diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/batman-adv/bat_iv_ogm.c | 30 | ||||
-rw-r--r-- | net/batman-adv/hard-interface.c | 22 | ||||
-rw-r--r-- | net/batman-adv/originator.c | 36 | ||||
-rw-r--r-- | net/batman-adv/originator.h | 4 | ||||
-rw-r--r-- | net/batman-adv/routing.c | 4 | ||||
-rw-r--r-- | net/batman-adv/send.c | 9 | ||||
-rw-r--r-- | net/batman-adv/translation-table.c | 23 | ||||
-rw-r--r-- | net/bluetooth/hidp/core.c | 16 | ||||
-rw-r--r-- | net/bluetooth/hidp/hidp.h | 4 | ||||
-rw-r--r-- | net/core/dev.c | 22 | ||||
-rw-r--r-- | net/core/flow_dissector.c | 20 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 19 | ||||
-rw-r--r-- | net/dccp/ccids/lib/tfrc.c | 2 | ||||
-rw-r--r-- | net/dccp/ccids/lib/tfrc.h | 1 | ||||
-rw-r--r-- | net/ipv4/ip_forward.c | 71 | ||||
-rw-r--r-- | net/ipv4/ipconfig.c | 2 | ||||
-rw-r--r-- | net/ipv4/route.c | 13 | ||||
-rw-r--r-- | net/ipv6/addrconf.c | 2 | ||||
-rw-r--r-- | net/ipv6/ip6_output.c | 17 | ||||
-rw-r--r-- | net/mac80211/iface.c | 6 | ||||
-rw-r--r-- | net/packet/af_packet.c | 26 | ||||
-rw-r--r-- | net/sched/sch_pie.c | 21 | ||||
-rw-r--r-- | net/sctp/associola.c | 82 | ||||
-rw-r--r-- | net/sctp/sm_statefuns.c | 2 | ||||
-rw-r--r-- | net/sctp/socket.c | 47 | ||||
-rw-r--r-- | net/sctp/sysctl.c | 18 | ||||
-rw-r--r-- | net/sctp/ulpevent.c | 8 | ||||
-rw-r--r-- | net/tipc/core.h | 1 | ||||
-rw-r--r-- | net/tipc/link.c | 7 |
29 files changed, 362 insertions, 173 deletions
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 512159bf607f..8323bced8e5b 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -241,19 +241,19 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const uint8_t *addr) size = bat_priv->num_ifaces * sizeof(uint8_t); orig_node->bat_iv.bcast_own_sum = kzalloc(size, GFP_ATOMIC); if (!orig_node->bat_iv.bcast_own_sum) - goto free_bcast_own; + goto free_orig_node; hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig, batadv_choose_orig, orig_node, &orig_node->hash_entry); if (hash_added != 0) - goto free_bcast_own; + goto free_orig_node; return orig_node; -free_bcast_own: - kfree(orig_node->bat_iv.bcast_own); free_orig_node: + /* free twice, as batadv_orig_node_new sets refcount to 2 */ + batadv_orig_node_free_ref(orig_node); batadv_orig_node_free_ref(orig_node); return NULL; @@ -266,7 +266,7 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, struct batadv_orig_node *orig_neigh) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct batadv_neigh_node *neigh_node; + struct batadv_neigh_node *neigh_node, *tmp_neigh_node; neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, orig_node); if (!neigh_node) @@ -281,14 +281,24 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, neigh_node->orig_node = orig_neigh; neigh_node->if_incoming = hard_iface; - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Creating new neighbor %pM for orig_node %pM on interface %s\n", - neigh_addr, orig_node->orig, hard_iface->net_dev->name); - spin_lock_bh(&orig_node->neigh_list_lock); - hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); + tmp_neigh_node = batadv_neigh_node_get(orig_node, hard_iface, + neigh_addr); + if (!tmp_neigh_node) { + hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); + } else { + kfree(neigh_node); + batadv_hardif_free_ref(hard_iface); + neigh_node = tmp_neigh_node; + } spin_unlock_bh(&orig_node->neigh_list_lock); + if (!tmp_neigh_node) + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Creating new neighbor %pM for orig_node %pM on interface %s\n", + neigh_addr, orig_node->orig, + hard_iface->net_dev->name); + out: return neigh_node; } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 3d417d3641c6..b851cc580853 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -241,7 +241,7 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); const struct batadv_hard_iface *hard_iface; - int min_mtu = ETH_DATA_LEN; + int min_mtu = INT_MAX; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { @@ -256,8 +256,6 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) } rcu_read_unlock(); - atomic_set(&bat_priv->packet_size_max, min_mtu); - if (atomic_read(&bat_priv->fragmentation) == 0) goto out; @@ -268,13 +266,21 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) min_mtu = min_t(int, min_mtu, BATADV_FRAG_MAX_FRAG_SIZE); min_mtu -= sizeof(struct batadv_frag_packet); min_mtu *= BATADV_FRAG_MAX_FRAGMENTS; - atomic_set(&bat_priv->packet_size_max, min_mtu); - - /* with fragmentation enabled we can fragment external packets easily */ - min_mtu = min_t(int, min_mtu, ETH_DATA_LEN); out: - return min_mtu - batadv_max_header_len(); + /* report to the other components the maximum amount of bytes that + * batman-adv can send over the wire (without considering the payload + * overhead). For example, this value is used by TT to compute the + * maximum local table table size + */ + atomic_set(&bat_priv->packet_size_max, min_mtu); + + /* the real soft-interface MTU is computed by removing the payload + * overhead from the maximum amount of bytes that was just computed. + * + * However batman-adv does not support MTUs bigger than ETH_DATA_LEN + */ + return min_t(int, min_mtu - batadv_max_header_len(), ETH_DATA_LEN); } /* adjusts the MTU if a new interface with a smaller MTU appeared. */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 6df12a2e3605..853941629dc1 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -458,6 +458,42 @@ out: } /** + * batadv_neigh_node_get - retrieve a neighbour from the list + * @orig_node: originator which the neighbour belongs to + * @hard_iface: the interface where this neighbour is connected to + * @addr: the address of the neighbour + * + * Looks for and possibly returns a neighbour belonging to this originator list + * which is connected through the provided hard interface. + * Returns NULL if the neighbour is not found. + */ +struct batadv_neigh_node * +batadv_neigh_node_get(const struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *hard_iface, + const uint8_t *addr) +{ + struct batadv_neigh_node *tmp_neigh_node, *res = NULL; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { + if (!batadv_compare_eth(tmp_neigh_node->addr, addr)) + continue; + + if (tmp_neigh_node->if_incoming != hard_iface) + continue; + + if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) + continue; + + res = tmp_neigh_node; + break; + } + rcu_read_unlock(); + + return res; +} + +/** * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object * @rcu: rcu pointer of the orig_ifinfo object */ diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 37be290f63f6..db3a9ed734cb 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -29,6 +29,10 @@ void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_neigh_node * +batadv_neigh_node_get(const struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *hard_iface, + const uint8_t *addr); +struct batadv_neigh_node * batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, const uint8_t *neigh_addr, struct batadv_orig_node *orig_node); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 1ed9f7c9ecea..a953d5b196a3 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -688,7 +688,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, int is_old_ttvn; /* check if there is enough data before accessing it */ - if (pskb_may_pull(skb, hdr_len + ETH_HLEN) < 0) + if (!pskb_may_pull(skb, hdr_len + ETH_HLEN)) return 0; /* create a copy of the skb (in case of for re-routing) to modify it. */ @@ -918,6 +918,8 @@ int batadv_recv_unicast_tvlv(struct sk_buff *skb, if (ret != NET_RX_SUCCESS) ret = batadv_route_unicast_packet(skb, recv_if); + else + consume_skb(skb); return ret; } diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 579f5f00a385..843febd1e519 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -254,9 +254,9 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, unsigned short vid) { - struct ethhdr *ethhdr = (struct ethhdr *)skb->data; + struct ethhdr *ethhdr; struct batadv_unicast_packet *unicast_packet; - int ret = NET_XMIT_DROP; + int ret = NET_XMIT_DROP, hdr_size; if (!orig_node) goto out; @@ -265,12 +265,16 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, case BATADV_UNICAST: if (!batadv_send_skb_prepare_unicast(skb, orig_node)) goto out; + + hdr_size = sizeof(*unicast_packet); break; case BATADV_UNICAST_4ADDR: if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb, orig_node, packet_subtype)) goto out; + + hdr_size = sizeof(struct batadv_unicast_4addr_packet); break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It @@ -279,6 +283,7 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, goto out; } + ethhdr = (struct ethhdr *)(skb->data + hdr_size); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index b6071f675a3e..959dde721c46 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1975,6 +1975,7 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, struct hlist_head *head; uint32_t i, crc_tmp, crc = 0; uint8_t flags; + __be16 tmp_vid; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -2011,8 +2012,11 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, orig_node)) continue; - crc_tmp = crc32c(0, &tt_common->vid, - sizeof(tt_common->vid)); + /* use network order to read the VID: this ensures that + * every node reads the bytes in the same order. + */ + tmp_vid = htons(tt_common->vid); + crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid)); /* compute the CRC on flags that have to be kept in sync * among nodes @@ -2046,6 +2050,7 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, struct hlist_head *head; uint32_t i, crc_tmp, crc = 0; uint8_t flags; + __be16 tmp_vid; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -2064,8 +2069,11 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, if (tt_common->flags & BATADV_TT_CLIENT_NEW) continue; - crc_tmp = crc32c(0, &tt_common->vid, - sizeof(tt_common->vid)); + /* use network order to read the VID: this ensures that + * every node reads the bytes in the same order. + */ + tmp_vid = htons(tt_common->vid); + crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid)); /* compute the CRC on flags that have to be kept in sync * among nodes @@ -2262,6 +2270,7 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, { struct batadv_tvlv_tt_vlan_data *tt_vlan_tmp; struct batadv_orig_node_vlan *vlan; + uint32_t crc; int i; /* check if each received CRC matches the locally stored one */ @@ -2281,7 +2290,10 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, if (!vlan) return false; - if (vlan->tt.crc != ntohl(tt_vlan_tmp->crc)) + crc = vlan->tt.crc; + batadv_orig_node_vlan_free_ref(vlan); + + if (crc != ntohl(tt_vlan_tmp->crc)) return false; } @@ -3218,7 +3230,6 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv, spin_lock_bh(&orig_node->tt_lock); - tt_change = (struct batadv_tvlv_tt_change *)tt_buff; batadv_tt_update_changes(bat_priv, orig_node, tt_num_changes, ttvn, tt_change); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 292e619db896..d9fb93451442 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -430,6 +430,16 @@ static void hidp_del_timer(struct hidp_session *session) del_timer(&session->timer); } +static void hidp_process_report(struct hidp_session *session, + int type, const u8 *data, int len, int intr) +{ + if (len > HID_MAX_BUFFER_SIZE) + len = HID_MAX_BUFFER_SIZE; + + memcpy(session->input_buf, data, len); + hid_input_report(session->hid, type, session->input_buf, len, intr); +} + static void hidp_process_handshake(struct hidp_session *session, unsigned char param) { @@ -502,7 +512,8 @@ static int hidp_process_data(struct hidp_session *session, struct sk_buff *skb, hidp_input_report(session, skb); if (session->hid) - hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 0); + hidp_process_report(session, HID_INPUT_REPORT, + skb->data, skb->len, 0); break; case HIDP_DATA_RTYPE_OTHER: @@ -584,7 +595,8 @@ static void hidp_recv_intr_frame(struct hidp_session *session, hidp_input_report(session, skb); if (session->hid) { - hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 1); + hidp_process_report(session, HID_INPUT_REPORT, + skb->data, skb->len, 1); BT_DBG("report len %d", skb->len); } } else { diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h index ab5241400cf7..8798492a6e99 100644 --- a/net/bluetooth/hidp/hidp.h +++ b/net/bluetooth/hidp/hidp.h @@ -24,6 +24,7 @@ #define __HIDP_H #include <linux/types.h> +#include <linux/hid.h> #include <linux/kref.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/l2cap.h> @@ -179,6 +180,9 @@ struct hidp_session { /* Used in hidp_output_raw_report() */ int output_report_success; /* boolean */ + + /* temporary input buffer */ + u8 input_buf[HID_MAX_BUFFER_SIZE]; }; /* HIDP init defines */ diff --git a/net/core/dev.c b/net/core/dev.c index 4ad1b78c9c77..b1b0c8d4d7df 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2420,7 +2420,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 2. No high memory really exists on this machine. */ -static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; @@ -2495,34 +2495,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) } static netdev_features_t harmonize_features(struct sk_buff *skb, - netdev_features_t features) + const struct net_device *dev, + netdev_features_t features) { if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, skb_network_protocol(skb))) { features &= ~NETIF_F_ALL_CSUM; - } else if (illegal_highdma(skb->dev, skb)) { + } else if (illegal_highdma(dev, skb)) { features &= ~NETIF_F_SG; } return features; } -netdev_features_t netif_skb_features(struct sk_buff *skb) +netdev_features_t netif_skb_dev_features(struct sk_buff *skb, + const struct net_device *dev) { __be16 protocol = skb->protocol; - netdev_features_t features = skb->dev->features; + netdev_features_t features = dev->features; - if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, features); + return harmonize_features(skb, dev, features); } - features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) @@ -2530,9 +2532,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - return harmonize_features(skb, features); + return harmonize_features(skb, dev, features); } -EXPORT_SYMBOL(netif_skb_features); +EXPORT_SYMBOL(netif_skb_dev_features); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 87577d447554..e29e810663d7 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -323,17 +323,6 @@ u32 __skb_get_poff(const struct sk_buff *skb) return poff; } -static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) -{ - if (unlikely(queue_index >= dev->real_num_tx_queues)) { - net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", - dev->name, queue_index, - dev->real_num_tx_queues); - return 0; - } - return queue_index; -} - static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_XPS @@ -372,7 +361,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) #endif } -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); @@ -392,7 +381,6 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) return queue_index; } -EXPORT_SYMBOL(__netdev_pick_tx); struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, @@ -403,13 +391,13 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb, - accel_priv); + queue_index = ops->ndo_select_queue(dev, skb, accel_priv, + __netdev_pick_tx); else queue_index = __netdev_pick_tx(dev, skb); if (!accel_priv) - queue_index = dev_cap_txqueue(dev, queue_index); + queue_index = netdev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 7b2ad564b303..fc122fdb266a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1968,16 +1968,21 @@ replay: dev->ifindex = ifm->ifi_index; - if (ops->newlink) + if (ops->newlink) { err = ops->newlink(net, dev, tb, data); - else + /* Drivers should call free_netdev() in ->destructor + * and unregister it on failure so that device could be + * finally freed in rtnl_unlock. + */ + if (err < 0) + goto out; + } else { err = register_netdevice(dev); - - if (err < 0) { - free_netdev(dev); - goto out; + if (err < 0) { + free_netdev(dev); + goto out; + } } - err = rtnl_configure_link(dev, ifm); if (err < 0) unregister_netdevice(dev); diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c index c073b81a1f3e..62b5828acde0 100644 --- a/net/dccp/ccids/lib/tfrc.c +++ b/net/dccp/ccids/lib/tfrc.c @@ -8,7 +8,7 @@ #include "tfrc.h" #ifdef CONFIG_IP_DCCP_TFRC_DEBUG -static bool tfrc_debug; +bool tfrc_debug; module_param(tfrc_debug, bool, 0644); MODULE_PARM_DESC(tfrc_debug, "Enable TFRC debug messages"); #endif diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index a3d8f7c76ae0..40ee7d62b652 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -21,6 +21,7 @@ #include "packet_history.h" #ifdef CONFIG_IP_DCCP_TFRC_DEBUG +extern bool tfrc_debug; #define tfrc_pr_debug(format, a...) DCCP_PR_DEBUG(tfrc_debug, format, ##a) #else #define tfrc_pr_debug(format, a...) diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index d9d929042a89..be8abe73bb9f 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -39,6 +39,71 @@ #include <net/route.h> #include <net/xfrm.h> +static bool ip_may_fragment(const struct sk_buff *skb) +{ + return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) || + !skb->local_df; +} + +static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + +static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb) +{ + unsigned int mtu; + + if (skb->local_df || !skb_is_gso(skb)) + return false; + + mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true); + + /* if seglen > mtu, do software segmentation for IP fragmentation on + * output. DF bit cannot be set since ip_forward would have sent + * icmp error. + */ + return skb_gso_network_seglen(skb) > mtu; +} + +/* called if GSO skb needs to be fragmented on forward */ +static int ip_forward_finish_gso(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + netdev_features_t features; + struct sk_buff *segs; + int ret = 0; + + features = netif_skb_dev_features(skb, dst->dev); + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR(segs)) { + kfree_skb(skb); + return -ENOMEM; + } + + consume_skb(skb); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = dst_output(segs); + + if (err && ret == 0) + ret = err; + segs = nskb; + } while (segs); + + return ret; +} + static int ip_forward_finish(struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); @@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb) if (unlikely(opt->optlen)) ip_forward_options(skb); + if (ip_gso_exceeds_dst_mtu(skb)) + return ip_forward_finish_gso(skb); + return dst_output(skb); } @@ -92,8 +160,7 @@ int ip_forward(struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); - if (unlikely(skb->len > mtu && !skb_is_gso(skb) && - (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { + if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index efa1138fa523..b3e86ea7b71b 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -273,7 +273,7 @@ static int __init ic_open_devs(void) msleep(1); - if time_before(jiffies, next_msg) + if (time_before(jiffies, next_msg)) continue; elapsed = jiffies_to_msecs(jiffies - start); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 271554c61276..11e4384daaf9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1596,6 +1596,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rth->dst.output = ip_output; @@ -1694,10 +1695,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; err = fib_lookup(net, &fl4, &res); - if (err != 0) + if (err != 0) { + if (!IN_DEV_FORWARD(in_dev)) + err = -EHOSTUNREACH; goto no_route; - - RT_CACHE_STAT_INC(in_slow_tot); + } if (res.type == RTN_BROADCAST) goto brd_input; @@ -1711,8 +1713,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto local_input; } - if (!IN_DEV_FORWARD(in_dev)) + if (!IN_DEV_FORWARD(in_dev)) { + err = -EHOSTUNREACH; goto no_route; + } if (res.type != RTN_UNICAST) goto martian_destination; @@ -1767,6 +1771,7 @@ local_input: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ad235690684c..fdbfeca36d63 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2783,6 +2783,8 @@ static void addrconf_gre_config(struct net_device *dev) ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) addrconf_add_linklocal(idev, &addr); + else + addrconf_prefix_route(&addr, 64, dev, 0, 0); } #endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ef02b26ccf81..070a2fae2375 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -342,6 +342,20 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) return mtu; } +static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) + return true; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -466,8 +480,7 @@ int ip6_forward(struct sk_buff *skb) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) || - (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) { + if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index d6d1f1df9119..ce1c44370610 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1057,7 +1057,8 @@ static void ieee80211_uninit(struct net_device *dev) static u16 ieee80211_netdev_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb); } @@ -1075,7 +1076,8 @@ static const struct net_device_ops ieee80211_dataif_ops = { static u16 ieee80211_monitor_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6a2bb37506c5..48a6a93db296 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -308,11 +308,27 @@ static bool packet_use_direct_xmit(const struct packet_sock *po) return po->xmit == packet_direct_xmit; } -static u16 packet_pick_tx_queue(struct net_device *dev) +static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) { return (u16) raw_smp_processor_id() % dev->real_num_tx_queues; } +static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) +{ + const struct net_device_ops *ops = dev->netdev_ops; + u16 queue_index; + + if (ops->ndo_select_queue) { + queue_index = ops->ndo_select_queue(dev, skb, NULL, + __packet_pick_tx_queue); + queue_index = netdev_cap_txqueue(dev, queue_index); + } else { + queue_index = __packet_pick_tx_queue(dev, skb); + } + + skb_set_queue_mapping(skb, queue_index); +} + /* register_prot_hook must be invoked with the po->bind_lock held, * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). @@ -2285,7 +2301,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } } - skb_set_queue_mapping(skb, packet_pick_tx_queue(dev)); + packet_pick_tx_queue(dev, skb); + skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); @@ -2499,7 +2516,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->dev = dev; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb_set_queue_mapping(skb, packet_pick_tx_queue(dev)); + + packet_pick_tx_queue(dev, skb); if (po->has_vnet_hdr) { if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { @@ -3786,7 +3804,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, */ if (!tx_ring) init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring); - break; + break; default: break; } diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index a255d0200a59..fefeeb73f15f 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -15,6 +15,11 @@ * * ECN support is added by Naeem Khademi <naeemk@ifi.uio.no> * University of Oslo, Norway. + * + * References: + * IETF draft submission: http://tools.ietf.org/html/draft-pan-aqm-pie-00 + * IEEE Conference on High Performance Switching and Routing 2013 : + * "PIE: A * Lightweight Control Scheme to Address the Bufferbloat Problem" */ #include <linux/module.h> @@ -36,7 +41,7 @@ struct pie_params { psched_time_t target; /* user specified target delay in pschedtime */ u32 tupdate; /* timer frequency (in jiffies) */ u32 limit; /* number of packets that can be enqueued */ - u32 alpha; /* alpha and beta are between -4 and 4 */ + u32 alpha; /* alpha and beta are between 0 and 32 */ u32 beta; /* and are used for shift relative to 1 */ bool ecn; /* true if ecn is enabled */ bool bytemode; /* to scale drop early prob based on pkt size */ @@ -326,10 +331,16 @@ static void calculate_probability(struct Qdisc *sch) if (qdelay == 0 && qlen != 0) update_prob = false; - /* Add ranges for alpha and beta, more aggressive for high dropping - * mode and gentle steps for light dropping mode - * In light dropping mode, take gentle steps; in medium dropping mode, - * take medium steps; in high dropping mode, take big steps. + /* In the algorithm, alpha and beta are between 0 and 2 with typical + * value for alpha as 0.125. In this implementation, we use values 0-32 + * passed from user space to represent this. Also, alpha and beta have + * unit of HZ and need to be scaled before they can used to update + * probability. alpha/beta are updated locally below by 1) scaling them + * appropriately 2) scaling down by 16 to come to 0-2 range. + * Please see paper for details. + * + * We scale alpha and beta differently depending on whether we are in + * light, medium or high dropping mode. */ if (q->vars.prob < MAX_PROB / 100) { alpha = diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5ae609200674..f558433537b8 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1367,44 +1367,35 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc) return false; } -/* Increase asoc's rwnd by len and send any window update SACK if needed. */ -void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) +/* Update asoc's rwnd for the approximated state in the buffer, + * and check whether SACK needs to be sent. + */ +void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer) { + int rx_count; struct sctp_chunk *sack; struct timer_list *timer; - if (asoc->rwnd_over) { - if (asoc->rwnd_over >= len) { - asoc->rwnd_over -= len; - } else { - asoc->rwnd += (len - asoc->rwnd_over); - asoc->rwnd_over = 0; - } - } else { - asoc->rwnd += len; - } + if (asoc->ep->rcvbuf_policy) + rx_count = atomic_read(&asoc->rmem_alloc); + else + rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - /* If we had window pressure, start recovering it - * once our rwnd had reached the accumulated pressure - * threshold. The idea is to recover slowly, but up - * to the initial advertised window. - */ - if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) { - int change = min(asoc->pathmtu, asoc->rwnd_press); - asoc->rwnd += change; - asoc->rwnd_press -= change; - } + if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0) + asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1; + else + asoc->rwnd = 0; - pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->a_rwnd); + pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n", + __func__, asoc, asoc->rwnd, rx_count, + asoc->base.sk->sk_rcvbuf); /* Send a window update SACK if the rwnd has increased by at least the * minimum of the association's PMTU and half of the receive buffer. * The algorithm used is similar to the one described in * Section 4.2.3.3 of RFC 1122. */ - if (sctp_peer_needs_update(asoc)) { + if (update_peer && sctp_peer_needs_update(asoc)) { asoc->a_rwnd = asoc->rwnd; pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u " @@ -1426,45 +1417,6 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) } } -/* Decrease asoc's rwnd by len. */ -void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) -{ - int rx_count; - int over = 0; - - if (unlikely(!asoc->rwnd || asoc->rwnd_over)) - pr_debug("%s: association:%p has asoc->rwnd:%u, " - "asoc->rwnd_over:%u!\n", __func__, asoc, - asoc->rwnd, asoc->rwnd_over); - - if (asoc->ep->rcvbuf_policy) - rx_count = atomic_read(&asoc->rmem_alloc); - else - rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - - /* If we've reached or overflowed our receive buffer, announce - * a 0 rwnd if rwnd would still be positive. Store the - * the potential pressure overflow so that the window can be restored - * back to original value. - */ - if (rx_count >= asoc->base.sk->sk_rcvbuf) - over = 1; - - if (asoc->rwnd >= len) { - asoc->rwnd -= len; - if (over) { - asoc->rwnd_press += asoc->rwnd; - asoc->rwnd = 0; - } - } else { - asoc->rwnd_over = len - asoc->rwnd; - asoc->rwnd = 0; - } - - pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->rwnd_press); -} /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 483dcd71b3c5..591b44d3b7de 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -6176,7 +6176,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * PMTU. In cases, such as loopback, this might be a rather * large spill over. */ - if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over || + if ((!chunk->data_accepted) && (!asoc->rwnd || (datalen > asoc->rwnd + asoc->frag_point))) { /* If this is the next TSN, consider reneging to make diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9e91d6e5df63..981aaf8b6ace 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -64,6 +64,7 @@ #include <linux/crypto.h> #include <linux/slab.h> #include <linux/file.h> +#include <linux/compat.h> #include <net/ip.h> #include <net/icmp.h> @@ -1368,11 +1369,19 @@ static int sctp_setsockopt_connectx(struct sock *sk, /* * New (hopefully final) interface for the API. * We use the sctp_getaddrs_old structure so that use-space library - * can avoid any unnecessary allocations. The only defferent part + * can avoid any unnecessary allocations. The only different part * is that we store the actual length of the address buffer into the - * addrs_num structure member. That way we can re-use the existing + * addrs_num structure member. That way we can re-use the existing * code. */ +#ifdef CONFIG_COMPAT +struct compat_sctp_getaddrs_old { + sctp_assoc_t assoc_id; + s32 addr_num; + compat_uptr_t addrs; /* struct sockaddr * */ +}; +#endif + static int sctp_getsockopt_connectx3(struct sock *sk, int len, char __user *optval, int __user *optlen) @@ -1381,16 +1390,30 @@ static int sctp_getsockopt_connectx3(struct sock *sk, int len, sctp_assoc_t assoc_id = 0; int err = 0; - if (len < sizeof(param)) - return -EINVAL; +#ifdef CONFIG_COMPAT + if (is_compat_task()) { + struct compat_sctp_getaddrs_old param32; - if (copy_from_user(¶m, optval, sizeof(param))) - return -EFAULT; + if (len < sizeof(param32)) + return -EINVAL; + if (copy_from_user(¶m32, optval, sizeof(param32))) + return -EFAULT; - err = __sctp_setsockopt_connectx(sk, - (struct sockaddr __user *)param.addrs, - param.addr_num, &assoc_id); + param.assoc_id = param32.assoc_id; + param.addr_num = param32.addr_num; + param.addrs = compat_ptr(param32.addrs); + } else +#endif + { + if (len < sizeof(param)) + return -EINVAL; + if (copy_from_user(¶m, optval, sizeof(param))) + return -EFAULT; + } + err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *) + param.addrs, param.addr_num, + &assoc_id); if (err == 0 || err == -EINPROGRESS) { if (copy_to_user(optval, &assoc_id, sizeof(assoc_id))) return -EFAULT; @@ -2092,12 +2115,6 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, sctp_skb_pull(skb, copied); skb_queue_head(&sk->sk_receive_queue, skb); - /* When only partial message is copied to the user, increase - * rwnd by that amount. If all the data in the skb is read, - * rwnd is updated when the event is freed. - */ - if (!sctp_ulpevent_is_notification(event)) - sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 7135e617ab0f..35c8923b5554 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -151,6 +151,7 @@ static struct ctl_table sctp_net_table[] = { }, { .procname = "cookie_hmac_alg", + .data = &init_net.sctp.sctp_hmac_alg, .maxlen = 8, .mode = 0644, .proc_handler = proc_sctp_do_hmac_alg, @@ -401,15 +402,18 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, int sctp_sysctl_net_register(struct net *net) { - struct ctl_table *table; - int i; + struct ctl_table *table = sctp_net_table; + + if (!net_eq(net, &init_net)) { + int i; - table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL); - if (!table) - return -ENOMEM; + table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL); + if (!table) + return -ENOMEM; - for (i = 0; table[i].data; i++) - table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; + for (i = 0; table[i].data; i++) + table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; + } net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table); return 0; diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 85c64658bd0b..8d198ae03606 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -989,7 +989,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event, skb = sctp_event2skb(event); /* Set the owner and charge rwnd for bytes received. */ sctp_ulpevent_set_owner(event, asoc); - sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb)); + sctp_assoc_rwnd_update(asoc, false); if (!skb->data_len) return; @@ -1011,6 +1011,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) { struct sk_buff *skb, *frag; unsigned int len; + struct sctp_association *asoc; /* Current stack structures assume that the rcv buffer is * per socket. For UDP style sockets this is not true as @@ -1035,8 +1036,11 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) } done: - sctp_assoc_rwnd_increase(event->asoc, len); + asoc = event->asoc; + sctp_association_hold(asoc); sctp_ulpevent_release_owner(event); + sctp_assoc_rwnd_update(asoc, true); + sctp_association_put(asoc); } static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event) diff --git a/net/tipc/core.h b/net/tipc/core.h index 1ff477b0450d..5569d96b4da3 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -192,6 +192,7 @@ static inline void k_term_timer(struct timer_list *timer) struct tipc_skb_cb { void *handle; + bool deferred; }; #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0])) diff --git a/net/tipc/link.c b/net/tipc/link.c index e4f233d58d35..284d6383ad6c 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1408,6 +1408,12 @@ static int link_recv_buf_validate(struct sk_buff *buf) u32 hdr_size; u32 min_hdr_size; + /* If this packet comes from the defer queue, the skb has already + * been validated + */ + if (unlikely(TIPC_SKB_CB(buf)->deferred)) + return 1; + if (unlikely(buf->len < MIN_H_SIZE)) return 0; @@ -1717,6 +1723,7 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, &l_ptr->newest_deferred_in, buf)) { l_ptr->deferred_inqueue_sz++; l_ptr->stats.deferred_recv++; + TIPC_SKB_CB(buf)->deferred = true; if ((l_ptr->deferred_inqueue_sz % 16) == 1) tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); } else |