diff options
Diffstat (limited to 'net')
78 files changed, 681 insertions, 424 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 8a15eaadc4bd..6ee48aac776f 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -9,7 +9,7 @@ bool vlan_do_receive(struct sk_buff **skbp) { struct sk_buff *skb = *skbp; __be16 vlan_proto = skb->vlan_proto; - u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK; + u16 vlan_id = vlan_tx_tag_get_id(skb); struct net_device *vlan_dev; struct vlan_pcpu_stats *rx_stats; @@ -91,7 +91,12 @@ EXPORT_SYMBOL(__vlan_find_dev_deep); struct net_device *vlan_dev_real_dev(const struct net_device *dev) { - return vlan_dev_priv(dev)->real_dev; + struct net_device *ret = vlan_dev_priv(dev)->real_dev; + + while (is_vlan_dev(ret)) + ret = vlan_dev_priv(ret)->real_dev; + + return ret; } EXPORT_SYMBOL(vlan_dev_real_dev); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 3a8c8fd63c88..1cd3d2a406f5 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -73,6 +73,8 @@ vlan_dev_get_egress_qos_mask(struct net_device *dev, struct sk_buff *skb) { struct vlan_priority_tci_mapping *mp; + smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */ + mp = vlan_dev_priv(dev)->egress_priority_map[(skb->priority & 0xF)]; while (mp) { if (mp->priority == skb->priority) { @@ -249,6 +251,11 @@ int vlan_dev_set_egress_priority(const struct net_device *dev, np->next = mp; np->priority = skb_prio; np->vlan_qos = vlan_qos; + /* Before inserting this element in hash table, make sure all its fields + * are committed to memory. + * coupled with smp_rmb() in vlan_dev_get_egress_qos_mask() + */ + smp_wmb(); vlan->egress_priority_map[skb_prio & 0xF] = np; if (vlan_qos) vlan->nr_egress_mappings++; diff --git a/net/Kconfig b/net/Kconfig index 37702491abe9..2b406608a1a4 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -244,7 +244,7 @@ config NETPRIO_CGROUP Cgroup subsystem for use in assigning processes to network priorities on a per-interface basis -config NET_LL_RX_POLL +config NET_RX_BUSY_POLL boolean default y diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index e14531f1ce1c..264de88db320 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1529,6 +1529,8 @@ out: * in these cases, the skb is further handled by this function and * returns 1, otherwise it returns 0 and the caller shall further * process the skb. + * + * This call might reallocate skb data. */ int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index f105219f4a4b..7614af31daff 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -508,6 +508,7 @@ out: return 0; } +/* this call might reallocate skb data */ static bool batadv_is_type_dhcprequest(struct sk_buff *skb, int header_len) { int ret = false; @@ -568,6 +569,7 @@ out: return ret; } +/* this call might reallocate skb data */ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) { struct ethhdr *ethhdr; @@ -619,6 +621,12 @@ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) if (!pskb_may_pull(skb, *header_len + sizeof(*udphdr))) return false; + + /* skb->data might have been reallocated by pskb_may_pull() */ + ethhdr = (struct ethhdr *)skb->data; + if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) + ethhdr = (struct ethhdr *)(skb->data + VLAN_HLEN); + udphdr = (struct udphdr *)(skb->data + *header_len); *header_len += sizeof(*udphdr); @@ -634,12 +642,14 @@ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) return true; } +/* this call might reallocate skb data */ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, - struct sk_buff *skb, struct ethhdr *ethhdr) + struct sk_buff *skb) { struct batadv_neigh_node *neigh_curr = NULL, *neigh_old = NULL; struct batadv_orig_node *orig_dst_node = NULL; struct batadv_gw_node *curr_gw = NULL; + struct ethhdr *ethhdr; bool ret, out_of_range = false; unsigned int header_len = 0; uint8_t curr_tq_avg; @@ -648,6 +658,7 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, if (!ret) goto out; + ethhdr = (struct ethhdr *)skb->data; orig_dst_node = batadv_transtable_search(bat_priv, ethhdr->h_source, ethhdr->h_dest); if (!orig_dst_node) diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 039902dca4a6..1037d75da51f 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -34,7 +34,6 @@ void batadv_gw_node_delete(struct batadv_priv *bat_priv, void batadv_gw_node_purge(struct batadv_priv *bat_priv); int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset); bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len); -bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, - struct sk_buff *skb, struct ethhdr *ethhdr); +bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct sk_buff *skb); #endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 700d0b49742d..0f04e1c302b4 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -180,6 +180,9 @@ static int batadv_interface_tx(struct sk_buff *skb, if (batadv_bla_tx(bat_priv, skb, vid)) goto dropped; + /* skb->data might have been reallocated by batadv_bla_tx() */ + ethhdr = (struct ethhdr *)skb->data; + /* Register the client MAC in the transtable */ if (!is_multicast_ether_addr(ethhdr->h_source)) batadv_tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif); @@ -220,6 +223,10 @@ static int batadv_interface_tx(struct sk_buff *skb, default: break; } + + /* reminder: ethhdr might have become unusable from here on + * (batadv_gw_is_dhcp_target() might have reallocated skb data) + */ } /* ethernet packet should be broadcasted */ @@ -266,7 +273,7 @@ static int batadv_interface_tx(struct sk_buff *skb, /* unicast packet */ } else { if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_OFF) { - ret = batadv_gw_out_of_range(bat_priv, skb, ethhdr); + ret = batadv_gw_out_of_range(bat_priv, skb); if (ret) goto dropped; } diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index dc8b5d4dd636..688a0419756b 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -326,7 +326,9 @@ static bool batadv_unicast_push_and_fill_skb(struct sk_buff *skb, int hdr_size, * @skb: the skb containing the payload to encapsulate * @orig_node: the destination node * - * Returns false if the payload could not be encapsulated or true otherwise + * Returns false if the payload could not be encapsulated or true otherwise. + * + * This call might reallocate skb data. */ static bool batadv_unicast_prepare_skb(struct sk_buff *skb, struct batadv_orig_node *orig_node) @@ -343,7 +345,9 @@ static bool batadv_unicast_prepare_skb(struct sk_buff *skb, * @orig_node: the destination node * @packet_subtype: the batman 4addr packet subtype to use * - * Returns false if the payload could not be encapsulated or true otherwise + * Returns false if the payload could not be encapsulated or true otherwise. + * + * This call might reallocate skb data. */ bool batadv_unicast_4addr_prepare_skb(struct batadv_priv *bat_priv, struct sk_buff *skb, @@ -401,7 +405,7 @@ int batadv_unicast_generic_send_skb(struct batadv_priv *bat_priv, struct batadv_neigh_node *neigh_node; int data_len = skb->len; int ret = NET_RX_DROP; - unsigned int dev_mtu; + unsigned int dev_mtu, header_len; /* get routing information */ if (is_multicast_ether_addr(ethhdr->h_dest)) { @@ -429,10 +433,12 @@ find_router: switch (packet_type) { case BATADV_UNICAST: batadv_unicast_prepare_skb(skb, orig_node); + header_len = sizeof(struct batadv_unicast_packet); break; case BATADV_UNICAST_4ADDR: batadv_unicast_4addr_prepare_skb(bat_priv, skb, orig_node, packet_subtype); + header_len = sizeof(struct batadv_unicast_4addr_packet); break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It @@ -441,6 +447,7 @@ find_router: goto out; } + ethhdr = (struct ethhdr *)(skb->data + header_len); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 2ef66781fedb..69363bd37f64 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -70,7 +70,8 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) } mdst = br_mdb_get(br, skb, vid); - if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) + if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && + br_multicast_querier_exists(br)) br_multicast_deliver(mdst, skb); else br_flood_deliver(br, skb, false); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 1b8b8b824cd7..8c561c0aa636 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -101,7 +101,8 @@ int br_handle_frame_finish(struct sk_buff *skb) unicast = false; } else if (is_multicast_ether_addr(dest)) { mdst = br_mdb_get(br, skb, vid); - if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) { + if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && + br_multicast_querier_exists(br)) { if ((mdst && mdst->mglist) || br_multicast_is_router(br)) skb2 = skb; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 69af490cce44..08e576ada0b2 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -619,6 +619,9 @@ rehash: mp->br = br; mp->addr = *group; + setup_timer(&mp->timer, br_multicast_group_expired, + (unsigned long)mp); + hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]); mdb->size++; @@ -1011,6 +1014,16 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, } #endif +static void br_multicast_update_querier_timer(struct net_bridge *br, + unsigned long max_delay) +{ + if (!timer_pending(&br->multicast_querier_timer)) + br->multicast_querier_delay_time = jiffies + max_delay; + + mod_timer(&br->multicast_querier_timer, + jiffies + br->multicast_querier_interval); +} + /* * Add port to router_list * list is maintained ordered by pointer value @@ -1061,11 +1074,11 @@ timer: static void br_multicast_query_received(struct net_bridge *br, struct net_bridge_port *port, - int saddr) + int saddr, + unsigned long max_delay) { if (saddr) - mod_timer(&br->multicast_querier_timer, - jiffies + br->multicast_querier_interval); + br_multicast_update_querier_timer(br, max_delay); else if (timer_pending(&br->multicast_querier_timer)) return; @@ -1093,8 +1106,6 @@ static int br_ip4_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; - br_multicast_query_received(br, port, !!iph->saddr); - group = ih->group; if (skb->len == sizeof(*ih)) { @@ -1118,6 +1129,8 @@ static int br_ip4_multicast_query(struct net_bridge *br, IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1; } + br_multicast_query_received(br, port, !!iph->saddr, max_delay); + if (!group) goto out; @@ -1126,7 +1139,6 @@ static int br_ip4_multicast_query(struct net_bridge *br, if (!mp) goto out; - setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp); mod_timer(&mp->timer, now + br->multicast_membership_interval); mp->timer_armed = true; @@ -1174,8 +1186,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; - br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr)); - if (skb->len == sizeof(*mld)) { if (!pskb_may_pull(skb, sizeof(*mld))) { err = -EINVAL; @@ -1185,7 +1195,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay)); if (max_delay) group = &mld->mld_mca; - } else if (skb->len >= sizeof(*mld2q)) { + } else { if (!pskb_may_pull(skb, sizeof(*mld2q))) { err = -EINVAL; goto out; @@ -1196,6 +1206,9 @@ static int br_ip6_multicast_query(struct net_bridge *br, max_delay = mld2q->mld2q_mrc ? MLDV2_MRC(ntohs(mld2q->mld2q_mrc)) : 1; } + br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr), + max_delay); + if (!group) goto out; @@ -1204,7 +1217,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (!mp) goto out; - setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp); mod_timer(&mp->timer, now + br->multicast_membership_interval); mp->timer_armed = true; @@ -1642,6 +1654,8 @@ void br_multicast_init(struct net_bridge *br) br->multicast_querier_interval = 255 * HZ; br->multicast_membership_interval = 260 * HZ; + br->multicast_querier_delay_time = 0; + spin_lock_init(&br->multicast_lock); setup_timer(&br->multicast_router_timer, br_multicast_local_router_expired, 0); @@ -1830,6 +1844,8 @@ unlock: int br_multicast_set_querier(struct net_bridge *br, unsigned long val) { + unsigned long max_delay; + val = !!val; spin_lock_bh(&br->multicast_lock); @@ -1837,8 +1853,14 @@ int br_multicast_set_querier(struct net_bridge *br, unsigned long val) goto unlock; br->multicast_querier = val; - if (val) - br_multicast_start_querier(br); + if (!val) + goto unlock; + + max_delay = br->multicast_query_response_interval; + if (!timer_pending(&br->multicast_querier_timer)) + br->multicast_querier_delay_time = jiffies + max_delay; + + br_multicast_start_querier(br); unlock: spin_unlock_bh(&br->multicast_lock); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 3be89b3ce17b..2f7da41851bf 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -267,6 +267,7 @@ struct net_bridge unsigned long multicast_query_interval; unsigned long multicast_query_response_interval; unsigned long multicast_startup_query_interval; + unsigned long multicast_querier_delay_time; spinlock_t multicast_lock; struct net_bridge_mdb_htable __rcu *mdb; @@ -501,6 +502,13 @@ static inline bool br_multicast_is_router(struct net_bridge *br) (br->multicast_router == 1 && timer_pending(&br->multicast_router_timer)); } + +static inline bool br_multicast_querier_exists(struct net_bridge *br) +{ + return time_is_before_jiffies(br->multicast_querier_delay_time) && + (br->multicast_querier || + timer_pending(&br->multicast_querier_timer)); +} #else static inline int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, @@ -557,6 +565,10 @@ static inline bool br_multicast_is_router(struct net_bridge *br) { return 0; } +static inline bool br_multicast_querier_exists(struct net_bridge *br) +{ + return false; +} static inline void br_mdb_init(void) { } diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 394bb96b6087..3b9637fb7939 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -1,5 +1,5 @@ /* - * Sysfs attributes of bridge ports + * Sysfs attributes of bridge * Linux ethernet bridge * * Authors: diff --git a/net/core/dev.c b/net/core/dev.c index a3d8d44cb7f4..26755dd40daa 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3580,8 +3580,15 @@ ncls: } } - if (vlan_tx_nonzero_tag_present(skb)) - skb->pkt_type = PACKET_OTHERHOST; + if (unlikely(vlan_tx_tag_present(skb))) { + if (vlan_tx_tag_get_id(skb)) + skb->pkt_type = PACKET_OTHERHOST; + /* Note: we might in the future use prio bits + * and set skb->priority like in vlan_do_receive() + * For the time being, just ignore Priority Code Point + */ + skb->vlan_tci = 0; + } /* deliver only exact match when indicated */ null_or_dev = deliver_exact ? skb->dev : NULL; diff --git a/net/core/ethtool.c b/net/core/ethtool.c index ab5fa6336c84..78e9d9223e40 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -279,11 +279,16 @@ static u32 __ethtool_get_flags(struct net_device *dev) { u32 flags = 0; - if (dev->features & NETIF_F_LRO) flags |= ETH_FLAG_LRO; - if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) flags |= ETH_FLAG_RXVLAN; - if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) flags |= ETH_FLAG_TXVLAN; - if (dev->features & NETIF_F_NTUPLE) flags |= ETH_FLAG_NTUPLE; - if (dev->features & NETIF_F_RXHASH) flags |= ETH_FLAG_RXHASH; + if (dev->features & NETIF_F_LRO) + flags |= ETH_FLAG_LRO; + if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) + flags |= ETH_FLAG_RXVLAN; + if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) + flags |= ETH_FLAG_TXVLAN; + if (dev->features & NETIF_F_NTUPLE) + flags |= ETH_FLAG_NTUPLE; + if (dev->features & NETIF_F_RXHASH) + flags |= ETH_FLAG_RXHASH; return flags; } @@ -295,11 +300,16 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data) if (data & ~ETH_ALL_FLAGS) return -EINVAL; - if (data & ETH_FLAG_LRO) features |= NETIF_F_LRO; - if (data & ETH_FLAG_RXVLAN) features |= NETIF_F_HW_VLAN_CTAG_RX; - if (data & ETH_FLAG_TXVLAN) features |= NETIF_F_HW_VLAN_CTAG_TX; - if (data & ETH_FLAG_NTUPLE) features |= NETIF_F_NTUPLE; - if (data & ETH_FLAG_RXHASH) features |= NETIF_F_RXHASH; + if (data & ETH_FLAG_LRO) + features |= NETIF_F_LRO; + if (data & ETH_FLAG_RXVLAN) + features |= NETIF_F_HW_VLAN_CTAG_RX; + if (data & ETH_FLAG_TXVLAN) + features |= NETIF_F_HW_VLAN_CTAG_TX; + if (data & ETH_FLAG_NTUPLE) + features |= NETIF_F_NTUPLE; + if (data & ETH_FLAG_RXHASH) + features |= NETIF_F_RXHASH; /* allow changing only bits set in hw_features */ changed = (features ^ dev->features) & ETH_ALL_FEATURES; diff --git a/net/core/flow.c b/net/core/flow.c index 7102f166482d..dfa602ceb8cd 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -403,7 +403,7 @@ void flow_cache_flush_deferred(void) schedule_work(&flow_cache_flush_work); } -static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) +static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) { struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc); @@ -421,7 +421,7 @@ static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) return 0; } -static int __cpuinit flow_cache_cpu(struct notifier_block *nfb, +static int flow_cache_cpu(struct notifier_block *nfb, unsigned long action, void *hcpu) { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 00ee068efc1c..b84a1b155bc1 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -65,6 +65,7 @@ ipv6: nhoff += sizeof(struct ipv6hdr); break; } + case __constant_htons(ETH_P_8021AD): case __constant_htons(ETH_P_8021Q): { const struct vlan_hdr *vlan; struct vlan_hdr _vlan; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index b7de821f98df..60533db8b72d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1441,16 +1441,18 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, atomic_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(p->base_reachable_time); + dev_hold(dev); + p->dev = dev; + write_pnet(&p->net, hold_net(net)); + p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { + release_net(net); + dev_put(dev); kfree(p); return NULL; } - dev_hold(dev); - p->dev = dev; - write_pnet(&p->net, hold_net(net)); - p->sysctl_table = NULL; write_lock_bh(&tbl->lock); p->next = tbl->parms.next; tbl->parms.next = p; @@ -2767,6 +2769,7 @@ EXPORT_SYMBOL(neigh_app_ns); #ifdef CONFIG_SYSCTL static int zero; +static int int_max = INT_MAX; static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN); static int proc_unres_qlen(struct ctl_table *ctl, int write, @@ -2819,19 +2822,25 @@ static struct neigh_sysctl_table { .procname = "mcast_solicit", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_UCAST_PROBE] = { .procname = "ucast_solicit", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_APP_PROBE] = { .procname = "app_solicit", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_RETRANS_TIME] = { .procname = "retrans_time", @@ -2874,7 +2883,9 @@ static struct neigh_sysctl_table { .procname = "proxy_qlen", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_ANYCAST_DELAY] = { .procname = "anycast_delay", @@ -2916,19 +2927,25 @@ static struct neigh_sysctl_table { .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_GC_THRESH2] = { .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_GC_THRESH3] = { .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, {}, }, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3de740834d1f..ca198c1d1d30 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2156,7 +2156,7 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, /* If aging addresses are supported device will need to * implement its own handler for this. */ - if (ndm->ndm_state & NUD_PERMANENT) { + if (!(ndm->ndm_state & NUD_PERMANENT)) { pr_info("%s: FDB only supports static addresses\n", dev->name); return -EINVAL; } @@ -2384,7 +2384,7 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) struct nlattr *extfilt; u32 filter_mask = 0; - extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct rtgenmsg), + extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg), IFLA_EXT_MASK); if (extfilt) filter_mask = nla_get_u32(extfilt); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 20e02d2605ec..2c3d0f53d198 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -309,7 +309,8 @@ EXPORT_SYMBOL(__alloc_skb); * @frag_size: size of fragment, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and - * skb_shared_info. @data must have been allocated by kmalloc() + * skb_shared_info. @data must have been allocated by kmalloc() only if + * @frag_size is 0, otherwise data should come from the page allocator. * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : @@ -739,7 +740,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) skb_copy_secmark(new, old); -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL new->napi_id = old->napi_id; #endif } diff --git a/net/core/sock.c b/net/core/sock.c index 548d716c5f62..2c097c5a35dd 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -900,7 +900,7 @@ set_rcvbuf: sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); break; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: /* allow unprivileged users to decrease the value */ if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) @@ -1170,7 +1170,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: v.val = sk->sk_ll_usec; break; @@ -2292,7 +2292,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_stamp = ktime_set(-1L, 0); -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; sk->sk_ll_usec = sysctl_net_busy_read; #endif diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 660968616637..31107abd2783 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -21,7 +21,9 @@ #include <net/net_ratelimit.h> #include <net/busy_poll.h> +static int zero = 0; static int one = 1; +static int ushort_max = USHRT_MAX; #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(struct ctl_table *table, int write, @@ -298,7 +300,7 @@ static struct ctl_table net_core_table[] = { .proc_handler = flow_limit_table_len_sysctl }, #endif /* CONFIG_NET_FLOW_LIMIT */ -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL { .procname = "busy_poll", .data = &sysctl_net_busy_poll, @@ -339,7 +341,9 @@ static struct ctl_table netns_core_table[] = { .data = &init_net.core.sysctl_somaxconn, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .extra1 = &zero, + .extra2 = &ushort_max, + .proc_handler = proc_dointvec_minmax }, { } }; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 5359560926bc..be1f64d35358 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -401,27 +401,8 @@ struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, } EXPORT_SYMBOL(alloc_etherdev_mqs); -static size_t _format_mac_addr(char *buf, int buflen, - const unsigned char *addr, int len) -{ - int i; - char *cp = buf; - - for (i = 0; i < len; i++) { - cp += scnprintf(cp, buflen - (cp - buf), "%02x", addr[i]); - if (i == len - 1) - break; - cp += scnprintf(cp, buflen - (cp - buf), ":"); - } - return cp - buf; -} - ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len) { - size_t l; - - l = _format_mac_addr(buf, PAGE_SIZE, addr, len); - l += scnprintf(buf + l, PAGE_SIZE - l, "\n"); - return (ssize_t)l; + return scnprintf(buf, PAGE_SIZE, "%*phC\n", len, addr); } EXPORT_SYMBOL(sysfs_format_mac); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 8d48c392adcc..34ca6d5a3a4b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -772,7 +772,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, ci = nla_data(tb[IFA_CACHEINFO]); if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { err = -EINVAL; - goto errout; + goto errout_free; } *pvalid_lft = ci->ifa_valid; *pprefered_lft = ci->ifa_prefered; @@ -780,6 +780,8 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, return ifa; +errout_free: + inet_free_ifa(ifa); errout: return ERR_PTR(err); } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index ab3d814bc80a..109ee89f123e 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -477,7 +477,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu) } return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) - - net_adj) & ~(align - 1)) + (net_adj - 2); + net_adj) & ~(align - 1)) + net_adj - 2; } static void esp4_err(struct sk_buff *skb, u32 info) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 49616fed9340..3df6d3edb2a1 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -71,7 +71,6 @@ #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> -#include <linux/prefetch.h> #include <linux/export.h> #include <net/net_namespace.h> #include <net/ip.h> @@ -1761,10 +1760,8 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct rt_trie_node *c) if (!c) continue; - if (IS_LEAF(c)) { - prefetch(rcu_dereference_rtnl(p->child[idx])); + if (IS_LEAF(c)) return (struct leaf *) c; - } /* Rescan start scanning in new node */ p = (struct tnode *) c; @@ -2133,7 +2130,7 @@ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) max--; pointers = 0; - for (i = 1; i <= max; i++) + for (i = 1; i < max; i++) if (stat->nodesizes[i] != 0) { seq_printf(seq, " %u: %u", i, stat->nodesizes[i]); pointers += (1<<i) * stat->nodesizes[i]; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 1f6eab66f7ce..8d6939eeb492 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -383,7 +383,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, if (daddr) memcpy(&iph->daddr, daddr, 4); if (iph->daddr) - return t->hlen; + return t->hlen + sizeof(*iph); return -(t->hlen + sizeof(*iph)); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 3da817b89e9b..15e3e683adec 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -190,10 +190,7 @@ static int ip_local_deliver_finish(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); - __skb_pull(skb, ip_hdrlen(skb)); - - /* Point into the IP datagram, just past the header. */ - skb_reset_transport_header(skb); + __skb_pull(skb, skb_network_header_len(skb)); rcu_read_lock(); { @@ -437,6 +434,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, goto drop; } + skb->transport_header = skb->network_header + iph->ihl*4; + /* Remove any debris in the socket control block */ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 7167b08977df..850525b34899 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -76,9 +76,7 @@ int iptunnel_xmit(struct net *net, struct rtable *rt, iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; - tunnel_ip_select_ident(skb, - (const struct iphdr *)skb_inner_network_header(skb), - &rt->dst); + __ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1); err = ip_local_out(skb); if (unlikely(net_xmit_eval(err))) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 6577a1149a47..463bd1273346 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -273,7 +273,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW), SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD), SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES), - SNMP_MIB_ITEM("LowLatencyRxPackets", LINUX_MIB_LOWLATENCYRXPACKETS), + SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index b2c123c44d69..610e324348d1 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -36,6 +36,8 @@ static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; static int ip_ttl_min = 1; static int ip_ttl_max = 255; +static int tcp_syn_retries_min = 1; +static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; @@ -332,7 +334,9 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_syn_retries, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_syn_retries_min, + .extra2 = &tcp_syn_retries_max }, { .procname = "tcp_synack_retries", diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index a9077f441cb2..b6ae92a51f58 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -206,8 +206,8 @@ static u32 cubic_root(u64 a) */ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) { - u64 offs; - u32 delta, t, bic_target, max_cnt; + u32 delta, bic_target, max_cnt; + u64 offs, t; ca->ack_cnt++; /* count the number of ACKs */ @@ -250,9 +250,11 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) * if the cwnd < 1 million packets !!! */ + t = (s32)(tcp_time_stamp - ca->epoch_start); + t += msecs_to_jiffies(ca->delay_min >> 3); /* change the unit from HZ to bictcp_HZ */ - t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3) - - ca->epoch_start) << BICTCP_HZ) / HZ; + t <<= BICTCP_HZ; + do_div(t, HZ); if (t < ca->bic_K) /* t - K */ offs = ca->bic_K - t; @@ -414,7 +416,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) return; /* Discard delay samples right after fast recovery */ - if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ) + if (ca->epoch_start && (s32)(tcp_time_stamp - ca->epoch_start) < HZ) return; delay = (rtt_us << 3) / USEC_PER_MSEC; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index cfdcf7b2daf6..da4241c8c7da 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -813,8 +813,9 @@ static u32 inet6_addr_hash(const struct in6_addr *addr) /* On success it returns ifp with increased reference count */ static struct inet6_ifaddr * -ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, - int scope, u32 flags) +ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, + const struct in6_addr *peer_addr, int pfxlen, + int scope, u32 flags, u32 valid_lft, u32 prefered_lft) { struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; @@ -863,6 +864,8 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, } ifa->addr = *addr; + if (peer_addr) + ifa->peer_addr = *peer_addr; spin_lock_init(&ifa->lock); spin_lock_init(&ifa->state_lock); @@ -872,6 +875,8 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, ifa->scope = scope; ifa->prefix_len = pfxlen; ifa->flags = flags | IFA_F_TENTATIVE; + ifa->valid_lft = valid_lft; + ifa->prefered_lft = prefered_lft; ifa->cstamp = ifa->tstamp = jiffies; ifa->tokenized = false; @@ -1123,8 +1128,9 @@ retry: ift = !max_addresses || ipv6_count_addresses(idev) < max_addresses ? - ipv6_add_addr(idev, &addr, tmp_plen, ipv6_addr_scope(&addr), - addr_flags) : NULL; + ipv6_add_addr(idev, &addr, NULL, tmp_plen, + ipv6_addr_scope(&addr), addr_flags, + tmp_valid_lft, tmp_prefered_lft) : NULL; if (IS_ERR_OR_NULL(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); @@ -1136,8 +1142,6 @@ retry: spin_lock_bh(&ift->lock); ift->ifpub = ifp; - ift->valid_lft = tmp_valid_lft; - ift->prefered_lft = tmp_prefered_lft; ift->cstamp = now; ift->tstamp = tmp_tstamp; spin_unlock_bh(&ift->lock); @@ -2179,16 +2183,19 @@ ok: */ if (!max_addresses || ipv6_count_addresses(in6_dev) < max_addresses) - ifp = ipv6_add_addr(in6_dev, &addr, pinfo->prefix_len, + ifp = ipv6_add_addr(in6_dev, &addr, NULL, + pinfo->prefix_len, addr_type&IPV6_ADDR_SCOPE_MASK, - addr_flags); + addr_flags, valid_lft, + prefered_lft); if (IS_ERR_OR_NULL(ifp)) { in6_dev_put(in6_dev); return; } - update_lft = create = 1; + update_lft = 0; + create = 1; ifp->cstamp = jiffies; ifp->tokenized = tokenized; addrconf_dad_start(ifp); @@ -2209,7 +2216,7 @@ ok: stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; else stored_lft = 0; - if (!update_lft && stored_lft) { + if (!update_lft && !create && stored_lft) { if (valid_lft > MIN_VALID_LIFETIME || valid_lft > stored_lft) update_lft = 1; @@ -2455,17 +2462,10 @@ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *p prefered_lft = timeout; } - ifp = ipv6_add_addr(idev, pfx, plen, scope, ifa_flags); + ifp = ipv6_add_addr(idev, pfx, peer_pfx, plen, scope, ifa_flags, + valid_lft, prefered_lft); if (!IS_ERR(ifp)) { - spin_lock_bh(&ifp->lock); - ifp->valid_lft = valid_lft; - ifp->prefered_lft = prefered_lft; - ifp->tstamp = jiffies; - if (peer_pfx) - ifp->peer_addr = *peer_pfx; - spin_unlock_bh(&ifp->lock); - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev, expires, flags); /* @@ -2557,7 +2557,8 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, { struct inet6_ifaddr *ifp; - ifp = ipv6_add_addr(idev, addr, plen, scope, IFA_F_PERMANENT); + ifp = ipv6_add_addr(idev, addr, NULL, plen, + scope, IFA_F_PERMANENT, 0, 0); if (!IS_ERR(ifp)) { spin_lock_bh(&ifp->lock); ifp->flags &= ~IFA_F_TENTATIVE; @@ -2683,7 +2684,7 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr #endif - ifp = ipv6_add_addr(idev, addr, 64, IFA_LINK, addr_flags); + ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, 0, 0); if (!IS_ERR(ifp)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0); addrconf_dad_start(ifp); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 40ffd72243a4..aeac0dc3635d 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -425,7 +425,7 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu) net_adj = 0; return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) - - net_adj) & ~(align - 1)) + (net_adj - 2); + net_adj) & ~(align - 1)) + net_adj - 2; } static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5fc9c7a68d8d..c4ff5bbb45c4 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -993,14 +993,22 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES - if (fn->subtree) - fn = fib6_lookup_1(fn->subtree, args + 1); + if (fn->subtree) { + struct fib6_node *sfn; + sfn = fib6_lookup_1(fn->subtree, + args + 1); + if (!sfn) + goto backtrack; + fn = sfn; + } #endif - if (!fn || fn->fn_flags & RTN_RTINFO) + if (fn->fn_flags & RTN_RTINFO) return fn; } } - +#ifdef CONFIG_IPV6_SUBTREES +backtrack: +#endif if (fn->fn_flags & RTN_ROOT) break; @@ -1632,27 +1640,28 @@ static int fib6_age(struct rt6_info *rt, void *arg) static DEFINE_SPINLOCK(fib6_gc_lock); -void fib6_run_gc(unsigned long expires, struct net *net) +void fib6_run_gc(unsigned long expires, struct net *net, bool force) { - if (expires != ~0UL) { + unsigned long now; + + if (force) { spin_lock_bh(&fib6_gc_lock); - gc_args.timeout = expires ? (int)expires : - net->ipv6.sysctl.ip6_rt_gc_interval; - } else { - if (!spin_trylock_bh(&fib6_gc_lock)) { - mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); - return; - } - gc_args.timeout = net->ipv6.sysctl.ip6_rt_gc_interval; + } else if (!spin_trylock_bh(&fib6_gc_lock)) { + mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); + return; } + gc_args.timeout = expires ? (int)expires : + net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = icmp6_dst_gc(); fib6_clean_all(net, fib6_age, 0, NULL); + now = jiffies; + net->ipv6.ip6_rt_last_gc = now; if (gc_args.more) mod_timer(&net->ipv6.ip6_fib_timer, - round_jiffies(jiffies + round_jiffies(now + net->ipv6.sysctl.ip6_rt_gc_interval)); else del_timer(&net->ipv6.ip6_fib_timer); @@ -1661,7 +1670,7 @@ void fib6_run_gc(unsigned long expires, struct net *net) static void fib6_gc_timer_cb(unsigned long arg) { - fib6_run_gc(0, (struct net *)arg); + fib6_run_gc(0, (struct net *)arg, true); } static int __net_init fib6_net_init(struct net *net) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 583e8d435f9a..03986d31fa41 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -259,10 +259,12 @@ static void __net_exit ip6mr_rules_exit(struct net *net) { struct mr6_table *mrt, *next; + rtnl_lock(); list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) { list_del(&mrt->list); ip6mr_free_table(mrt); } + rtnl_unlock(); fib_rules_unregister(net->ipv6.mr6_rules_ops); } #else @@ -289,7 +291,10 @@ static int __net_init ip6mr_rules_init(struct net *net) static void __net_exit ip6mr_rules_exit(struct net *net) { + rtnl_lock(); ip6mr_free_table(net->ipv6.mrt6); + net->ipv6.mrt6 = NULL; + rtnl_unlock(); } #endif diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index b3b5730b48c5..79aa9652ed86 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -479,7 +479,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) - override = 0; + override = false; inc_opt |= ifp->idev->cnf.force_tllao; in6_ifa_put(ifp); } else { @@ -557,7 +557,7 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, } if (ipv6_addr_any(saddr)) - inc_opt = 0; + inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev); @@ -790,7 +790,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && - inc != 0 && + inc && idev->nd_parms->proxy_delay != 0) { /* * for anycast or proxy, @@ -1576,7 +1576,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); - fib6_run_gc(~0UL, net); + fib6_run_gc(0, net, false); idev = in6_dev_get(dev); if (!idev) break; @@ -1586,7 +1586,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); - fib6_run_gc(~0UL, net); + fib6_run_gc(0, net, false); break; case NETDEV_NOTIFY_PEERS: ndisc_send_unsol_na(dev); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a8c891aa2464..b70f8979003b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1311,7 +1311,6 @@ static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg), static int ip6_dst_gc(struct dst_ops *ops) { - unsigned long now = jiffies; struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size; @@ -1321,13 +1320,12 @@ static int ip6_dst_gc(struct dst_ops *ops) int entries; entries = dst_entries_get_fast(ops); - if (time_after(rt_last_gc + rt_min_interval, now) && + if (time_after(rt_last_gc + rt_min_interval, jiffies) && entries <= rt_max_size) goto out; net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net); - net->ipv6.ip6_rt_last_gc = now; + fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, entries > rt_max_size); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; @@ -2827,7 +2825,7 @@ int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write, net = (struct net *)ctl->extra1; delay = net->ipv6.sysctl.flush_delay; proc_dointvec(ctl, write, buffer, lenp, ppos); - fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); + fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c index d14152e866d9..ffcec225b5d9 100644 --- a/net/irda/irlan/irlan_eth.c +++ b/net/irda/irlan/irlan_eth.c @@ -44,12 +44,12 @@ static int irlan_eth_open(struct net_device *dev); static int irlan_eth_close(struct net_device *dev); static netdev_tx_t irlan_eth_xmit(struct sk_buff *skb, struct net_device *dev); -static void irlan_eth_set_multicast_list( struct net_device *dev); +static void irlan_eth_set_multicast_list(struct net_device *dev); static const struct net_device_ops irlan_eth_netdev_ops = { - .ndo_open = irlan_eth_open, - .ndo_stop = irlan_eth_close, - .ndo_start_xmit = irlan_eth_xmit, + .ndo_open = irlan_eth_open, + .ndo_stop = irlan_eth_close, + .ndo_start_xmit = irlan_eth_xmit, .ndo_set_rx_mode = irlan_eth_set_multicast_list, .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, @@ -110,7 +110,7 @@ static int irlan_eth_open(struct net_device *dev) { struct irlan_cb *self = netdev_priv(dev); - IRDA_DEBUG(2, "%s()\n", __func__ ); + IRDA_DEBUG(2, "%s()\n", __func__); /* Ready to play! */ netif_stop_queue(dev); /* Wait until data link is ready */ @@ -137,7 +137,7 @@ static int irlan_eth_close(struct net_device *dev) { struct irlan_cb *self = netdev_priv(dev); - IRDA_DEBUG(2, "%s()\n", __func__ ); + IRDA_DEBUG(2, "%s()\n", __func__); /* Stop device */ netif_stop_queue(dev); @@ -310,35 +310,32 @@ static void irlan_eth_set_multicast_list(struct net_device *dev) { struct irlan_cb *self = netdev_priv(dev); - IRDA_DEBUG(2, "%s()\n", __func__ ); + IRDA_DEBUG(2, "%s()\n", __func__); /* Check if data channel has been connected yet */ if (self->client.state != IRLAN_DATA) { - IRDA_DEBUG(1, "%s(), delaying!\n", __func__ ); + IRDA_DEBUG(1, "%s(), delaying!\n", __func__); return; } if (dev->flags & IFF_PROMISC) { /* Enable promiscuous mode */ IRDA_WARNING("Promiscuous mode not implemented by IrLAN!\n"); - } - else if ((dev->flags & IFF_ALLMULTI) || + } else if ((dev->flags & IFF_ALLMULTI) || netdev_mc_count(dev) > HW_MAX_ADDRS) { /* Disable promiscuous mode, use normal mode. */ - IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__ ); + IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__); /* hardware_set_filter(NULL); */ irlan_set_multicast_filter(self, TRUE); - } - else if (!netdev_mc_empty(dev)) { - IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__ ); + } else if (!netdev_mc_empty(dev)) { + IRDA_DEBUG(4, "%s(), Setting multicast filter\n", __func__); /* Walk the address list, and load the filter */ /* hardware_set_filter(dev->mc_list); */ irlan_set_multicast_filter(self, TRUE); - } - else { - IRDA_DEBUG(4, "%s(), Clearing multicast filter\n", __func__ ); + } else { + IRDA_DEBUG(4, "%s(), Clearing multicast filter\n", __func__); irlan_set_multicast_filter(self, FALSE); } diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 4fe76ff214c2..cd5b8ec9be04 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -621,7 +621,7 @@ static void iucv_disable(void) put_online_cpus(); } -static int __cpuinit iucv_cpu_notify(struct notifier_block *self, +static int iucv_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { cpumask_t cpumask; diff --git a/net/key/af_key.c b/net/key/af_key.c index 9da862070dd8..ab8bd2cabfa0 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2081,6 +2081,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * pol->sadb_x_policy_type = IPSEC_POLICY_NONE; } pol->sadb_x_policy_dir = dir+1; + pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; pol->sadb_x_policy_priority = xp->priority; @@ -3137,7 +3138,9 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = XFRM_POLICY_OUT + 1; + pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; + pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ if (x->id.proto == IPPROTO_AH) @@ -3525,6 +3528,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = dir + 1; + pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = 0; pol->sadb_x_policy_priority = 0; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index c63b618cd619..4fd1ca94fd4a 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -293,6 +293,11 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class, sizeof(exp->tuple.dst.u3) - len); exp->tuple.dst.u.all = *dst; + +#ifdef CONFIG_NF_NAT_NEEDED + memset(&exp->saved_addr, 0, sizeof(exp->saved_addr)); + memset(&exp->saved_proto, 0, sizeof(exp->saved_proto)); +#endif } EXPORT_SYMBOL_GPL(nf_ct_expect_init); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 7dcc376eea5f..2f8010707d01 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -526,7 +526,7 @@ static bool tcp_in_window(const struct nf_conn *ct, const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; __u32 seq, ack, sack, end, win, swin; s16 receiver_offset; - bool res; + bool res, in_recv_win; /* * Get the required data from the packet. @@ -649,14 +649,18 @@ static bool tcp_in_window(const struct nf_conn *ct, receiver->td_end, receiver->td_maxend, receiver->td_maxwin, receiver->td_scale); + /* Is the ending sequence in the receive window (if available)? */ + in_recv_win = !receiver->td_maxwin || + after(end, sender->td_end - receiver->td_maxwin - 1); + pr_debug("tcp_in_window: I=%i II=%i III=%i IV=%i\n", before(seq, sender->td_maxend + 1), - after(end, sender->td_end - receiver->td_maxwin - 1), + (in_recv_win ? 1 : 0), before(sack, receiver->td_end + 1), after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)); if (before(seq, sender->td_maxend + 1) && - after(end, sender->td_end - receiver->td_maxwin - 1) && + in_recv_win && before(sack, receiver->td_end + 1) && after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) { /* @@ -725,7 +729,7 @@ static bool tcp_in_window(const struct nf_conn *ct, nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: %s ", before(seq, sender->td_maxend + 1) ? - after(end, sender->td_end - receiver->td_maxwin - 1) ? + in_recv_win ? before(sack, receiver->td_end + 1) ? after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1) ? "BUG" : "ACK is under the lower bound (possible overly delayed ACK)" diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 962e9792e317..d92cc317bf8b 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -419,6 +419,7 @@ __build_packet_message(struct nfnl_log_net *log, nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(inst->group_num); + memset(&pmsg, 0, sizeof(pmsg)); pmsg.hw_protocol = skb->protocol; pmsg.hook = hooknum; @@ -498,7 +499,10 @@ __build_packet_message(struct nfnl_log_net *log, if (indev && skb->dev && skb->mac_header != skb->network_header) { struct nfulnl_msg_packet_hw phw; - int len = dev_parse_header(skb, phw.hw_addr); + int len; + + memset(&phw, 0, sizeof(phw)); + len = dev_parse_header(skb, phw.hw_addr); if (len > 0) { phw.hw_addrlen = htons(len); if (nla_put(inst->skb, NFULA_HWADDR, sizeof(phw), &phw)) diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 971ea145ab3e..8a703c3dd318 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -463,7 +463,10 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, if (indev && entskb->dev && entskb->mac_header != entskb->network_header) { struct nfqnl_msg_packet_hw phw; - int len = dev_parse_header(entskb, phw.hw_addr); + int len; + + memset(&phw, 0, sizeof(phw)); + len = dev_parse_header(entskb, phw.hw_addr); if (len) { phw.hw_addrlen = htons(len); if (nla_put(skb, NFQA_HWADDR, sizeof(phw), &phw)) diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 7011c71646f0..6113cc7efffc 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -52,7 +52,8 @@ tcpmss_mangle_packet(struct sk_buff *skb, { const struct xt_tcpmss_info *info = par->targinfo; struct tcphdr *tcph; - unsigned int tcplen, i; + int len, tcp_hdrlen; + unsigned int i; __be16 oldval; u16 newmss; u8 *opt; @@ -64,11 +65,14 @@ tcpmss_mangle_packet(struct sk_buff *skb, if (!skb_make_writable(skb, skb->len)) return -1; - tcplen = skb->len - tcphoff; + len = skb->len - tcphoff; + if (len < (int)sizeof(struct tcphdr)) + return -1; + tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); + tcp_hdrlen = tcph->doff * 4; - /* Header cannot be larger than the packet */ - if (tcplen < tcph->doff*4) + if (len < tcp_hdrlen) return -1; if (info->mss == XT_TCPMSS_CLAMP_PMTU) { @@ -87,9 +91,8 @@ tcpmss_mangle_packet(struct sk_buff *skb, newmss = info->mss; opt = (u_int8_t *)tcph; - for (i = sizeof(struct tcphdr); i < tcph->doff*4; i += optlen(opt, i)) { - if (opt[i] == TCPOPT_MSS && tcph->doff*4 - i >= TCPOLEN_MSS && - opt[i+1] == TCPOLEN_MSS) { + for (i = sizeof(struct tcphdr); i <= tcp_hdrlen - TCPOLEN_MSS; i += optlen(opt, i)) { + if (opt[i] == TCPOPT_MSS && opt[i+1] == TCPOLEN_MSS) { u_int16_t oldmss; oldmss = (opt[i+2] << 8) | opt[i+3]; @@ -112,9 +115,10 @@ tcpmss_mangle_packet(struct sk_buff *skb, } /* There is data after the header so the option can't be added - without moving it, and doing so may make the SYN packet - itself too large. Accept the packet unmodified instead. */ - if (tcplen > tcph->doff*4) + * without moving it, and doing so may make the SYN packet + * itself too large. Accept the packet unmodified instead. + */ + if (len > tcp_hdrlen) return 0; /* @@ -143,10 +147,10 @@ tcpmss_mangle_packet(struct sk_buff *skb, newmss = min(newmss, (u16)1220); opt = (u_int8_t *)tcph + sizeof(struct tcphdr); - memmove(opt + TCPOLEN_MSS, opt, tcplen - sizeof(struct tcphdr)); + memmove(opt + TCPOLEN_MSS, opt, len - sizeof(struct tcphdr)); inet_proto_csum_replace2(&tcph->check, skb, - htons(tcplen), htons(tcplen + TCPOLEN_MSS), 1); + htons(len), htons(len + TCPOLEN_MSS), 1); opt[0] = TCPOPT_MSS; opt[1] = TCPOLEN_MSS; opt[2] = (newmss & 0xff00) >> 8; diff --git a/net/netfilter/xt_TCPOPTSTRIP.c b/net/netfilter/xt_TCPOPTSTRIP.c index b68fa191710f..625fa1d636a0 100644 --- a/net/netfilter/xt_TCPOPTSTRIP.c +++ b/net/netfilter/xt_TCPOPTSTRIP.c @@ -38,7 +38,7 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, struct tcphdr *tcph; u_int16_t n, o; u_int8_t *opt; - int len; + int len, tcp_hdrlen; /* This is a fragment, no TCP header is available */ if (par->fragoff != 0) @@ -52,7 +52,9 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, return NF_DROP; tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); - if (tcph->doff * 4 > len) + tcp_hdrlen = tcph->doff * 4; + + if (len < tcp_hdrlen) return NF_DROP; opt = (u_int8_t *)tcph; @@ -61,10 +63,10 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, * Walk through all TCP options - if we find some option to remove, * set all octets to %TCPOPT_NOP and adjust checksum. */ - for (i = sizeof(struct tcphdr); i < tcp_hdrlen(skb); i += optl) { + for (i = sizeof(struct tcphdr); i < tcp_hdrlen - 1; i += optl) { optl = optlen(opt, i); - if (i + optl > tcp_hdrlen(skb)) + if (i + optl > tcp_hdrlen) break; if (!tcpoptstrip_test_bit(info->strip_bmap, opt[i])) diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index f8b71911037a..20b15916f403 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -172,7 +172,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ - if (info && info->flags & XT_SOCKET_TRANSPARENT) + if (info->flags & XT_SOCKET_TRANSPARENT) transparent = ((sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->transparent) || (sk->sk_state == TCP_TIME_WAIT && @@ -196,7 +196,11 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, static bool socket_mt4_v0(const struct sk_buff *skb, struct xt_action_param *par) { - return socket_match(skb, par, NULL); + static struct xt_socket_mtinfo1 xt_info_v0 = { + .flags = 0, + }; + + return socket_match(skb, par, &xt_info_v0); } static bool @@ -314,7 +318,7 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ - if (info && info->flags & XT_SOCKET_TRANSPARENT) + if (info->flags & XT_SOCKET_TRANSPARENT) transparent = ((sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->transparent) || (sk->sk_state == TCP_TIME_WAIT && diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index c15042f987bd..a1100640495d 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -691,8 +691,8 @@ static int netlbl_cipsov4_remove_cb(struct netlbl_dom_map *entry, void *arg) { struct netlbl_domhsh_walk_arg *cb_arg = arg; - if (entry->type == NETLBL_NLTYPE_CIPSOV4 && - entry->type_def.cipsov4->doi == cb_arg->doi) + if (entry->def.type == NETLBL_NLTYPE_CIPSOV4 && + entry->def.cipso->doi == cb_arg->doi) return netlbl_domhsh_remove_entry(entry, cb_arg->audit_info); return 0; diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index 6bb1d42f0fac..85d842e6e431 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -84,15 +84,15 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry) #endif /* IPv6 */ ptr = container_of(entry, struct netlbl_dom_map, rcu); - if (ptr->type == NETLBL_NLTYPE_ADDRSELECT) { + if (ptr->def.type == NETLBL_NLTYPE_ADDRSELECT) { netlbl_af4list_foreach_safe(iter4, tmp4, - &ptr->type_def.addrsel->list4) { + &ptr->def.addrsel->list4) { netlbl_af4list_remove_entry(iter4); kfree(netlbl_domhsh_addr4_entry(iter4)); } #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_safe(iter6, tmp6, - &ptr->type_def.addrsel->list6) { + &ptr->def.addrsel->list6) { netlbl_af6list_remove_entry(iter6); kfree(netlbl_domhsh_addr6_entry(iter6)); } @@ -213,21 +213,21 @@ static void netlbl_domhsh_audit_add(struct netlbl_dom_map *entry, if (addr4 != NULL) { struct netlbl_domaddr4_map *map4; map4 = netlbl_domhsh_addr4_entry(addr4); - type = map4->type; - cipsov4 = map4->type_def.cipsov4; + type = map4->def.type; + cipsov4 = map4->def.cipso; netlbl_af4list_audit_addr(audit_buf, 0, NULL, addr4->addr, addr4->mask); #if IS_ENABLED(CONFIG_IPV6) } else if (addr6 != NULL) { struct netlbl_domaddr6_map *map6; map6 = netlbl_domhsh_addr6_entry(addr6); - type = map6->type; + type = map6->def.type; netlbl_af6list_audit_addr(audit_buf, 0, NULL, &addr6->addr, &addr6->mask); #endif /* IPv6 */ } else { - type = entry->type; - cipsov4 = entry->type_def.cipsov4; + type = entry->def.type; + cipsov4 = entry->def.cipso; } switch (type) { case NETLBL_NLTYPE_UNLABELED: @@ -265,26 +265,25 @@ static int netlbl_domhsh_validate(const struct netlbl_dom_map *entry) if (entry == NULL) return -EINVAL; - switch (entry->type) { + switch (entry->def.type) { case NETLBL_NLTYPE_UNLABELED: - if (entry->type_def.cipsov4 != NULL || - entry->type_def.addrsel != NULL) + if (entry->def.cipso != NULL || entry->def.addrsel != NULL) return -EINVAL; break; case NETLBL_NLTYPE_CIPSOV4: - if (entry->type_def.cipsov4 == NULL) + if (entry->def.cipso == NULL) return -EINVAL; break; case NETLBL_NLTYPE_ADDRSELECT: - netlbl_af4list_foreach(iter4, &entry->type_def.addrsel->list4) { + netlbl_af4list_foreach(iter4, &entry->def.addrsel->list4) { map4 = netlbl_domhsh_addr4_entry(iter4); - switch (map4->type) { + switch (map4->def.type) { case NETLBL_NLTYPE_UNLABELED: - if (map4->type_def.cipsov4 != NULL) + if (map4->def.cipso != NULL) return -EINVAL; break; case NETLBL_NLTYPE_CIPSOV4: - if (map4->type_def.cipsov4 == NULL) + if (map4->def.cipso == NULL) return -EINVAL; break; default: @@ -292,9 +291,9 @@ static int netlbl_domhsh_validate(const struct netlbl_dom_map *entry) } } #if IS_ENABLED(CONFIG_IPV6) - netlbl_af6list_foreach(iter6, &entry->type_def.addrsel->list6) { + netlbl_af6list_foreach(iter6, &entry->def.addrsel->list6) { map6 = netlbl_domhsh_addr6_entry(iter6); - switch (map6->type) { + switch (map6->def.type) { case NETLBL_NLTYPE_UNLABELED: break; default: @@ -402,32 +401,31 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry, rcu_assign_pointer(netlbl_domhsh_def, entry); } - if (entry->type == NETLBL_NLTYPE_ADDRSELECT) { + if (entry->def.type == NETLBL_NLTYPE_ADDRSELECT) { netlbl_af4list_foreach_rcu(iter4, - &entry->type_def.addrsel->list4) + &entry->def.addrsel->list4) netlbl_domhsh_audit_add(entry, iter4, NULL, ret_val, audit_info); #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(iter6, - &entry->type_def.addrsel->list6) + &entry->def.addrsel->list6) netlbl_domhsh_audit_add(entry, NULL, iter6, ret_val, audit_info); #endif /* IPv6 */ } else netlbl_domhsh_audit_add(entry, NULL, NULL, ret_val, audit_info); - } else if (entry_old->type == NETLBL_NLTYPE_ADDRSELECT && - entry->type == NETLBL_NLTYPE_ADDRSELECT) { + } else if (entry_old->def.type == NETLBL_NLTYPE_ADDRSELECT && + entry->def.type == NETLBL_NLTYPE_ADDRSELECT) { struct list_head *old_list4; struct list_head *old_list6; - old_list4 = &entry_old->type_def.addrsel->list4; - old_list6 = &entry_old->type_def.addrsel->list6; + old_list4 = &entry_old->def.addrsel->list4; + old_list6 = &entry_old->def.addrsel->list6; /* we only allow the addition of address selectors if all of * the selectors do not exist in the existing domain map */ - netlbl_af4list_foreach_rcu(iter4, - &entry->type_def.addrsel->list4) + netlbl_af4list_foreach_rcu(iter4, &entry->def.addrsel->list4) if (netlbl_af4list_search_exact(iter4->addr, iter4->mask, old_list4)) { @@ -435,8 +433,7 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry, goto add_return; } #if IS_ENABLED(CONFIG_IPV6) - netlbl_af6list_foreach_rcu(iter6, - &entry->type_def.addrsel->list6) + netlbl_af6list_foreach_rcu(iter6, &entry->def.addrsel->list6) if (netlbl_af6list_search_exact(&iter6->addr, &iter6->mask, old_list6)) { @@ -446,7 +443,7 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry, #endif /* IPv6 */ netlbl_af4list_foreach_safe(iter4, tmp4, - &entry->type_def.addrsel->list4) { + &entry->def.addrsel->list4) { netlbl_af4list_remove_entry(iter4); iter4->valid = 1; ret_val = netlbl_af4list_add(iter4, old_list4); @@ -457,7 +454,7 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry, } #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_safe(iter6, tmp6, - &entry->type_def.addrsel->list6) { + &entry->def.addrsel->list6) { netlbl_af6list_remove_entry(iter6); iter6->valid = 1; ret_val = netlbl_af6list_add(iter6, old_list6); @@ -538,18 +535,18 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, struct netlbl_af4list *iter4; struct netlbl_domaddr4_map *map4; - switch (entry->type) { + switch (entry->def.type) { case NETLBL_NLTYPE_ADDRSELECT: netlbl_af4list_foreach_rcu(iter4, - &entry->type_def.addrsel->list4) { + &entry->def.addrsel->list4) { map4 = netlbl_domhsh_addr4_entry(iter4); - cipso_v4_doi_putdef(map4->type_def.cipsov4); + cipso_v4_doi_putdef(map4->def.cipso); } /* no need to check the IPv6 list since we currently * support only unlabeled protocols for IPv6 */ break; case NETLBL_NLTYPE_CIPSOV4: - cipso_v4_doi_putdef(entry->type_def.cipsov4); + cipso_v4_doi_putdef(entry->def.cipso); break; } call_rcu(&entry->rcu, netlbl_domhsh_free_entry); @@ -590,20 +587,21 @@ int netlbl_domhsh_remove_af4(const char *domain, entry_map = netlbl_domhsh_search(domain); else entry_map = netlbl_domhsh_search_def(domain); - if (entry_map == NULL || entry_map->type != NETLBL_NLTYPE_ADDRSELECT) + if (entry_map == NULL || + entry_map->def.type != NETLBL_NLTYPE_ADDRSELECT) goto remove_af4_failure; spin_lock(&netlbl_domhsh_lock); entry_addr = netlbl_af4list_remove(addr->s_addr, mask->s_addr, - &entry_map->type_def.addrsel->list4); + &entry_map->def.addrsel->list4); spin_unlock(&netlbl_domhsh_lock); if (entry_addr == NULL) goto remove_af4_failure; - netlbl_af4list_foreach_rcu(iter4, &entry_map->type_def.addrsel->list4) + netlbl_af4list_foreach_rcu(iter4, &entry_map->def.addrsel->list4) goto remove_af4_single_addr; #if IS_ENABLED(CONFIG_IPV6) - netlbl_af6list_foreach_rcu(iter6, &entry_map->type_def.addrsel->list6) + netlbl_af6list_foreach_rcu(iter6, &entry_map->def.addrsel->list6) goto remove_af4_single_addr; #endif /* IPv6 */ /* the domain mapping is empty so remove it from the mapping table */ @@ -616,7 +614,7 @@ remove_af4_single_addr: * shouldn't be a problem */ synchronize_rcu(); entry = netlbl_domhsh_addr4_entry(entry_addr); - cipso_v4_doi_putdef(entry->type_def.cipsov4); + cipso_v4_doi_putdef(entry->def.cipso); kfree(entry); return 0; @@ -693,8 +691,8 @@ struct netlbl_dom_map *netlbl_domhsh_getentry(const char *domain) * responsible for ensuring that rcu_read_[un]lock() is called. * */ -struct netlbl_domaddr4_map *netlbl_domhsh_getentry_af4(const char *domain, - __be32 addr) +struct netlbl_dommap_def *netlbl_domhsh_getentry_af4(const char *domain, + __be32 addr) { struct netlbl_dom_map *dom_iter; struct netlbl_af4list *addr_iter; @@ -702,15 +700,13 @@ struct netlbl_domaddr4_map *netlbl_domhsh_getentry_af4(const char *domain, dom_iter = netlbl_domhsh_search_def(domain); if (dom_iter == NULL) return NULL; - if (dom_iter->type != NETLBL_NLTYPE_ADDRSELECT) - return NULL; - addr_iter = netlbl_af4list_search(addr, - &dom_iter->type_def.addrsel->list4); + if (dom_iter->def.type != NETLBL_NLTYPE_ADDRSELECT) + return &dom_iter->def; + addr_iter = netlbl_af4list_search(addr, &dom_iter->def.addrsel->list4); if (addr_iter == NULL) return NULL; - - return netlbl_domhsh_addr4_entry(addr_iter); + return &(netlbl_domhsh_addr4_entry(addr_iter)->def); } #if IS_ENABLED(CONFIG_IPV6) @@ -725,7 +721,7 @@ struct netlbl_domaddr4_map *netlbl_domhsh_getentry_af4(const char *domain, * responsible for ensuring that rcu_read_[un]lock() is called. * */ -struct netlbl_domaddr6_map *netlbl_domhsh_getentry_af6(const char *domain, +struct netlbl_dommap_def *netlbl_domhsh_getentry_af6(const char *domain, const struct in6_addr *addr) { struct netlbl_dom_map *dom_iter; @@ -734,15 +730,13 @@ struct netlbl_domaddr6_map *netlbl_domhsh_getentry_af6(const char *domain, dom_iter = netlbl_domhsh_search_def(domain); if (dom_iter == NULL) return NULL; - if (dom_iter->type != NETLBL_NLTYPE_ADDRSELECT) - return NULL; - addr_iter = netlbl_af6list_search(addr, - &dom_iter->type_def.addrsel->list6); + if (dom_iter->def.type != NETLBL_NLTYPE_ADDRSELECT) + return &dom_iter->def; + addr_iter = netlbl_af6list_search(addr, &dom_iter->def.addrsel->list6); if (addr_iter == NULL) return NULL; - - return netlbl_domhsh_addr6_entry(addr_iter); + return &(netlbl_domhsh_addr6_entry(addr_iter)->def); } #endif /* IPv6 */ diff --git a/net/netlabel/netlabel_domainhash.h b/net/netlabel/netlabel_domainhash.h index 90872c4ca30f..b9be0eed8980 100644 --- a/net/netlabel/netlabel_domainhash.h +++ b/net/netlabel/netlabel_domainhash.h @@ -43,37 +43,35 @@ #define NETLBL_DOMHSH_BITSIZE 7 /* Domain mapping definition structures */ +struct netlbl_domaddr_map { + struct list_head list4; + struct list_head list6; +}; +struct netlbl_dommap_def { + u32 type; + union { + struct netlbl_domaddr_map *addrsel; + struct cipso_v4_doi *cipso; + }; +}; #define netlbl_domhsh_addr4_entry(iter) \ container_of(iter, struct netlbl_domaddr4_map, list) struct netlbl_domaddr4_map { - u32 type; - union { - struct cipso_v4_doi *cipsov4; - } type_def; + struct netlbl_dommap_def def; struct netlbl_af4list list; }; #define netlbl_domhsh_addr6_entry(iter) \ container_of(iter, struct netlbl_domaddr6_map, list) struct netlbl_domaddr6_map { - u32 type; - - /* NOTE: no 'type_def' union needed at present since we don't currently - * support any IPv6 labeling protocols */ + struct netlbl_dommap_def def; struct netlbl_af6list list; }; -struct netlbl_domaddr_map { - struct list_head list4; - struct list_head list6; -}; + struct netlbl_dom_map { char *domain; - u32 type; - union { - struct cipso_v4_doi *cipsov4; - struct netlbl_domaddr_map *addrsel; - } type_def; + struct netlbl_dommap_def def; u32 valid; struct list_head list; @@ -97,16 +95,16 @@ int netlbl_domhsh_remove_af4(const char *domain, int netlbl_domhsh_remove(const char *domain, struct netlbl_audit *audit_info); int netlbl_domhsh_remove_default(struct netlbl_audit *audit_info); struct netlbl_dom_map *netlbl_domhsh_getentry(const char *domain); -struct netlbl_domaddr4_map *netlbl_domhsh_getentry_af4(const char *domain, - __be32 addr); +struct netlbl_dommap_def *netlbl_domhsh_getentry_af4(const char *domain, + __be32 addr); +#if IS_ENABLED(CONFIG_IPV6) +struct netlbl_dommap_def *netlbl_domhsh_getentry_af6(const char *domain, + const struct in6_addr *addr); +#endif /* IPv6 */ + int netlbl_domhsh_walk(u32 *skip_bkt, u32 *skip_chain, int (*callback) (struct netlbl_dom_map *entry, void *arg), void *cb_arg); -#if IS_ENABLED(CONFIG_IPV6) -struct netlbl_domaddr6_map *netlbl_domhsh_getentry_af6(const char *domain, - const struct in6_addr *addr); -#endif /* IPv6 */ - #endif diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 7c94aedd0912..96a458e12f60 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -122,7 +122,7 @@ int netlbl_cfg_unlbl_map_add(const char *domain, } if (addr == NULL && mask == NULL) - entry->type = NETLBL_NLTYPE_UNLABELED; + entry->def.type = NETLBL_NLTYPE_UNLABELED; else if (addr != NULL && mask != NULL) { addrmap = kzalloc(sizeof(*addrmap), GFP_ATOMIC); if (addrmap == NULL) @@ -137,7 +137,7 @@ int netlbl_cfg_unlbl_map_add(const char *domain, map4 = kzalloc(sizeof(*map4), GFP_ATOMIC); if (map4 == NULL) goto cfg_unlbl_map_add_failure; - map4->type = NETLBL_NLTYPE_UNLABELED; + map4->def.type = NETLBL_NLTYPE_UNLABELED; map4->list.addr = addr4->s_addr & mask4->s_addr; map4->list.mask = mask4->s_addr; map4->list.valid = 1; @@ -154,7 +154,7 @@ int netlbl_cfg_unlbl_map_add(const char *domain, map6 = kzalloc(sizeof(*map6), GFP_ATOMIC); if (map6 == NULL) goto cfg_unlbl_map_add_failure; - map6->type = NETLBL_NLTYPE_UNLABELED; + map6->def.type = NETLBL_NLTYPE_UNLABELED; map6->list.addr = *addr6; map6->list.addr.s6_addr32[0] &= mask6->s6_addr32[0]; map6->list.addr.s6_addr32[1] &= mask6->s6_addr32[1]; @@ -174,8 +174,8 @@ int netlbl_cfg_unlbl_map_add(const char *domain, break; } - entry->type_def.addrsel = addrmap; - entry->type = NETLBL_NLTYPE_ADDRSELECT; + entry->def.addrsel = addrmap; + entry->def.type = NETLBL_NLTYPE_ADDRSELECT; } else { ret_val = -EINVAL; goto cfg_unlbl_map_add_failure; @@ -355,8 +355,8 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, } if (addr == NULL && mask == NULL) { - entry->type_def.cipsov4 = doi_def; - entry->type = NETLBL_NLTYPE_CIPSOV4; + entry->def.cipso = doi_def; + entry->def.type = NETLBL_NLTYPE_CIPSOV4; } else if (addr != NULL && mask != NULL) { addrmap = kzalloc(sizeof(*addrmap), GFP_ATOMIC); if (addrmap == NULL) @@ -367,8 +367,8 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, addrinfo = kzalloc(sizeof(*addrinfo), GFP_ATOMIC); if (addrinfo == NULL) goto out_addrinfo; - addrinfo->type_def.cipsov4 = doi_def; - addrinfo->type = NETLBL_NLTYPE_CIPSOV4; + addrinfo->def.cipso = doi_def; + addrinfo->def.type = NETLBL_NLTYPE_CIPSOV4; addrinfo->list.addr = addr->s_addr & mask->s_addr; addrinfo->list.mask = mask->s_addr; addrinfo->list.valid = 1; @@ -376,8 +376,8 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, if (ret_val != 0) goto cfg_cipsov4_map_add_failure; - entry->type_def.addrsel = addrmap; - entry->type = NETLBL_NLTYPE_ADDRSELECT; + entry->def.addrsel = addrmap; + entry->def.type = NETLBL_NLTYPE_ADDRSELECT; } else { ret_val = -EINVAL; goto out_addrmap; @@ -657,14 +657,14 @@ int netlbl_sock_setattr(struct sock *sk, } switch (family) { case AF_INET: - switch (dom_entry->type) { + switch (dom_entry->def.type) { case NETLBL_NLTYPE_ADDRSELECT: ret_val = -EDESTADDRREQ; break; case NETLBL_NLTYPE_CIPSOV4: ret_val = cipso_v4_sock_setattr(sk, - dom_entry->type_def.cipsov4, - secattr); + dom_entry->def.cipso, + secattr); break; case NETLBL_NLTYPE_UNLABELED: ret_val = 0; @@ -754,23 +754,22 @@ int netlbl_conn_setattr(struct sock *sk, { int ret_val; struct sockaddr_in *addr4; - struct netlbl_domaddr4_map *af4_entry; + struct netlbl_dommap_def *entry; rcu_read_lock(); switch (addr->sa_family) { case AF_INET: addr4 = (struct sockaddr_in *)addr; - af4_entry = netlbl_domhsh_getentry_af4(secattr->domain, - addr4->sin_addr.s_addr); - if (af4_entry == NULL) { + entry = netlbl_domhsh_getentry_af4(secattr->domain, + addr4->sin_addr.s_addr); + if (entry == NULL) { ret_val = -ENOENT; goto conn_setattr_return; } - switch (af4_entry->type) { + switch (entry->type) { case NETLBL_NLTYPE_CIPSOV4: ret_val = cipso_v4_sock_setattr(sk, - af4_entry->type_def.cipsov4, - secattr); + entry->cipso, secattr); break; case NETLBL_NLTYPE_UNLABELED: /* just delete the protocols we support for right now @@ -812,36 +811,21 @@ int netlbl_req_setattr(struct request_sock *req, const struct netlbl_lsm_secattr *secattr) { int ret_val; - struct netlbl_dom_map *dom_entry; - struct netlbl_domaddr4_map *af4_entry; - u32 proto_type; - struct cipso_v4_doi *proto_cv4; + struct netlbl_dommap_def *entry; rcu_read_lock(); - dom_entry = netlbl_domhsh_getentry(secattr->domain); - if (dom_entry == NULL) { - ret_val = -ENOENT; - goto req_setattr_return; - } switch (req->rsk_ops->family) { case AF_INET: - if (dom_entry->type == NETLBL_NLTYPE_ADDRSELECT) { - struct inet_request_sock *req_inet = inet_rsk(req); - af4_entry = netlbl_domhsh_getentry_af4(secattr->domain, - req_inet->rmt_addr); - if (af4_entry == NULL) { - ret_val = -ENOENT; - goto req_setattr_return; - } - proto_type = af4_entry->type; - proto_cv4 = af4_entry->type_def.cipsov4; - } else { - proto_type = dom_entry->type; - proto_cv4 = dom_entry->type_def.cipsov4; + entry = netlbl_domhsh_getentry_af4(secattr->domain, + inet_rsk(req)->rmt_addr); + if (entry == NULL) { + ret_val = -ENOENT; + goto req_setattr_return; } - switch (proto_type) { + switch (entry->type) { case NETLBL_NLTYPE_CIPSOV4: - ret_val = cipso_v4_req_setattr(req, proto_cv4, secattr); + ret_val = cipso_v4_req_setattr(req, + entry->cipso, secattr); break; case NETLBL_NLTYPE_UNLABELED: /* just delete the protocols we support for right now @@ -899,23 +883,21 @@ int netlbl_skbuff_setattr(struct sk_buff *skb, { int ret_val; struct iphdr *hdr4; - struct netlbl_domaddr4_map *af4_entry; + struct netlbl_dommap_def *entry; rcu_read_lock(); switch (family) { case AF_INET: hdr4 = ip_hdr(skb); - af4_entry = netlbl_domhsh_getentry_af4(secattr->domain, - hdr4->daddr); - if (af4_entry == NULL) { + entry = netlbl_domhsh_getentry_af4(secattr->domain,hdr4->daddr); + if (entry == NULL) { ret_val = -ENOENT; goto skbuff_setattr_return; } - switch (af4_entry->type) { + switch (entry->type) { case NETLBL_NLTYPE_CIPSOV4: - ret_val = cipso_v4_skbuff_setattr(skb, - af4_entry->type_def.cipsov4, - secattr); + ret_val = cipso_v4_skbuff_setattr(skb, entry->cipso, + secattr); break; case NETLBL_NLTYPE_UNLABELED: /* just delete the protocols we support for right now diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index c5384ffc6146..dd1c37d7acbc 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -104,7 +104,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = -ENOMEM; goto add_failure; } - entry->type = nla_get_u32(info->attrs[NLBL_MGMT_A_PROTOCOL]); + entry->def.type = nla_get_u32(info->attrs[NLBL_MGMT_A_PROTOCOL]); if (info->attrs[NLBL_MGMT_A_DOMAIN]) { size_t tmp_size = nla_len(info->attrs[NLBL_MGMT_A_DOMAIN]); entry->domain = kmalloc(tmp_size, GFP_KERNEL); @@ -116,12 +116,12 @@ static int netlbl_mgmt_add_common(struct genl_info *info, info->attrs[NLBL_MGMT_A_DOMAIN], tmp_size); } - /* NOTE: internally we allow/use a entry->type value of + /* NOTE: internally we allow/use a entry->def.type value of * NETLBL_NLTYPE_ADDRSELECT but we don't currently allow users * to pass that as a protocol value because we need to know the * "real" protocol */ - switch (entry->type) { + switch (entry->def.type) { case NETLBL_NLTYPE_UNLABELED: break; case NETLBL_NLTYPE_CIPSOV4: @@ -132,7 +132,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, cipsov4 = cipso_v4_doi_getdef(tmp_val); if (cipsov4 == NULL) goto add_failure; - entry->type_def.cipsov4 = cipsov4; + entry->def.cipso = cipsov4; break; default: goto add_failure; @@ -172,9 +172,9 @@ static int netlbl_mgmt_add_common(struct genl_info *info, map->list.addr = addr->s_addr & mask->s_addr; map->list.mask = mask->s_addr; map->list.valid = 1; - map->type = entry->type; + map->def.type = entry->def.type; if (cipsov4) - map->type_def.cipsov4 = cipsov4; + map->def.cipso = cipsov4; ret_val = netlbl_af4list_add(&map->list, &addrmap->list4); if (ret_val != 0) { @@ -182,8 +182,8 @@ static int netlbl_mgmt_add_common(struct genl_info *info, goto add_failure; } - entry->type = NETLBL_NLTYPE_ADDRSELECT; - entry->type_def.addrsel = addrmap; + entry->def.type = NETLBL_NLTYPE_ADDRSELECT; + entry->def.addrsel = addrmap; #if IS_ENABLED(CONFIG_IPV6) } else if (info->attrs[NLBL_MGMT_A_IPV6ADDR]) { struct in6_addr *addr; @@ -223,7 +223,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, map->list.addr.s6_addr32[3] &= mask->s6_addr32[3]; map->list.mask = *mask; map->list.valid = 1; - map->type = entry->type; + map->def.type = entry->def.type; ret_val = netlbl_af6list_add(&map->list, &addrmap->list6); if (ret_val != 0) { @@ -231,8 +231,8 @@ static int netlbl_mgmt_add_common(struct genl_info *info, goto add_failure; } - entry->type = NETLBL_NLTYPE_ADDRSELECT; - entry->type_def.addrsel = addrmap; + entry->def.type = NETLBL_NLTYPE_ADDRSELECT; + entry->def.addrsel = addrmap; #endif /* IPv6 */ } @@ -281,14 +281,13 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb, return ret_val; } - switch (entry->type) { + switch (entry->def.type) { case NETLBL_NLTYPE_ADDRSELECT: nla_a = nla_nest_start(skb, NLBL_MGMT_A_SELECTORLIST); if (nla_a == NULL) return -ENOMEM; - netlbl_af4list_foreach_rcu(iter4, - &entry->type_def.addrsel->list4) { + netlbl_af4list_foreach_rcu(iter4, &entry->def.addrsel->list4) { struct netlbl_domaddr4_map *map4; struct in_addr addr_struct; @@ -310,13 +309,13 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb, return ret_val; map4 = netlbl_domhsh_addr4_entry(iter4); ret_val = nla_put_u32(skb, NLBL_MGMT_A_PROTOCOL, - map4->type); + map4->def.type); if (ret_val != 0) return ret_val; - switch (map4->type) { + switch (map4->def.type) { case NETLBL_NLTYPE_CIPSOV4: ret_val = nla_put_u32(skb, NLBL_MGMT_A_CV4DOI, - map4->type_def.cipsov4->doi); + map4->def.cipso->doi); if (ret_val != 0) return ret_val; break; @@ -325,8 +324,7 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb, nla_nest_end(skb, nla_b); } #if IS_ENABLED(CONFIG_IPV6) - netlbl_af6list_foreach_rcu(iter6, - &entry->type_def.addrsel->list6) { + netlbl_af6list_foreach_rcu(iter6, &entry->def.addrsel->list6) { struct netlbl_domaddr6_map *map6; nla_b = nla_nest_start(skb, NLBL_MGMT_A_ADDRSELECTOR); @@ -345,7 +343,7 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb, return ret_val; map6 = netlbl_domhsh_addr6_entry(iter6); ret_val = nla_put_u32(skb, NLBL_MGMT_A_PROTOCOL, - map6->type); + map6->def.type); if (ret_val != 0) return ret_val; @@ -356,14 +354,14 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb, nla_nest_end(skb, nla_a); break; case NETLBL_NLTYPE_UNLABELED: - ret_val = nla_put_u32(skb, NLBL_MGMT_A_PROTOCOL, entry->type); + ret_val = nla_put_u32(skb,NLBL_MGMT_A_PROTOCOL,entry->def.type); break; case NETLBL_NLTYPE_CIPSOV4: - ret_val = nla_put_u32(skb, NLBL_MGMT_A_PROTOCOL, entry->type); + ret_val = nla_put_u32(skb,NLBL_MGMT_A_PROTOCOL,entry->def.type); if (ret_val != 0) return ret_val; ret_val = nla_put_u32(skb, NLBL_MGMT_A_CV4DOI, - entry->type_def.cipsov4->doi); + entry->def.cipso->doi); break; } diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index af3531926ee0..8f0897407a2c 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1541,7 +1541,7 @@ int __init netlbl_unlabel_defconf(void) entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (entry == NULL) return -ENOMEM; - entry->type = NETLBL_NLTYPE_UNLABELED; + entry->def.type = NETLBL_NLTYPE_UNLABELED; ret_val = netlbl_domhsh_add_default(entry, &audit_info); if (ret_val != 0) return ret_val; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 2fd6dbea327a..f85f8a2ad6cf 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -571,7 +571,7 @@ static int genl_family_rcv_msg(struct genl_family *family, !capable(CAP_NET_ADMIN)) return -EPERM; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ops->dumpit, .done = ops->done, @@ -789,6 +789,10 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) struct net *net = sock_net(skb->sk); int chains_to_skip = cb->args[0]; int fams_to_skip = cb->args[1]; + bool need_locking = chains_to_skip || fams_to_skip; + + if (need_locking) + genl_lock(); for (i = chains_to_skip; i < GENL_FAM_TAB_SIZE; i++) { n = 0; @@ -810,6 +814,9 @@ errout: cb->args[0] = i; cb->args[1] = n; + if (need_locking) + genl_unlock(); + return skb->len; } @@ -877,8 +884,10 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) #ifdef CONFIG_MODULES if (res == NULL) { genl_unlock(); + up_read(&cb_lock); request_module("net-pf-%d-proto-%d-family-%s", PF_NETLINK, NETLINK_GENERIC, name); + down_read(&cb_lock); genl_lock(); res = genl_family_find_byname(name); } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 22c5f399f1cf..ab101f715447 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -535,6 +535,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb) { struct sw_flow_actions *acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts); + OVS_CB(skb)->tun_key = NULL; return do_execute_actions(dp, skb, acts->actions, acts->actions_len, false); } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index f7e3a0d84c40..f2ed7600084e 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2076,9 +2076,6 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) ovs_notify(reply, info, &ovs_dp_vport_multicast_group); return 0; - rtnl_unlock(); - return 0; - exit_free: kfree_skb(reply); exit_unlock: diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 5c519b121e1b..1aa84dc58777 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -240,7 +240,7 @@ static struct flex_array *alloc_buckets(unsigned int n_buckets) struct flex_array *buckets; int i, err; - buckets = flex_array_alloc(sizeof(struct hlist_head *), + buckets = flex_array_alloc(sizeof(struct hlist_head), n_buckets, GFP_KERNEL); if (!buckets) return NULL; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 281c1bded1f6..51b968d3febb 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -285,6 +285,45 @@ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind) return q; } +/* The linklayer setting were not transferred from iproute2, in older + * versions, and the rate tables lookup systems have been dropped in + * the kernel. To keep backward compatible with older iproute2 tc + * utils, we detect the linklayer setting by detecting if the rate + * table were modified. + * + * For linklayer ATM table entries, the rate table will be aligned to + * 48 bytes, thus some table entries will contain the same value. The + * mpu (min packet unit) is also encoded into the old rate table, thus + * starting from the mpu, we find low and high table entries for + * mapping this cell. If these entries contain the same value, when + * the rate tables have been modified for linklayer ATM. + * + * This is done by rounding mpu to the nearest 48 bytes cell/entry, + * and then roundup to the next cell, calc the table entry one below, + * and compare. + */ +static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab) +{ + int low = roundup(r->mpu, 48); + int high = roundup(low+1, 48); + int cell_low = low >> r->cell_log; + int cell_high = (high >> r->cell_log) - 1; + + /* rtab is too inaccurate at rates > 100Mbit/s */ + if ((r->rate > (100000000/8)) || (rtab[0] == 0)) { + pr_debug("TC linklayer: Giving up ATM detection\n"); + return TC_LINKLAYER_ETHERNET; + } + + if ((cell_high > cell_low) && (cell_high < 256) + && (rtab[cell_low] == rtab[cell_high])) { + pr_debug("TC linklayer: Detected ATM, low(%d)=high(%d)=%u\n", + cell_low, cell_high, rtab[cell_high]); + return TC_LINKLAYER_ATM; + } + return TC_LINKLAYER_ETHERNET; +} + static struct qdisc_rate_table *qdisc_rtab_list; struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab) @@ -308,6 +347,8 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *ta rtab->rate = *r; rtab->refcnt = 1; memcpy(rtab->data, nla_data(tab), 1024); + if (r->linklayer == TC_LINKLAYER_UNAWARE) + r->linklayer = __detect_linklayer(r, rtab->data); rtab->next = qdisc_rtab_list; qdisc_rtab_list = rtab; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index ca8e0a57d945..1f9c31411f19 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -605,6 +605,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, struct sockaddr_atmpvc pvc; int state; + memset(&pvc, 0, sizeof(pvc)); pvc.sap_family = AF_ATMPVC; pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; pvc.sap_addr.vpi = flow->vcc->vpi; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 71a568862557..7a42c81a19eb 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1465,6 +1465,7 @@ static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_wrropt opt; + memset(&opt, 0, sizeof(opt)); opt.flags = 0; opt.allot = cl->allot; opt.priority = cl->priority + 1; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 4626cef4b76e..48be3d5c0d92 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -25,6 +25,7 @@ #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/if_vlan.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> @@ -207,15 +208,19 @@ void __qdisc_run(struct Qdisc *q) unsigned long dev_trans_start(struct net_device *dev) { - unsigned long val, res = dev->trans_start; + unsigned long val, res; unsigned int i; + if (is_vlan_dev(dev)) + dev = vlan_dev_real_dev(dev); + res = dev->trans_start; for (i = 0; i < dev->num_tx_queues; i++) { val = netdev_get_tx_queue(dev, i)->trans_start; if (val && time_after(val, res)) res = val; } dev->trans_start = res; + return res; } EXPORT_SYMBOL(dev_trans_start); @@ -904,6 +909,7 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r, memset(r, 0, sizeof(*r)); r->overhead = conf->overhead; r->rate_bytes_ps = conf->rate; + r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK); r->mult = 1; /* * The deal here is to replace a divide by a reciprocal one diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index c2124ea29f45..c2178b15ca6e 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -100,7 +100,7 @@ struct htb_class { struct psched_ratecfg ceil; s64 buffer, cbuffer;/* token bucket depth/rate */ s64 mbuffer; /* max wait time */ - int prio; /* these two are used only by leaves... */ + u32 prio; /* these two are used only by leaves... */ int quantum; /* but stored for parent-to-leaf return */ struct tcf_proto *filter_list; /* class attached filters */ @@ -1329,6 +1329,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)*arg, *parent; struct nlattr *opt = tca[TCA_OPTIONS]; + struct qdisc_rate_table *rtab = NULL, *ctab = NULL; struct nlattr *tb[TCA_HTB_MAX + 1]; struct tc_htb_opt *hopt; @@ -1350,6 +1351,18 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!hopt->rate.rate || !hopt->ceil.rate) goto failure; + /* Keeping backward compatible with rate_table based iproute2 tc */ + if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) { + rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]); + if (rtab) + qdisc_put_rtab(rtab); + } + if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE) { + ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]); + if (ctab) + qdisc_put_rtab(ctab); + } + if (!cl) { /* new class */ struct Qdisc *new_q; int prio; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index a7ab323849b6..8056fb4e618a 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -113,7 +113,6 @@ #define FRAC_BITS 30 /* fixed point arithmetic */ #define ONE_FP (1UL << FRAC_BITS) -#define IWSUM (ONE_FP/QFQ_MAX_WSUM) #define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */ #define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */ @@ -189,6 +188,7 @@ struct qfq_sched { struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */ u32 num_active_agg; /* Num. of active aggregates */ u32 wsum; /* weight sum */ + u32 iwsum; /* inverse weight sum */ unsigned long bitmaps[QFQ_MAX_STATE]; /* Group bitmaps. */ struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */ @@ -314,6 +314,7 @@ static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg, q->wsum += (int) agg->class_weight * (new_num_classes - agg->num_classes); + q->iwsum = ONE_FP / q->wsum; agg->num_classes = new_num_classes; } @@ -340,6 +341,10 @@ static void qfq_destroy_agg(struct qfq_sched *q, struct qfq_aggregate *agg) { if (!hlist_unhashed(&agg->nonfull_next)) hlist_del_init(&agg->nonfull_next); + q->wsum -= agg->class_weight; + if (q->wsum != 0) + q->iwsum = ONE_FP / q->wsum; + if (q->in_serv_agg == agg) q->in_serv_agg = qfq_choose_next_agg(q); kfree(agg); @@ -834,38 +839,60 @@ static void qfq_make_eligible(struct qfq_sched *q) } } - /* - * The index of the slot in which the aggregate is to be inserted must - * not be higher than QFQ_MAX_SLOTS-2. There is a '-2' and not a '-1' - * because the start time of the group may be moved backward by one - * slot after the aggregate has been inserted, and this would cause - * non-empty slots to be right-shifted by one position. + * The index of the slot in which the input aggregate agg is to be + * inserted must not be higher than QFQ_MAX_SLOTS-2. There is a '-2' + * and not a '-1' because the start time of the group may be moved + * backward by one slot after the aggregate has been inserted, and + * this would cause non-empty slots to be right-shifted by one + * position. + * + * QFQ+ fully satisfies this bound to the slot index if the parameters + * of the classes are not changed dynamically, and if QFQ+ never + * happens to postpone the service of agg unjustly, i.e., it never + * happens that the aggregate becomes backlogged and eligible, or just + * eligible, while an aggregate with a higher approximated finish time + * is being served. In particular, in this case QFQ+ guarantees that + * the timestamps of agg are low enough that the slot index is never + * higher than 2. Unfortunately, QFQ+ cannot provide the same + * guarantee if it happens to unjustly postpone the service of agg, or + * if the parameters of some class are changed. + * + * As for the first event, i.e., an out-of-order service, the + * upper bound to the slot index guaranteed by QFQ+ grows to + * 2 + + * QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) * + * (current_max_weight/current_wsum) <= 2 + 8 * 128 * 1. * - * If the weight and lmax (max_pkt_size) of the classes do not change, - * then QFQ+ does meet the above contraint according to the current - * values of its parameters. In fact, if the weight and lmax of the - * classes do not change, then, from the theory, QFQ+ guarantees that - * the slot index is never higher than - * 2 + QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) * - * (QFQ_MAX_WEIGHT/QFQ_MAX_WSUM) = 2 + 8 * 128 * (1 / 64) = 18 + * The following function deals with this problem by backward-shifting + * the timestamps of agg, if needed, so as to guarantee that the slot + * index is never higher than QFQ_MAX_SLOTS-2. This backward-shift may + * cause the service of other aggregates to be postponed, yet the + * worst-case guarantees of these aggregates are not violated. In + * fact, in case of no out-of-order service, the timestamps of agg + * would have been even lower than they are after the backward shift, + * because QFQ+ would have guaranteed a maximum value equal to 2 for + * the slot index, and 2 < QFQ_MAX_SLOTS-2. Hence the aggregates whose + * service is postponed because of the backward-shift would have + * however waited for the service of agg before being served. * - * When the weight of a class is increased or the lmax of the class is - * decreased, a new aggregate with smaller slot size than the original - * parent aggregate of the class may happen to be activated. The - * activation of this aggregate should be properly delayed to when the - * service of the class has finished in the ideal system tracked by - * QFQ+. If the activation of the aggregate is not delayed to this - * reference time instant, then this aggregate may be unjustly served - * before other aggregates waiting for service. This may cause the - * above bound to the slot index to be violated for some of these - * unlucky aggregates. + * The other event that may cause the slot index to be higher than 2 + * for agg is a recent change of the parameters of some class. If the + * weight of a class is increased or the lmax (max_pkt_size) of the + * class is decreased, then a new aggregate with smaller slot size + * than the original parent aggregate of the class may happen to be + * activated. The activation of this aggregate should be properly + * delayed to when the service of the class has finished in the ideal + * system tracked by QFQ+. If the activation of the aggregate is not + * delayed to this reference time instant, then this aggregate may be + * unjustly served before other aggregates waiting for service. This + * may cause the above bound to the slot index to be violated for some + * of these unlucky aggregates. * * Instead of delaying the activation of the new aggregate, which is - * quite complex, the following inaccurate but simple solution is used: - * if the slot index is higher than QFQ_MAX_SLOTS-2, then the - * timestamps of the aggregate are shifted backward so as to let the - * slot index become equal to QFQ_MAX_SLOTS-2. + * quite complex, the above-discussed capping of the slot index is + * used to handle also the consequences of a change of the parameters + * of a class. */ static void qfq_slot_insert(struct qfq_group *grp, struct qfq_aggregate *agg, u64 roundedS) @@ -1136,7 +1163,7 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) else in_serv_agg->budget -= len; - q->V += (u64)len * IWSUM; + q->V += (u64)len * q->iwsum; pr_debug("qfq dequeue: len %u F %lld now %lld\n", len, (unsigned long long) in_serv_agg->F, (unsigned long long) q->V); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index bce5b79662a6..ab67efc64b24 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -846,12 +846,12 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, else spc_state = SCTP_ADDR_AVAILABLE; /* Don't inform ULP about transition from PF to - * active state and set cwnd to 1, see SCTP + * active state and set cwnd to 1 MTU, see SCTP * Quick failover draft section 5.1, point 5 */ if (transport->state == SCTP_PF) { ulp_notify = false; - transport->cwnd = 1; + transport->cwnd = asoc->pathmtu; } transport->state = SCTP_ACTIVE; break; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index bdbbc3fd7c14..8fdd16046d66 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -181,12 +181,12 @@ static void sctp_transport_destroy(struct sctp_transport *transport) return; } - call_rcu(&transport->rcu, sctp_transport_destroy_rcu); - sctp_packet_free(&transport->packet); if (transport->asoc) sctp_association_put(transport->asoc); + + call_rcu(&transport->rcu, sctp_transport_destroy_rcu); } /* Start T3_rtx timer if it is not already running and update the heartbeat diff --git a/net/socket.c b/net/socket.c index 829b460acb87..b2d7c629eeb9 100644 --- a/net/socket.c +++ b/net/socket.c @@ -106,7 +106,7 @@ #include <linux/atalk.h> #include <net/busy_poll.h> -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; #endif diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index d304f41260f2..af7ffd447fee 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -120,7 +120,7 @@ static int gssp_rpc_create(struct net *net, struct rpc_clnt **_clnt) if (IS_ERR(clnt)) { dprintk("RPC: failed to create AF_LOCAL gssproxy " "client (errno %ld).\n", PTR_ERR(clnt)); - result = -PTR_ERR(clnt); + result = PTR_ERR(clnt); *_clnt = NULL; goto out; } @@ -328,7 +328,6 @@ void gssp_free_upcall_data(struct gssp_upcall_data *data) kfree(data->in_handle.data); kfree(data->out_handle.data); kfree(data->out_token.data); - kfree(data->mech_oid.data); free_svc_cred(&data->creds); } diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 357f613df7ff..3c85d1c8a028 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -430,7 +430,7 @@ static int dummy_enc_nameattr_array(struct xdr_stream *xdr, static int dummy_dec_nameattr_array(struct xdr_stream *xdr, struct gssx_name_attr_array *naa) { - struct gssx_name_attr dummy; + struct gssx_name_attr dummy = { .attr = {.len = 0} }; u32 count, i; __be32 *p; @@ -493,12 +493,13 @@ static int gssx_enc_name(struct xdr_stream *xdr, return err; } + static int gssx_dec_name(struct xdr_stream *xdr, struct gssx_name *name) { - struct xdr_netobj dummy_netobj; - struct gssx_name_attr_array dummy_name_attr_array; - struct gssx_option_array dummy_option_array; + struct xdr_netobj dummy_netobj = { .len = 0 }; + struct gssx_name_attr_array dummy_name_attr_array = { .count = 0 }; + struct gssx_option_array dummy_option_array = { .count = 0 }; int err; /* name->display_name */ diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index d0347d148b34..09fb638bcaa4 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1180,6 +1180,7 @@ static int gss_proxy_save_rsc(struct cache_detail *cd, gm = gss_mech_get_by_OID(&ud->mech_oid); if (!gm) goto out; + rsci.cred.cr_gss_mech = gm; status = -EINVAL; /* mech-specific data: */ @@ -1195,7 +1196,6 @@ static int gss_proxy_save_rsc(struct cache_detail *cd, rscp = rsc_update(cd, &rsci, rscp); status = 0; out: - gss_mech_put(gm); rsc_free(&rsci); if (rscp) cache_put(&rscp->h, cd); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 9963584605c0..ecbc4e3d83ad 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -309,6 +309,7 @@ static int rpc_client_register(const struct rpc_create_args *args, return 0; err_auth: pipefs_sb = rpc_get_sb_net(net); + rpc_unregister_client(clnt); __rpc_clnt_remove_pipedir(clnt); out: if (pipefs_sb) @@ -1659,6 +1660,10 @@ call_connect(struct rpc_task *task) task->tk_action = call_connect_status; if (task->tk_status < 0) return; + if (task->tk_flags & RPC_TASK_NOCONNECT) { + rpc_exit(task, -ENOTCONN); + return; + } xprt_connect(task); } } diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h index 74d948f5d5a1..779742cfc1ff 100644 --- a/net/sunrpc/netns.h +++ b/net/sunrpc/netns.h @@ -23,6 +23,7 @@ struct sunrpc_net { struct rpc_clnt *rpcb_local_clnt4; spinlock_t rpcb_clnt_lock; unsigned int rpcb_users; + unsigned int rpcb_is_af_local : 1; struct mutex gssp_lock; wait_queue_head_t gssp_wq; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 3df764dc330c..1891a1022c17 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -204,13 +204,15 @@ void rpcb_put_local(struct net *net) } static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt, - struct rpc_clnt *clnt4) + struct rpc_clnt *clnt4, + bool is_af_local) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); /* Protected by rpcb_create_local_mutex */ sn->rpcb_local_clnt = clnt; sn->rpcb_local_clnt4 = clnt4; + sn->rpcb_is_af_local = is_af_local ? 1 : 0; smp_wmb(); sn->rpcb_users = 1; dprintk("RPC: created new rpcb local clients (rpcb_local_clnt: " @@ -238,6 +240,14 @@ static int rpcb_create_local_unix(struct net *net) .program = &rpcb_program, .version = RPCBVERS_2, .authflavor = RPC_AUTH_NULL, + /* + * We turn off the idle timeout to prevent the kernel + * from automatically disconnecting the socket. + * Otherwise, we'd have to cache the mount namespace + * of the caller and somehow pass that to the socket + * reconnect code. + */ + .flags = RPC_CLNT_CREATE_NO_IDLE_TIMEOUT, }; struct rpc_clnt *clnt, *clnt4; int result = 0; @@ -263,7 +273,7 @@ static int rpcb_create_local_unix(struct net *net) clnt4 = NULL; } - rpcb_set_local(net, clnt, clnt4); + rpcb_set_local(net, clnt, clnt4, true); out: return result; @@ -315,7 +325,7 @@ static int rpcb_create_local_net(struct net *net) clnt4 = NULL; } - rpcb_set_local(net, clnt, clnt4); + rpcb_set_local(net, clnt, clnt4, false); out: return result; @@ -376,13 +386,16 @@ static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname, return rpc_create(&args); } -static int rpcb_register_call(struct rpc_clnt *clnt, struct rpc_message *msg) +static int rpcb_register_call(struct sunrpc_net *sn, struct rpc_clnt *clnt, struct rpc_message *msg, bool is_set) { - int result, error = 0; + int flags = RPC_TASK_NOCONNECT; + int error, result = 0; + if (is_set || !sn->rpcb_is_af_local) + flags = RPC_TASK_SOFTCONN; msg->rpc_resp = &result; - error = rpc_call_sync(clnt, msg, RPC_TASK_SOFTCONN); + error = rpc_call_sync(clnt, msg, flags); if (error < 0) { dprintk("RPC: failed to contact local rpcbind " "server (errno %d).\n", -error); @@ -439,16 +452,19 @@ int rpcb_register(struct net *net, u32 prog, u32 vers, int prot, unsigned short .rpc_argp = &map, }; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + bool is_set = false; dprintk("RPC: %sregistering (%u, %u, %d, %u) with local " "rpcbind\n", (port ? "" : "un"), prog, vers, prot, port); msg.rpc_proc = &rpcb_procedures2[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg.rpc_proc = &rpcb_procedures2[RPCBPROC_SET]; + is_set = true; + } - return rpcb_register_call(sn->rpcb_local_clnt, &msg); + return rpcb_register_call(sn, sn->rpcb_local_clnt, &msg, is_set); } /* @@ -461,6 +477,7 @@ static int rpcb_register_inet4(struct sunrpc_net *sn, const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin->sin_port); + bool is_set = false; int result; map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); @@ -471,10 +488,12 @@ static int rpcb_register_inet4(struct sunrpc_net *sn, map->r_addr, map->r_netid); msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; + is_set = true; + } - result = rpcb_register_call(sn->rpcb_local_clnt4, msg); + result = rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, is_set); kfree(map->r_addr); return result; } @@ -489,6 +508,7 @@ static int rpcb_register_inet6(struct sunrpc_net *sn, const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin6->sin6_port); + bool is_set = false; int result; map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); @@ -499,10 +519,12 @@ static int rpcb_register_inet6(struct sunrpc_net *sn, map->r_addr, map->r_netid); msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - if (port) + if (port != 0) { msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; + is_set = true; + } - result = rpcb_register_call(sn->rpcb_local_clnt4, msg); + result = rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, is_set); kfree(map->r_addr); return result; } @@ -519,7 +541,7 @@ static int rpcb_unregister_all_protofamilies(struct sunrpc_net *sn, map->r_addr = ""; msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; - return rpcb_register_call(sn->rpcb_local_clnt4, msg); + return rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, false); } /** diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 305374d4fb98..7762b9f8a8b7 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1193,7 +1193,9 @@ static int svc_tcp_has_wspace(struct svc_xprt *xprt) if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) return 1; required = atomic_read(&xprt->xpt_reserved) + serv->sv_max_mesg; - if (sk_stream_wspace(svsk->sk_sk) >= required) + if (sk_stream_wspace(svsk->sk_sk) >= required || + (sk_stream_min_wspace(svsk->sk_sk) == 0 && + atomic_read(&xprt->xpt_reserved) == 0)) return 1; set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); return 0; diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c index 8d2edddf48cf..65b146297f5a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c +++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c @@ -98,6 +98,7 @@ void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch, */ static u32 *decode_write_list(u32 *va, u32 *vaend) { + unsigned long start, end; int nchunks; struct rpcrdma_write_array *ary = @@ -113,9 +114,12 @@ static u32 *decode_write_list(u32 *va, u32 *vaend) return NULL; } nchunks = ntohl(ary->wc_nchunks); - if (((unsigned long)&ary->wc_array[0] + - (sizeof(struct rpcrdma_write_chunk) * nchunks)) > - (unsigned long)vaend) { + + start = (unsigned long)&ary->wc_array[0]; + end = (unsigned long)vaend; + if (nchunks < 0 || + nchunks > (SIZE_MAX - start) / sizeof(struct rpcrdma_write_chunk) || + (start + (sizeof(struct rpcrdma_write_chunk) * nchunks)) > end) { dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n", ary, nchunks, vaend); return NULL; @@ -129,6 +133,7 @@ static u32 *decode_write_list(u32 *va, u32 *vaend) static u32 *decode_reply_array(u32 *va, u32 *vaend) { + unsigned long start, end; int nchunks; struct rpcrdma_write_array *ary = (struct rpcrdma_write_array *)va; @@ -143,9 +148,12 @@ static u32 *decode_reply_array(u32 *va, u32 *vaend) return NULL; } nchunks = ntohl(ary->wc_nchunks); - if (((unsigned long)&ary->wc_array[0] + - (sizeof(struct rpcrdma_write_chunk) * nchunks)) > - (unsigned long)vaend) { + + start = (unsigned long)&ary->wc_array[0]; + end = (unsigned long)vaend; + if (nchunks < 0 || + nchunks > (SIZE_MAX - start) / sizeof(struct rpcrdma_write_chunk) || + (start + (sizeof(struct rpcrdma_write_chunk) * nchunks)) > end) { dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n", ary, nchunks, vaend); return NULL; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index cb29ef7ba2f0..609c30c80816 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -460,6 +460,7 @@ static void bearer_disable(struct tipc_bearer *b_ptr) { struct tipc_link *l_ptr; struct tipc_link *temp_l_ptr; + struct tipc_link_req *temp_req; pr_info("Disabling bearer <%s>\n", b_ptr->name); spin_lock_bh(&b_ptr->lock); @@ -468,9 +469,13 @@ static void bearer_disable(struct tipc_bearer *b_ptr) list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { tipc_link_delete(l_ptr); } - if (b_ptr->link_req) - tipc_disc_delete(b_ptr->link_req); + temp_req = b_ptr->link_req; + b_ptr->link_req = NULL; spin_unlock_bh(&b_ptr->lock); + + if (temp_req) + tipc_disc_delete(temp_req); + memset(b_ptr, 0, sizeof(struct tipc_bearer)); } diff --git a/net/tipc/server.c b/net/tipc/server.c index 19da5abe0fa6..fd3fa57a410e 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -355,8 +355,12 @@ static int tipc_open_listening_sock(struct tipc_server *s) return PTR_ERR(con); sock = tipc_create_listen_sock(con); - if (!sock) + if (!sock) { + idr_remove(&s->conn_idr, con->conid); + s->idr_in_use--; + kfree(con); return -EINVAL; + } tipc_register_callbacks(sock, con); return 0; @@ -563,9 +567,14 @@ int tipc_server_start(struct tipc_server *s) kmem_cache_destroy(s->rcvbuf_cache); return ret; } + ret = tipc_open_listening_sock(s); + if (ret < 0) { + tipc_work_stop(s); + kmem_cache_destroy(s->rcvbuf_cache); + return ret; + } s->enabled = 1; - - return tipc_open_listening_sock(s); + return ret; } void tipc_server_stop(struct tipc_server *s) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 593071dabd1c..4d9334683f84 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -347,7 +347,7 @@ void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)) for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) { struct vsock_sock *vsk; list_for_each_entry(vsk, &vsock_connected_table[i], - connected_table); + connected_table) fn(sk_vsock(vsk)); } |