow + * updating it: if other nodes now have lower MTUs, PMTU discovery will + * handle this. + */ + + if (dst_mtu(&rt->dst) >= mtu) + return true; + + if (dst_mtu(&rt->dst) == idev->cnf.mtu6) + return true; + + return false; +} + +static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1518,20 +1541,22 @@ static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); - if (bucket) { - for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { - hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { - struct rt6_info *entry = rt6_ex->rt6i; - /* For RTF_CACHE with rt6i_pmtu == 0 - * (i.e. a redirected route), - * the metrics of its rt->dst.from has already - * been updated. - */ - if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu) - entry->rt6i_pmtu = mtu; - } - bucket++; + if (!bucket) + return; + + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + + /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected + * route), the metrics of its rt->dst.from have already + * been updated. + */ + if (entry->rt6i_pmtu && + rt6_mtu_change_route_allowed(idev, entry, mtu)) + entry->rt6i_pmtu = mtu; } + bucket++; } } @@ -3809,25 +3834,13 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) Since RFC 1981 doesn't include administrative MTU increase update PMTU increase is a MUST. (i.e. jumbo frame) */ - /* - If new MTU is less than route PMTU, this new MTU will be the - lowest MTU in the path, update the route PMTU to reflect PMTU - decreases; if new MTU is greater than route PMTU, and the - old MTU is the lowest MTU in the path, update the route PMTU - to reflect the increase. In this case if the other nodes' MTU - also have the lowest MTU, TOO BIG MESSAGE will be lead to - PMTU discovery. - */ if (rt->dst.dev == arg->dev && - dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { spin_lock_bh(&rt6_exception_lock); - if (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + if (dst_metric_raw(&rt->dst, RTAX_MTU) && + rt6_mtu_change_route_allowed(idev, rt, arg->mtu)) dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); - } - rt6_exceptions_update_pmtu(rt, arg->mtu); + rt6_exceptions_update_pmtu(idev, rt, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } return 0; @@ -4099,6 +4112,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, r_cfg.fc_encap_type = nla_get_u16(nla); } + r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); rt = ip6_route_info_create(&r_cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index bd6cc68..7a78dcf 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -93,7 +93,8 @@ static void set_tun_src(struct net *net, struct net_device *dev, /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) { - struct net *net = dev_net(skb_dst(skb)->dev); + struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(dst->dev); struct ipv6hdr *hdr, *inner_hdr; struct ipv6_sr_hdr *isrh; int hdrlen, tot_len, err; @@ -134,7 +135,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) isrh->nexthdr = proto; hdr->daddr = isrh->segments[isrh->first_segment]; - set_tun_src(net, skb->dev, &hdr->daddr, &hdr->saddr); + set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { @@ -418,7 +419,7 @@ static int seg6_build_state(struct nlattr *nla, slwt = seg6_lwt_lwtunnel(newts); - err = dst_cache_init(&slwt->cache, GFP_KERNEL); + err = dst_cache_init(&slwt->cache, GFP_ATOMIC); if (err) { kfree(newts); return err; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3a1775a..0195598 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1578,6 +1578,13 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; + if (tb[IFLA_MTU]) { + u32 mtu = nla_get_u32(tb[IFLA_MTU]); + + if (mtu >= IPV6_MIN_MTU && mtu <= 0xFFF8 - dev->hard_header_len) + dev->mtu = mtu; + } + #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) err = ipip6_tunnel_update_6rd(nt, &ip6rd); diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index bb935a3..de1b0b8 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -92,7 +92,8 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) skb_reset_network_header(skb); skb_mac_header_rebuild(skb); - eth_hdr(skb)->h_proto = skb->protocol; + if (skb->mac_len) + eth_hdr(skb)->h_proto = skb->protocol; err = 0; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8ae87d4..5959ce9 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -82,7 +82,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) && - skb_gso_network_seglen(skb) > ip6_skb_dst_mtu(skb))) { + !skb_gso_validate_network_len(skb, ip6_skb_dst_mtu(skb)))) { skb->dev = dst->dev; skb->protocol = htons(ETH_P_IPV6); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 09fb44e..416fe67 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -113,6 +113,9 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; xdst->u.rt6.rt6i_src = rt->rt6i_src; + INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached); + rt6_uncached_list_add(&xdst->u.rt6); + atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache); return 0; } @@ -244,6 +247,8 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); + if (xdst->u.rt6.rt6i_uncached_list) + rt6_uncached_list_del(&xdst->u.rt6); xfrm_dst_destroy(xdst); } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 1e8cc7b..9e2643a 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -2433,9 +2433,11 @@ static int afiucv_iucv_init(void) af_iucv_dev->driver = &af_iucv_driver; err = device_register(af_iucv_dev); if (err) - goto out_driver; + goto out_iucv_dev; return 0; +out_iucv_dev: + put_device(af_iucv_dev); out_driver: driver_unregister(&af_iucv_driver); out_iucv: diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index f297d53..34355fd 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1381,24 +1381,32 @@ static int kcm_attach(struct socket *sock, struct socket *csock, .parse_msg = kcm_parse_func_strparser, .read_sock_done = kcm_read_sock_done, }; - int err; + int err = 0; csk = csock->sk; if (!csk) return -EINVAL; + lock_sock(csk); + /* Only allow TCP sockets to be attached for now */ if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) || - csk->sk_protocol != IPPROTO_TCP) - return -EOPNOTSUPP; + csk->sk_protocol != IPPROTO_TCP) { + err = -EOPNOTSUPP; + goto out; + } /* Don't allow listeners or closed sockets */ - if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) - return -EOPNOTSUPP; + if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) { + err = -EOPNOTSUPP; + goto out; + } psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); - if (!psock) - return -ENOMEM; + if (!psock) { + err = -ENOMEM; + goto out; + } psock->mux = mux; psock->sk = csk; @@ -1407,7 +1415,7 @@ static int kcm_attach(struct socket *sock, struct socket *csock, err = strp_init(&psock->strp, csk, &cb); if (err) { kmem_cache_free(kcm_psockp, psock); - return err; + goto out; } write_lock_bh(&csk->sk_callback_lock); @@ -1419,7 +1427,8 @@ static int kcm_attach(struct socket *sock, struct socket *csock, write_unlock_bh(&csk->sk_callback_lock); strp_done(&psock->strp); kmem_cache_free(kcm_psockp, psock); - return -EALREADY; + err = -EALREADY; + goto out; } psock->save_data_ready = csk->sk_data_ready; @@ -1455,7 +1464,10 @@ static int kcm_attach(struct socket *sock, struct socket *csock, /* Schedule RX work in case there are already bytes queued */ strp_check_rcv(&psock->strp); - return 0; +out: + release_sock(csk); + + return err; } static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info) @@ -1507,6 +1519,7 @@ static void kcm_unattach(struct kcm_psock *psock) if (WARN_ON(psock->rx_kcm)) { write_unlock_bh(&csk->sk_callback_lock); + release_sock(csk); return; } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 194a748..14b67df 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -111,6 +111,13 @@ struct l2tp_net { spinlock_t l2tp_session_hlist_lock; }; +#if IS_ENABLED(CONFIG_IPV6) +static bool l2tp_sk_is_v6(struct sock *sk) +{ + return sk->sk_family == PF_INET6 && + !ipv6_addr_v4mapped(&sk->sk_v6_daddr); +} +#endif static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) { @@ -136,51 +143,6 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) } -/* Lookup the tunnel socket, possibly involving the fs code if the socket is - * owned by userspace. A struct sock returned from this function must be - * released using l2tp_tunnel_sock_put once you're done with it. - */ -static struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) -{ - int err = 0; - struct socket *sock = NULL; - struct sock *sk = NULL; - - if (!tunnel) - goto out; - - if (tunnel->fd >= 0) { - /* Socket is owned by userspace, who might be in the process - * of closing it. Look the socket up using the fd to ensure - * consistency. - */ - sock = sockfd_lookup(tunnel->fd, &err); - if (sock) - sk = sock->sk; - } else { - /* Socket is owned by kernelspace */ - sk = tunnel->sock; - sock_hold(sk); - } - -out: - return sk; -} - -/* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */ -static void l2tp_tunnel_sock_put(struct sock *sk) -{ - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); - if (tunnel) { - if (tunnel->fd >= 0) { - /* Socket is owned by userspace */ - sockfd_put(sk->sk_socket); - } - sock_put(sk); - } - sock_put(sk); -} - /* Session hash list. * The session_id SHOULD be random according to RFC2661, but several * L2TP implementations (Cisco and Microsoft) use incrementing @@ -193,6 +155,13 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)]; } +void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) +{ + sock_put(tunnel->sock); + /* the tunnel is freed in the socket destructor */ +} +EXPORT_SYMBOL(l2tp_tunnel_free); + /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) { @@ -345,13 +314,11 @@ int l2tp_session_register(struct l2tp_session *session, } l2tp_tunnel_inc_refcount(tunnel); - sock_hold(tunnel->sock); hlist_add_head_rcu(&session->global_hlist, g_head); spin_unlock_bh(&pn->l2tp_session_hlist_lock); } else { l2tp_tunnel_inc_refcount(tunnel); - sock_hold(tunnel->sock); } hlist_add_head(&session->hlist, head); @@ -969,7 +936,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_tunnel *tunnel; - tunnel = l2tp_sock_to_tunnel(sk); + tunnel = l2tp_tunnel(sk); if (tunnel == NULL) goto pass_up; @@ -977,13 +944,10 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) tunnel->name, skb->len); if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook)) - goto pass_up_put; + goto pass_up; - sock_put(sk); return 0; -pass_up_put: - sock_put(sk); pass_up: return 1; } @@ -1092,7 +1056,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->ignore_df = 1; #if IS_ENABLED(CONFIG_IPV6) - if (tunnel->sock->sk_family == PF_INET6 && !tunnel->v4mapped) + if (l2tp_sk_is_v6(tunnel->sock)) error = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif @@ -1155,6 +1119,15 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len goto out_unlock; } + /* The user-space may change the connection status for the user-space + * provided socket at run time: we must check it under the socket lock + */ + if (tunnel->fd >= 0 && sk->sk_state != TCP_ESTABLISHED) { + kfree_skb(skb); + ret = NET_XMIT_DROP; + goto out_unlock; + } + /* Get routing info from the tunnel socket */ skb_dst_drop(skb); skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0))); @@ -1174,7 +1147,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) + if (l2tp_sk_is_v6(sk)) udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr, &sk->sk_v6_daddr, udp_len); @@ -1207,14 +1180,12 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); static void l2tp_tunnel_destruct(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); - struct l2tp_net *pn; if (tunnel == NULL) goto end; l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name); - /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: @@ -1231,18 +1202,11 @@ static void l2tp_tunnel_destruct(struct sock *sk) sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; - /* Remove the tunnel struct from the tunnel list */ - pn = l2tp_pernet(tunnel->l2tp_net); - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_del_rcu(&tunnel->list); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - - tunnel->sock = NULL; - l2tp_tunnel_dec_refcount(tunnel); - /* Call the original destructor */ if (sk->sk_destruct) (*sk->sk_destruct)(sk); + + kfree_rcu(tunnel, rcu); end: return; } @@ -1303,49 +1267,43 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall); /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } + struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); + + if (tunnel) + l2tp_tunnel_delete(tunnel); } /* Workqueue tunnel deletion function */ static void l2tp_tunnel_del_work(struct work_struct *work) { - struct l2tp_tunnel *tunnel = NULL; - struct socket *sock = NULL; - struct sock *sk = NULL; - - tunnel = container_of(work, struct l2tp_tunnel, del_work); + struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel, + del_work); + struct sock *sk = tunnel->sock; + struct socket *sock = sk->sk_socket; + struct l2tp_net *pn; l2tp_tunnel_closeall(tunnel); - sk = l2tp_tunnel_sock_lookup(tunnel); - if (!sk) - goto out; - - sock = sk->sk_socket; - - /* If the tunnel socket was created by userspace, then go through the - * inet layer to shut the socket down, and let userspace close it. - * Otherwise, if we created the socket directly within the kernel, use + /* If the tunnel socket was created within the kernel, use * the sk API to release it here. - * In either case the tunnel resources are freed in the socket - * destructor when the tunnel socket goes away. */ - if (tunnel->fd >= 0) { - if (sock) - inet_shutdown(sock, 2); - } else { + if (tunnel->fd < 0) { if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } } - l2tp_tunnel_sock_put(sk); -out: + /* Remove the tunnel struct from the tunnel list */ + pn = l2tp_pernet(tunnel->l2tp_net); + spin_lock_bh(&pn->l2tp_tunnel_list_lock); + list_del_rcu(&tunnel->list); + spin_unlock_bh(&pn->l2tp_tunnel_list_lock); + + /* drop initial ref */ + l2tp_tunnel_dec_refcount(tunnel); + + /* drop workqueue ref */ l2tp_tunnel_dec_refcount(tunnel); } @@ -1515,9 +1473,14 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 encap = cfg->encap; /* Quick sanity checks */ + err = -EPROTONOSUPPORT; + if (sk->sk_type != SOCK_DGRAM) { + pr_debug("tunl %hu: fd %d wrong socket type\n", + tunnel_id, fd); + goto err; + } switch (encap) { case L2TP_ENCAPTYPE_UDP: - err = -EPROTONOSUPPORT; if (sk->sk_protocol != IPPROTO_UDP) { pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n", tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP); @@ -1525,7 +1488,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 } break; case L2TP_ENCAPTYPE_IP: - err = -EPROTONOSUPPORT; if (sk->sk_protocol != IPPROTO_L2TP) { pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n", tunnel_id, fd, sk->sk_protocol, IPPROTO_L2TP); @@ -1565,24 +1527,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 if (cfg != NULL) tunnel->debug = cfg->debug; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - - if (ipv6_addr_v4mapped(&np->saddr) && - ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { - struct inet_sock *inet = inet_sk(sk); - - tunnel->v4mapped = true; - inet->inet_saddr = np->saddr.s6_addr32[3]; - inet->inet_rcv_saddr = sk->sk_v6_rcv_saddr.s6_addr32[3]; - inet->inet_daddr = sk->sk_v6_daddr.s6_addr32[3]; - } else { - tunnel->v4mapped = false; - } - } -#endif - /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */ tunnel->encap = encap; if (encap == L2TP_ENCAPTYPE_UDP) { @@ -1598,13 +1542,22 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 sk->sk_user_data = tunnel; } + /* Bump the reference count. The tunnel context is deleted + * only when this drops to zero. A reference is also held on + * the tunnel socket to ensure that it is not released while + * the tunnel is extant. Must be done before sk_destruct is + * set. + */ + refcount_set(&tunnel->ref_count, 1); + sock_hold(sk); + tunnel->sock = sk; + tunnel->fd = fd; + /* Hook on the tunnel socket destructor so that we can cleanup * if the tunnel socket goes away. */ tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; - tunnel->sock = sk; - tunnel->fd = fd; lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; @@ -1614,11 +1567,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 /* Add tunnel to our list */ INIT_LIST_HEAD(&tunnel->list); - - /* Bump the reference count. The tunnel context is deleted - * only when this drops to zero. Must be done before list insertion - */ - refcount_set(&tunnel->ref_count, 1); spin_lock_bh(&pn->l2tp_tunnel_list_lock); list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); spin_unlock_bh(&pn->l2tp_tunnel_list_lock); @@ -1659,8 +1607,6 @@ void l2tp_session_free(struct l2tp_session *session) if (tunnel) { BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); - sock_put(tunnel->sock); - session->tunnel = NULL; l2tp_tunnel_dec_refcount(tunnel); } diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 9bbee90..2718d0b 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -188,9 +188,6 @@ struct l2tp_tunnel { struct sock *sock; /* Parent socket */ int fd; /* Parent fd, if tunnel socket * was created by userspace */ -#if IS_ENABLED(CONFIG_IPV6) - bool v4mapped; -#endif struct work_struct del_work; @@ -214,27 +211,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session) return &session->priv[0]; } -static inline struct l2tp_tunnel *l2tp_sock_to_tunnel(struct sock *sk) -{ - struct l2tp_tunnel *tunnel; - - if (sk == NULL) - return NULL; - - sock_hold(sk); - tunnel = (struct l2tp_tunnel *)(sk->sk_user_data); - if (tunnel == NULL) { - sock_put(sk); - goto out; - } - - BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); - -out: - return tunnel; -} - struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); +void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); struct l2tp_session *l2tp_session_get(const struct net *net, struct l2tp_tunnel *tunnel, @@ -283,7 +261,7 @@ static inline void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) static inline void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) { if (refcount_dec_and_test(&tunnel->ref_count)) - kfree_rcu(tunnel, rcu); + l2tp_tunnel_free(tunnel); } /* Session reference counts. Incremented when code obtains a reference diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index ff61124..3428fba 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -234,17 +234,13 @@ static void l2tp_ip_close(struct sock *sk, long timeout) static void l2tp_ip_destroy_sock(struct sock *sk) { struct sk_buff *skb; - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + struct l2tp_tunnel *tunnel = sk->sk_user_data; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } - - sk_refcnt_debug_dec(sk); + if (tunnel) + l2tp_tunnel_delete(tunnel); } static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 1923446..6f009ea 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -248,16 +248,14 @@ static void l2tp_ip6_close(struct sock *sk, long timeout) static void l2tp_ip6_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + struct l2tp_tunnel *tunnel = sk->sk_user_data; lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } + if (tunnel) + l2tp_tunnel_delete(tunnel); inet6_destroy_sock(sk); } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 59f246d..3b02f24 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -416,20 +416,28 @@ abort: * Session (and tunnel control) socket create/destroy. *****************************************************************************/ +static void pppol2tp_put_sk(struct rcu_head *head) +{ + struct pppol2tp_session *ps; + + ps = container_of(head, typeof(*ps), rcu); + sock_put(ps->__sk); +} + /* Called by l2tp_core when a session socket is being closed. */ static void pppol2tp_session_close(struct l2tp_session *session) { - struct sock *sk; - - BUG_ON(session->magic != L2TP_SESSION_MAGIC); + struct pppol2tp_session *ps; - sk = pppol2tp_session_get_sock(session); - if (sk) { - if (sk->sk_socket) - inet_shutdown(sk->sk_socket, SEND_SHUTDOWN); - sock_put(sk); - } + ps = l2tp_session_priv(session); + mutex_lock(&ps->sk_lock); + ps->__sk = rcu_dereference_protected(ps->sk, + lockdep_is_held(&ps->sk_lock)); + RCU_INIT_POINTER(ps->sk, NULL); + if (ps->__sk) + call_rcu(&ps->rcu, pppol2tp_put_sk); + mutex_unlock(&ps->sk_lock); } /* Really kill the session socket. (Called from sock_put() if @@ -449,14 +457,6 @@ static void pppol2tp_session_destruct(struct sock *sk) } } -static void pppol2tp_put_sk(struct rcu_head *head) -{ - struct pppol2tp_session *ps; - - ps = container_of(head, typeof(*ps), rcu); - sock_put(ps->__sk); -} - /* Called when the PPPoX socket (session) is closed. */ static int pppol2tp_release(struct socket *sock) @@ -480,26 +480,17 @@ static int pppol2tp_release(struct socket *sock) sock_orphan(sk); sock->sk = NULL; + /* If the socket is associated with a session, + * l2tp_session_delete will call pppol2tp_session_close which + * will drop the session's ref on the socket. + */ session = pppol2tp_sock_to_session(sk); - - if (session != NULL) { - struct pppol2tp_session *ps; - + if (session) { l2tp_session_delete(session); - - ps = l2tp_session_priv(session); - mutex_lock(&ps->sk_lock); - ps->__sk = rcu_dereference_protected(ps->sk, - lockdep_is_held(&ps->sk_lock)); - RCU_INIT_POINTER(ps->sk, NULL); - mutex_unlock(&ps->sk_lock); - call_rcu(&ps->rcu, pppol2tp_put_sk); - - /* Rely on the sock_put() call at the end of the function for - * dropping the reference held by pppol2tp_sock_to_session(). - * The last reference will be dropped by pppol2tp_put_sk(). - */ + /* drop the ref obtained by pppol2tp_sock_to_session */ + sock_put(sk); } + release_sock(sk); /* This will delete the session context via @@ -796,6 +787,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, out_no_ppp: /* This is how we get the session context from the socket. */ + sock_hold(sk); sk->sk_user_data = session; rcu_assign_pointer(ps->sk, sk); mutex_unlock(&ps->sk_lock); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 1f466d1..94c7ee9 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -212,6 +212,7 @@ static const char *hw_flag_names[] = { FLAG(REPORTS_LOW_ACK), FLAG(SUPPORTS_TX_FRAG), FLAG(SUPPORTS_TDLS_BUFFER_STA), + FLAG(DOESNT_SUPPORT_QOS_NDP), #undef FLAG }; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 39b660b..5f303ab 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -896,7 +896,8 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_hdr_3addr *nullfunc; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, true); + skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, + !ieee80211_hw_check(&local->hw, DOESNT_SUPPORT_QOS_NDP)); if (!skb) return; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fd58061..56fe16b 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3921,7 +3921,7 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, if ((hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS)) != fast_rx->expected_ds_bits) - goto drop; + return false; /* assign the key to drop unencrypted frames (later) * and strip the IV/MIC if necessary diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 25904af..6972250 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3574,6 +3574,14 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, if (!IS_ERR_OR_NULL(sta)) { struct ieee80211_fast_tx *fast_tx; + /* We need a bit of data queued to build aggregates properly, so + * instruct the TCP stack to allow more than a single ms of data + * to be queued in the stack. The value is a bit-shift of 1 + * second, so 8 is ~4ms of queued data. Only affects local TCP + * sockets. + */ + sk_pacing_shift_update(skb->sk, 8); + fast_tx = rcu_dereference(sta->fast_tx); if (fast_tx && diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index e545a3c..7a4de6d 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -122,7 +122,7 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) if (skb->len <= mtu) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 3e17d32..58d5d05 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -260,7 +260,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, buf_len = strlen(buf); ct = nf_ct_get(skb, &ctinfo); - if (ct && (ct->status & IPS_NAT_MASK)) { + if (ct) { bool mangled; /* If mangling fails this function will return 0 diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8b9fe30..c4acc73 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5037,9 +5037,9 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nf_flowtable_type *type; + struct nft_flowtable *flowtable, *ft; u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; - struct nft_flowtable *flowtable; struct nft_table *table; struct nft_ctx ctx; int err, i, k; @@ -5099,6 +5099,22 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, goto err3; for (i = 0; i < flowtable->ops_len; i++) { + if (!flowtable->ops[i].dev) + continue; + + list_for_each_entry(ft, &table->flowtables, list) { + for (k = 0; k < ft->ops_len; k++) { + if (!ft->ops[k].dev) + continue; + + if (flowtable->ops[i].dev == ft->ops[k].dev && + flowtable->ops[i].pf == ft->ops[k].pf) { + err = -EBUSY; + goto err4; + } + } + } + err = nf_register_net_hook(net, &flowtable->ops[i]); if (err < 0) goto err4; @@ -5120,7 +5136,7 @@ err5: i = flowtable->ops_len; err4: for (k = i - 1; k >= 0; k--) - nf_unregister_net_hook(net, &flowtable->ops[i]); + nf_unregister_net_hook(net, &flowtable->ops[k]); kfree(flowtable->ops); err3: @@ -5145,6 +5161,11 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, struct nft_table *table; struct nft_ctx ctx; + if (!nla[NFTA_FLOWTABLE_TABLE] || + (!nla[NFTA_FLOWTABLE_NAME] && + !nla[NFTA_FLOWTABLE_HANDLE])) + return -EINVAL; + table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, genmask); if (IS_ERR(table)) @@ -5402,6 +5423,7 @@ err: static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { cancel_delayed_work_sync(&flowtable->data.gc_work); + kfree(flowtable->ops); kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); rhashtable_destroy(&flowtable->data.rhashtable); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 3f1624e..d40591f 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -674,7 +674,7 @@ static const struct nft_set_ops * nft_hash_select_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, u32 flags) { - if (desc->size) { + if (desc->size && !(flags & NFT_SET_TIMEOUT)) { switch (desc->klen) { case 4: return &nft_hash_fast_ops; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index fa1655a..4aa01c9 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -423,6 +423,36 @@ textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) return buf; } +/** + * xt_check_proc_name - check that name is suitable for /proc file creation + * + * @name: file name candidate + * @size: length of buffer + * + * some x_tables modules wish to create a file in /proc. + * This function makes sure that the name is suitable for this + * purpose, it checks that name is NUL terminated and isn't a 'special' + * name, like "..". + * + * returns negative number on error or 0 if name is useable. + */ +int xt_check_proc_name(const char *name, unsigned int size) +{ + if (name[0] == '\0') + return -EINVAL; + + if (strnlen(name, size) == size) + return -ENAMETOOLONG; + + if (strcmp(name, ".") == 0 || + strcmp(name, "..") == 0 || + strchr(name, '/')) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL(xt_check_proc_name); + int xt_check_match(struct xt_mtchk_param *par, unsigned int size, u_int8_t proto, bool inv_proto) { diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 66f5aca..3360f13 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -917,8 +917,9 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) struct hashlimit_cfg3 cfg = {}; int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); @@ -935,8 +936,9 @@ static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) struct hashlimit_cfg3 cfg = {}; int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); @@ -950,9 +952,11 @@ static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) static int hashlimit_mt_check(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo3 *info = par->matchinfo; + int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg, info->name, 3); diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 6d232d1..81ee1d6 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -361,9 +361,9 @@ static int recent_mt_check(const struct xt_mtchk_param *par, info->hit_count, XT_RECENT_MAX_NSTAMPS - 1); return -EINVAL; } - if (info->name[0] == '\0' || - strnlen(info->name, XT_RECENT_NAME_LEN) == XT_RECENT_NAME_LEN) - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; if (ip_pkt_list_tot && info->hit_count < ip_pkt_list_tot) nstamp_mask = roundup_pow_of_two(ip_pkt_list_tot) - 1; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 6f02499..b9ce82c 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1106,7 +1106,7 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, if (!err) delivered = true; else if (err != -ESRCH) - goto error; + return err; return delivered ? 0 : -ESRCH; error: kfree_skb(skb); diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 04b9428..b891a91 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -242,14 +242,20 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) band->type = nla_get_u32(attr[OVS_BAND_ATTR_TYPE]); band->rate = nla_get_u32(attr[OVS_BAND_ATTR_RATE]); + if (band->rate == 0) { + err = -EINVAL; + goto exit_free_meter; + } + band->burst_size = nla_get_u32(attr[OVS_BAND_ATTR_BURST]); /* Figure out max delta_t that is enough to fill any bucket. * Keep max_delta_t size to the bucket units: * pkts => 1/1000 packets, kilobits => bits. + * + * Start with a full bucket. */ - band_max_delta_t = (band->burst_size + band->rate) * 1000; - /* Start with a full bucket. */ - band->bucket = band_max_delta_t; + band->bucket = (band->burst_size + band->rate) * 1000; + band_max_delta_t = band->bucket / band->rate; if (band_max_delta_t > meter->max_delta_t) meter->max_delta_t = band_max_delta_t; band++; diff --git a/net/qrtr/smd.c b/net/qrtr/smd.c index 50615d5..9cf089b 100644 --- a/net/qrtr/smd.c +++ b/net/qrtr/smd.c @@ -114,5 +114,6 @@ static struct rpmsg_driver qcom_smd_qrtr_driver = { module_rpmsg_driver(qcom_smd_qrtr_driver); +MODULE_ALIAS("rpmsg:IPCRTR"); MODULE_DESCRIPTION("Qualcomm IPC-Router SMD interface driver"); MODULE_LICENSE("GPL v2"); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index c061d6e..2257118 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006 Oracle. All rights reserved. + * Copyright (c) 2006, 2018 Oracle. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -142,12 +142,20 @@ int rds_tcp_accept_one(struct socket *sock) if (ret) goto out; - new_sock->type = sock->type; - new_sock->ops = sock->ops; ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true); if (ret < 0) goto out; + /* sock_create_lite() does not get a hold on the owner module so we + * need to do it here. Note that sock_release() uses sock->ops to + * determine if it needs to decrement the reference count. So set + * sock->ops after calling accept() in case that fails. And there's + * no need to do try_module_get() as the listener should have a hold + * already. + */ + new_sock->ops = sock->ops; + __module_get(new_sock->ops->owner); + ret = rds_tcp_keepalive(new_sock); if (ret < 0) goto out; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index b3f2c15..9d2cabf 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -352,7 +352,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, return res; out: if (res == ACT_P_CREATED) - tcf_idr_cleanup(*act, est); + tcf_idr_release(*act, bind); return ret; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index b7ba9b0..2a5c8fd 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -350,7 +350,7 @@ static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, { struct sctphdr *sctph; - if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) + if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return 1; sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph)); @@ -626,7 +626,8 @@ static void tcf_csum_cleanup(struct tc_action *a) struct tcf_csum_params *params; params = rcu_dereference_protected(p->params, 1); - kfree_rcu(params, rcu); + if (params) + kfree_rcu(params, rcu); } static int tcf_csum_walker(struct net *net, struct sk_buff *skb, diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 06e380a..7e06b9b 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -80,9 +80,12 @@ static void ipt_destroy_target(struct xt_entry_target *t) static void tcf_ipt_release(struct tc_action *a) { struct tcf_ipt *ipt = to_ipt(a); - ipt_destroy_target(ipt->tcfi_t); + + if (ipt->tcfi_t) { + ipt_destroy_target(ipt->tcfi_t); + kfree(ipt->tcfi_t); + } kfree(ipt->tcfi_tname); - kfree(ipt->tcfi_t); } static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { @@ -187,7 +190,7 @@ err2: kfree(tname); err1: if (ret == ACT_P_CREATED) - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return err; } diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 349beaf..fef0883 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -176,7 +176,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, p = to_pedit(*a); keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); kfree(keys_ex); return -ENOMEM; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 95d3c90..faebf82 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -194,7 +194,7 @@ failure: qdisc_put_rtab(P_tab); qdisc_put_rtab(R_tab); if (ret == ACT_P_CREATED) - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return err; } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 1ba0df2..74c5d7e 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -103,7 +103,8 @@ static void tcf_sample_cleanup(struct tc_action *a) psample_group = rtnl_dereference(s->psample_group); RCU_INIT_POINTER(s->psample_group, NULL); - psample_group_put(psample_group); + if (psample_group) + psample_group_put(psample_group); } static bool tcf_sample_dev_ok_push(struct net_device *dev) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 425eac1..b1f3806 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -121,7 +121,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, d = to_defact(*a); ret = alloc_defdata(d, defdata); if (ret < 0) { - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return ret; } d->tcf_action = parm->action; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index fa97526..7b0700f 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -152,7 +152,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, ASSERT_RTNL(); p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL); if (unlikely(!p)) { - if (ovr) + if (ret == ACT_P_CREATED) tcf_idr_release(*a, bind); return -ENOMEM; } @@ -190,7 +190,8 @@ static void tcf_skbmod_cleanup(struct tc_action *a) struct tcf_skbmod_params *p; p = rcu_dereference_protected(d->skbmod_p, 1); - kfree_rcu(p, rcu); + if (p) + kfree_rcu(p, rcu); } static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 0e23aac..1281ca46 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -153,6 +153,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; break; default: + ret = -EINVAL; goto err_out; } @@ -207,11 +208,12 @@ static void tunnel_key_release(struct tc_action *a) struct tcf_tunnel_key_params *params; params = rcu_dereference_protected(t->params, 1); + if (params) { + if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) + dst_release(¶ms->tcft_enc_metadata->dst); - if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) - dst_release(¶ms->tcft_enc_metadata->dst); - - kfree_rcu(params, rcu); + kfree_rcu(params, rcu); + } } static int tunnel_key_dump_addresses(struct sk_buff *skb, diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index e1a1b3f..c49cb61 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -195,7 +195,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, ASSERT_RTNL(); p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) { - if (ovr) + if (ret == ACT_P_CREATED) tcf_idr_release(*a, bind); return -ENOMEM; } @@ -225,7 +225,8 @@ static void tcf_vlan_cleanup(struct tc_action *a) struct tcf_vlan_params *p; p = rcu_dereference_protected(v->vlan_p, 1); - kfree_rcu(p, rcu); + if (p) + kfree_rcu(p, rcu); } static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 190570f..7e3fbe9 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -106,6 +106,14 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, __skb_queue_tail(&q->skb_bad_txq, skb); + if (qdisc_is_percpu_stats(q)) { + qdisc_qstats_cpu_backlog_inc(q, skb); + qdisc_qstats_cpu_qlen_inc(q); + } else { + qdisc_qstats_backlog_inc(q, skb); + q->q.qlen++; + } + if (lock) spin_unlock(lock); } @@ -196,14 +204,6 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, break; if (unlikely(skb_get_queue_mapping(nskb) != mapping)) { qdisc_enqueue_skb_bad_txq(q, nskb); - - if (qdisc_is_percpu_stats(q)) { - qdisc_qstats_cpu_backlog_inc(q, nskb); - qdisc_qstats_cpu_qlen_inc(q); - } else { - qdisc_qstats_backlog_inc(q, nskb); - q->q.qlen++; - } break; } skb->next = nskb; @@ -628,6 +628,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, int band = prio2band[skb->priority & TC_PRIO_MAX]; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct skb_array *q = band2list(priv, band); + unsigned int pkt_len = qdisc_pkt_len(skb); int err; err = skb_array_produce(q, skb); @@ -636,7 +637,10 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, return qdisc_drop_cpu(skb, qdisc, to_free); qdisc_qstats_cpu_qlen_inc(qdisc); - qdisc_qstats_cpu_backlog_inc(qdisc, skb); + /* Note: skb can not be used after skb_array_produce(), + * so we better not use qdisc_qstats_cpu_backlog_inc() + */ + this_cpu_add(qdisc->cpu_qstats->backlog, pkt_len); return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 7c179ad..7d6801f 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -509,7 +509,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, } if (unlikely(sch->q.qlen >= sch->limit)) - return qdisc_drop(skb, sch, to_free); + return qdisc_drop_all(skb, sch, to_free); qdisc_qstats_backlog_inc(sch, skb); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 229172d..03225a8 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -188,7 +188,8 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, int ret; if (qdisc_pkt_len(skb) > q->max_size) { - if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size) + if (skb_is_gso(skb) && + skb_gso_validate_mac_len(skb, q->max_size)) return tbf_segment(skb, sch, to_free); return qdisc_drop(skb, sch, to_free); } diff --git a/net/sctp/input.c b/net/sctp/input.c index 0247cc4..b381d78 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -106,6 +106,7 @@ int sctp_rcv(struct sk_buff *skb) int family; struct sctp_af *af; struct net *net = dev_net(skb->dev); + bool is_gso = skb_is_gso(skb) && skb_is_gso_sctp(skb); if (skb->pkt_type != PACKET_HOST) goto discard_it; @@ -123,8 +124,7 @@ int sctp_rcv(struct sk_buff *skb) * it's better to just linearize it otherwise crc computing * takes longer. */ - if ((!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && - skb_linearize(skb)) || + if ((!is_gso && skb_linearize(skb)) || !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; @@ -135,7 +135,7 @@ int sctp_rcv(struct sk_buff *skb) if (skb_csum_unnecessary(skb)) __skb_decr_checksum_unnecessary(skb); else if (!sctp_checksum_disable && - !(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && + !is_gso && sctp_rcv_checksum(net, skb) < 0) goto discard_it; skb->csum_valid = 1; @@ -1218,7 +1218,7 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, * issue as packets hitting this are mostly INIT or INIT-ACK and * those cannot be on GSO-style anyway. */ - if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) + if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return NULL; ch = (struct sctp_chunkhdr *)skb->data; diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 4839255..23ebc53 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -170,7 +170,7 @@ next_chunk: chunk = list_entry(entry, struct sctp_chunk, list); - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) { + if (skb_is_gso(chunk->skb) && skb_is_gso_sctp(chunk->skb)) { /* GSO-marked skbs but without frags, handle * them normally */ diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 35bc710..123e9f2 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -45,7 +45,7 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb, struct sk_buff *segs = ERR_PTR(-EINVAL); struct sctphdr *sh; - if (!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP)) + if (!skb_is_gso_sctp(skb)) goto out; sh = sctp_hdr(skb); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index da1a5cd..1e0d780 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -978,10 +978,6 @@ out: lsmc->clcsock = NULL; } release_sock(lsk); - /* no more listening, wake up smc_close_wait_listen_clcsock and - * accept - */ - lsk->sk_state_change(lsk); sock_put(&lsmc->sk); /* sock_hold in smc_listen */ } @@ -1406,8 +1402,10 @@ static int smc_create(struct net *net, struct socket *sock, int protocol, smc->use_fallback = false; /* assume rdma capability first */ rc = sock_create_kern(net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &smc->clcsock); - if (rc) + if (rc) { sk_common_release(sk); + goto out; + } smc->sk.sk_sndbuf = max(smc->clcsock->sk->sk_sndbuf, SMC_BUF_MIN_SIZE); smc->sk.sk_rcvbuf = max(smc->clcsock->sk->sk_rcvbuf, SMC_BUF_MIN_SIZE); diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 3cd086e..b42395d 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -269,7 +269,7 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf) if (wc->byte_len < offsetof(struct smc_cdc_msg, reserved)) return; /* short message */ - if (cdc->len != sizeof(*cdc)) + if (cdc->len != SMC_WR_TX_SIZE) return; /* invalid message */ smc_cdc_msg_recv(cdc, link, wc->wr_id); } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index e339c01..fa41d98 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -30,27 +30,6 @@ static void smc_close_cleanup_listen(struct sock *parent) smc_close_non_accepted(sk); } -static void smc_close_wait_listen_clcsock(struct smc_sock *smc) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - struct sock *sk = &smc->sk; - signed long timeout; - - timeout = SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME; - add_wait_queue(sk_sleep(sk), &wait); - do { - release_sock(sk); - if (smc->clcsock) - timeout = wait_woken(&wait, TASK_UNINTERRUPTIBLE, - timeout); - sched_annotate_sleep(); - lock_sock(sk); - if (!smc->clcsock) - break; - } while (timeout); - remove_wait_queue(sk_sleep(sk), &wait); -} - /* wait for sndbuf data being transmitted */ static void smc_close_stream_wait(struct smc_sock *smc, long timeout) { @@ -204,9 +183,11 @@ again: rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); /* wake up kernel_accept of smc_tcp_listen_worker */ smc->clcsock->sk->sk_data_ready(smc->clcsock->sk); - smc_close_wait_listen_clcsock(smc); } smc_close_cleanup_listen(sk); + release_sock(sk); + flush_work(&smc->tcp_listen_work); + lock_sock(sk); break; case SMC_ACTIVE: smc_close_stream_wait(smc, timeout); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2424c71..645dd22 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -177,6 +177,7 @@ static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr, lnk = &lgr->lnk[SMC_SINGLE_LINK]; /* initialize link */ + lnk->link_id = SMC_SINGLE_LINK; lnk->smcibdev = smcibdev; lnk->ibport = ibport; lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu; @@ -465,7 +466,7 @@ create: rc = smc_link_determine_gid(conn->lgr); } conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; - conn->local_tx_ctrl.len = sizeof(struct smc_cdc_msg); + conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); #endif diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 92fe4cc..b4aa4fc 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -92,7 +92,7 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[], memcpy(confllc->sender_mac, mac, ETH_ALEN); memcpy(confllc->sender_gid, gid, SMC_GID_SIZE); hton24(confllc->sender_qp_num, link->roce_qp->qp_num); - /* confllc->link_num = SMC_SINGLE_LINK; already done by memset above */ + confllc->link_num = link->link_id; memcpy(confllc->link_uid, lgr->id, SMC_LGR_ID_SIZE); confllc->max_links = SMC_LINKS_PER_LGR_MAX; /* send llc message */ diff --git a/net/socket.c b/net/socket.c index a93c99b5..08847c3 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2587,6 +2587,11 @@ void sock_unregister(int family) } EXPORT_SYMBOL(sock_unregister); +bool sock_is_registered(int family) +{ + return family < NPROTO && rcu_access_pointer(net_families[family]); +} + static int __init sock_init(void) { int err; diff --git a/net/tipc/group.c b/net/tipc/group.c index 122162a..04e516d 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -189,6 +189,7 @@ struct tipc_group *tipc_group_create(struct net *net, u32 portid, grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS; grp->open = group_is_open; + *grp->open = false; filter |= global ? TIPC_SUB_CLUSTER_SCOPE : TIPC_SUB_NODE_SCOPE; if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, filter, &grp->subid)) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b0323ec..7dfa9fc 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -473,6 +473,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, sk->sk_write_space = tipc_write_space; sk->sk_destruct = tipc_sock_destruct; tsk->conn_timeout = CONN_TIMEOUT_DEFAULT; + tsk->group_is_open = true; atomic_set(&tsk->dupl_rcvcnt, 0); /* Start out with safe limits until we receive an advertised window */ diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index e9b4b53..d824d54 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -46,16 +46,26 @@ MODULE_DESCRIPTION("Transport Layer Security Support"); MODULE_LICENSE("Dual BSD/GPL"); enum { + TLSV4, + TLSV6, + TLS_NUM_PROTS, +}; + +enum { TLS_BASE_TX, TLS_SW_TX, TLS_NUM_CONFIG, }; -static struct proto tls_prots[TLS_NUM_CONFIG]; +static struct proto *saved_tcpv6_prot; +static DEFINE_MUTEX(tcpv6_prot_mutex); +static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG]; static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx) { - sk->sk_prot = &tls_prots[ctx->tx_conf]; + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; + + sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf]; } int wait_on_pending_writer(struct sock *sk, long *timeo) @@ -453,8 +463,21 @@ static int tls_setsockopt(struct sock *sk, int level, int optname, return do_tls_setsockopt(sk, optname, optval, optlen); } +static void build_protos(struct proto *prot, struct proto *base) +{ + prot[TLS_BASE_TX] = *base; + prot[TLS_BASE_TX].setsockopt = tls_setsockopt; + prot[TLS_BASE_TX].getsockopt = tls_getsockopt; + prot[TLS_BASE_TX].close = tls_sk_proto_close; + + prot[TLS_SW_TX] = prot[TLS_BASE_TX]; + prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; + prot[TLS_SW_TX].sendpage = tls_sw_sendpage; +} + static int tls_init(struct sock *sk) { + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx; int rc = 0; @@ -479,6 +502,17 @@ static int tls_init(struct sock *sk) ctx->getsockopt = sk->sk_prot->getsockopt; ctx->sk_proto_close = sk->sk_prot->close; + /* Build IPv6 TLS whenever the address of tcpv6_prot changes */ + if (ip_ver == TLSV6 && + unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { + mutex_lock(&tcpv6_prot_mutex); + if (likely(sk->sk_prot != saved_tcpv6_prot)) { + build_protos(tls_prots[TLSV6], sk->sk_prot); + smp_store_release(&saved_tcpv6_prot, sk->sk_prot); + } + mutex_unlock(&tcpv6_prot_mutex); + } + ctx->tx_conf = TLS_BASE_TX; update_sk_prot(sk, ctx); out: @@ -493,21 +527,9 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { .init = tls_init, }; -static void build_protos(struct proto *prot, struct proto *base) -{ - prot[TLS_BASE_TX] = *base; - prot[TLS_BASE_TX].setsockopt = tls_setsockopt; - prot[TLS_BASE_TX].getsockopt = tls_getsockopt; - prot[TLS_BASE_TX].close = tls_sk_proto_close; - - prot[TLS_SW_TX] = prot[TLS_BASE_TX]; - prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; - prot[TLS_SW_TX].sendpage = tls_sw_sendpage; -} - static int __init tls_register(void) { - build_protos(tls_prots, &tcp_prot); + build_protos(tls_prots[TLSV4], &tcp_prot); tcp_register_ulp(&tcp_tls_ulp_ops); diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 1abcc4f..4172204 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -34,9 +34,10 @@ config CFG80211 When built as a module it will be called cfg80211. +if CFG80211 + config NL80211_TESTMODE bool "nl80211 testmode command" - depends on CFG80211 help The nl80211 testmode command helps implementing things like factory calibration or validation tools for wireless chips. @@ -51,7 +52,6 @@ config NL80211_TESTMODE config CFG80211_DEVELOPER_WARNINGS bool "enable developer warnings" - depends on CFG80211 default n help This option enables some additional warnings that help @@ -68,7 +68,7 @@ config CFG80211_DEVELOPER_WARNINGS config CFG80211_CERTIFICATION_ONUS bool "cfg80211 certification onus" - depends on CFG80211 && EXPERT + depends on EXPERT default n ---help--- You should disable this option unless you are both capable @@ -159,7 +159,6 @@ config CFG80211_REG_RELAX_NO_IR config CFG80211_DEFAULT_PS bool "enable powersave by default" - depends on CFG80211 default y help This option enables powersave mode by default. @@ -170,7 +169,6 @@ config CFG80211_DEFAULT_PS config CFG80211_DEBUGFS bool "cfg80211 DebugFS entries" - depends on CFG80211 depends on DEBUG_FS ---help--- You can enable this if you want debugfs entries for cfg80211. @@ -180,7 +178,6 @@ config CFG80211_DEBUGFS config CFG80211_CRDA_SUPPORT bool "support CRDA" if EXPERT default y - depends on CFG80211 help You should enable this option unless you know for sure you have no need for it, for example when using internal regdb (above) or the @@ -190,7 +187,6 @@ config CFG80211_CRDA_SUPPORT config CFG80211_WEXT bool "cfg80211 wireless extensions compatibility" if !CFG80211_WEXT_EXPORT - depends on CFG80211 select WEXT_CORE default y if CFG80211_WEXT_EXPORT help @@ -199,11 +195,12 @@ config CFG80211_WEXT config CFG80211_WEXT_EXPORT bool - depends on CFG80211 help Drivers should select this option if they require cfg80211's wext compatibility symbols to be exported. +endif # CFG80211 + config LIB80211 tristate default n diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 8e70291..e87d6c4 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -217,7 +217,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) if (skb->len <= mtu) goto ok; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) goto ok; } diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index ccfdc71..a00ec71 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -283,7 +283,7 @@ static struct crypto_comp * __percpu *ipcomp_alloc_tfms(const char *alg_name) struct crypto_comp *tfm; /* This can be any valid CPU ID so we don't need locking. */ - tfm = __this_cpu_read(*pos->tfms); + tfm = this_cpu_read(*pos->tfms); if (!strcmp(crypto_comp_name(tfm), alg_name)) { pos->users++; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7a23078..625b3fc 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1458,10 +1458,13 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, static int xfrm_get_tos(const struct flowi *fl, int family) { const struct xfrm_policy_afinfo *afinfo; - int tos = 0; + int tos; afinfo = xfrm_policy_get_afinfo(family); - tos = afinfo ? afinfo->get_tos(fl) : 0; + if (!afinfo) + return 0; + + tos = afinfo->get_tos(fl); rcu_read_unlock(); @@ -1891,7 +1894,7 @@ static void xfrm_policy_queue_process(struct timer_list *t) spin_unlock(&pq->hold_queue.lock); dst_hold(xfrm_dst_path(dst)); - dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, 0); + dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) goto purge_queue; @@ -2729,14 +2732,14 @@ static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst, while (dst->xfrm) { const struct xfrm_state *xfrm = dst->xfrm; + dst = xfrm_dst_child(dst); + if (xfrm->props.mode == XFRM_MODE_TRANSPORT) continue; if (xfrm->type->flags & XFRM_TYPE_REMOTE_COADDR) daddr = xfrm->coaddr; else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR)) daddr = &xfrm->id.daddr; - - dst = xfrm_dst_child(dst); } return daddr; } diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 1d38c6a..9e3a5e85 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -660,7 +660,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff } else { XFRM_SKB_CB(skb)->seq.output.low = oseq + 1; XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi; - xo->seq.low = oseq = oseq + 1; + xo->seq.low = oseq + 1; xo->seq.hi = oseq_hi; oseq += skb_shinfo(skb)->gso_segs; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 54e21f1..f9d2f22 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2056,6 +2056,11 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen struct xfrm_mgr *km; struct xfrm_policy *pol = NULL; +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + return -EOPNOTSUPP; +#endif + if (!optval && !optlen) { xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 7f52b8e..080035f 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -121,22 +121,17 @@ static inline int verify_replay(struct xfrm_usersa_info *p, struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL]; struct xfrm_replay_state_esn *rs; - if (p->flags & XFRM_STATE_ESN) { - if (!rt) - return -EINVAL; + if (!rt) + return (p->flags & XFRM_STATE_ESN) ? -EINVAL : 0; - rs = nla_data(rt); + rs = nla_data(rt); - if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) - return -EINVAL; - - if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) && - nla_len(rt) != sizeof(*rs)) - return -EINVAL; - } + if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) + return -EINVAL; - if (!rt) - return 0; + if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) && + nla_len(rt) != sizeof(*rs)) + return -EINVAL; /* As only ESP and AH support ESN feature. */ if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH)) |
